Merge tag 'v4.15-rc1' into next-seccomp

Linux 4.15-rc1

1405 files changed, 54072 insertions, 11121 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 221e1ce78b06..be02c8b904db 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Some of the tools (perf) use same make variables
 # as in kernel build.
 export srctree=
@@ -18,9 +19,8 @@ help:
         @echo '  iio                    - IIO tools'
         @echo '  kvm_stat               - top-like utility for displaying kvm statistics'
         @echo '  leds                   - LEDs  tools'
-        @echo '  lguest                 - a minimal 32-bit x86 hypervisor'
         @echo '  liblockdep             - user-space wrapper for kernel locking-validator'
-        @echo '  net                    - misc networking tools'
+        @echo '  bpf                    - misc BPF tools'
         @echo '  perf                   - Linux performance measurement and analysis tool'
         @echo '  selftests              - various kernel selftests'
         @echo '  spi                    - spi tools'
@@ -30,6 +30,7 @@ help:
         @echo '  usb                    - USB testing tools'
         @echo '  virtio                 - vhost test module'
         @echo '  vm                     - misc vm tools'
+        @echo '  wmi                    - WMI interface examples'
         @echo '  x86_energy_perf_policy - Intel energy policy tool'
         @echo ''
         @echo 'You can do:'
@@ -58,7 +59,7 @@ acpi: FORCE
 cpupower: FORCE
         $(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds: FORCE
+cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi: FORCE
         $(call descend,$@)
 
 liblockdep: FORCE
@@ -90,10 +91,10 @@ freefall: FORCE
 kvm_stat: FORCE
         $(call descend,kvm/$@)
 
-all: acpi cgroup cpupower gpio hv firewire lguest liblockdep \
-                perf selftests turbostat usb \
-                virtio vm net x86_energy_perf_policy \
-                tmon freefall objtool kvm_stat
+all: acpi cgroup cpupower gpio hv firewire liblockdep \
+                perf selftests spi turbostat usb \
+                virtio vm bpf x86_energy_perf_policy \
+                tmon freefall iio objtool kvm_stat wmi
 
 acpi_install:
         $(call descend,power/$(@:_install=),install)
@@ -101,7 +102,7 @@ acpi_install:
 cpupower_install:
         $(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install gpio_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install:
+cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install:
         $(call descend,$(@:_install=),install)
 
 liblockdep_install:
@@ -123,10 +124,11 @@ kvm_stat_install:
         $(call descend,kvm/$(@:_install=),install)
 
 install: acpi_install cgroup_install cpupower_install gpio_install \
-                hv_install firewire_install lguest_install liblockdep_install \
+                hv_install firewire_install iio_install liblockdep_install \
                 perf_install selftests_install turbostat_install usb_install \
-                virtio_install vm_install net_install x86_energy_perf_policy_install \
-                tmon_install freefall_install objtool_install kvm_stat_install
+                virtio_install vm_install bpf_install x86_energy_perf_policy_install \
+                tmon_install freefall_install objtool_install kvm_stat_install \
+                wmi_install
 
 acpi_clean:
         $(call descend,power/acpi,clean)
@@ -134,7 +136,7 @@ acpi_clean:
 cpupower_clean:
         $(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean:
+cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean:
         $(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -168,10 +170,10 @@ freefall_clean:
 build_clean:
         $(call descend,build,clean)
 
-clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \
+clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
                 perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
-                vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
+                vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
                 freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
-                gpio_clean objtool_clean leds_clean
+                gpio_clean objtool_clean leds_clean wmi_clean
 
 .PHONY: FORCE
diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile
index 647c94a219bf..03687f19cbb1 100644
--- a/tools/accounting/Makefile
+++ b/tools/accounting/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC := $(CROSS_COMPILE)gcc
 CFLAGS := -I../../usr/include
 
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index b5ca536e56a8..9f420d98b5fb 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* getdelays.c
  *
  * Utility to get per-pid and per-tgid delay accounting statistics
diff --git a/tools/arch/alpha/include/asm/barrier.h b/tools/arch/alpha/include/asm/barrier.h
index 95df19c95482..da8d6457ed4f 100644
--- a/tools/arch/alpha/include/asm/barrier.h
+++ b/tools/arch/alpha/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
 #define __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
 
diff --git a/tools/arch/alpha/include/uapi/asm/bitsperlong.h b/tools/arch/alpha/include/uapi/asm/bitsperlong.h
index ad57f7868203..6c5bf7d03f4e 100644
--- a/tools/arch/alpha/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/alpha/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_ALPHA_BITSPERLONG_H
 #define __ASM_ALPHA_BITSPERLONG_H
 
diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h
index e38b64c82b97..c317d3e6867a 100644
--- a/tools/arch/alpha/include/uapi/asm/mman.h
+++ b/tools/arch/alpha/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_ALPHA_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_ALPHA_UAPI_ASM_MMAN_FIX_H
 #define MADV_DODUMP     17
diff --git a/tools/arch/arc/include/uapi/asm/mman.h b/tools/arch/arc/include/uapi/asm/mman.h
index aa3acd2aa9af..81f0f9bf0c25 100644
--- a/tools/arch/arc/include/uapi/asm/mman.h
+++ b/tools/arch/arc/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_ARC_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_ARC_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 5e3c673fa3f4..1f57bbe82b6f 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (C) 2012 - Virtual Open Systems and Columbia University
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
@@ -203,6 +204,14 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
 #define VGIC_LEVEL_INFO_LINE_LEVEL      0
 
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL        0
+#define   KVM_ARM_VCPU_PMU_V3_IRQ       0
+#define   KVM_ARM_VCPU_PMU_V3_INIT      1
+#define KVM_ARM_VCPU_TIMER_CTRL         1
+#define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER         0
+#define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER         1
+
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT            0
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
diff --git a/tools/arch/arm/include/uapi/asm/mman.h b/tools/arch/arm/include/uapi/asm/mman.h
index 478f699f56fd..a6d46321e330 100644
--- a/tools/arch/arm/include/uapi/asm/mman.h
+++ b/tools/arch/arm/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_ARM_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_ARM_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/arm/include/uapi/asm/perf_regs.h b/tools/arch/arm/include/uapi/asm/perf_regs.h
index ce59448458b2..a3c046174e6b 100644
--- a/tools/arch/arm/include/uapi/asm/perf_regs.h
+++ b/tools/arch/arm/include/uapi/asm/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_ARM_PERF_REGS_H
 #define _ASM_ARM_PERF_REGS_H
 
diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index a0483c8e0142..40bde6b23501 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
 #define _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
 
diff --git a/tools/arch/arm64/include/uapi/asm/bitsperlong.h b/tools/arch/arm64/include/uapi/asm/bitsperlong.h
index fce9c2924fa3..485d60bee26c 100644
--- a/tools/arch/arm64/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/arm64/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (C) 2012 ARM Ltd.
  *
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 70eea2ecc663..51149ec75fe4 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (C) 2012,2013 - ARM Ltd
  * Author: Marc Zyngier <marc.zyngier@arm.com>
@@ -232,6 +233,9 @@ struct kvm_arch_memory_slot {
 #define KVM_ARM_VCPU_PMU_V3_CTRL        0
 #define   KVM_ARM_VCPU_PMU_V3_IRQ       0
 #define   KVM_ARM_VCPU_PMU_V3_INIT      1
+#define KVM_ARM_VCPU_TIMER_CTRL         1
+#define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER         0
+#define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER         1
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT          24
diff --git a/tools/arch/arm64/include/uapi/asm/mman.h b/tools/arch/arm64/include/uapi/asm/mman.h
index 70fd3113710a..2ee288e447ec 100644
--- a/tools/arch/arm64/include/uapi/asm/mman.h
+++ b/tools/arch/arm64/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_ARM64_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_ARM64_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
index 172b8317ee49..d54daafa89e3 100644
--- a/tools/arch/arm64/include/uapi/asm/perf_regs.h
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_ARM64_PERF_REGS_H
 #define _ASM_ARM64_PERF_REGS_H
 
diff --git a/tools/arch/frv/include/uapi/asm/bitsperlong.h b/tools/arch/frv/include/uapi/asm/bitsperlong.h
index 6dc0bb0c13b2..76da34b10f59 100644
--- a/tools/arch/frv/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/frv/include/uapi/asm/bitsperlong.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/frv/include/uapi/asm/mman.h b/tools/arch/frv/include/uapi/asm/mman.h
index 5be78ac12464..5bc900b0bc78 100644
--- a/tools/arch/frv/include/uapi/asm/mman.h
+++ b/tools/arch/frv/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_FRV_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_FRV_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/h8300/include/asm/bitsperlong.h b/tools/arch/h8300/include/asm/bitsperlong.h
index e140e46729ac..fa1508337ffc 100644
--- a/tools/arch/h8300/include/asm/bitsperlong.h
+++ b/tools/arch/h8300/include/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_H8300_BITS_PER_LONG
 #define __ASM_H8300_BITS_PER_LONG
 
diff --git a/tools/arch/h8300/include/uapi/asm/mman.h b/tools/arch/h8300/include/uapi/asm/mman.h
index 9d9ac54d3c5a..be7bbe0528d1 100644
--- a/tools/arch/h8300/include/uapi/asm/mman.h
+++ b/tools/arch/h8300/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
index 4a658151383d..5adca0d26913 100644
--- a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
  *
diff --git a/tools/arch/hexagon/include/uapi/asm/mman.h b/tools/arch/hexagon/include/uapi/asm/mman.h
index 102f3fae6085..cd59ba932b3a 100644
--- a/tools/arch/hexagon/include/uapi/asm/mman.h
+++ b/tools/arch/hexagon/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_HEXAGON_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_HEXAGON_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
index e4422b4b634e..d808ee0e77b5 100644
--- a/tools/arch/ia64/include/asm/barrier.h
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copied from the kernel sources to tools/:
  *
diff --git a/tools/arch/ia64/include/uapi/asm/bitsperlong.h b/tools/arch/ia64/include/uapi/asm/bitsperlong.h
index ec4db3c970b7..1146d55563db 100644
--- a/tools/arch/ia64/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/ia64/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_IA64_BITSPERLONG_H
 #define __ASM_IA64_BITSPERLONG_H
 
diff --git a/tools/arch/ia64/include/uapi/asm/mman.h b/tools/arch/ia64/include/uapi/asm/mman.h
index 1d6e5ac6442d..2a19bb1db4ab 100644
--- a/tools/arch/ia64/include/uapi/asm/mman.h
+++ b/tools/arch/ia64/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_IA64_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_IA64_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/m32r/include/uapi/asm/bitsperlong.h b/tools/arch/m32r/include/uapi/asm/bitsperlong.h
index 6dc0bb0c13b2..76da34b10f59 100644
--- a/tools/arch/m32r/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/m32r/include/uapi/asm/bitsperlong.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/m32r/include/uapi/asm/mman.h b/tools/arch/m32r/include/uapi/asm/mman.h
index 1c29635bb73b..d19b82c9c290 100644
--- a/tools/arch/m32r/include/uapi/asm/mman.h
+++ b/tools/arch/m32r/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_M32R_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_M32R_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
index 6dc0bb0c13b2..76da34b10f59 100644
--- a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/microblaze/include/uapi/asm/mman.h b/tools/arch/microblaze/include/uapi/asm/mman.h
index 005cd50b50e1..f3f2103fd02c 100644
--- a/tools/arch/microblaze/include/uapi/asm/mman.h
+++ b/tools/arch/microblaze/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_MICROBLAZE_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_MICROBLAZE_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/mips/include/asm/barrier.h b/tools/arch/mips/include/asm/barrier.h
index 80f96f7556e3..0d1191523cd0 100644
--- a/tools/arch/mips/include/asm/barrier.h
+++ b/tools/arch/mips/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_MIPS_BARRIER_H
 #define _TOOLS_LINUX_ASM_MIPS_BARRIER_H
 /*
diff --git a/tools/arch/mips/include/uapi/asm/bitsperlong.h b/tools/arch/mips/include/uapi/asm/bitsperlong.h
index 3e4c10a8e787..7268380d8d28 100644
--- a/tools/arch/mips/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/mips/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_MIPS_BITSPERLONG_H
 #define __ASM_MIPS_BITSPERLONG_H
 
diff --git a/tools/arch/mips/include/uapi/asm/kvm.h b/tools/arch/mips/include/uapi/asm/kvm.h
index 6985eb59b085..d2714cc1cd93 100644
--- a/tools/arch/mips/include/uapi/asm/kvm.h
+++ b/tools/arch/mips/include/uapi/asm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h
index c02052965d50..de2206883abc 100644
--- a/tools/arch/mips/include/uapi/asm/mman.h
+++ b/tools/arch/mips/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_MIPS_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_MIPS_UAPI_ASM_MMAN_FIX_H
 #define MADV_DODUMP     17
diff --git a/tools/arch/mn10300/include/uapi/asm/mman.h b/tools/arch/mn10300/include/uapi/asm/mman.h
index c1ea36d83acc..b9360639974f 100644
--- a/tools/arch/mn10300/include/uapi/asm/mman.h
+++ b/tools/arch/mn10300/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_MN10300_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_MN10300_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/parisc/include/uapi/asm/bitsperlong.h b/tools/arch/parisc/include/uapi/asm/bitsperlong.h
index e0a23c7bdd43..23ac7562927a 100644
--- a/tools/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_PARISC_BITSPERLONG_H
 #define __ASM_PARISC_BITSPERLONG_H
 
diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h
index 03d8d5b7ae7f..1bd78758bde9 100644
--- a/tools/arch/parisc/include/uapi/asm/mman.h
+++ b/tools/arch/parisc/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H
 #define MADV_DODUMP     70
@@ -36,9 +37,7 @@
 #define PROT_READ       0x1
 #define PROT_SEM        0x8
 #define PROT_WRITE      0x2
-/* MADV_HWPOISON is undefined on parisc, fix it for perf */
 #define MADV_HWPOISON   100
-/* MADV_SOFT_OFFLINE is undefined on parisc, fix it for perf */
 #define MADV_SOFT_OFFLINE 101
 /* MAP_32BIT is undefined on parisc, fix it for perf */
 #define MAP_32BIT       0
diff --git a/tools/arch/powerpc/include/asm/barrier.h b/tools/arch/powerpc/include/asm/barrier.h
index b23aee8e6d90..a634da05bc97 100644
--- a/tools/arch/powerpc/include/asm/barrier.h
+++ b/tools/arch/powerpc/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copied from the kernel sources:
  *
diff --git a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
index 5f1659032c40..46ece3ecff31 100644
--- a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_POWERPC_BITSPERLONG_H
 #define __ASM_POWERPC_BITSPERLONG_H
 
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 07fbeb927834..61d6049f4c1e 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, version 2, as
@@ -60,6 +61,12 @@ struct kvm_regs {
 
 #define KVM_SREGS_E_FSL_PIDn    (1 << 0) /* PID1/PID2 */
 
+/* flags for kvm_run.flags */
+#define KVM_RUN_PPC_NMI_DISP_MASK               (3 << 0)
+#define   KVM_RUN_PPC_NMI_DISP_FULLY_RECOV      (1 << 0)
+#define   KVM_RUN_PPC_NMI_DISP_LIMITED_RECOV    (2 << 0)
+#define   KVM_RUN_PPC_NMI_DISP_NOT_RECOV        (3 << 0)
+
 /*
  * Feature bits indicate which sections of the sregs struct are valid,
  * both in KVM_GET_SREGS and KVM_SET_SREGS.  On KVM_SET_SREGS, registers
diff --git a/tools/arch/powerpc/include/uapi/asm/mman.h b/tools/arch/powerpc/include/uapi/asm/mman.h
index 761db43172fe..f33105bc5ca6 100644
--- a/tools/arch/powerpc/include/uapi/asm/mman.h
+++ b/tools/arch/powerpc/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_POWERPC_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_POWERPC_UAPI_ASM_MMAN_FIX_H
 #define MAP_DENYWRITE   0x0800
diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
index 6a93209748a1..9e52c86ccbd3 100644
--- a/tools/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_ASM_POWERPC_PERF_REGS_H
 #define _UAPI_ASM_POWERPC_PERF_REGS_H
 
diff --git a/tools/arch/s390/include/asm/barrier.h b/tools/arch/s390/include/asm/barrier.h
index f85141266b92..5030c99f47d2 100644
--- a/tools/arch/s390/include/asm/barrier.h
+++ b/tools/arch/s390/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copied from the kernel sources:
  *
diff --git a/tools/arch/s390/include/uapi/asm/bitsperlong.h b/tools/arch/s390/include/uapi/asm/bitsperlong.h
index e351ea2ad43e..d2bb620119bf 100644
--- a/tools/arch/s390/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/s390/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_S390_BITSPERLONG_H
 #define __ASM_S390_BITSPERLONG_H
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 3dd2a1d308dd..9ad172dcd912 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __LINUX_KVM_S390_H
 #define __LINUX_KVM_S390_H
 /*
@@ -28,6 +29,7 @@
 #define KVM_DEV_FLIC_CLEAR_IO_IRQ       8
 #define KVM_DEV_FLIC_AISM               9
 #define KVM_DEV_FLIC_AIRQ_INJECT        10
+#define KVM_DEV_FLIC_AISM_ALL           11
 /*
  * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
  * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
@@ -53,6 +55,11 @@ struct kvm_s390_ais_req {
         __u16 mode;
 };
 
+struct kvm_s390_ais_all {
+        __u8 simm;
+        __u8 nimm;
+};
+
 #define KVM_S390_IO_ADAPTER_MASK 1
 #define KVM_S390_IO_ADAPTER_MAP 2
 #define KVM_S390_IO_ADAPTER_UNMAP 3
@@ -70,6 +77,7 @@ struct kvm_s390_io_adapter_req {
 #define KVM_S390_VM_TOD                 1
 #define KVM_S390_VM_CRYPTO              2
 #define KVM_S390_VM_CPU_MODEL           3
+#define KVM_S390_VM_MIGRATION           4
 
 /* kvm attributes for mem_ctrl */
 #define KVM_S390_VM_MEM_ENABLE_CMMA     0
@@ -81,6 +89,12 @@ struct kvm_s390_io_adapter_req {
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW             0
 #define KVM_S390_VM_TOD_HIGH            1
+#define KVM_S390_VM_TOD_EXT             2
+
+struct kvm_s390_vm_tod_clock {
+        __u8  epoch_idx;
+        __u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */
@@ -151,6 +165,11 @@ struct kvm_s390_vm_cpu_subfunc {
 #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW       2
 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW       3
 
+/* kvm attributes for migration mode */
+#define KVM_S390_VM_MIGRATION_STOP      0
+#define KVM_S390_VM_MIGRATION_START     1
+#define KVM_S390_VM_MIGRATION_STATUS    2
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
         /* general purpose regs for s390 */
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
index 397282727e21..c36c97ffdc6f 100644
--- a/tools/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Definitions for perf-kvm on s390
  *
diff --git a/tools/arch/s390/include/uapi/asm/mman.h b/tools/arch/s390/include/uapi/asm/mman.h
index b03dea9e1f56..4ec32e4251a4 100644
--- a/tools/arch/s390/include/uapi/asm/mman.h
+++ b/tools/arch/s390/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_S390_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_S390_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
index 3ac634368939..6ca1e68d7103 100644
--- a/tools/arch/s390/include/uapi/asm/sie.h
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_ASM_S390_SIE_H
 #define _UAPI_ASM_S390_SIE_H
 
diff --git a/tools/arch/score/include/uapi/asm/bitsperlong.h b/tools/arch/score/include/uapi/asm/bitsperlong.h
index 86ff337aa459..df48f2717da2 100644
--- a/tools/arch/score/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/score/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_SCORE_BITSPERLONG_H
 #define _ASM_SCORE_BITSPERLONG_H
 
diff --git a/tools/arch/score/include/uapi/asm/mman.h b/tools/arch/score/include/uapi/asm/mman.h
index 2f8fb89944fd..b4bd195a8586 100644
--- a/tools/arch/score/include/uapi/asm/mman.h
+++ b/tools/arch/score/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_SCORE_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_SCORE_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/sh/include/asm/barrier.h b/tools/arch/sh/include/asm/barrier.h
index c18fd7599b97..bde5221af282 100644
--- a/tools/arch/sh/include/asm/barrier.h
+++ b/tools/arch/sh/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copied from the kernel sources:
  *
diff --git a/tools/arch/sh/include/uapi/asm/mman.h b/tools/arch/sh/include/uapi/asm/mman.h
index 26504f6f060e..88c0e2930c47 100644
--- a/tools/arch/sh/include/uapi/asm/mman.h
+++ b/tools/arch/sh/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_SH_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_SH_UAPI_ASM_MMAN_FIX_H
 #include <uapi/asm-generic/mman.h>
diff --git a/tools/arch/sparc/include/asm/barrier.h b/tools/arch/sparc/include/asm/barrier.h
index 8c017b3b1391..95d1618465a6 100644
--- a/tools/arch/sparc/include/asm/barrier.h
+++ b/tools/arch/sparc/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
 #define ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
 #if defined(__sparc__) && defined(__arch64__)
diff --git a/tools/arch/sparc/include/asm/barrier_32.h b/tools/arch/sparc/include/asm/barrier_32.h
index c5eadd0a7233..cc19ed1dde0b 100644
--- a/tools/arch/sparc/include/asm/barrier_32.h
+++ b/tools/arch/sparc/include/asm/barrier_32.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_PERF_SPARC_BARRIER_H
 #define __TOOLS_PERF_SPARC_BARRIER_H
 
diff --git a/tools/arch/sparc/include/asm/barrier_64.h b/tools/arch/sparc/include/asm/barrier_64.h
index 9a7d7322c3f7..ba61344287d5 100644
--- a/tools/arch/sparc/include/asm/barrier_64.h
+++ b/tools/arch/sparc/include/asm/barrier_64.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_SPARC64_BARRIER_H
 #define __TOOLS_LINUX_SPARC64_BARRIER_H
 
diff --git a/tools/arch/sparc/include/uapi/asm/bitsperlong.h b/tools/arch/sparc/include/uapi/asm/bitsperlong.h
index b62dd907d7c3..3b4e61740b75 100644
--- a/tools/arch/sparc/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/sparc/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_ALPHA_BITSPERLONG_H
 #define __ASM_ALPHA_BITSPERLONG_H
 
diff --git a/tools/arch/sparc/include/uapi/asm/mman.h b/tools/arch/sparc/include/uapi/asm/mman.h
index 8640525de991..38920eed8cbf 100644
--- a/tools/arch/sparc/include/uapi/asm/mman.h
+++ b/tools/arch/sparc/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_SPARC_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_SPARC_UAPI_ASM_MMAN_FIX_H
 #define MAP_DENYWRITE   0x0800
diff --git a/tools/arch/tile/include/asm/barrier.h b/tools/arch/tile/include/asm/barrier.h
index 7d3692c3d4ac..7ad02a591b43 100644
--- a/tools/arch/tile/include/asm/barrier.h
+++ b/tools/arch/tile/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_TILE_BARRIER_H
 #define _TOOLS_LINUX_ASM_TILE_BARRIER_H
 /*
diff --git a/tools/arch/tile/include/uapi/asm/bitsperlong.h b/tools/arch/tile/include/uapi/asm/bitsperlong.h
index 58c771f2af2f..57cca78c0fbb 100644
--- a/tools/arch/tile/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/tile/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright 2010 Tilera Corporation. All Rights Reserved.
  *
diff --git a/tools/arch/tile/include/uapi/asm/mman.h b/tools/arch/tile/include/uapi/asm/mman.h
index 7116c4b928b3..65ec92925c6c 100644
--- a/tools/arch/tile/include/uapi/asm/mman.h
+++ b/tools/arch/tile/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_TILE_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_TILE_UAPI_ASM_MMAN_FIX_H
 #define MAP_DENYWRITE   0x0800
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
index 328eeceec709..1f5e26aae9fc 100644
--- a/tools/arch/x86/include/asm/atomic.h
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_X86_ATOMIC_H
 #define _TOOLS_LINUX_ASM_X86_ATOMIC_H
 
@@ -24,7 +25,7 @@
  */
 static inline int atomic_read(const atomic_t *v)
 {
-        return ACCESS_ONCE((v)->counter);
+        return READ_ONCE((v)->counter);
 }
 
 /**
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
index f366d8e550e4..8774dee27471 100644
--- a/tools/arch/x86/include/asm/barrier.h
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_X86_BARRIER_H
 #define _TOOLS_LINUX_ASM_X86_BARRIER_H
 
diff --git a/tools/arch/x86/include/asm/cmpxchg.h b/tools/arch/x86/include/asm/cmpxchg.h
index f5253260f3cc..0ed9ca2766ad 100644
--- a/tools/arch/x86/include/asm/cmpxchg.h
+++ b/tools/arch/x86/include/asm/cmpxchg.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef TOOLS_ASM_X86_CMPXCHG_H
 #define TOOLS_ASM_X86_CMPXCHG_H
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 2701e5f8145b..793690fbda36 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_CPUFEATURES_H
 #define _ASM_X86_CPUFEATURES_H
 
@@ -177,7 +178,7 @@
 #define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
 #define X86_FEATURE_BPEXT       (6*32+26) /* data breakpoint extension */
 #define X86_FEATURE_PTSC        ( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_L2  ( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */
 #define X86_FEATURE_MWAITX      ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
 
 /*
@@ -196,6 +197,7 @@
 
 #define X86_FEATURE_HW_PSTATE   ( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME         ( 7*32+10) /* AMD Secure Memory Encryption */
 
 #define X86_FEATURE_INTEL_PPIN  ( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT    ( 7*32+15) /* Intel Processor Trace */
@@ -286,6 +288,8 @@
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC        (15*32+13) /* Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF        (15*32+16) /* Virtual GIF */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 5dff775af7cd..c10c9128f54e 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -21,11 +21,13 @@
 # define DISABLE_K6_MTRR        (1<<(X86_FEATURE_K6_MTRR & 31))
 # define DISABLE_CYRIX_ARR      (1<<(X86_FEATURE_CYRIX_ARR & 31))
 # define DISABLE_CENTAUR_MCR    (1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID           0
 #else
 # define DISABLE_VME            0
 # define DISABLE_K6_MTRR        0
 # define DISABLE_CYRIX_ARR      0
 # define DISABLE_CENTAUR_MCR    0
+# define DISABLE_PCID           (1<<(X86_FEATURE_PCID & 31))
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
@@ -49,7 +51,7 @@
 #define DISABLED_MASK1  0
 #define DISABLED_MASK2  0
 #define DISABLED_MASK3  (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4  0
+#define DISABLED_MASK4  (DISABLE_PCID)
 #define DISABLED_MASK5  0
 #define DISABLED_MASK6  0
 #define DISABLED_MASK7  0
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index a6669bc06939..dc90c0c2fae3 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_X86_RMWcc
 #define _TOOLS_LINUX_ASM_X86_RMWcc
 
diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/asm/unistd_32.h
index 88b3f8c8920c..60a89dba01b6 100644
--- a/tools/arch/x86/include/asm/unistd_32.h
+++ b/tools/arch/x86/include/asm/unistd_32.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 336
 #endif
@@ -10,3 +11,6 @@
 #ifndef __NR_getcpu
 # define __NR_getcpu 318
 #endif
+#ifndef __NR_setns
+# define __NR_setns 346
+#endif
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h
index fbdb70ee8837..cb52a3a8b8fc 100644
--- a/tools/arch/x86/include/asm/unistd_64.h
+++ b/tools/arch/x86/include/asm/unistd_64.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
@@ -10,3 +11,6 @@
 #ifndef __NR_getcpu
 # define __NR_getcpu 309
 #endif
+#ifndef __NR_setns
+#define __NR_setns 308
+#endif
diff --git a/tools/arch/x86/include/uapi/asm/bitsperlong.h b/tools/arch/x86/include/uapi/asm/bitsperlong.h
index 6e23c543cd80..f8a92e0009d6 100644
--- a/tools/arch/x86/include/uapi/asm/bitsperlong.h
+++ b/tools/arch/x86/include/uapi/asm/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_X86_BITSPERLONG_H
 #define __ASM_X86_BITSPERLONG_H
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index c2824d02ba37..f3a960488eae 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_KVM_H
 #define _ASM_X86_KVM_H
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm_perf.h b/tools/arch/x86/include/uapi/asm/kvm_perf.h
index 3bb964f88aa1..125cf5cdf6c5 100644
--- a/tools/arch/x86/include/uapi/asm/kvm_perf.h
+++ b/tools/arch/x86/include/uapi/asm/kvm_perf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_KVM_PERF_H
 #define _ASM_X86_KVM_PERF_H
 
diff --git a/tools/arch/x86/include/uapi/asm/mman.h b/tools/arch/x86/include/uapi/asm/mman.h
index b73c1af8b1dd..8449778de2ed 100644
--- a/tools/arch/x86/include/uapi/asm/mman.h
+++ b/tools/arch/x86/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_X86_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_X86_UAPI_ASM_MMAN_FIX_H
 #define MAP_32BIT       0x40
diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
index 3f2207bfd17b..f3329cabce5c 100644
--- a/tools/arch/x86/include/uapi/asm/perf_regs.h
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_PERF_REGS_H
 #define _ASM_X86_PERF_REGS_H
 
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 3725e145aa58..a9731f8a480f 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI__SVM_H
 #define _UAPI__SVM_H
 
diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..30d7d04d72d6
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/unistd.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_X86_UNISTD_H
+#define _UAPI_ASM_X86_UNISTD_H
+
+/* x32 syscall flag bit */
+#define __X32_SYSCALL_BIT       0x40000000
+
+#ifndef __KERNEL__
+# ifdef __i386__
+#  include <asm/unistd_32.h>
+# elif defined(__ILP32__)
+#  include <asm/unistd_x32.h>
+# else
+#  include <asm/unistd_64.h>
+# endif
+#endif
+
+#endif /* _UAPI_ASM_X86_UNISTD_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 690a2dcf4078..f0b0c90dd398 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * vmx.h: VMX Architecture related definitions
  * Copyright (c) 2004, Intel Corporation.
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 98dcc112b363..9a53a06e5a3e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -4,6 +4,7 @@
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
+#include <asm/export.h>
 
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
@@ -40,6 +41,8 @@ ENTRY(memcpy)
         ret
 ENDPROC(memcpy)
 ENDPROC(__memcpy)
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(__memcpy)
 
 /*
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
@@ -274,6 +277,7 @@ ENTRY(memcpy_mcsafe_unrolled)
         xorq %rax, %rax
         ret
 ENDPROC(memcpy_mcsafe_unrolled)
+EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
 
         .section .fixup, "ax"
         /* Return -EFAULT for any failure */
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index e1229ecd2a82..f8f3dc0a6690 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h
index 4453195c450c..34dde6f44dae 100644
--- a/tools/arch/xtensa/include/uapi/asm/mman.h
+++ b/tools/arch/xtensa/include/uapi/asm/mman.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef TOOLS_ARCH_XTENSA_UAPI_ASM_MMAN_FIX_H
 #define TOOLS_ARCH_XTENSA_UAPI_ASM_MMAN_FIX_H
 #define MADV_DODUMP     17
diff --git a/tools/net/Makefile b/tools/bpf/Makefile
index ddf888010652..07a6697466ef 100644
--- a/tools/net/Makefile
+++ b/tools/bpf/Makefile
@@ -1,8 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 prefix = /usr
 
 CC = gcc
 LEX = flex
 YACC = bison
+MAKE = make
 
 CFLAGS += -Wall -O2
 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
@@ -13,7 +15,7 @@ CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
 %.lex.c: %.l
         $(LEX) -o $@ $<
 
-all : bpf_jit_disasm bpf_dbg bpf_asm
+all: bpf_jit_disasm bpf_dbg bpf_asm bpftool
 
 bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
@@ -26,10 +28,21 @@ bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
 
-clean :
+clean: bpftool_clean
         rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
 
-install :
+install: bpftool_install
         install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
         install bpf_dbg $(prefix)/bin/bpf_dbg
         install bpf_asm $(prefix)/bin/bpf_asm
+
+bpftool:
+        $(MAKE) -C bpftool
+
+bpftool_install:
+        $(MAKE) -C bpftool install
+
+bpftool_clean:
+        $(MAKE) -C bpftool clean
+
+.PHONY: bpftool FORCE
diff --git a/tools/net/bpf_asm.c b/tools/bpf/bpf_asm.c
index c15aef097b04..c15aef097b04 100644
--- a/tools/net/bpf_asm.c
+++ b/tools/bpf/bpf_asm.c
diff --git a/tools/net/bpf_dbg.c b/tools/bpf/bpf_dbg.c
index 4f254bcc4423..4f254bcc4423 100644
--- a/tools/net/bpf_dbg.c
+++ b/tools/bpf/bpf_dbg.c
diff --git a/tools/net/bpf_exp.l b/tools/bpf/bpf_exp.l
index bd83149e7be0..bd83149e7be0 100644
--- a/tools/net/bpf_exp.l
+++ b/tools/bpf/bpf_exp.l
diff --git a/tools/net/bpf_exp.y b/tools/bpf/bpf_exp.y
index 56ba1de50784..56ba1de50784 100644
--- a/tools/net/bpf_exp.y
+++ b/tools/bpf/bpf_exp.y
diff --git a/tools/net/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c
index 422d9abd666a..75bf526a0168 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/bpf/bpf_jit_disasm.c
@@ -27,6 +27,7 @@
 #include <sys/klog.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <limits.h>
 
 #define CMD_ACTION_SIZE_BUFFER          10
 #define CMD_ACTION_READ_ALL             3
@@ -51,7 +52,7 @@ static void get_exec_path(char *tpath, size_t size)
 static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
 {
         int count, i, pc = 0;
-        char tpath[256];
+        char tpath[PATH_MAX];
         struct disassemble_info info;
         disassembler_ftype disassemble;
         bfd *bfdf;
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
new file mode 100644
index 000000000000..bde77d7c4390
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -0,0 +1,34 @@
+include ../../../scripts/Makefile.include
+include ../../../scripts/utilities.mak
+
+INSTALL ?= install
+RM ?= rm -f
+
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
+prefix?=$(HOME)
+endif
+mandir ?= $(prefix)/share/man
+man8dir = $(mandir)/man8
+
+MAN8_RST = $(wildcard *.rst)
+
+_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
+DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
+
+man: man8
+man8: $(DOC_MAN8)
+
+$(OUTPUT)%.8: %.rst
+        rst2man $< > $@
+
+clean:
+        $(call QUIET_CLEAN, Documentation) $(RM) $(DOC_MAN8)
+
+install: man
+        $(call QUIET_INSTALL, Documentation-man) \
+                $(INSTALL) -d -m 755 $(DESTDIR)$(man8dir); \
+                $(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir);
+
+.PHONY: man man8 clean install
+.DEFAULT_GOAL := man
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
new file mode 100644
index 000000000000..9f51a268eb06
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -0,0 +1,131 @@
+================
+bpftool-map
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF maps
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+        **bpftool** [*OPTIONS*] **map** *COMMAND*
+
+        *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
+
+        *COMMANDS* :=
+        { **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
+        | **pin** | **help** }
+
+MAP COMMANDS
+=============
+
+|       **bpftool** **map show**   [*MAP*]
+|       **bpftool** **map dump**    *MAP*
+|       **bpftool** **map update**  *MAP*  **key** *BYTES*   **value** *VALUE* [*UPDATE_FLAGS*]
+|       **bpftool** **map lookup**  *MAP*  **key** *BYTES*
+|       **bpftool** **map getnext** *MAP* [**key** *BYTES*]
+|       **bpftool** **map delete**  *MAP*  **key** *BYTES*
+|       **bpftool** **map pin**     *MAP*  *FILE*
+|       **bpftool** **map help**
+|
+|       *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
+|       *VALUE* := { *BYTES* | *MAP* | *PROGRAM* }
+|       *UPDATE_FLAGS* := { **any** | **exist** | **noexist** }
+
+DESCRIPTION
+===========
+        **bpftool map show**   [*MAP*]
+                  Show information about loaded maps.  If *MAP* is specified
+                  show information only about given map, otherwise list all
+                  maps currently loaded on the system.
+
+                  Output will start with map ID followed by map type and
+                  zero or more named attributes (depending on kernel version).
+
+        **bpftool map dump**    *MAP*
+                  Dump all entries in a given *MAP*.
+
+        **bpftool map update**  *MAP*  **key** *BYTES*   **value** *VALUE* [*UPDATE_FLAGS*]
+                  Update map entry for a given *KEY*.
+
+                  *UPDATE_FLAGS* can be one of: **any** update existing entry
+                  or add if doesn't exit; **exist** update only if entry already
+                  exists; **noexist** update only if entry doesn't exist.
+
+        **bpftool map lookup**  *MAP*  **key** *BYTES*
+                  Lookup **key** in the map.
+
+        **bpftool map getnext** *MAP* [**key** *BYTES*]
+                  Get next key.  If *key* is not specified, get first key.
+
+        **bpftool map delete**  *MAP*  **key** *BYTES*
+                  Remove entry from the map.
+
+        **bpftool map pin**     *MAP*  *FILE*
+                  Pin map *MAP* as *FILE*.
+
+                  Note: *FILE* must be located in *bpffs* mount.
+
+        **bpftool map help**
+                  Print short help message.
+
+OPTIONS
+=======
+        -h, --help
+                  Print short generic help message (similar to **bpftool help**).
+
+        -v, --version
+                  Print version number (similar to **bpftool version**).
+
+        -j, --json
+                  Generate JSON output. For commands that cannot produce JSON, this
+                  option has no effect.
+
+        -p, --pretty
+                  Generate human-readable JSON output. Implies **-j**.
+
+        -f, --bpffs
+                  Show file names of pinned maps.
+
+EXAMPLES
+========
+**# bpftool map show**
+::
+
+  10: hash  name some_map  flags 0x0
+        key 4B  value 8B  max_entries 2048  memlock 167936B
+
+**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04**
+
+**# bpftool map lookup id 10 key 0 1 2 3**
+
+::
+
+  key: 00 01 02 03 value: 00 01 02 03 04 05 06 07
+
+
+**# bpftool map dump id 10**
+::
+
+  key: 00 01 02 03  value: 00 01 02 03 04 05 06 07
+  key: 0d 00 07 00  value: 02 00 00 00 01 02 03 04
+  Found 2 elements
+
+**# bpftool map getnext id 10 key 0 1 2 3**
+::
+
+  key:
+  00 01 02 03
+  next key:
+  0d 00 07 00
+
+|
+| **# mount -t bpf none /sys/fs/bpf/**
+| **# bpftool map pin id 10 /sys/fs/bpf/map**
+| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00**
+
+SEE ALSO
+========
+        **bpftool**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
new file mode 100644
index 000000000000..36e8d1c3c40d
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -0,0 +1,150 @@
+================
+bpftool-prog
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF progs
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+        **bpftool** [*OPTIONS*] **prog** *COMMAND*
+
+        *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
+
+        *COMMANDS* :=
+        { **show** | **dump xlated** | **dump jited** | **pin** | **help** }
+
+MAP COMMANDS
+=============
+
+|       **bpftool** **prog show** [*PROG*]
+|       **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes**}]
+|       **bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
+|       **bpftool** **prog pin** *PROG* *FILE*
+|       **bpftool** **prog help**
+|
+|       *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+
+DESCRIPTION
+===========
+        **bpftool prog show** [*PROG*]
+                  Show information about loaded programs.  If *PROG* is
+                  specified show information only about given program, otherwise
+                  list all programs currently loaded on the system.
+
+                  Output will start with program ID followed by program type and
+                  zero or more named attributes (depending on kernel version).
+
+        **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** }]
+                  Dump eBPF instructions of the program from the kernel.
+                  If *FILE* is specified image will be written to a file,
+                  otherwise it will be disassembled and printed to stdout.
+
+                  **opcodes** controls if raw opcodes will be printed.
+
+        **bpftool prog dump jited**  *PROG* [{ **file** *FILE* | **opcodes** }]
+                  Dump jited image (host machine code) of the program.
+                  If *FILE* is specified image will be written to a file,
+                  otherwise it will be disassembled and printed to stdout.
+
+                  **opcodes** controls if raw opcodes will be printed.
+
+        **bpftool prog pin** *PROG* *FILE*
+                  Pin program *PROG* as *FILE*.
+
+                  Note: *FILE* must be located in *bpffs* mount.
+
+        **bpftool prog help**
+                  Print short help message.
+
+OPTIONS
+=======
+        -h, --help
+                  Print short generic help message (similar to **bpftool help**).
+
+        -v, --version
+                  Print version number (similar to **bpftool version**).
+
+        -j, --json
+                  Generate JSON output. For commands that cannot produce JSON, this
+                  option has no effect.
+
+        -p, --pretty
+                  Generate human-readable JSON output. Implies **-j**.
+
+        -f, --bpffs
+                  Show file names of pinned programs.
+
+EXAMPLES
+========
+**# bpftool prog show**
+::
+
+  10: xdp  name some_prog  tag 005a3d2123620c8b
+        loaded_at Sep 29/20:11  uid 0
+        xlated 528B  jited 370B  memlock 4096B  map_ids 10
+
+**# bpftool --json --pretty prog show**
+
+::
+
+    {
+        "programs": [{
+                "id": 10,
+                "type": "xdp",
+                "tag": "005a3d2123620c8b",
+                "loaded_at": "Sep 29/20:11",
+                "uid": 0,
+                "bytes_xlated": 528,
+                "jited": true,
+                "bytes_jited": 370,
+                "bytes_memlock": 4096,
+                "map_ids": [10
+                ]
+            }
+        ]
+    }
+
+|
+| **# bpftool prog dump xlated id 10 file /tmp/t**
+| **# ls -l /tmp/t**
+|   -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
+
+**# bpftool prog dum jited tag 005a3d2123620c8b**
+
+::
+
+    push   %rbp
+    mov    %rsp,%rbp
+    sub    $0x228,%rsp
+    sub    $0x28,%rbp
+    mov    %rbx,0x0(%rbp)
+
+|
+| **# mount -t bpf none /sys/fs/bpf/**
+| **# bpftool prog pin id 10 /sys/fs/bpf/prog**
+| **# ls -l /sys/fs/bpf/**
+|   -rw------- 1 root root 0 Jul 22 01:43 prog
+
+**# bpftool prog dum jited pinned /sys/fs/bpf/prog opcodes**
+
+::
+
+    push   %rbp
+    55
+    mov    %rsp,%rbp
+    48 89 e5
+    sub    $0x228,%rsp
+    48 81 ec 28 02 00 00
+    sub    $0x28,%rbp
+    48 83 ed 28
+    mov    %rbx,0x0(%rbp)
+    48 89 5d 00
+
+
+SEE ALSO
+========
+        **bpftool**\ (8), **bpftool-map**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
new file mode 100644
index 000000000000..926c03d5a8da
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -0,0 +1,56 @@
+================
+BPFTOOL
+================
+-------------------------------------------------------------------------------
+tool for inspection and simple manipulation of eBPF programs and maps
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+        **bpftool** [*OPTIONS*] *OBJECT* { *COMMAND* | **help** }
+
+        **bpftool** **batch file** *FILE*
+
+        **bpftool** **version**
+
+        *OBJECT* := { **map** | **program** }
+
+        *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
+        | { **-j** | **--json** } [{ **-p** | **--pretty** }] }
+
+        *MAP-COMMANDS* :=
+        { **show** | **dump** | **update** | **lookup** | **getnext** | **delete**
+        | **pin** | **help** }
+
+        *PROG-COMMANDS* := { **show** | **dump jited** | **dump xlated** | **pin**
+        | **help** }
+
+DESCRIPTION
+===========
+        *bpftool* allows for inspection and simple modification of BPF objects
+        on the system.
+
+        Note that format of the output of all tools is not guaranteed to be
+        stable and should not be depended upon.
+
+OPTIONS
+=======
+        -h, --help
+                  Print short help message (similar to **bpftool help**).
+
+        -v, --version
+                  Print version number (similar to **bpftool version**).
+
+        -j, --json
+                  Generate JSON output. For commands that cannot produce JSON, this
+                  option has no effect.
+
+        -p, --pretty
+                  Generate human-readable JSON output. Implies **-j**.
+
+SEE ALSO
+========
+        **bpftool-map**\ (8), **bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
new file mode 100644
index 000000000000..813826c50936
--- /dev/null
+++ b/tools/bpf/bpftool/Makefile
@@ -0,0 +1,92 @@
+include ../../scripts/Makefile.include
+
+include ../../scripts/utilities.mak
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+# Adding $(OUTPUT) as a directory to look for source files,
+# because use generated output files as sources dependency
+# for flex/bison parsers.
+VPATH += $(OUTPUT)
+export VPATH
+endif
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+BPF_DIR = $(srctree)/tools/lib/bpf/
+
+ifneq ($(OUTPUT),)
+  BPF_PATH=$(OUTPUT)
+else
+  BPF_PATH=$(BPF_DIR)
+endif
+
+LIBBPF = $(BPF_PATH)libbpf.a
+
+$(LIBBPF): FORCE
+        $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
+
+$(LIBBPF)-clean:
+        $(call QUIET_CLEAN, libbpf)
+        $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null
+
+prefix = /usr
+bash_compdir ?= $(prefix)/share/bash-completion/completions
+
+CC = gcc
+
+CFLAGS += -O2
+CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow
+CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/
+LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
+
+include $(wildcard *.d)
+
+all: $(OUTPUT)bpftool
+
+SRCS=$(wildcard *.c)
+OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+
+$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
+        $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
+
+$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
+        $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS)
+
+$(OUTPUT)%.o: %.c
+        $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
+
+clean: $(LIBBPF)-clean
+        $(call QUIET_CLEAN, bpftool)
+        $(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
+
+install:
+        install $(OUTPUT)bpftool $(prefix)/sbin/bpftool
+        install -m 0755 -d $(bash_compdir)
+        install -m 0644 bash-completion/bpftool $(bash_compdir)
+
+doc:
+        $(Q)$(MAKE) -C Documentation/
+
+doc-install:
+        $(Q)$(MAKE) -C Documentation/ install
+
+FORCE:
+
+.PHONY: all clean FORCE
+.DEFAULT_GOAL := all
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
new file mode 100644
index 000000000000..7febee05c8e7
--- /dev/null
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -0,0 +1,354 @@
+# bpftool(8) bash completion                               -*- shell-script -*-
+#
+# Copyright (C) 2017 Netronome Systems, Inc.
+#
+# This software is dual licensed under the GNU General License
+# Version 2, June 1991 as shown in the file COPYING in the top-level
+# directory of this source tree or the BSD 2-Clause License provided
+# below.  You have the option to license this software under the
+# complete terms of either license.
+#
+# The BSD 2-Clause License:
+#
+#     Redistribution and use in source and binary forms, with or
+#     without modification, are permitted provided that the following
+#     conditions are met:
+#
+#      1. Redistributions of source code must retain the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer.
+#
+#      2. Redistributions in binary form must reproduce the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer in the documentation and/or other materials
+#         provided with the distribution.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+#
+# Author: Quentin Monnet <quentin.monnet@netronome.com>
+
+# Takes a list of words in argument; each one of them is added to COMPREPLY if
+# it is not already present on the command line. Returns no value.
+_bpftool_once_attr()
+{
+    local w idx found
+    for w in $*; do
+        found=0
+        for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+            if [[ $w == ${words[idx]} ]]; then
+                found=1
+                break
+            fi
+        done
+        [[ $found -eq 0 ]] && \
+            COMPREPLY+=( $( compgen -W "$w" -- "$cur" ) )
+    done
+}
+
+# Takes a list of words in argument; adds them all to COMPREPLY if none of them
+# is already present on the command line. Returns no value.
+_bpftool_one_of_list()
+{
+    local w idx
+    for w in $*; do
+        for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+            [[ $w == ${words[idx]} ]] && return 1
+        done
+    done
+    COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) )
+}
+
+_bpftool_get_map_ids()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp map  2>&1 | \
+        command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+_bpftool_get_prog_ids()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
+        command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+_bpftool_get_prog_tags()
+{
+    COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
+        command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
+}
+
+# For bpftool map update: retrieve type of the map to update.
+_bpftool_map_update_map_type()
+{
+    local keyword ref
+    for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+        if [[ ${words[$((idx-2))]} == "update" ]]; then
+            keyword=${words[$((idx-1))]}
+            ref=${words[$((idx))]}
+        fi
+    done
+    [[ -z $ref ]] && return 0
+
+    local type
+    type=$(bpftool -jp map show $keyword $ref | \
+        command sed -n 's/.*"type": "\(.*\)",$/\1/p')
+    printf $type
+}
+
+_bpftool_map_update_get_id()
+{
+    # Is it the map to update, or a map to insert into the map to update?
+    # Search for "value" keyword.
+    local idx value
+    for (( idx=7; idx < ${#words[@]}-1; idx++ )); do
+        if [[ ${words[idx]} == "value" ]]; then
+            value=1
+            break
+        fi
+    done
+    [[ $value -eq 0 ]] && _bpftool_get_map_ids && return 0
+
+    # Id to complete is for a value. It can be either prog id or map id. This
+    # depends on the type of the map to update.
+    local type=$(_bpftool_map_update_map_type)
+    case $type in
+        array_of_maps|hash_of_maps)
+            _bpftool_get_map_ids
+            return 0
+            ;;
+        prog_array)
+            _bpftool_get_prog_ids
+            return 0
+            ;;
+        *)
+            return 0
+            ;;
+    esac
+}
+
+_bpftool()
+{
+    local cur prev words objword
+    _init_completion || return
+
+    # Deal with simplest keywords
+    case $prev in
+        help|key|opcodes)
+            return 0
+            ;;
+        tag)
+            _bpftool_get_prog_tags
+            return 0
+            ;;
+        file|pinned)
+            _filedir
+            return 0
+            ;;
+        batch)
+            COMPREPLY=( $( compgen -W 'file' -- "$cur" ) )
+            return 0
+            ;;
+    esac
+
+    # Search for object and command
+    local object command cmdword
+    for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do
+        [[ -n $object ]] && command=${words[cmdword]} && break
+        [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]}
+    done
+
+    if [[ -z $object ]]; then
+        case $cur in
+            -*)
+                local c='--version --json --pretty'
+                COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
+                return 0
+                ;;
+            *)
+                COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \
+                    command sed \
+                    -e '/OBJECT := /!d' \
+                    -e 's/.*{//' \
+                    -e 's/}.*//' \
+                    -e 's/|//g' )" -- "$cur" ) )
+                COMPREPLY+=( $( compgen -W 'batch help' -- "$cur" ) )
+                return 0
+                ;;
+        esac
+    fi
+
+    [[ $command == help ]] && return 0
+
+    # Completion depends on object and command in use
+    case $object in
+        prog)
+            case $prev in
+                id)
+                    _bpftool_get_prog_ids
+                    return 0
+                    ;;
+            esac
+
+            local PROG_TYPE='id pinned tag'
+            case $command in
+                show)
+                    [[ $prev != "$command" ]] && return 0
+                    COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    return 0
+                    ;;
+                dump)
+                    case $prev in
+                        $command)
+                            COMPREPLY+=( $( compgen -W "xlated jited" -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                        xlated|jited)
+                            COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                    *)
+                            _bpftool_once_attr 'file'
+                            COMPREPLY+=( $( compgen -W 'opcodes' -- \
+                                "$cur" ) )
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                pin)
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    else
+                        _filedir
+                    fi
+                    return 0
+                    ;;
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'dump help pin show' -- \
+                            "$cur" ) )
+                    ;;
+            esac
+            ;;
+        map)
+            local MAP_TYPE='id pinned'
+            case $command in
+                show|dump)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        *)
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                lookup|getnext|delete)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        key)
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'key'
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                update)
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_map_update_get_id
+                            return 0
+                            ;;
+                        key)
+                            return 0
+                            ;;
+                        value)
+                            # We can have bytes, or references to a prog or a
+                            # map, depending on the type of the map to update.
+                            case $(_bpftool_map_update_map_type) in
+                                array_of_maps|hash_of_maps)
+                                    local MAP_TYPE='id pinned'
+                                    COMPREPLY+=( $( compgen -W "$MAP_TYPE" \
+                                        -- "$cur" ) )
+                                    return 0
+                                    ;;
+                                prog_array)
+                                    local PROG_TYPE='id pinned tag'
+                                    COMPREPLY+=( $( compgen -W "$PROG_TYPE" \
+                                        -- "$cur" ) )
+                                    return 0
+                                    ;;
+                                *)
+                                    return 0
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'key'
+                            local UPDATE_FLAGS='any exist noexist'
+                            for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+                                if [[ ${words[idx]} == 'value' ]]; then
+                                    # 'value' is present, but is not the last
+                                    # word i.e. we can now have UPDATE_FLAGS.
+                                    _bpftool_one_of_list "$UPDATE_FLAGS"
+                                    return 0
+                                fi
+                            done
+                            for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
+                                if [[ ${words[idx]} == 'key' ]]; then
+                                    # 'key' is present, but is not the last
+                                    # word i.e. we can now have 'value'.
+                                    _bpftool_once_attr 'value'
+                                    return 0
+                                fi
+                            done
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                pin)
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                    else
+                        _filedir
+                    fi
+                    return 0
+                    ;;
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'delete dump getnext help \
+                            lookup pin show update' -- "$cur" ) )
+                    ;;
+            esac
+            ;;
+    esac
+} &&
+complete -F _bpftool bpftool
+
+# ex: ts=4 sw=4 et filetype=sh
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
new file mode 100644
index 000000000000..2bd3b280e6dd
--- /dev/null
+++ b/tools/bpf/bpftool/common.c
@@ -0,0 +1,405 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <errno.h>
+#include <fts.h>
+#include <libgen.h>
+#include <mntent.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/limits.h>
+#include <linux/magic.h>
+#include <sys/mount.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+void p_err(const char *fmt, ...)
+{
+        va_list ap;
+
+        va_start(ap, fmt);
+        if (json_output) {
+                jsonw_start_object(json_wtr);
+                jsonw_name(json_wtr, "error");
+                jsonw_vprintf_enquote(json_wtr, fmt, ap);
+                jsonw_end_object(json_wtr);
+        } else {
+                fprintf(stderr, "Error: ");
+                vfprintf(stderr, fmt, ap);
+                fprintf(stderr, "\n");
+        }
+        va_end(ap);
+}
+
+void p_info(const char *fmt, ...)
+{
+        va_list ap;
+
+        if (json_output)
+                return;
+
+        va_start(ap, fmt);
+        vfprintf(stderr, fmt, ap);
+        fprintf(stderr, "\n");
+        va_end(ap);
+}
+
+static bool is_bpffs(char *path)
+{
+        struct statfs st_fs;
+
+        if (statfs(path, &st_fs) < 0)
+                return false;
+
+        return (unsigned long)st_fs.f_type == BPF_FS_MAGIC;
+}
+
+static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
+{
+        bool bind_done = false;
+
+        while (mount("", target, "none", MS_PRIVATE | MS_REC, NULL)) {
+                if (errno != EINVAL || bind_done) {
+                        snprintf(buff, bufflen,
+                                 "mount --make-private %s failed: %s",
+                                 target, strerror(errno));
+                        return -1;
+                }
+
+                if (mount(target, target, "none", MS_BIND, NULL)) {
+                        snprintf(buff, bufflen,
+                                 "mount --bind %s %s failed: %s",
+                                 target, target, strerror(errno));
+                        return -1;
+                }
+
+                bind_done = true;
+        }
+
+        if (mount("bpf", target, "bpf", 0, "mode=0700")) {
+                snprintf(buff, bufflen, "mount -t bpf bpf %s failed: %s",
+                         target, strerror(errno));
+                return -1;
+        }
+
+        return 0;
+}
+
+int open_obj_pinned(char *path)
+{
+        int fd;
+
+        fd = bpf_obj_get(path);
+        if (fd < 0) {
+                p_err("bpf obj get (%s): %s", path,
+                      errno == EACCES && !is_bpffs(dirname(path)) ?
+                    "directory not in bpf file system (bpffs)" :
+                    strerror(errno));
+                return -1;
+        }
+
+        return fd;
+}
+
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
+{
+        enum bpf_obj_type type;
+        int fd;
+
+        fd = open_obj_pinned(path);
+        if (fd < 0)
+                return -1;
+
+        type = get_fd_type(fd);
+        if (type < 0) {
+                close(fd);
+                return type;
+        }
+        if (type != exp_type) {
+                p_err("incorrect object type: %s", get_fd_type_name(type));
+                close(fd);
+                return -1;
+        }
+
+        return fd;
+}
+
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
+{
+        char err_str[ERR_MAX_LEN];
+        unsigned int id;
+        char *endptr;
+        char *file;
+        char *dir;
+        int err;
+        int fd;
+
+        if (!is_prefix(*argv, "id")) {
+                p_err("expected 'id' got %s", *argv);
+                return -1;
+        }
+        NEXT_ARG();
+
+        id = strtoul(*argv, &endptr, 0);
+        if (*endptr) {
+                p_err("can't parse %s as ID", *argv);
+                return -1;
+        }
+        NEXT_ARG();
+
+        if (argc != 1)
+                usage();
+
+        fd = get_fd_by_id(id);
+        if (fd < 0) {
+                p_err("can't get prog by id (%u): %s", id, strerror(errno));
+                return -1;
+        }
+
+        err = bpf_obj_pin(fd, *argv);
+        if (!err)
+                goto out_close;
+
+        file = malloc(strlen(*argv) + 1);
+        strcpy(file, *argv);
+        dir = dirname(file);
+
+        if (errno != EPERM || is_bpffs(dir)) {
+                p_err("can't pin the object (%s): %s", *argv, strerror(errno));
+                goto out_free;
+        }
+
+        /* Attempt to mount bpffs, then retry pinning. */
+        err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
+        if (!err) {
+                err = bpf_obj_pin(fd, *argv);
+                if (err)
+                        p_err("can't pin the object (%s): %s", *argv,
+                              strerror(errno));
+        } else {
+                err_str[ERR_MAX_LEN - 1] = '\0';
+                p_err("can't mount BPF file system to pin the object (%s): %s",
+                      *argv, err_str);
+        }
+
+out_free:
+        free(file);
+out_close:
+        close(fd);
+        return err;
+}
+
+const char *get_fd_type_name(enum bpf_obj_type type)
+{
+        static const char * const names[] = {
+                [BPF_OBJ_UNKNOWN]       = "unknown",
+                [BPF_OBJ_PROG]          = "prog",
+                [BPF_OBJ_MAP]           = "map",
+        };
+
+        if (type < 0 || type >= ARRAY_SIZE(names) || !names[type])
+                return names[BPF_OBJ_UNKNOWN];
+
+        return names[type];
+}
+
+int get_fd_type(int fd)
+{
+        char path[PATH_MAX];
+        char buf[512];
+        ssize_t n;
+
+        snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd);
+
+        n = readlink(path, buf, sizeof(buf));
+        if (n < 0) {
+                p_err("can't read link type: %s", strerror(errno));
+                return -1;
+        }
+        if (n == sizeof(path)) {
+                p_err("can't read link type: path too long!");
+                return -1;
+        }
+
+        if (strstr(buf, "bpf-map"))
+                return BPF_OBJ_MAP;
+        else if (strstr(buf, "bpf-prog"))
+                return BPF_OBJ_PROG;
+
+        return BPF_OBJ_UNKNOWN;
+}
+
+char *get_fdinfo(int fd, const char *key)
+{
+        char path[PATH_MAX];
+        char *line = NULL;
+        size_t line_n = 0;
+        ssize_t n;
+        FILE *fdi;
+
+        snprintf(path, sizeof(path), "/proc/%d/fdinfo/%d", getpid(), fd);
+
+        fdi = fopen(path, "r");
+        if (!fdi) {
+                p_err("can't open fdinfo: %s", strerror(errno));
+                return NULL;
+        }
+
+        while ((n = getline(&line, &line_n, fdi))) {
+                char *value;
+                int len;
+
+                if (!strstr(line, key))
+                        continue;
+
+                fclose(fdi);
+
+                value = strchr(line, '\t');
+                if (!value || !value[1]) {
+                        p_err("malformed fdinfo!?");
+                        free(line);
+                        return NULL;
+                }
+                value++;
+
+                len = strlen(value);
+                memmove(line, value, len);
+                line[len - 1] = '\0';
+
+                return line;
+        }
+
+        p_err("key '%s' not found in fdinfo", key);
+        free(line);
+        fclose(fdi);
+        return NULL;
+}
+
+void print_hex_data_json(uint8_t *data, size_t len)
+{
+        unsigned int i;
+
+        jsonw_start_array(json_wtr);
+        for (i = 0; i < len; i++)
+                jsonw_printf(json_wtr, "\"0x%02hhx\"", data[i]);
+        jsonw_end_array(json_wtr);
+}
+
+int build_pinned_obj_table(struct pinned_obj_table *tab,
+                           enum bpf_obj_type type)
+{
+        struct bpf_prog_info pinned_info = {};
+        struct pinned_obj *obj_node = NULL;
+        __u32 len = sizeof(pinned_info);
+        struct mntent *mntent = NULL;
+        enum bpf_obj_type objtype;
+        FILE *mntfile = NULL;
+        FTSENT *ftse = NULL;
+        FTS *fts = NULL;
+        int fd, err;
+
+        mntfile = setmntent("/proc/mounts", "r");
+        if (!mntfile)
+                return -1;
+
+        while ((mntent = getmntent(mntfile))) {
+                char *path[] = { mntent->mnt_dir, NULL };
+
+                if (strncmp(mntent->mnt_type, "bpf", 3) != 0)
+                        continue;
+
+                fts = fts_open(path, 0, NULL);
+                if (!fts)
+                        continue;
+
+                while ((ftse = fts_read(fts))) {
+                        if (!(ftse->fts_info & FTS_F))
+                                continue;
+                        fd = open_obj_pinned(ftse->fts_path);
+                        if (fd < 0)
+                                continue;
+
+                        objtype = get_fd_type(fd);
+                        if (objtype != type) {
+                                close(fd);
+                                continue;
+                        }
+                        memset(&pinned_info, 0, sizeof(pinned_info));
+                        err = bpf_obj_get_info_by_fd(fd, &pinned_info, &len);
+                        if (err) {
+                                close(fd);
+                                continue;
+                        }
+
+                        obj_node = malloc(sizeof(*obj_node));
+                        if (!obj_node) {
+                                close(fd);
+                                fts_close(fts);
+                                fclose(mntfile);
+                                return -1;
+                        }
+
+                        memset(obj_node, 0, sizeof(*obj_node));
+                        obj_node->id = pinned_info.id;
+                        obj_node->path = strdup(ftse->fts_path);
+                        hash_add(tab->table, &obj_node->hash, obj_node->id);
+
+                        close(fd);
+                }
+                fts_close(fts);
+        }
+        fclose(mntfile);
+        return 0;
+}
+
+void delete_pinned_obj_table(struct pinned_obj_table *tab)
+{
+        struct pinned_obj *obj;
+        struct hlist_node *tmp;
+        unsigned int bkt;
+
+        hash_for_each_safe(tab->table, bkt, tmp, obj, hash) {
+                hash_del(&obj->hash);
+                free(obj->path);
+                free(obj);
+        }
+}
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
new file mode 100644
index 000000000000..1551d3918d4c
--- /dev/null
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -0,0 +1,162 @@
+/*
+ * Based on:
+ *
+ * Minimal BPF JIT image disassembler
+ *
+ * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for
+ * debugging or verification purposes.
+ *
+ * Copyright 2013 Daniel Borkmann <daniel@iogearbox.net>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdarg.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <string.h>
+#include <bfd.h>
+#include <dis-asm.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <limits.h>
+
+#include "json_writer.h"
+#include "main.h"
+
+static void get_exec_path(char *tpath, size_t size)
+{
+        ssize_t len;
+        char *path;
+
+        snprintf(tpath, size, "/proc/%d/exe", (int) getpid());
+        tpath[size - 1] = 0;
+
+        path = strdup(tpath);
+        assert(path);
+
+        len = readlink(path, tpath, size - 1);
+        assert(len > 0);
+        tpath[len] = 0;
+
+        free(path);
+}
+
+static int oper_count;
+static int fprintf_json(void *out, const char *fmt, ...)
+{
+        va_list ap;
+        char *s;
+
+        va_start(ap, fmt);
+        if (!oper_count) {
+                int i;
+
+                s = va_arg(ap, char *);
+
+                /* Strip trailing spaces */
+                i = strlen(s) - 1;
+                while (s[i] == ' ')
+                        s[i--] = '\0';
+
+                jsonw_string_field(json_wtr, "operation", s);
+                jsonw_name(json_wtr, "operands");
+                jsonw_start_array(json_wtr);
+                oper_count++;
+        } else if (!strcmp(fmt, ",")) {
+                   /* Skip */
+        } else {
+                s = va_arg(ap, char *);
+                jsonw_string(json_wtr, s);
+                oper_count++;
+        }
+        va_end(ap);
+        return 0;
+}
+
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
+{
+        disassembler_ftype disassemble;
+        struct disassemble_info info;
+        int count, i, pc = 0;
+        char tpath[PATH_MAX];
+        bfd *bfdf;
+
+        if (!len)
+                return;
+
+        memset(tpath, 0, sizeof(tpath));
+        get_exec_path(tpath, sizeof(tpath));
+
+        bfdf = bfd_openr(tpath, NULL);
+        assert(bfdf);
+        assert(bfd_check_format(bfdf, bfd_object));
+
+        if (json_output)
+                init_disassemble_info(&info, stdout,
+                                      (fprintf_ftype) fprintf_json);
+        else
+                init_disassemble_info(&info, stdout,
+                                      (fprintf_ftype) fprintf);
+        info.arch = bfd_get_arch(bfdf);
+        info.mach = bfd_get_mach(bfdf);
+        info.buffer = image;
+        info.buffer_length = len;
+
+        disassemble_init_for_target(&info);
+
+        disassemble = disassembler(bfdf);
+        assert(disassemble);
+
+        if (json_output)
+                jsonw_start_array(json_wtr);
+        do {
+                if (json_output) {
+                        jsonw_start_object(json_wtr);
+                        oper_count = 0;
+                        jsonw_name(json_wtr, "pc");
+                        jsonw_printf(json_wtr, "\"0x%x\"", pc);
+                } else {
+                        printf("%4x:\t", pc);
+                }
+
+                count = disassemble(pc, &info);
+                if (json_output) {
+                        /* Operand array, was started in fprintf_json. Before
+                         * that, make sure we have a _null_ value if no operand
+                         * other than operation code was present.
+                         */
+                        if (oper_count == 1)
+                                jsonw_null(json_wtr);
+                        jsonw_end_array(json_wtr);
+                }
+
+                if (opcodes) {
+                        if (json_output) {
+                                jsonw_name(json_wtr, "opcodes");
+                                jsonw_start_array(json_wtr);
+                                for (i = 0; i < count; ++i)
+                                        jsonw_printf(json_wtr, "\"0x%02hhx\"",
+                                                     (uint8_t)image[pc + i]);
+                                jsonw_end_array(json_wtr);
+                        } else {
+                                printf("\n\t");
+                                for (i = 0; i < count; ++i)
+                                        printf("%02x ",
+                                               (uint8_t)image[pc + i]);
+                        }
+                }
+                if (json_output)
+                        jsonw_end_object(json_wtr);
+                else
+                        printf("\n");
+
+                pc += count;
+        } while (count > 0 && pc < len);
+        if (json_output)
+                jsonw_end_array(json_wtr);
+
+        bfd_close(bfdf);
+}
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
new file mode 100644
index 000000000000..c6eef76322ae
--- /dev/null
+++ b/tools/bpf/bpftool/json_writer.c
@@ -0,0 +1,356 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors:     Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
+#include <assert.h>
+#include <malloc.h>
+#include <inttypes.h>
+#include <stdint.h>
+
+#include "json_writer.h"
+
+struct json_writer {
+        FILE            *out;   /* output file */
+        unsigned        depth;  /* nesting */
+        bool            pretty; /* optional whitepace */
+        char            sep;    /* either nul or comma */
+};
+
+/* indentation for pretty print */
+static void jsonw_indent(json_writer_t *self)
+{
+        unsigned i;
+        for (i = 0; i < self->depth; ++i)
+                fputs("    ", self->out);
+}
+
+/* end current line and indent if pretty printing */
+static void jsonw_eol(json_writer_t *self)
+{
+        if (!self->pretty)
+                return;
+
+        putc('\n', self->out);
+        jsonw_indent(self);
+}
+
+/* If current object is not empty print a comma */
+static void jsonw_eor(json_writer_t *self)
+{
+        if (self->sep != '\0')
+                putc(self->sep, self->out);
+        self->sep = ',';
+}
+
+
+/* Output JSON encoded string */
+/* Handles C escapes, does not do Unicode */
+static void jsonw_puts(json_writer_t *self, const char *str)
+{
+        putc('"', self->out);
+        for (; *str; ++str)
+                switch (*str) {
+                case '\t':
+                        fputs("\\t", self->out);
+                        break;
+                case '\n':
+                        fputs("\\n", self->out);
+                        break;
+                case '\r':
+                        fputs("\\r", self->out);
+                        break;
+                case '\f':
+                        fputs("\\f", self->out);
+                        break;
+                case '\b':
+                        fputs("\\b", self->out);
+                        break;
+                case '\\':
+                        fputs("\\n", self->out);
+                        break;
+                case '"':
+                        fputs("\\\"", self->out);
+                        break;
+                case '\'':
+                        fputs("\\\'", self->out);
+                        break;
+                default:
+                        putc(*str, self->out);
+                }
+        putc('"', self->out);
+}
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f)
+{
+        json_writer_t *self = malloc(sizeof(*self));
+        if (self) {
+                self->out = f;
+                self->depth = 0;
+                self->pretty = false;
+                self->sep = '\0';
+        }
+        return self;
+}
+
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p)
+{
+        json_writer_t *self = *self_p;
+
+        assert(self->depth == 0);
+        fputs("\n", self->out);
+        fflush(self->out);
+        free(self);
+        *self_p = NULL;
+}
+
+void jsonw_pretty(json_writer_t *self, bool on)
+{
+        self->pretty = on;
+}
+
+/* Basic blocks */
+static void jsonw_begin(json_writer_t *self, int c)
+{
+        jsonw_eor(self);
+        putc(c, self->out);
+        ++self->depth;
+        self->sep = '\0';
+}
+
+static void jsonw_end(json_writer_t *self, int c)
+{
+        assert(self->depth > 0);
+
+        --self->depth;
+        if (self->sep != '\0')
+                jsonw_eol(self);
+        putc(c, self->out);
+        self->sep = ',';
+}
+
+
+/* Add a JSON property name */
+void jsonw_name(json_writer_t *self, const char *name)
+{
+        jsonw_eor(self);
+        jsonw_eol(self);
+        self->sep = '\0';
+        jsonw_puts(self, name);
+        putc(':', self->out);
+        if (self->pretty)
+                putc(' ', self->out);
+}
+
+void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
+{
+        jsonw_eor(self);
+        putc('"', self->out);
+        vfprintf(self->out, fmt, ap);
+        putc('"', self->out);
+}
+
+void jsonw_printf(json_writer_t *self, const char *fmt, ...)
+{
+        va_list ap;
+
+        va_start(ap, fmt);
+        jsonw_eor(self);
+        vfprintf(self->out, fmt, ap);
+        va_end(ap);
+}
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self)
+{
+        jsonw_begin(self, '{');
+}
+
+void jsonw_end_object(json_writer_t *self)
+{
+        jsonw_end(self, '}');
+}
+
+void jsonw_start_array(json_writer_t *self)
+{
+        jsonw_begin(self, '[');
+}
+
+void jsonw_end_array(json_writer_t *self)
+{
+        jsonw_end(self, ']');
+}
+
+/* JSON value types */
+void jsonw_string(json_writer_t *self, const char *value)
+{
+        jsonw_eor(self);
+        jsonw_puts(self, value);
+}
+
+void jsonw_bool(json_writer_t *self, bool val)
+{
+        jsonw_printf(self, "%s", val ? "true" : "false");
+}
+
+void jsonw_null(json_writer_t *self)
+{
+        jsonw_printf(self, "null");
+}
+
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num)
+{
+        jsonw_printf(self, fmt, num);
+}
+
+#ifdef notused
+void jsonw_float(json_writer_t *self, double num)
+{
+        jsonw_printf(self, "%g", num);
+}
+#endif
+
+void jsonw_hu(json_writer_t *self, unsigned short num)
+{
+        jsonw_printf(self, "%hu", num);
+}
+
+void jsonw_uint(json_writer_t *self, uint64_t num)
+{
+        jsonw_printf(self, "%"PRIu64, num);
+}
+
+void jsonw_lluint(json_writer_t *self, unsigned long long int num)
+{
+        jsonw_printf(self, "%llu", num);
+}
+
+void jsonw_int(json_writer_t *self, int64_t num)
+{
+        jsonw_printf(self, "%"PRId64, num);
+}
+
+/* Basic name/value objects */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val)
+{
+        jsonw_name(self, prop);
+        jsonw_string(self, val);
+}
+
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool val)
+{
+        jsonw_name(self, prop);
+        jsonw_bool(self, val);
+}
+
+#ifdef notused
+void jsonw_float_field(json_writer_t *self, const char *prop, double val)
+{
+        jsonw_name(self, prop);
+        jsonw_float(self, val);
+}
+#endif
+
+void jsonw_float_field_fmt(json_writer_t *self,
+                           const char *prop,
+                           const char *fmt,
+                           double val)
+{
+        jsonw_name(self, prop);
+        jsonw_float_fmt(self, fmt, val);
+}
+
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num)
+{
+        jsonw_name(self, prop);
+        jsonw_uint(self, num);
+}
+
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num)
+{
+        jsonw_name(self, prop);
+        jsonw_hu(self, num);
+}
+
+void jsonw_lluint_field(json_writer_t *self,
+                        const char *prop,
+                        unsigned long long int num)
+{
+        jsonw_name(self, prop);
+        jsonw_lluint(self, num);
+}
+
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num)
+{
+        jsonw_name(self, prop);
+        jsonw_int(self, num);
+}
+
+void jsonw_null_field(json_writer_t *self, const char *prop)
+{
+        jsonw_name(self, prop);
+        jsonw_null(self);
+}
+
+#ifdef TEST
+int main(int argc, char **argv)
+{
+        json_writer_t *wr = jsonw_new(stdout);
+
+        jsonw_start_object(wr);
+        jsonw_pretty(wr, true);
+        jsonw_name(wr, "Vyatta");
+        jsonw_start_object(wr);
+        jsonw_string_field(wr, "url", "http://vyatta.com");
+        jsonw_uint_field(wr, "downloads", 2000000ul);
+        jsonw_float_field(wr, "stock", 8.16);
+
+        jsonw_name(wr, "ARGV");
+        jsonw_start_array(wr);
+        while (--argc)
+                jsonw_string(wr, *++argv);
+        jsonw_end_array(wr);
+
+        jsonw_name(wr, "empty");
+        jsonw_start_array(wr);
+        jsonw_end_array(wr);
+
+        jsonw_name(wr, "NIL");
+        jsonw_start_object(wr);
+        jsonw_end_object(wr);
+
+        jsonw_null_field(wr, "my_null");
+
+        jsonw_name(wr, "special chars");
+        jsonw_start_array(wr);
+        jsonw_string_field(wr, "slash", "/");
+        jsonw_string_field(wr, "newline", "\n");
+        jsonw_string_field(wr, "tab", "\t");
+        jsonw_string_field(wr, "ff", "\f");
+        jsonw_string_field(wr, "quote", "\"");
+        jsonw_string_field(wr, "tick", "\'");
+        jsonw_string_field(wr, "backslash", "\\");
+        jsonw_end_array(wr);
+
+        jsonw_end_object(wr);
+
+        jsonw_end_object(wr);
+        jsonw_destroy(&wr);
+        return 0;
+}
+
+#endif
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
new file mode 100644
index 000000000000..0fa2fb1b6351
--- /dev/null
+++ b/tools/bpf/bpftool/json_writer.h
@@ -0,0 +1,72 @@
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors:     Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#ifndef _JSON_WRITER_H_
+#define _JSON_WRITER_H_
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdarg.h>
+
+/* Opaque class structure */
+typedef struct json_writer json_writer_t;
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f);
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p);
+
+/* Cause output to have pretty whitespace */
+void jsonw_pretty(json_writer_t *self, bool on);
+
+/* Add property name */
+void jsonw_name(json_writer_t *self, const char *name);
+
+/* Add value  */
+void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap);
+void jsonw_printf(json_writer_t *self, const char *fmt, ...);
+void jsonw_string(json_writer_t *self, const char *value);
+void jsonw_bool(json_writer_t *self, bool value);
+void jsonw_float(json_writer_t *self, double number);
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num);
+void jsonw_uint(json_writer_t *self, uint64_t number);
+void jsonw_hu(json_writer_t *self, unsigned short number);
+void jsonw_int(json_writer_t *self, int64_t number);
+void jsonw_null(json_writer_t *self);
+void jsonw_lluint(json_writer_t *self, unsigned long long int num);
+
+/* Useful Combinations of name and value */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
+void jsonw_float_field(json_writer_t *self, const char *prop, double num);
+void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num);
+void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num);
+void jsonw_null_field(json_writer_t *self, const char *prop);
+void jsonw_lluint_field(json_writer_t *self, const char *prop,
+                        unsigned long long int num);
+void jsonw_float_field_fmt(json_writer_t *self, const char *prop,
+                           const char *fmt, double val);
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self);
+void jsonw_end_object(json_writer_t *self);
+
+void jsonw_start_array(json_writer_t *self);
+void jsonw_end_array(json_writer_t *self);
+
+/* Override default exception handling */
+typedef void (jsonw_err_handler_fn)(const char *);
+
+#endif /* _JSON_WRITER_H_ */
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
new file mode 100644
index 000000000000..d6e4762170a4
--- /dev/null
+++ b/tools/bpf/bpftool/main.c
@@ -0,0 +1,331 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <bfd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <getopt.h>
+#include <linux/bpf.h>
+#include <linux/version.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+const char *bin_name;
+static int last_argc;
+static char **last_argv;
+static int (*last_do_help)(int argc, char **argv);
+json_writer_t *json_wtr;
+bool pretty_output;
+bool json_output;
+bool show_pinned;
+struct pinned_obj_table prog_table;
+struct pinned_obj_table map_table;
+
+void usage(void)
+{
+        last_do_help(last_argc - 1, last_argv + 1);
+
+        exit(-1);
+}
+
+static int do_help(int argc, char **argv)
+{
+        if (json_output) {
+                jsonw_null(json_wtr);
+                return 0;
+        }
+
+        fprintf(stderr,
+                "Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n"
+                "       %s batch file FILE\n"
+                "       %s version\n"
+                "\n"
+                "       OBJECT := { prog | map }\n"
+                "       " HELP_SPEC_OPTIONS "\n"
+                "",
+                bin_name, bin_name, bin_name);
+
+        return 0;
+}
+
+static int do_version(int argc, char **argv)
+{
+        unsigned int version[3];
+
+        version[0] = LINUX_VERSION_CODE >> 16;
+        version[1] = LINUX_VERSION_CODE >> 8 & 0xf;
+        version[2] = LINUX_VERSION_CODE & 0xf;
+
+        if (json_output) {
+                jsonw_start_object(json_wtr);
+                jsonw_name(json_wtr, "version");
+                jsonw_printf(json_wtr, "\"%u.%u.%u\"",
+                             version[0], version[1], version[2]);
+                jsonw_end_object(json_wtr);
+        } else {
+                printf("%s v%u.%u.%u\n", bin_name,
+                       version[0], version[1], version[2]);
+        }
+        return 0;
+}
+
+int cmd_select(const struct cmd *cmds, int argc, char **argv,
+               int (*help)(int argc, char **argv))
+{
+        unsigned int i;
+
+        last_argc = argc;
+        last_argv = argv;
+        last_do_help = help;
+
+        if (argc < 1 && cmds[0].func)
+                return cmds[0].func(argc, argv);
+
+        for (i = 0; cmds[i].func; i++)
+                if (is_prefix(*argv, cmds[i].cmd))
+                        return cmds[i].func(argc - 1, argv + 1);
+
+        help(argc - 1, argv + 1);
+
+        return -1;
+}
+
+bool is_prefix(const char *pfx, const char *str)
+{
+        if (!pfx)
+                return false;
+        if (strlen(str) < strlen(pfx))
+                return false;
+
+        return !memcmp(str, pfx, strlen(pfx));
+}
+
+void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep)
+{
+        unsigned char *data = arg;
+        unsigned int i;
+
+        for (i = 0; i < n; i++) {
+                const char *pfx = "";
+
+                if (!i)
+                        /* nothing */;
+                else if (!(i % 16))
+                        fprintf(f, "\n");
+                else if (!(i % 8))
+                        fprintf(f, "  ");
+                else
+                        pfx = sep;
+
+                fprintf(f, "%s%02hhx", i ? pfx : "", data[i]);
+        }
+}
+
+static int do_batch(int argc, char **argv);
+
+static const struct cmd cmds[] = {
+        { "help",       do_help },
+        { "batch",      do_batch },
+        { "prog",       do_prog },
+        { "map",        do_map },
+        { "version",    do_version },
+        { 0 }
+};
+
+static int do_batch(int argc, char **argv)
+{
+        unsigned int lines = 0;
+        char *n_argv[4096];
+        char buf[65536];
+        int n_argc;
+        FILE *fp;
+        int err;
+        int i;
+
+        if (argc < 2) {
+                p_err("too few parameters for batch");
+                return -1;
+        } else if (!is_prefix(*argv, "file")) {
+                p_err("expected 'file', got: %s", *argv);
+                return -1;
+        } else if (argc > 2) {
+                p_err("too many parameters for batch");
+                return -1;
+        }
+        NEXT_ARG();
+
+        fp = fopen(*argv, "r");
+        if (!fp) {
+                p_err("Can't open file (%s): %s", *argv, strerror(errno));
+                return -1;
+        }
+
+        if (json_output)
+                jsonw_start_array(json_wtr);
+        while (fgets(buf, sizeof(buf), fp)) {
+                if (strlen(buf) == sizeof(buf) - 1) {
+                        errno = E2BIG;
+                        break;
+                }
+
+                n_argc = 0;
+                n_argv[n_argc] = strtok(buf, " \t\n");
+
+                while (n_argv[n_argc]) {
+                        n_argc++;
+                        if (n_argc == ARRAY_SIZE(n_argv)) {
+                                p_err("line %d has too many arguments, skip",
+                                      lines);
+                                n_argc = 0;
+                                break;
+                        }
+                        n_argv[n_argc] = strtok(NULL, " \t\n");
+                }
+
+                if (!n_argc)
+                        continue;
+
+                if (json_output) {
+                        jsonw_start_object(json_wtr);
+                        jsonw_name(json_wtr, "command");
+                        jsonw_start_array(json_wtr);
+                        for (i = 0; i < n_argc; i++)
+                                jsonw_string(json_wtr, n_argv[i]);
+                        jsonw_end_array(json_wtr);
+                        jsonw_name(json_wtr, "output");
+                }
+
+                err = cmd_select(cmds, n_argc, n_argv, do_help);
+
+                if (json_output)
+                        jsonw_end_object(json_wtr);
+
+                if (err)
+                        goto err_close;
+
+                lines++;
+        }
+
+        if (errno && errno != ENOENT) {
+                perror("reading batch file failed");
+                err = -1;
+        } else {
+                p_info("processed %d lines", lines);
+                err = 0;
+        }
+err_close:
+        fclose(fp);
+
+        if (json_output)
+                jsonw_end_array(json_wtr);
+
+        return err;
+}
+
+int main(int argc, char **argv)
+{
+        static const struct option options[] = {
+                { "json",       no_argument,    NULL,   'j' },
+                { "help",       no_argument,    NULL,   'h' },
+                { "pretty",     no_argument,    NULL,   'p' },
+                { "version",    no_argument,    NULL,   'V' },
+                { "bpffs",      no_argument,    NULL,   'f' },
+                { 0 }
+        };
+        int opt, ret;
+
+        last_do_help = do_help;
+        pretty_output = false;
+        json_output = false;
+        show_pinned = false;
+        bin_name = argv[0];
+
+        hash_init(prog_table.table);
+        hash_init(map_table.table);
+
+        while ((opt = getopt_long(argc, argv, "Vhpjf",
+                                  options, NULL)) >= 0) {
+                switch (opt) {
+                case 'V':
+                        return do_version(argc, argv);
+                case 'h':
+                        return do_help(argc, argv);
+                case 'p':
+                        pretty_output = true;
+                        /* fall through */
+                case 'j':
+                        json_output = true;
+                        break;
+                case 'f':
+                        show_pinned = true;
+                        break;
+                default:
+                        usage();
+                }
+        }
+
+        argc -= optind;
+        argv += optind;
+        if (argc < 0)
+                usage();
+
+        if (json_output) {
+                json_wtr = jsonw_new(stdout);
+                if (!json_wtr) {
+                        p_err("failed to create JSON writer");
+                        return -1;
+                }
+                jsonw_pretty(json_wtr, pretty_output);
+        }
+
+        bfd_init();
+
+        ret = cmd_select(cmds, argc, argv, do_help);
+
+        if (json_output)
+                jsonw_destroy(&json_wtr);
+
+        if (show_pinned) {
+                delete_pinned_obj_table(&prog_table);
+                delete_pinned_obj_table(&map_table);
+        }
+
+        return ret;
+}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
new file mode 100644
index 000000000000..9c191e222d6f
--- /dev/null
+++ b/tools/bpf/bpftool/main.h
@@ -0,0 +1,122 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#ifndef __BPF_TOOL_H
+#define __BPF_TOOL_H
+
+/* BFD and kernel.h both define GCC_VERSION, differently */
+#undef GCC_VERSION
+#include <stdbool.h>
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <linux/kernel.h>
+#include <linux/hashtable.h>
+
+#include "json_writer.h"
+
+#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr))
+
+#define NEXT_ARG()      ({ argc--; argv++; if (argc < 0) usage(); })
+#define NEXT_ARGP()     ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
+#define BAD_ARG()       ({ p_err("what is '%s'?\n", *argv); -1; })
+
+#define ERR_MAX_LEN     1024
+
+#define BPF_TAG_FMT     "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
+
+#define HELP_SPEC_PROGRAM                                               \
+        "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
+#define HELP_SPEC_OPTIONS                                               \
+        "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+
+enum bpf_obj_type {
+        BPF_OBJ_UNKNOWN,
+        BPF_OBJ_PROG,
+        BPF_OBJ_MAP,
+};
+
+extern const char *bin_name;
+
+extern json_writer_t *json_wtr;
+extern bool json_output;
+extern bool show_pinned;
+extern struct pinned_obj_table prog_table;
+extern struct pinned_obj_table map_table;
+
+void p_err(const char *fmt, ...);
+void p_info(const char *fmt, ...);
+
+bool is_prefix(const char *pfx, const char *str);
+void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
+void usage(void) __attribute__((noreturn));
+
+struct pinned_obj_table {
+        DECLARE_HASHTABLE(table, 16);
+};
+
+struct pinned_obj {
+        __u32 id;
+        char *path;
+        struct hlist_node hash;
+};
+
+int build_pinned_obj_table(struct pinned_obj_table *table,
+                           enum bpf_obj_type type);
+void delete_pinned_obj_table(struct pinned_obj_table *tab);
+
+struct cmd {
+        const char *cmd;
+        int (*func)(int argc, char **argv);
+};
+
+int cmd_select(const struct cmd *cmds, int argc, char **argv,
+               int (*help)(int argc, char **argv));
+
+int get_fd_type(int fd);
+const char *get_fd_type_name(enum bpf_obj_type type);
+char *get_fdinfo(int fd, const char *key);
+int open_obj_pinned(char *path);
+int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
+
+int do_prog(int argc, char **arg);
+int do_map(int argc, char **arg);
+
+int prog_parse_fd(int *argc, char ***argv);
+
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
+void print_hex_data_json(uint8_t *data, size_t len);
+
+#endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
new file mode 100644
index 000000000000..e2450c8e88e6
--- /dev/null
+++ b/tools/bpf/bpftool/map.c
@@ -0,0 +1,899 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <assert.h>
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <bpf.h>
+
+#include "main.h"
+
+static const char * const map_type_name[] = {
+        [BPF_MAP_TYPE_UNSPEC]           = "unspec",
+        [BPF_MAP_TYPE_HASH]             = "hash",
+        [BPF_MAP_TYPE_ARRAY]            = "array",
+        [BPF_MAP_TYPE_PROG_ARRAY]       = "prog_array",
+        [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array",
+        [BPF_MAP_TYPE_PERCPU_HASH]      = "percpu_hash",
+        [BPF_MAP_TYPE_PERCPU_ARRAY]     = "percpu_array",
+        [BPF_MAP_TYPE_STACK_TRACE]      = "stack_trace",
+        [BPF_MAP_TYPE_CGROUP_ARRAY]     = "cgroup_array",
+        [BPF_MAP_TYPE_LRU_HASH]         = "lru_hash",
+        [BPF_MAP_TYPE_LRU_PERCPU_HASH]  = "lru_percpu_hash",
+        [BPF_MAP_TYPE_LPM_TRIE]         = "lpm_trie",
+        [BPF_MAP_TYPE_ARRAY_OF_MAPS]    = "array_of_maps",
+        [BPF_MAP_TYPE_HASH_OF_MAPS]     = "hash_of_maps",
+        [BPF_MAP_TYPE_DEVMAP]           = "devmap",
+        [BPF_MAP_TYPE_SOCKMAP]          = "sockmap",
+};
+
+static unsigned int get_possible_cpus(void)
+{
+        static unsigned int result;
+        char buf[128];
+        long int n;
+        char *ptr;
+        int fd;
+
+        if (result)
+                return result;
+
+        fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
+        if (fd < 0) {
+                p_err("can't open sysfs possible cpus");
+                exit(-1);
+        }
+
+        n = read(fd, buf, sizeof(buf));
+        if (n < 2) {
+                p_err("can't read sysfs possible cpus");
+                exit(-1);
+        }
+        close(fd);
+
+        if (n == sizeof(buf)) {
+                p_err("read sysfs possible cpus overflow");
+                exit(-1);
+        }
+
+        ptr = buf;
+        n = 0;
+        while (*ptr && *ptr != '\n') {
+                unsigned int a, b;
+
+                if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
+                        n += b - a + 1;
+
+                        ptr = strchr(ptr, '-') + 1;
+                } else if (sscanf(ptr, "%u", &a) == 1) {
+                        n++;
+                } else {
+                        assert(0);
+                }
+
+                while (isdigit(*ptr))
+                        ptr++;
+                if (*ptr == ',')
+                        ptr++;
+        }
+
+        result = n;
+
+        return result;
+}
+
+static bool map_is_per_cpu(__u32 type)
+{
+        return type == BPF_MAP_TYPE_PERCPU_HASH ||
+               type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+               type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool map_is_map_of_maps(__u32 type)
+{
+        return type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+               type == BPF_MAP_TYPE_HASH_OF_MAPS;
+}
+
+static bool map_is_map_of_progs(__u32 type)
+{
+        return type == BPF_MAP_TYPE_PROG_ARRAY;
+}
+
+static void *alloc_value(struct bpf_map_info *info)
+{
+        if (map_is_per_cpu(info->type))
+                return malloc(info->value_size * get_possible_cpus());
+        else
+                return malloc(info->value_size);
+}
+
+static int map_parse_fd(int *argc, char ***argv)
+{
+        int fd;
+
+        if (is_prefix(**argv, "id")) {
+                unsigned int id;
+                char *endptr;
+
+                NEXT_ARGP();
+
+                id = strtoul(**argv, &endptr, 0);
+                if (*endptr) {
+                        p_err("can't parse %s as ID", **argv);
+                        return -1;
+                }
+                NEXT_ARGP();
+
+                fd = bpf_map_get_fd_by_id(id);
+                if (fd < 0)
+                        p_err("get map by id (%u): %s", id, strerror(errno));
+                return fd;
+        } else if (is_prefix(**argv, "pinned")) {
+                char *path;
+
+                NEXT_ARGP();
+
+                path = **argv;
+                NEXT_ARGP();
+
+                return open_obj_pinned_any(path, BPF_OBJ_MAP);
+        }
+
+        p_err("expected 'id' or 'pinned', got: '%s'?", **argv);
+        return -1;
+}
+
+static int
+map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
+{
+        int err;
+        int fd;
+
+        fd = map_parse_fd(argc, argv);
+        if (fd < 0)
+                return -1;
+
+        err = bpf_obj_get_info_by_fd(fd, info, info_len);
+        if (err) {
+                p_err("can't get map info: %s", strerror(errno));
+                close(fd);
+                return err;
+        }
+
+        return fd;
+}
+
+static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
+                             unsigned char *value)
+{
+        jsonw_start_object(json_wtr);
+
+        if (!map_is_per_cpu(info->type)) {
+                jsonw_name(json_wtr, "key");
+                print_hex_data_json(key, info->key_size);
+                jsonw_name(json_wtr, "value");
+                print_hex_data_json(value, info->value_size);
+        } else {
+                unsigned int i, n;
+
+                n = get_possible_cpus();
+
+                jsonw_name(json_wtr, "key");
+                print_hex_data_json(key, info->key_size);
+
+                jsonw_name(json_wtr, "values");
+                jsonw_start_array(json_wtr);
+                for (i = 0; i < n; i++) {
+                        jsonw_start_object(json_wtr);
+
+                        jsonw_int_field(json_wtr, "cpu", i);
+
+                        jsonw_name(json_wtr, "value");
+                        print_hex_data_json(value + i * info->value_size,
+                                            info->value_size);
+
+                        jsonw_end_object(json_wtr);
+                }
+                jsonw_end_array(json_wtr);
+        }
+
+        jsonw_end_object(json_wtr);
+}
+
+static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
+                              unsigned char *value)
+{
+        if (!map_is_per_cpu(info->type)) {
+                bool single_line, break_names;
+
+                break_names = info->key_size > 16 || info->value_size > 16;
+                single_line = info->key_size + info->value_size <= 24 &&
+                        !break_names;
+
+                printf("key:%c", break_names ? '\n' : ' ');
+                fprint_hex(stdout, key, info->key_size, " ");
+
+                printf(single_line ? "  " : "\n");
+
+                printf("value:%c", break_names ? '\n' : ' ');
+                fprint_hex(stdout, value, info->value_size, " ");
+
+                printf("\n");
+        } else {
+                unsigned int i, n;
+
+                n = get_possible_cpus();
+
+                printf("key:\n");
+                fprint_hex(stdout, key, info->key_size, " ");
+                printf("\n");
+                for (i = 0; i < n; i++) {
+                        printf("value (CPU %02d):%c",
+                               i, info->value_size > 16 ? '\n' : ' ');
+                        fprint_hex(stdout, value + i * info->value_size,
+                                   info->value_size, " ");
+                        printf("\n");
+                }
+        }
+}
+
+static char **parse_bytes(char **argv, const char *name, unsigned char *val,
+                          unsigned int n)
+{
+        unsigned int i = 0;
+        char *endptr;
+
+        while (i < n && argv[i]) {
+                val[i] = strtoul(argv[i], &endptr, 0);
+                if (*endptr) {
+                        p_err("error parsing byte: %s", argv[i]);
+                        return NULL;
+                }
+                i++;
+        }
+
+        if (i != n) {
+                p_err("%s expected %d bytes got %d", name, n, i);
+                return NULL;
+        }
+
+        return argv + i;
+}
+
+static int parse_elem(char **argv, struct bpf_map_info *info,
+                      void *key, void *value, __u32 key_size, __u32 value_size,
+                      __u32 *flags, __u32 **value_fd)
+{
+        if (!*argv) {
+                if (!key && !value)
+                        return 0;
+                p_err("did not find %s", key ? "key" : "value");
+                return -1;
+        }
+
+        if (is_prefix(*argv, "key")) {
+                if (!key) {
+                        if (key_size)
+                                p_err("duplicate key");
+                        else
+                                p_err("unnecessary key");
+                        return -1;
+                }
+
+                argv = parse_bytes(argv + 1, "key", key, key_size);
+                if (!argv)
+                        return -1;
+
+                return parse_elem(argv, info, NULL, value, key_size, value_size,
+                                  flags, value_fd);
+        } else if (is_prefix(*argv, "value")) {
+                int fd;
+
+                if (!value) {
+                        if (value_size)
+                                p_err("duplicate value");
+                        else
+                                p_err("unnecessary value");
+                        return -1;
+                }
+
+                argv++;
+
+                if (map_is_map_of_maps(info->type)) {
+                        int argc = 2;
+
+                        if (value_size != 4) {
+                                p_err("value smaller than 4B for map in map?");
+                                return -1;
+                        }
+                        if (!argv[0] || !argv[1]) {
+                                p_err("not enough value arguments for map in map");
+                                return -1;
+                        }
+
+                        fd = map_parse_fd(&argc, &argv);
+                        if (fd < 0)
+                                return -1;
+
+                        *value_fd = value;
+                        **value_fd = fd;
+                } else if (map_is_map_of_progs(info->type)) {
+                        int argc = 2;
+
+                        if (value_size != 4) {
+                                p_err("value smaller than 4B for map of progs?");
+                                return -1;
+                        }
+                        if (!argv[0] || !argv[1]) {
+                                p_err("not enough value arguments for map of progs");
+                                return -1;
+                        }
+
+                        fd = prog_parse_fd(&argc, &argv);
+                        if (fd < 0)
+                                return -1;
+
+                        *value_fd = value;
+                        **value_fd = fd;
+                } else {
+                        argv = parse_bytes(argv, "value", value, value_size);
+                        if (!argv)
+                                return -1;
+                }
+
+                return parse_elem(argv, info, key, NULL, key_size, value_size,
+                                  flags, NULL);
+        } else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") ||
+                   is_prefix(*argv, "exist")) {
+                if (!flags) {
+                        p_err("flags specified multiple times: %s", *argv);
+                        return -1;
+                }
+
+                if (is_prefix(*argv, "any"))
+                        *flags = BPF_ANY;
+                else if (is_prefix(*argv, "noexist"))
+                        *flags = BPF_NOEXIST;
+                else if (is_prefix(*argv, "exist"))
+                        *flags = BPF_EXIST;
+
+                return parse_elem(argv + 1, info, key, value, key_size,
+                                  value_size, NULL, value_fd);
+        }
+
+        p_err("expected key or value, got: %s", *argv);
+        return -1;
+}
+
+static int show_map_close_json(int fd, struct bpf_map_info *info)
+{
+        char *memlock;
+
+        memlock = get_fdinfo(fd, "memlock");
+        close(fd);
+
+        jsonw_start_object(json_wtr);
+
+        jsonw_uint_field(json_wtr, "id", info->id);
+        if (info->type < ARRAY_SIZE(map_type_name))
+                jsonw_string_field(json_wtr, "type",
+                                   map_type_name[info->type]);
+        else
+                jsonw_uint_field(json_wtr, "type", info->type);
+
+        if (*info->name)
+                jsonw_string_field(json_wtr, "name", info->name);
+
+        jsonw_name(json_wtr, "flags");
+        jsonw_printf(json_wtr, "%#x", info->map_flags);
+        jsonw_uint_field(json_wtr, "bytes_key", info->key_size);
+        jsonw_uint_field(json_wtr, "bytes_value", info->value_size);
+        jsonw_uint_field(json_wtr, "max_entries", info->max_entries);
+
+        if (memlock)
+                jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+        free(memlock);
+
+        if (!hash_empty(map_table.table)) {
+                struct pinned_obj *obj;
+
+                jsonw_name(json_wtr, "pinned");
+                jsonw_start_array(json_wtr);
+                hash_for_each_possible(map_table.table, obj, hash, info->id) {
+                        if (obj->id == info->id)
+                                jsonw_string(json_wtr, obj->path);
+                }
+                jsonw_end_array(json_wtr);
+        }
+
+        jsonw_end_object(json_wtr);
+
+        return 0;
+}
+
+static int show_map_close_plain(int fd, struct bpf_map_info *info)
+{
+        char *memlock;
+
+        memlock = get_fdinfo(fd, "memlock");
+        close(fd);
+
+        printf("%u: ", info->id);
+        if (info->type < ARRAY_SIZE(map_type_name))
+                printf("%s  ", map_type_name[info->type]);
+        else
+                printf("type %u  ", info->type);
+
+        if (*info->name)
+                printf("name %s  ", info->name);
+
+        printf("flags 0x%x\n", info->map_flags);
+        printf("\tkey %uB  value %uB  max_entries %u",
+               info->key_size, info->value_size, info->max_entries);
+
+        if (memlock)
+                printf("  memlock %sB", memlock);
+        free(memlock);
+
+        printf("\n");
+        if (!hash_empty(map_table.table)) {
+                struct pinned_obj *obj;
+
+                hash_for_each_possible(map_table.table, obj, hash, info->id) {
+                        if (obj->id == info->id)
+                                printf("\tpinned %s\n", obj->path);
+                }
+        }
+        return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        __u32 id = 0;
+        int err;
+        int fd;
+
+        if (show_pinned)
+                build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
+
+        if (argc == 2) {
+                fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+                if (fd < 0)
+                        return -1;
+
+                if (json_output)
+                        return show_map_close_json(fd, &info);
+                else
+                        return show_map_close_plain(fd, &info);
+        }
+
+        if (argc)
+                return BAD_ARG();
+
+        if (json_output)
+                jsonw_start_array(json_wtr);
+        while (true) {
+                err = bpf_map_get_next_id(id, &id);
+                if (err) {
+                        if (errno == ENOENT)
+                                break;
+                        p_err("can't get next map: %s%s", strerror(errno),
+                              errno == EINVAL ? " -- kernel too old?" : "");
+                        return -1;
+                }
+
+                fd = bpf_map_get_fd_by_id(id);
+                if (fd < 0) {
+                        p_err("can't get map by id (%u): %s",
+                              id, strerror(errno));
+                        return -1;
+                }
+
+                err = bpf_obj_get_info_by_fd(fd, &info, &len);
+                if (err) {
+                        p_err("can't get map info: %s", strerror(errno));
+                        close(fd);
+                        return -1;
+                }
+
+                if (json_output)
+                        show_map_close_json(fd, &info);
+                else
+                        show_map_close_plain(fd, &info);
+        }
+        if (json_output)
+                jsonw_end_array(json_wtr);
+
+        return errno == ENOENT ? 0 : -1;
+}
+
+static int do_dump(int argc, char **argv)
+{
+        void *key, *value, *prev_key;
+        unsigned int num_elems = 0;
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        int err;
+        int fd;
+
+        if (argc != 2)
+                usage();
+
+        fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+        if (fd < 0)
+                return -1;
+
+        if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
+                p_err("Dumping maps of maps and program maps not supported");
+                close(fd);
+                return -1;
+        }
+
+        key = malloc(info.key_size);
+        value = alloc_value(&info);
+        if (!key || !value) {
+                p_err("mem alloc failed");
+                err = -1;
+                goto exit_free;
+        }
+
+        prev_key = NULL;
+        if (json_output)
+                jsonw_start_array(json_wtr);
+        while (true) {
+                err = bpf_map_get_next_key(fd, prev_key, key);
+                if (err) {
+                        if (errno == ENOENT)
+                                err = 0;
+                        break;
+                }
+
+                if (!bpf_map_lookup_elem(fd, key, value)) {
+                        if (json_output)
+                                print_entry_json(&info, key, value);
+                        else
+                                print_entry_plain(&info, key, value);
+                } else {
+                        if (json_output) {
+                                jsonw_name(json_wtr, "key");
+                                print_hex_data_json(key, info.key_size);
+                                jsonw_name(json_wtr, "value");
+                                jsonw_start_object(json_wtr);
+                                jsonw_string_field(json_wtr, "error",
+                                                   "can't lookup element");
+                                jsonw_end_object(json_wtr);
+                        } else {
+                                p_info("can't lookup element with key: ");
+                                fprint_hex(stderr, key, info.key_size, " ");
+                                fprintf(stderr, "\n");
+                        }
+                }
+
+                prev_key = key;
+                num_elems++;
+        }
+
+        if (json_output)
+                jsonw_end_array(json_wtr);
+        else
+                printf("Found %u element%s\n", num_elems,
+                       num_elems != 1 ? "s" : "");
+
+exit_free:
+        free(key);
+        free(value);
+        close(fd);
+
+        return err;
+}
+
+static int do_update(int argc, char **argv)
+{
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        __u32 *value_fd = NULL;
+        __u32 flags = BPF_ANY;
+        void *key, *value;
+        int fd, err;
+
+        if (argc < 2)
+                usage();
+
+        fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+        if (fd < 0)
+                return -1;
+
+        key = malloc(info.key_size);
+        value = alloc_value(&info);
+        if (!key || !value) {
+                p_err("mem alloc failed");
+                err = -1;
+                goto exit_free;
+        }
+
+        err = parse_elem(argv, &info, key, value, info.key_size,
+                         info.value_size, &flags, &value_fd);
+        if (err)
+                goto exit_free;
+
+        err = bpf_map_update_elem(fd, key, value, flags);
+        if (err) {
+                p_err("update failed: %s", strerror(errno));
+                goto exit_free;
+        }
+
+exit_free:
+        if (value_fd)
+                close(*value_fd);
+        free(key);
+        free(value);
+        close(fd);
+
+        if (!err && json_output)
+                jsonw_null(json_wtr);
+        return err;
+}
+
+static int do_lookup(int argc, char **argv)
+{
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        void *key, *value;
+        int err;
+        int fd;
+
+        if (argc < 2)
+                usage();
+
+        fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+        if (fd < 0)
+                return -1;
+
+        key = malloc(info.key_size);
+        value = alloc_value(&info);
+        if (!key || !value) {
+                p_err("mem alloc failed");
+                err = -1;
+                goto exit_free;
+        }
+
+        err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+        if (err)
+                goto exit_free;
+
+        err = bpf_map_lookup_elem(fd, key, value);
+        if (!err) {
+                if (json_output)
+                        print_entry_json(&info, key, value);
+                else
+                        print_entry_plain(&info, key, value);
+        } else if (errno == ENOENT) {
+                if (json_output) {
+                        jsonw_null(json_wtr);
+                } else {
+                        printf("key:\n");
+                        fprint_hex(stdout, key, info.key_size, " ");
+                        printf("\n\nNot found\n");
+                }
+        } else {
+                p_err("lookup failed: %s", strerror(errno));
+        }
+
+exit_free:
+        free(key);
+        free(value);
+        close(fd);
+
+        return err;
+}
+
+static int do_getnext(int argc, char **argv)
+{
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        void *key, *nextkey;
+        int err;
+        int fd;
+
+        if (argc < 2)
+                usage();
+
+        fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+        if (fd < 0)
+                return -1;
+
+        key = malloc(info.key_size);
+        nextkey = malloc(info.key_size);
+        if (!key || !nextkey) {
+                p_err("mem alloc failed");
+                err = -1;
+                goto exit_free;
+        }
+
+        if (argc) {
+                err = parse_elem(argv, &info, key, NULL, info.key_size, 0,
+                                 NULL, NULL);
+                if (err)
+                        goto exit_free;
+        } else {
+                free(key);
+                key = NULL;
+        }
+
+        err = bpf_map_get_next_key(fd, key, nextkey);
+        if (err) {
+                p_err("can't get next key: %s", strerror(errno));
+                goto exit_free;
+        }
+
+        if (json_output) {
+                jsonw_start_object(json_wtr);
+                if (key) {
+                        jsonw_name(json_wtr, "key");
+                        print_hex_data_json(key, info.key_size);
+                } else {
+                        jsonw_null_field(json_wtr, "key");
+                }
+                jsonw_name(json_wtr, "next_key");
+                print_hex_data_json(nextkey, info.key_size);
+                jsonw_end_object(json_wtr);
+        } else {
+                if (key) {
+                        printf("key:\n");
+                        fprint_hex(stdout, key, info.key_size, " ");
+                        printf("\n");
+                } else {
+                        printf("key: None\n");
+                }
+                printf("next key:\n");
+                fprint_hex(stdout, nextkey, info.key_size, " ");
+                printf("\n");
+        }
+
+exit_free:
+        free(nextkey);
+        free(key);
+        close(fd);
+
+        return err;
+}
+
+static int do_delete(int argc, char **argv)
+{
+        struct bpf_map_info info = {};
+        __u32 len = sizeof(info);
+        void *key;
+        int err;
+        int fd;
+
+        if (argc < 2)
+                usage();
+
+        fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+        if (fd < 0)
+                return -1;
+
+        key = malloc(info.key_size);
+        if (!key) {
+                p_err("mem alloc failed");
+                err = -1;
+                goto exit_free;
+        }
+
+        err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+        if (err)
+                goto exit_free;
+
+        err = bpf_map_delete_elem(fd, key);
+        if (err)
+                p_err("delete failed: %s", strerror(errno));
+
+exit_free:
+        free(key);
+        close(fd);
+
+        if (!err && json_output)
+                jsonw_null(json_wtr);
+        return err;
+}
+
+static int do_pin(int argc, char **argv)
+{
+        int err;
+
+        err = do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+        if (!err && json_output)
+                jsonw_null(json_wtr);
+        return err;
+}
+
+static int do_help(int argc, char **argv)
+{
+        if (json_output) {
+                jsonw_null(json_wtr);
+                return 0;
+        }
+
+        fprintf(stderr,
+                "Usage: %s %s show   [MAP]\n"
+                "       %s %s dump    MAP\n"
+                "       %s %s update  MAP  key BYTES value VALUE [UPDATE_FLAGS]\n"
+                "       %s %s lookup  MAP  key BYTES\n"
+                "       %s %s getnext MAP [key BYTES]\n"
+                "       %s %s delete  MAP  key BYTES\n"
+                "       %s %s pin     MAP  FILE\n"
+                "       %s %s help\n"
+                "\n"
+                "       MAP := { id MAP_ID | pinned FILE }\n"
+                "       " HELP_SPEC_PROGRAM "\n"
+                "       VALUE := { BYTES | MAP | PROG }\n"
+                "       UPDATE_FLAGS := { any | exist | noexist }\n"
+                "       " HELP_SPEC_OPTIONS "\n"
+                "",
+                bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+                bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+                bin_name, argv[-2], bin_name, argv[-2]);
+
+        return 0;
+}
+
+static const struct cmd cmds[] = {
+        { "show",       do_show },
+        { "help",       do_help },
+        { "dump",       do_dump },
+        { "update",     do_update },
+        { "lookup",     do_lookup },
+        { "getnext",    do_getnext },
+        { "delete",     do_delete },
+        { "pin",        do_pin },
+        { 0 }
+};
+
+int do_map(int argc, char **argv)
+{
+        return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
new file mode 100644
index 000000000000..ad619b96c276
--- /dev/null
+++ b/tools/bpf/bpftool/prog.c
@@ -0,0 +1,672 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. Redistributions in binary form must reproduce the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer in the documentation and/or other materials
+ *         provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+/* Author: Jakub Kicinski <kubakici@wp.pl> */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <bpf.h>
+
+#include "main.h"
+#include "disasm.h"
+
+static const char * const prog_type_name[] = {
+        [BPF_PROG_TYPE_UNSPEC]          = "unspec",
+        [BPF_PROG_TYPE_SOCKET_FILTER]   = "socket_filter",
+        [BPF_PROG_TYPE_KPROBE]          = "kprobe",
+        [BPF_PROG_TYPE_SCHED_CLS]       = "sched_cls",
+        [BPF_PROG_TYPE_SCHED_ACT]       = "sched_act",
+        [BPF_PROG_TYPE_TRACEPOINT]      = "tracepoint",
+        [BPF_PROG_TYPE_XDP]             = "xdp",
+        [BPF_PROG_TYPE_PERF_EVENT]      = "perf_event",
+        [BPF_PROG_TYPE_CGROUP_SKB]      = "cgroup_skb",
+        [BPF_PROG_TYPE_CGROUP_SOCK]     = "cgroup_sock",
+        [BPF_PROG_TYPE_LWT_IN]          = "lwt_in",
+        [BPF_PROG_TYPE_LWT_OUT]         = "lwt_out",
+        [BPF_PROG_TYPE_LWT_XMIT]        = "lwt_xmit",
+        [BPF_PROG_TYPE_SOCK_OPS]        = "sock_ops",
+        [BPF_PROG_TYPE_SK_SKB]          = "sk_skb",
+};
+
+static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
+{
+        struct timespec real_time_ts, boot_time_ts;
+        time_t wallclock_secs;
+        struct tm load_tm;
+
+        buf[--size] = '\0';
+
+        if (clock_gettime(CLOCK_REALTIME, &real_time_ts) ||
+            clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) {
+                perror("Can't read clocks");
+                snprintf(buf, size, "%llu", nsecs / 1000000000);
+                return;
+        }
+
+        wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
+                nsecs / 1000000000;
+
+        if (!localtime_r(&wallclock_secs, &load_tm)) {
+                snprintf(buf, size, "%llu", nsecs / 1000000000);
+                return;
+        }
+
+        strftime(buf, size, "%b %d/%H:%M", &load_tm);
+}
+
+static int prog_fd_by_tag(unsigned char *tag)
+{
+        struct bpf_prog_info info = {};
+        __u32 len = sizeof(info);
+        unsigned int id = 0;
+        int err;
+        int fd;
+
+        while (true) {
+                err = bpf_prog_get_next_id(id, &id);
+                if (err) {
+                        p_err("%s", strerror(errno));
+                        return -1;
+                }
+
+                fd = bpf_prog_get_fd_by_id(id);
+                if (fd < 0) {
+                        p_err("can't get prog by id (%u): %s",
+                              id, strerror(errno));
+                        return -1;
+                }
+
+                err = bpf_obj_get_info_by_fd(fd, &info, &len);
+                if (err) {
+                        p_err("can't get prog info (%u): %s",
+                              id, strerror(errno));
+                        close(fd);
+                        return -1;
+                }
+
+                if (!memcmp(tag, info.tag, BPF_TAG_SIZE))
+                        return fd;
+
+                close(fd);
+        }
+}
+
+int prog_parse_fd(int *argc, char ***argv)
+{
+        int fd;
+
+        if (is_prefix(**argv, "id")) {
+                unsigned int id;
+                char *endptr;
+
+                NEXT_ARGP();
+
+                id = strtoul(**argv, &endptr, 0);
+                if (*endptr) {
+                        p_err("can't parse %s as ID", **argv);
+                        return -1;
+                }
+                NEXT_ARGP();
+
+                fd = bpf_prog_get_fd_by_id(id);
+                if (fd < 0)
+                        p_err("get by id (%u): %s", id, strerror(errno));
+                return fd;
+        } else if (is_prefix(**argv, "tag")) {
+                unsigned char tag[BPF_TAG_SIZE];
+
+                NEXT_ARGP();
+
+                if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
+                           tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
+                    != BPF_TAG_SIZE) {
+                        p_err("can't parse tag");
+                        return -1;
+                }
+                NEXT_ARGP();
+
+                return prog_fd_by_tag(tag);
+        } else if (is_prefix(**argv, "pinned")) {
+                char *path;
+
+                NEXT_ARGP();
+
+                path = **argv;
+                NEXT_ARGP();
+
+                return open_obj_pinned_any(path, BPF_OBJ_PROG);
+        }
+
+        p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv);
+        return -1;
+}
+
+static void show_prog_maps(int fd, u32 num_maps)
+{
+        struct bpf_prog_info info = {};
+        __u32 len = sizeof(info);
+        __u32 map_ids[num_maps];
+        unsigned int i;
+        int err;
+
+        info.nr_map_ids = num_maps;
+        info.map_ids = ptr_to_u64(map_ids);
+
+        err = bpf_obj_get_info_by_fd(fd, &info, &len);
+        if (err || !info.nr_map_ids)
+                return;
+
+        if (json_output) {
+                jsonw_name(json_wtr, "map_ids");
+                jsonw_start_array(json_wtr);
+                for (i = 0; i < info.nr_map_ids; i++)
+                        jsonw_uint(json_wtr, map_ids[i]);
+                jsonw_end_array(json_wtr);
+        } else {
+                printf("  map_ids ");
+                for (i = 0; i < info.nr_map_ids; i++)
+                        printf("%u%s", map_ids[i],
+                               i == info.nr_map_ids - 1 ? "" : ",");
+        }
+}
+
+static void print_prog_json(struct bpf_prog_info *info, int fd)
+{
+        char *memlock;
+
+        jsonw_start_object(json_wtr);
+        jsonw_uint_field(json_wtr, "id", info->id);
+        if (info->type < ARRAY_SIZE(prog_type_name))
+                jsonw_string_field(json_wtr, "type",
+                                   prog_type_name[info->type]);
+        else
+                jsonw_uint_field(json_wtr, "type", info->type);
+
+        if (*info->name)
+                jsonw_string_field(json_wtr, "name", info->name);
+
+        jsonw_name(json_wtr, "tag");
+        jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
+                     info->tag[0], info->tag[1], info->tag[2], info->tag[3],
+                     info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
+
+        if (info->load_time) {
+                char buf[32];
+
+                print_boot_time(info->load_time, buf, sizeof(buf));
+
+                /* Piggy back on load_time, since 0 uid is a valid one */
+                jsonw_string_field(json_wtr, "loaded_at", buf);
+                jsonw_uint_field(json_wtr, "uid", info->created_by_uid);
+        }
+
+        jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len);
+
+        if (info->jited_prog_len) {
+                jsonw_bool_field(json_wtr, "jited", true);
+                jsonw_uint_field(json_wtr, "bytes_jited", info->jited_prog_len);
+        } else {
+                jsonw_bool_field(json_wtr, "jited", false);
+        }
+
+        memlock = get_fdinfo(fd, "memlock");
+        if (memlock)
+                jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+        free(memlock);
+
+        if (info->nr_map_ids)
+                show_prog_maps(fd, info->nr_map_ids);
+
+        if (!hash_empty(prog_table.table)) {
+                struct pinned_obj *obj;
+
+                jsonw_name(json_wtr, "pinned");
+                jsonw_start_array(json_wtr);
+                hash_for_each_possible(prog_table.table, obj, hash, info->id) {
+                        if (obj->id == info->id)
+                                jsonw_string(json_wtr, obj->path);
+                }
+                jsonw_end_array(json_wtr);
+        }
+
+        jsonw_end_object(json_wtr);
+}
+
+static void print_prog_plain(struct bpf_prog_info *info, int fd)
+{
+        char *memlock;
+
+        printf("%u: ", info->id);
+        if (info->type < ARRAY_SIZE(prog_type_name))
+                printf("%s  ", prog_type_name[info->type]);
+        else
+                printf("type %u  ", info->type);
+
+        if (*info->name)
+                printf("name %s  ", info->name);
+
+        printf("tag ");
+        fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
+        printf("\n");
+
+        if (info->load_time) {
+                char buf[32];
+
+                print_boot_time(info->load_time, buf, sizeof(buf));
+
+                /* Piggy back on load_time, since 0 uid is a valid one */
+                printf("\tloaded_at %s  uid %u\n", buf, info->created_by_uid);
+        }
+
+        printf("\txlated %uB", info->xlated_prog_len);
+
+        if (info->jited_prog_len)
+                printf("  jited %uB", info->jited_prog_len);
+        else
+                printf("  not jited");
+
+        memlock = get_fdinfo(fd, "memlock");
+        if (memlock)
+                printf("  memlock %sB", memlock);
+        free(memlock);
+
+        if (info->nr_map_ids)
+                show_prog_maps(fd, info->nr_map_ids);
+
+        if (!hash_empty(prog_table.table)) {
+                struct pinned_obj *obj;
+
+                printf("\n");
+                hash_for_each_possible(prog_table.table, obj, hash, info->id) {
+                        if (obj->id == info->id)
+                                printf("\tpinned %s\n", obj->path);
+                }
+        }
+
+        printf("\n");
+}
+
+static int show_prog(int fd)
+{
+        struct bpf_prog_info info = {};
+        __u32 len = sizeof(info);
+        int err;
+
+        err = bpf_obj_get_info_by_fd(fd, &info, &len);
+        if (err) {
+                p_err("can't get prog info: %s", strerror(errno));
+                return -1;
+        }
+
+        if (json_output)
+                print_prog_json(&info, fd);
+        else
+                print_prog_plain(&info, fd);
+
+        return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+        __u32 id = 0;
+        int err;
+        int fd;
+
+        if (show_pinned)
+                build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+
+        if (argc == 2) {
+                fd = prog_parse_fd(&argc, &argv);
+                if (fd < 0)
+                        return -1;
+
+                return show_prog(fd);
+        }
+
+        if (argc)
+                return BAD_ARG();
+
+        if (json_output)
+                jsonw_start_array(json_wtr);
+        while (true) {
+                err = bpf_prog_get_next_id(id, &id);
+                if (err) {
+                        if (errno == ENOENT) {
+                                err = 0;
+                                break;
+                        }
+                        p_err("can't get next program: %s%s", strerror(errno),
+                              errno == EINVAL ? " -- kernel too old?" : "");
+                        err = -1;
+                        break;
+                }
+
+                fd = bpf_prog_get_fd_by_id(id);
+                if (fd < 0) {
+                        p_err("can't get prog by id (%u): %s",
+                              id, strerror(errno));
+                        err = -1;
+                        break;
+                }
+
+                err = show_prog(fd);
+                close(fd);
+                if (err)
+                        break;
+        }
+
+        if (json_output)
+                jsonw_end_array(json_wtr);
+
+        return err;
+}
+
+static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...)
+{
+        va_list args;
+
+        va_start(args, fmt);
+        vprintf(fmt, args);
+        va_end(args);
+}
+
+static void dump_xlated_plain(void *buf, unsigned int len, bool opcodes)
+{
+        struct bpf_insn *insn = buf;
+        bool double_insn = false;
+        unsigned int i;
+
+        for (i = 0; i < len / sizeof(*insn); i++) {
+                if (double_insn) {
+                        double_insn = false;
+                        continue;
+                }
+
+                double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
+
+                printf("% 4d: ", i);
+                print_bpf_insn(print_insn, NULL, insn + i, true);
+
+                if (opcodes) {
+                        printf("       ");
+                        fprint_hex(stdout, insn + i, 8, " ");
+                        if (double_insn && i < len - 1) {
+                                printf(" ");
+                                fprint_hex(stdout, insn + i + 1, 8, " ");
+                        }
+                        printf("\n");
+                }
+        }
+}
+
+static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...)
+{
+        unsigned int l = strlen(fmt);
+        char chomped_fmt[l];
+        va_list args;
+
+        va_start(args, fmt);
+        if (l > 0) {
+                strncpy(chomped_fmt, fmt, l - 1);
+                chomped_fmt[l - 1] = '\0';
+        }
+        jsonw_vprintf_enquote(json_wtr, chomped_fmt, args);
+        va_end(args);
+}
+
+static void dump_xlated_json(void *buf, unsigned int len, bool opcodes)
+{
+        struct bpf_insn *insn = buf;
+        bool double_insn = false;
+        unsigned int i;
+
+        jsonw_start_array(json_wtr);
+        for (i = 0; i < len / sizeof(*insn); i++) {
+                if (double_insn) {
+                        double_insn = false;
+                        continue;
+                }
+                double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
+
+                jsonw_start_object(json_wtr);
+                jsonw_name(json_wtr, "disasm");
+                print_bpf_insn(print_insn_json, NULL, insn + i, true);
+
+                if (opcodes) {
+                        jsonw_name(json_wtr, "opcodes");
+                        jsonw_start_object(json_wtr);
+
+                        jsonw_name(json_wtr, "code");
+                        jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code);
+
+                        jsonw_name(json_wtr, "src_reg");
+                        jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg);
+
+                        jsonw_name(json_wtr, "dst_reg");
+                        jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg);
+
+                        jsonw_name(json_wtr, "off");
+                        print_hex_data_json((uint8_t *)(&insn[i].off), 2);
+
+                        jsonw_name(json_wtr, "imm");
+                        if (double_insn && i < len - 1)
+                                print_hex_data_json((uint8_t *)(&insn[i].imm),
+                                                    12);
+                        else
+                                print_hex_data_json((uint8_t *)(&insn[i].imm),
+                                                    4);
+                        jsonw_end_object(json_wtr);
+                }
+                jsonw_end_object(json_wtr);
+        }
+        jsonw_end_array(json_wtr);
+}
+
+static int do_dump(int argc, char **argv)
+{
+        struct bpf_prog_info info = {};
+        __u32 len = sizeof(info);
+        unsigned int buf_size;
+        char *filepath = NULL;
+        bool opcodes = false;
+        unsigned char *buf;
+        __u32 *member_len;
+        __u64 *member_ptr;
+        ssize_t n;
+        int err;
+        int fd;
+
+        if (is_prefix(*argv, "jited")) {
+                member_len = &info.jited_prog_len;
+                member_ptr = &info.jited_prog_insns;
+        } else if (is_prefix(*argv, "xlated")) {
+                member_len = &info.xlated_prog_len;
+                member_ptr = &info.xlated_prog_insns;
+        } else {
+                p_err("expected 'xlated' or 'jited', got: %s", *argv);
+                return -1;
+        }
+        NEXT_ARG();
+
+        if (argc < 2)
+                usage();
+
+        fd = prog_parse_fd(&argc, &argv);
+        if (fd < 0)
+                return -1;
+
+        if (is_prefix(*argv, "file")) {
+                NEXT_ARG();
+                if (!argc) {
+                        p_err("expected file path");
+                        return -1;
+                }
+
+                filepath = *argv;
+                NEXT_ARG();
+        } else if (is_prefix(*argv, "opcodes")) {
+                opcodes = true;
+                NEXT_ARG();
+        }
+
+        if (argc) {
+                usage();
+                return -1;
+        }
+
+        err = bpf_obj_get_info_by_fd(fd, &info, &len);
+        if (err) {
+                p_err("can't get prog info: %s", strerror(errno));
+                return -1;
+        }
+
+        if (!*member_len) {
+                p_info("no instructions returned");
+                close(fd);
+                return 0;
+        }
+
+        buf_size = *member_len;
+
+        buf = malloc(buf_size);
+        if (!buf) {
+                p_err("mem alloc failed");
+                close(fd);
+                return -1;
+        }
+
+        memset(&info, 0, sizeof(info));
+
+        *member_ptr = ptr_to_u64(buf);
+        *member_len = buf_size;
+
+        err = bpf_obj_get_info_by_fd(fd, &info, &len);
+        close(fd);
+        if (err) {
+                p_err("can't get prog info: %s", strerror(errno));
+                goto err_free;
+        }
+
+        if (*member_len > buf_size) {
+                p_err("too many instructions returned");
+                goto err_free;
+        }
+
+        if (filepath) {
+                fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
+                if (fd < 0) {
+                        p_err("can't open file %s: %s", filepath,
+                              strerror(errno));
+                        goto err_free;
+                }
+
+                n = write(fd, buf, *member_len);
+                close(fd);
+                if (n != *member_len) {
+                        p_err("error writing output file: %s",
+                              n < 0 ? strerror(errno) : "short write");
+                        goto err_free;
+                }
+        } else {
+                if (member_len == &info.jited_prog_len)
+                        disasm_print_insn(buf, *member_len, opcodes);
+                else
+                        if (json_output)
+                                dump_xlated_json(buf, *member_len, opcodes);
+                        else
+                                dump_xlated_plain(buf, *member_len, opcodes);
+        }
+
+        free(buf);
+
+        return 0;
+
+err_free:
+        free(buf);
+        return -1;
+}
+
+static int do_pin(int argc, char **argv)
+{
+        int err;
+
+        err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+        if (!err && json_output)
+                jsonw_null(json_wtr);
+        return err;
+}
+
+static int do_help(int argc, char **argv)
+{
+        if (json_output) {
+                jsonw_null(json_wtr);
+                return 0;
+        }
+
+        fprintf(stderr,
+                "Usage: %s %s show [PROG]\n"
+                "       %s %s dump xlated PROG [{ file FILE | opcodes }]\n"
+                "       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
+                "       %s %s pin   PROG FILE\n"
+                "       %s %s help\n"
+                "\n"
+                "       " HELP_SPEC_PROGRAM "\n"
+                "       " HELP_SPEC_OPTIONS "\n"
+                "",
+                bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+                bin_name, argv[-2], bin_name, argv[-2]);
+
+        return 0;
+}
+
+static const struct cmd cmds[] = {
+        { "show",       do_show },
+        { "help",       do_help },
+        { "dump",       do_dump },
+        { "pin",        do_pin },
+        { 0 }
+};
+
+int do_prog(int argc, char **argv)
+{
+        return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 477f00eda591..5eb4b5ad79cb 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index c46b20e4ad87..cd72016c3cfa 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ###
 # Main build makefile.
 #
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 523911f316ce..c71a05b9c984 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -64,7 +64,8 @@ FEATURE_TESTS_BASIC :=                  \
         get_cpuid                       \
         bpf                             \
         sched_getcpu                    \
-        sdt
+        sdt                             \
+        setns
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index e35e4e5ad192..96982640fbf8 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 FILES=                                          \
          test-all.bin                           \
          test-backtrace.bin                     \
@@ -49,7 +50,8 @@ FILES=                                          \
          test-sdt.bin                           \
          test-cxx.bin                           \
          test-jvmti.bin                         \
-         test-sched_getcpu.bin
+         test-sched_getcpu.bin                  \
+         test-setns.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -95,6 +97,9 @@ $(OUTPUT)test-glibc.bin:
 $(OUTPUT)test-sched_getcpu.bin:
         $(BUILD)
 
+$(OUTPUT)test-setns.bin:
+        $(BUILD)
+
 DWARFLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
 DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index cc6c7c01f4ca..4112702e4aed 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * test-all.c: Try to build all the main testcases at once.
  *
@@ -153,6 +154,10 @@
 # include "test-sdt.c"
 #undef main
 
+#define main main_test_setns
+# include "test-setns.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -188,6 +193,7 @@ int main(int argc, char *argv[])
         main_test_libcrypto();
         main_test_sched_getcpu();
         main_test_sdt();
+        main_test_setns();
 
         return 0;
 }
diff --git a/tools/build/feature/test-backtrace.c b/tools/build/feature/test-backtrace.c
index 7124aa1dc8fb..e9ddd27c69c3 100644
--- a/tools/build/feature/test-backtrace.c
+++ b/tools/build/feature/test-backtrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <execinfo.h>
 #include <stdio.h>
 
diff --git a/tools/build/feature/test-bionic.c b/tools/build/feature/test-bionic.c
index eac24e9513eb..4bcc9776504c 100644
--- a/tools/build/feature/test-bionic.c
+++ b/tools/build/feature/test-bionic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <android/api-level.h>
 
 int main(void)
diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c
index 7598361ef1f1..82070eadfc07 100644
--- a/tools/build/feature/test-bpf.c
+++ b/tools/build/feature/test-bpf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include <unistd.h>
@@ -11,6 +12,8 @@
 #  define __NR_bpf 280
 # elif defined(__sparc__)
 #  define __NR_bpf 349
+# elif defined(__s390__)
+#  define __NR_bpf 351
 # else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif
diff --git a/tools/build/feature/test-clang.cpp b/tools/build/feature/test-clang.cpp
index e23c1b1f1b91..a2b3f092d2f0 100644
--- a/tools/build/feature/test-clang.cpp
+++ b/tools/build/feature/test-clang.cpp
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "clang/Basic/VirtualFileSystem.h"
 #include "clang/Driver/Driver.h"
 #include "clang/Frontend/TextDiagnosticPrinter.h"
diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c
index c54e6551ae4c..9821b8271dee 100644
--- a/tools/build/feature/test-compile.c
+++ b/tools/build/feature/test-compile.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 int main(void)
 {
diff --git a/tools/build/feature/test-cplus-demangle.c b/tools/build/feature/test-cplus-demangle.c
index 610c686e0009..2ba56474ab71 100644
--- a/tools/build/feature/test-cplus-demangle.c
+++ b/tools/build/feature/test-cplus-demangle.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 extern int printf(const char *format, ...);
 extern char *cplus_demangle(const char *, int);
 
diff --git a/tools/build/feature/test-cxx.cpp b/tools/build/feature/test-cxx.cpp
index b1dee9a31d6c..396aaedd2418 100644
--- a/tools/build/feature/test-cxx.cpp
+++ b/tools/build/feature/test-cxx.cpp
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <iostream>
 #include <memory>
 
diff --git a/tools/build/feature/test-dwarf.c b/tools/build/feature/test-dwarf.c
index 3fc1801ce4a9..8d474bd7371b 100644
--- a/tools/build/feature/test-dwarf.c
+++ b/tools/build/feature/test-dwarf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dwarf.h>
 #include <elfutils/libdw.h>
 #include <elfutils/version.h>
diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c
index 70162699dd43..78fb4a1fa68c 100644
--- a/tools/build/feature/test-dwarf_getlocations.c
+++ b/tools/build/feature/test-dwarf_getlocations.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <elfutils/libdw.h>
 
diff --git a/tools/build/feature/test-get_cpuid.c b/tools/build/feature/test-get_cpuid.c
index d7a2c407130d..bb4f065f28a6 100644
--- a/tools/build/feature/test-get_cpuid.c
+++ b/tools/build/feature/test-get_cpuid.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <cpuid.h>
 
 int main(void)
diff --git a/tools/build/feature/test-glibc.c b/tools/build/feature/test-glibc.c
index 9367f7586676..9ab8e90e7b88 100644
--- a/tools/build/feature/test-glibc.c
+++ b/tools/build/feature/test-glibc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 
 #if !defined(__UCLIBC__)
diff --git a/tools/build/feature/test-gtk2-infobar.c b/tools/build/feature/test-gtk2-infobar.c
index 397b4646d066..b1b716dd5733 100644
--- a/tools/build/feature/test-gtk2-infobar.c
+++ b/tools/build/feature/test-gtk2-infobar.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #pragma GCC diagnostic ignored "-Wstrict-prototypes"
 #include <gtk/gtk.h>
 #pragma GCC diagnostic error "-Wstrict-prototypes"
diff --git a/tools/build/feature/test-gtk2.c b/tools/build/feature/test-gtk2.c
index 6bd80e509439..2aaf4bfc2055 100644
--- a/tools/build/feature/test-gtk2.c
+++ b/tools/build/feature/test-gtk2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #pragma GCC diagnostic ignored "-Wstrict-prototypes"
 #include <gtk/gtk.h>
 #pragma GCC diagnostic error "-Wstrict-prototypes"
diff --git a/tools/build/feature/test-jvmti.c b/tools/build/feature/test-jvmti.c
index 1c665f09b9d6..5cf31192f204 100644
--- a/tools/build/feature/test-jvmti.c
+++ b/tools/build/feature/test-jvmti.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <jvmti.h>
 #include <jvmticmlr.h>
 
diff --git a/tools/build/feature/test-libaudit.c b/tools/build/feature/test-libaudit.c
index afc019f08641..f5b0863fa1ec 100644
--- a/tools/build/feature/test-libaudit.c
+++ b/tools/build/feature/test-libaudit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libaudit.h>
 
 extern int printf(const char *format, ...);
diff --git a/tools/build/feature/test-libbabeltrace.c b/tools/build/feature/test-libbabeltrace.c
index 9cf802a04885..10bb69d55694 100644
--- a/tools/build/feature/test-libbabeltrace.c
+++ b/tools/build/feature/test-libbabeltrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <babeltrace/ctf-writer/writer.h>
 #include <babeltrace/ctf-ir/stream-class.h>
diff --git a/tools/build/feature/test-libbfd.c b/tools/build/feature/test-libbfd.c
index 24059907e990..afa46b0465cd 100644
--- a/tools/build/feature/test-libbfd.c
+++ b/tools/build/feature/test-libbfd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <bfd.h>
 
 extern int printf(const char *format, ...);
diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c
index bd79dc7f28d3..a98174e0569c 100644
--- a/tools/build/feature/test-libcrypto.c
+++ b/tools/build/feature/test-libcrypto.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <openssl/sha.h>
 #include <openssl/md5.h>
 
diff --git a/tools/build/feature/test-libdw-dwarf-unwind.c b/tools/build/feature/test-libdw-dwarf-unwind.c
index f676a3ff442a..ed03d9505609 100644
--- a/tools/build/feature/test-libdw-dwarf-unwind.c
+++ b/tools/build/feature/test-libdw-dwarf-unwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <elfutils/libdwfl.h>
 
diff --git a/tools/build/feature/test-libelf-gelf_getnote.c b/tools/build/feature/test-libelf-gelf_getnote.c
index d78cf4d5271f..075d062fe841 100644
--- a/tools/build/feature/test-libelf-gelf_getnote.c
+++ b/tools/build/feature/test-libelf-gelf_getnote.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <gelf.h>
 
diff --git a/tools/build/feature/test-libelf-getphdrnum.c b/tools/build/feature/test-libelf-getphdrnum.c
index d710459306c3..96a7f8d30a59 100644
--- a/tools/build/feature/test-libelf-getphdrnum.c
+++ b/tools/build/feature/test-libelf-getphdrnum.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libelf.h>
 
 int main(void)
diff --git a/tools/build/feature/test-libelf-getshdrstrndx.c b/tools/build/feature/test-libelf-getshdrstrndx.c
index f0c3b47cce28..ae9f2fff5af0 100644
--- a/tools/build/feature/test-libelf-getshdrstrndx.c
+++ b/tools/build/feature/test-libelf-getshdrstrndx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libelf.h>
 
 int main(void)
diff --git a/tools/build/feature/test-libelf-mmap.c b/tools/build/feature/test-libelf-mmap.c
index 564427d7ef18..2c3ef81affe2 100644
--- a/tools/build/feature/test-libelf-mmap.c
+++ b/tools/build/feature/test-libelf-mmap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libelf.h>
 
 int main(void)
diff --git a/tools/build/feature/test-libelf.c b/tools/build/feature/test-libelf.c
index 08db322d8957..905044127d56 100644
--- a/tools/build/feature/test-libelf.c
+++ b/tools/build/feature/test-libelf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libelf.h>
 
 int main(void)
diff --git a/tools/build/feature/test-libnuma.c b/tools/build/feature/test-libnuma.c
index 4763d9cd587d..b3aa59f8b3cb 100644
--- a/tools/build/feature/test-libnuma.c
+++ b/tools/build/feature/test-libnuma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <numa.h>
 #include <numaif.h>
 
diff --git a/tools/build/feature/test-libperl.c b/tools/build/feature/test-libperl.c
index 8871f6a0fdb4..0415f437eb31 100644
--- a/tools/build/feature/test-libperl.c
+++ b/tools/build/feature/test-libperl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <EXTERN.h>
 #include <perl.h>
 
diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c
index facea122d812..47714b942d4d 100644
--- a/tools/build/feature/test-libpython-version.c
+++ b/tools/build/feature/test-libpython-version.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <Python.h>
 
 #if PY_VERSION_HEX >= 0x03000000
diff --git a/tools/build/feature/test-libpython.c b/tools/build/feature/test-libpython.c
index b24b28ad6324..0c1641b0d9a7 100644
--- a/tools/build/feature/test-libpython.c
+++ b/tools/build/feature/test-libpython.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <Python.h>
 
 int main(void)
diff --git a/tools/build/feature/test-libslang.c b/tools/build/feature/test-libslang.c
index 22ff22ed94d1..9cbff8d1df53 100644
--- a/tools/build/feature/test-libslang.c
+++ b/tools/build/feature/test-libslang.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <slang.h>
 
 int main(void)
diff --git a/tools/build/feature/test-libunwind-aarch64.c b/tools/build/feature/test-libunwind-aarch64.c
index fc03fb64e8c1..323803f49212 100644
--- a/tools/build/feature/test-libunwind-aarch64.c
+++ b/tools/build/feature/test-libunwind-aarch64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind-aarch64.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind-arm.c b/tools/build/feature/test-libunwind-arm.c
index 632d95ec641f..cb378b7d6866 100644
--- a/tools/build/feature/test-libunwind-arm.c
+++ b/tools/build/feature/test-libunwind-arm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind-arm.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind-debug-frame-aarch64.c b/tools/build/feature/test-libunwind-debug-frame-aarch64.c
index 22844673fc26..36d6646c185e 100644
--- a/tools/build/feature/test-libunwind-debug-frame-aarch64.c
+++ b/tools/build/feature/test-libunwind-debug-frame-aarch64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind-aarch64.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind-debug-frame-arm.c b/tools/build/feature/test-libunwind-debug-frame-arm.c
index f98859684fee..8696e48e1268 100644
--- a/tools/build/feature/test-libunwind-debug-frame-arm.c
+++ b/tools/build/feature/test-libunwind-debug-frame-arm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind-arm.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind-debug-frame.c b/tools/build/feature/test-libunwind-debug-frame.c
index 0ef8087a104a..efb55cdd8d01 100644
--- a/tools/build/feature/test-libunwind-debug-frame.c
+++ b/tools/build/feature/test-libunwind-debug-frame.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind-x86.c b/tools/build/feature/test-libunwind-x86.c
index 3561edce305e..e5e0f6c89637 100644
--- a/tools/build/feature/test-libunwind-x86.c
+++ b/tools/build/feature/test-libunwind-x86.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind-x86.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind-x86_64.c b/tools/build/feature/test-libunwind-x86_64.c
index 5add2517b2a1..62ae4db597dc 100644
--- a/tools/build/feature/test-libunwind-x86_64.c
+++ b/tools/build/feature/test-libunwind-x86_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind-x86_64.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-libunwind.c b/tools/build/feature/test-libunwind.c
index 43b9369bcab7..53fd26614ff0 100644
--- a/tools/build/feature/test-libunwind.c
+++ b/tools/build/feature/test-libunwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <libunwind.h>
 #include <stdlib.h>
 
diff --git a/tools/build/feature/test-llvm-version.cpp b/tools/build/feature/test-llvm-version.cpp
index 896d31724568..8a091625446a 100644
--- a/tools/build/feature/test-llvm-version.cpp
+++ b/tools/build/feature/test-llvm-version.cpp
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <cstdio>
 #include "llvm/Config/llvm-config.h"
 
diff --git a/tools/build/feature/test-llvm.cpp b/tools/build/feature/test-llvm.cpp
index 455a332dc8a8..88a3d1bdd9f6 100644
--- a/tools/build/feature/test-llvm.cpp
+++ b/tools/build/feature/test-llvm.cpp
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "llvm/Support/ManagedStatic.h"
 #include "llvm/Support/raw_ostream.h"
 #define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
diff --git a/tools/build/feature/test-lzma.c b/tools/build/feature/test-lzma.c
index 95adc8ced3dd..78682bb01d57 100644
--- a/tools/build/feature/test-lzma.c
+++ b/tools/build/feature/test-lzma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <lzma.h>
 
 int main(void)
diff --git a/tools/build/feature/test-numa_num_possible_cpus.c b/tools/build/feature/test-numa_num_possible_cpus.c
index 2606e94b0659..573d07b9c570 100644
--- a/tools/build/feature/test-numa_num_possible_cpus.c
+++ b/tools/build/feature/test-numa_num_possible_cpus.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <numa.h>
 
 int main(void)
diff --git a/tools/build/feature/test-pthread-attr-setaffinity-np.c b/tools/build/feature/test-pthread-attr-setaffinity-np.c
index fdada5e8d454..38c71131c452 100644
--- a/tools/build/feature/test-pthread-attr-setaffinity-np.c
+++ b/tools/build/feature/test-pthread-attr-setaffinity-np.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdint.h>
 #include <pthread.h>
 #include <sched.h>
diff --git a/tools/build/feature/test-sched_getcpu.c b/tools/build/feature/test-sched_getcpu.c
index 9c6b4cbffb1c..e448deb4124c 100644
--- a/tools/build/feature/test-sched_getcpu.c
+++ b/tools/build/feature/test-sched_getcpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifndef _GNU_SOURCE
 #define _GNU_SOURCE
 #endif
diff --git a/tools/build/feature/test-sdt.c b/tools/build/feature/test-sdt.c
index e4531a6e80ea..22737b0dadc8 100644
--- a/tools/build/feature/test-sdt.c
+++ b/tools/build/feature/test-sdt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/sdt.h>
 
 int main(void)
diff --git a/tools/build/feature/test-setns.c b/tools/build/feature/test-setns.c
new file mode 100644
index 000000000000..1f714d2a658b
--- /dev/null
+++ b/tools/build/feature/test-setns.c
@@ -0,0 +1,7 @@
+#define _GNU_SOURCE
+#include <sched.h>
+
+int main(void)
+{
+        return setns(0, 0);
+}
diff --git a/tools/build/feature/test-stackprotector-all.c b/tools/build/feature/test-stackprotector-all.c
index c9f398d87868..c8a57194f9f2 100644
--- a/tools/build/feature/test-stackprotector-all.c
+++ b/tools/build/feature/test-stackprotector-all.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 
 int main(void)
diff --git a/tools/build/feature/test-sync-compare-and-swap.c b/tools/build/feature/test-sync-compare-and-swap.c
index c34d4ca4af56..1e38d1930a97 100644
--- a/tools/build/feature/test-sync-compare-and-swap.c
+++ b/tools/build/feature/test-sync-compare-and-swap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdint.h>
 
 volatile uint64_t x;
diff --git a/tools/build/feature/test-timerfd.c b/tools/build/feature/test-timerfd.c
index 8c5c083b4d3c..9c72c697a9df 100644
--- a/tools/build/feature/test-timerfd.c
+++ b/tools/build/feature/test-timerfd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * test for timerfd functions used by perf-kvm-stat-live
  */
diff --git a/tools/build/feature/test-zlib.c b/tools/build/feature/test-zlib.c
index e111fff6240e..da6c35794b93 100644
--- a/tools/build/feature/test-zlib.c
+++ b/tools/build/feature/test-zlib.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <zlib.h>
 
 int main(void)
diff --git a/tools/build/fixdep.c b/tools/build/fixdep.c
index 734d1547cbae..2501fea7aa3e 100644
--- a/tools/build/fixdep.c
+++ b/tools/build/fixdep.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * "Optimize" a list of dependencies as spit out by gcc -MD
  * for the build framework.
diff --git a/tools/build/tests/ex/Makefile b/tools/build/tests/ex/Makefile
index c50d5782ad5a..fee032e06a85 100644
--- a/tools/build/tests/ex/Makefile
+++ b/tools/build/tests/ex/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 export srctree := $(abspath ../../../..)
 export CC      := gcc
 export LD      := ld
@@ -8,7 +9,7 @@ ex:
 include $(srctree)/tools/build/Makefile.include
 
 ex: ex-in.o libex-in.o
-        gcc -o $@ $^
+        $(CC) -o $@ $^
 
 ex.%: fixdep FORCE
         make -f $(srctree)/tools/build/Makefile.build dir=. $@
diff --git a/tools/build/tests/ex/a.c b/tools/build/tests/ex/a.c
index 851762798c83..66017a9f40b6 100644
--- a/tools/build/tests/ex/a.c
+++ b/tools/build/tests/ex/a.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int a(void)
 {
diff --git a/tools/build/tests/ex/arch/e.c b/tools/build/tests/ex/arch/e.c
index beaa4a1d7ba8..f6ef585b570c 100644
--- a/tools/build/tests/ex/arch/e.c
+++ b/tools/build/tests/ex/arch/e.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int e(void)
 {
diff --git a/tools/build/tests/ex/arch/f.c b/tools/build/tests/ex/arch/f.c
index 7c3e9e9da5b7..bffd9c67e9af 100644
--- a/tools/build/tests/ex/arch/f.c
+++ b/tools/build/tests/ex/arch/f.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int f(void)
 {
diff --git a/tools/build/tests/ex/b.c b/tools/build/tests/ex/b.c
index c24ff9ca9a97..2b29fb4d3c20 100644
--- a/tools/build/tests/ex/b.c
+++ b/tools/build/tests/ex/b.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int b(void)
 {
diff --git a/tools/build/tests/ex/c.c b/tools/build/tests/ex/c.c
index e216d0217499..a63b20ab83d5 100644
--- a/tools/build/tests/ex/c.c
+++ b/tools/build/tests/ex/c.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int c(void)
 {
diff --git a/tools/build/tests/ex/d.c b/tools/build/tests/ex/d.c
index 80dc0f06151b..e114e8dca0b6 100644
--- a/tools/build/tests/ex/d.c
+++ b/tools/build/tests/ex/d.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int d(void)
 {
diff --git a/tools/build/tests/ex/ex.c b/tools/build/tests/ex/ex.c
index 57de6074d252..3c02756ef912 100644
--- a/tools/build/tests/ex/ex.c
+++ b/tools/build/tests/ex/ex.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 int a(void);
 int b(void);
diff --git a/tools/build/tests/ex/inc.c b/tools/build/tests/ex/inc.c
index c20f1e9033a3..3636ab5bf339 100644
--- a/tools/build/tests/ex/inc.c
+++ b/tools/build/tests/ex/inc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifdef INCLUDE
 #include "krava.h"
 #endif
diff --git a/tools/build/tests/run.sh b/tools/build/tests/run.sh
index 44d2a0fade67..2c54e4d43546 100755
--- a/tools/build/tests/run.sh
+++ b/tools/build/tests/run.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 function test_ex {
         make -C ex V=1 clean > ex.out 2>&1
diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile
index b4286196b763..860fa151640a 100644
--- a/tools/cgroup/Makefile
+++ b/tools/cgroup/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for cgroup tools
 
 CC = $(CROSS_COMPILE)gcc
diff --git a/tools/cgroup/cgroup_event_listener.c b/tools/cgroup/cgroup_event_listener.c
index 4eb5507205c9..3d70dc831a76 100644
--- a/tools/cgroup/cgroup_event_listener.c
+++ b/tools/cgroup/cgroup_event_listener.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * cgroup_event_listener.c - Simple listener of cgroup events
  *
diff --git a/tools/firewire/Makefile b/tools/firewire/Makefile
index 81767adaae7d..67b6e9fca83c 100644
--- a/tools/firewire/Makefile
+++ b/tools/firewire/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 prefix = /usr
 nosy-dump-version = 0.4
 
diff --git a/tools/firewire/decode-fcp.c b/tools/firewire/decode-fcp.c
index e41223b6a4c8..b67ebc88434d 100644
--- a/tools/firewire/decode-fcp.c
+++ b/tools/firewire/decode-fcp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/firewire-constants.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/firewire/list.h b/tools/firewire/list.h
index 41f4bdadf634..6278d08e99e3 100644
--- a/tools/firewire/list.h
+++ b/tools/firewire/list.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 struct list {
         struct list *next, *prev;
 };
diff --git a/tools/firewire/nosy-dump.h b/tools/firewire/nosy-dump.h
index 3a4b5b33ba5d..69e5e594f284 100644
--- a/tools/firewire/nosy-dump.h
+++ b/tools/firewire/nosy-dump.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __nosy_dump_h__
 #define __nosy_dump_h__
 
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index b4401536cfa9..805a2c0cf4cd 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 include ../scripts/Makefile.include
 
 bindir ?= /usr/bin
diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c
index b86a32d90d88..cf7e2f3419ee 100644
--- a/tools/gpio/gpio-utils.c
+++ b/tools/gpio/gpio-utils.c
@@ -76,7 +76,8 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines,
         fd = open(chrdev_name, 0);
         if (fd == -1) {
                 ret = -errno;
-                fprintf(stderr, "Failed to open %s\n", chrdev_name);
+                fprintf(stderr, "Failed to open %s, %s\n",
+                        chrdev_name, strerror(errno));
                 goto exit_close_error;
         }
 
@@ -92,8 +93,8 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines,
         ret = ioctl(fd, GPIO_GET_LINEHANDLE_IOCTL, &req);
         if (ret == -1) {
                 ret = -errno;
-                fprintf(stderr, "Failed to issue GET LINEHANDLE IOCTL (%d)\n",
-                        ret);
+                fprintf(stderr, "Failed to issue %s (%d), %s\n",
+                        "GPIO_GET_LINEHANDLE_IOCTL", ret, strerror(errno));
         }
 
 exit_close_error:
@@ -118,8 +119,9 @@ int gpiotools_set_values(const int fd, struct gpiohandle_data *data)
         ret = ioctl(fd, GPIOHANDLE_SET_LINE_VALUES_IOCTL, data);
         if (ret == -1) {
                 ret = -errno;
-                fprintf(stderr, "Failed to issue %s (%d)\n",
-                        "GPIOHANDLE_SET_LINE_VALUES_IOCTL", ret);
+                fprintf(stderr, "Failed to issue %s (%d), %s\n",
+                        "GPIOHANDLE_SET_LINE_VALUES_IOCTL", ret,
+                        strerror(errno));
         }
 
         return ret;
@@ -141,8 +143,9 @@ int gpiotools_get_values(const int fd, struct gpiohandle_data *data)
         ret = ioctl(fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, data);
         if (ret == -1) {
                 ret = -errno;
-                fprintf(stderr, "Failed to issue %s (%d)\n",
-                        "GPIOHANDLE_GET_LINE_VALUES_IOCTL", ret);
+                fprintf(stderr, "Failed to issue %s (%d), %s\n",
+                        "GPIOHANDLE_GET_LINE_VALUES_IOCTL", ret,
+                        strerror(errno));
         }
 
         return ret;
diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index 0d1e61b81844..31503819454d 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for Hyper-V tools
 
 CC = $(CROSS_COMPILE)gcc
diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh
deleted file mode 100755
index 89b25068cd98..000000000000
--- a/tools/hv/bondvf.sh
+++ /dev/null
@@ -1,232 +0,0 @@
-#!/bin/bash
-
-# This example script creates bonding network devices based on synthetic NIC
-# (the virtual network adapter usually provided by Hyper-V) and the matching
-# VF NIC (SRIOV virtual function). So the synthetic NIC and VF NIC can
-# function as one network device, and fail over to the synthetic NIC if VF is
-# down.
-#
-# Usage:
-# - After configured vSwitch and vNIC with SRIOV, start Linux virtual
-#   machine (VM)
-# - Run this scripts on the VM. It will create configuration files in
-#   distro specific directory.
-# - Reboot the VM, so that the bonding config are enabled.
-#
-# The config files are DHCP by default. You may edit them if you need to change
-# to Static IP or change other settings.
-#
-
-sysdir=/sys/class/net
-netvsc_cls={f8615163-df3e-46c5-913f-f2d2f965ed0e}
-bondcnt=0
-
-# Detect Distro
-if [ -f /etc/redhat-release ];
-then
-        cfgdir=/etc/sysconfig/network-scripts
-        distro=redhat
-elif grep -q 'Ubuntu' /etc/issue
-then
-        cfgdir=/etc/network
-        distro=ubuntu
-elif grep -q 'SUSE' /etc/issue
-then
-        cfgdir=/etc/sysconfig/network
-        distro=suse
-else
-        echo "Unsupported Distro"
-        exit 1
-fi
-
-echo Detected Distro: $distro, or compatible
-
-# Get a list of ethernet names
-list_eth=(`cd $sysdir && ls -d */ | cut -d/ -f1 | grep -v bond`)
-eth_cnt=${#list_eth[@]}
-
-echo List of net devices:
-
-# Get the MAC addresses
-for (( i=0; i < $eth_cnt; i++ ))
-do
-        list_mac[$i]=`cat $sysdir/${list_eth[$i]}/address`
-        echo ${list_eth[$i]}, ${list_mac[$i]}
-done
-
-# Find NIC with matching MAC
-for (( i=0; i < $eth_cnt-1; i++ ))
-do
-        for (( j=i+1; j < $eth_cnt; j++ ))
-        do
-                if [ "${list_mac[$i]}" = "${list_mac[$j]}" ]
-                then
-                        list_match[$i]=${list_eth[$j]}
-                        break
-                fi
-        done
-done
-
-function create_eth_cfg_redhat {
-        local fn=$cfgdir/ifcfg-$1
-
-        rm -f $fn
-        echo DEVICE=$1 >>$fn
-        echo TYPE=Ethernet >>$fn
-        echo BOOTPROTO=none >>$fn
-        echo UUID=`uuidgen` >>$fn
-        echo ONBOOT=yes >>$fn
-        echo PEERDNS=yes >>$fn
-        echo IPV6INIT=yes >>$fn
-        echo MASTER=$2 >>$fn
-        echo SLAVE=yes >>$fn
-}
-
-function create_eth_cfg_pri_redhat {
-        create_eth_cfg_redhat $1 $2
-}
-
-function create_bond_cfg_redhat {
-        local fn=$cfgdir/ifcfg-$1
-
-        rm -f $fn
-        echo DEVICE=$1 >>$fn
-        echo TYPE=Bond >>$fn
-        echo BOOTPROTO=dhcp >>$fn
-        echo UUID=`uuidgen` >>$fn
-        echo ONBOOT=yes >>$fn
-        echo PEERDNS=yes >>$fn
-        echo IPV6INIT=yes >>$fn
-        echo BONDING_MASTER=yes >>$fn
-        echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn
-}
-
-function del_eth_cfg_ubuntu {
-        local mainfn=$cfgdir/interfaces
-        local fnlist=( $mainfn )
-
-        local dirlist=(`awk '/^[ \t]*source/{print $2}' $mainfn`)
-
-        local i
-        for i in "${dirlist[@]}"
-        do
-                fnlist+=(`ls $i 2>/dev/null`)
-        done
-
-        local tmpfl=$(mktemp)
-
-        local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1
-        local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)'
-
-        local fn
-        for fn in "${fnlist[@]}"
-        do
-                awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" \
-                        $fn >$tmpfl
-
-                cp $tmpfl $fn
-        done
-
-        rm $tmpfl
-}
-
-function create_eth_cfg_ubuntu {
-        local fn=$cfgdir/interfaces
-
-        del_eth_cfg_ubuntu $1
-        echo $'\n'auto $1 >>$fn
-        echo iface $1 inet manual >>$fn
-        echo bond-master $2 >>$fn
-}
-
-function create_eth_cfg_pri_ubuntu {
-        local fn=$cfgdir/interfaces
-
-        del_eth_cfg_ubuntu $1
-        echo $'\n'allow-hotplug $1 >>$fn
-        echo iface $1 inet manual >>$fn
-        echo bond-master $2 >>$fn
-        echo bond-primary $1 >>$fn
-}
-
-function create_bond_cfg_ubuntu {
-        local fn=$cfgdir/interfaces
-
-        del_eth_cfg_ubuntu $1
-
-        echo $'\n'auto $1 >>$fn
-        echo iface $1 inet dhcp >>$fn
-        echo bond-mode active-backup >>$fn
-        echo bond-miimon 100 >>$fn
-        echo bond-slaves none >>$fn
-}
-
-function create_eth_cfg_suse {
-        local fn=$cfgdir/ifcfg-$1
-
-        rm -f $fn
-        echo BOOTPROTO=none >>$fn
-        echo STARTMODE=auto >>$fn
-}
-
-function create_eth_cfg_pri_suse {
-        local fn=$cfgdir/ifcfg-$1
-
-        rm -f $fn
-        echo BOOTPROTO=none >>$fn
-        echo STARTMODE=hotplug >>$fn
-}
-
-function create_bond_cfg_suse {
-        local fn=$cfgdir/ifcfg-$1
-
-        rm -f $fn
-        echo BOOTPROTO=dhcp >>$fn
-        echo STARTMODE=auto >>$fn
-        echo BONDING_MASTER=yes >>$fn
-        echo BONDING_SLAVE_0=$2 >>$fn
-        echo BONDING_SLAVE_1=$3 >>$fn
-        echo BONDING_MODULE_OPTS=\'mode=active-backup miimon=100 primary=$2\' >>$fn
-}
-
-function create_bond {
-        local bondname=bond$bondcnt
-        local primary
-        local secondary
-
-        local class_id1=`cat $sysdir/$1/device/class_id 2>/dev/null`
-        local class_id2=`cat $sysdir/$2/device/class_id 2>/dev/null`
-
-        if [ "$class_id1" = "$netvsc_cls" ]
-        then
-                primary=$2
-                secondary=$1
-        elif [ "$class_id2" = "$netvsc_cls" ]
-        then
-                primary=$1
-                secondary=$2
-        else
-                return 0
-        fi
-
-        echo $'\nBond name:' $bondname
-
-        echo configuring $primary
-        create_eth_cfg_pri_$distro $primary $bondname
-
-        echo configuring $secondary
-        create_eth_cfg_$distro $secondary $bondname
-
-        echo creating: $bondname with primary slave: $primary
-        create_bond_cfg_$distro $bondname $primary $secondary
-
-        let bondcnt=bondcnt+1
-}
-
-for (( i=0; i < $eth_cnt-1; i++ ))
-do
-        if [ -n "${list_match[$i]}" ]
-        then
-                create_bond ${list_eth[$i]} ${list_match[$i]}
-        fi
-done
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index 26ae609a9448..457a1521f32f 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -138,14 +138,17 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-        int fcopy_fd, len;
+        int fcopy_fd;
         int error;
         int daemonize = 1, long_index = 0, opt;
         int version = FCOPY_CURRENT_VERSION;
-        char *buffer[4096 * 2];
-        struct hv_fcopy_hdr *in_msg;
+        union {
+                struct hv_fcopy_hdr hdr;
+                struct hv_start_fcopy start;
+                struct hv_do_fcopy copy;
+                __u32 kernel_modver;
+        } buffer = { };
         int in_handshake = 1;
-        __u32 kernel_modver;
 
         static struct option long_options[] = {
                 {"help",        no_argument,       0,  'h' },
@@ -195,32 +198,31 @@ int main(int argc, char *argv[])
                  * In this loop we process fcopy messages after the
                  * handshake is complete.
                  */
-                len = pread(fcopy_fd, buffer, (4096 * 2), 0);
+                ssize_t len;
+
+                len = pread(fcopy_fd, &buffer, sizeof(buffer), 0);
                 if (len < 0) {
                         syslog(LOG_ERR, "pread failed: %s", strerror(errno));
                         exit(EXIT_FAILURE);
                 }
 
                 if (in_handshake) {
-                        if (len != sizeof(kernel_modver)) {
+                        if (len != sizeof(buffer.kernel_modver)) {
                                 syslog(LOG_ERR, "invalid version negotiation");
                                 exit(EXIT_FAILURE);
                         }
-                        kernel_modver = *(__u32 *)buffer;
                         in_handshake = 0;
-                        syslog(LOG_INFO, "kernel module version: %d",
-                               kernel_modver);
+                        syslog(LOG_INFO, "kernel module version: %u",
+                               buffer.kernel_modver);
                         continue;
                 }
 
-                in_msg = (struct hv_fcopy_hdr *)buffer;
-
-                switch (in_msg->operation) {
+                switch (buffer.hdr.operation) {
                 case START_FILE_COPY:
-                        error = hv_start_fcopy((struct hv_start_fcopy *)in_msg);
+                        error = hv_start_fcopy(&buffer.start);
                         break;
                 case WRITE_TO_FILE:
-                        error = hv_copy_data((struct hv_do_fcopy *)in_msg);
+                        error = hv_copy_data(&buffer.copy);
                         break;
                 case COMPLETE_FCOPY:
                         error = hv_copy_finished();
@@ -231,7 +233,7 @@ int main(int argc, char *argv[])
 
                 default:
                         syslog(LOG_ERR, "Unknown operation: %d",
-                                in_msg->operation);
+                                buffer.hdr.operation);
 
                 }
 
diff --git a/tools/hv/hv_get_dhcp_info.sh b/tools/hv/hv_get_dhcp_info.sh
index ccd3e9532764..c38686c44656 100755
--- a/tools/hv/hv_get_dhcp_info.sh
+++ b/tools/hv/hv_get_dhcp_info.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 # This example script retrieves the DHCP state of a given interface.
 # In the interest of keeping the KVP daemon code free of distro specific
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 88b20e007c05..eaa3bec273c8 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -1136,7 +1136,7 @@ static int process_ip_string(FILE *f, char *ip_string, int type)
         int i = 0;
         int j = 0;
         char str[256];
-        char sub_str[10];
+        char sub_str[13];
         int offset = 0;
 
         memset(addr, 0, sizeof(addr));
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index 735aafd64a3f..7ed9f85ef908 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 # This example script activates an interface based on the specified
 # configuration.
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 7ba54195934c..b2b4ebffab8c 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -21,6 +21,7 @@
 #include <sys/types.h>
 #include <sys/poll.h>
 #include <sys/ioctl.h>
+#include <sys/stat.h>
 #include <fcntl.h>
 #include <stdio.h>
 #include <mntent.h>
@@ -30,6 +31,7 @@
 #include <ctype.h>
 #include <errno.h>
 #include <linux/fs.h>
+#include <linux/major.h>
 #include <linux/hyperv.h>
 #include <syslog.h>
 #include <getopt.h>
@@ -70,6 +72,7 @@ static int vss_operate(int operation)
         char match[] = "/dev/";
         FILE *mounts;
         struct mntent *ent;
+        struct stat sb;
         char errdir[1024] = {0};
         unsigned int cmd;
         int error = 0, root_seen = 0, save_errno = 0;
@@ -92,6 +95,10 @@ static int vss_operate(int operation)
         while ((ent = getmntent(mounts))) {
                 if (strncmp(ent->mnt_fsname, match, strlen(match)))
                         continue;
+                if (stat(ent->mnt_fsname, &sb) == -1)
+                        continue;
+                if (S_ISBLK(sb.st_mode) && major(sb.st_rdev) == LOOP_MAJOR)
+                        continue;
                 if (hasmntopt(ent, MNTOPT_RO) != NULL)
                         continue;
                 if (strcmp(ent->mnt_type, "vfat") == 0)
diff --git a/tools/hv/lsvmbus b/tools/hv/lsvmbus
index e8fecd61871f..353e56768df8 100644
--- a/tools/hv/lsvmbus
+++ b/tools/hv/lsvmbus
@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# SPDX-License-Identifier: GPL-2.0
 
 import os
 from optparse import OptionParser
diff --git a/tools/iio/Build b/tools/iio/Build
new file mode 100644
index 000000000000..f74cbda64710
--- /dev/null
+++ b/tools/iio/Build
@@ -0,0 +1,3 @@
+lsiio-y += lsiio.o iio_utils.o
+iio_event_monitor-y += iio_event_monitor.o iio_utils.o
+iio_generic_buffer-y += iio_generic_buffer.o iio_utils.o
diff --git a/tools/iio/Makefile b/tools/iio/Makefile
index 8f08e03a9a5e..a08e7a47d6a3 100644
--- a/tools/iio/Makefile
+++ b/tools/iio/Makefile
@@ -1,31 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
 CC = $(CROSS_COMPILE)gcc
-CFLAGS += -Wall -g -D_GNU_SOURCE -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+LD = $(CROSS_COMPILE)ld
+CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
-BINDIR=usr/bin
-INSTALL_PROGRAM=install -m 755 -p
-DEL_FILE=rm -f
+ALL_TARGETS := iio_event_monitor lsiio iio_generic_buffer
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
-all: iio_event_monitor lsiio iio_generic_buffer
+all: $(ALL_PROGRAMS)
 
-iio_event_monitor: iio_event_monitor.o iio_utils.o
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
 
-lsiio: lsiio.o iio_utils.o
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/iio: ../../include/uapi/linux/iio
+        mkdir -p $(OUTPUT)include/linux/iio 2>&1 || true
+        ln -sf $(CURDIR)/../../include/uapi/linux/iio/events.h $@
+        ln -sf $(CURDIR)/../../include/uapi/linux/iio/types.h $@
 
-iio_generic_buffer: iio_generic_buffer.o iio_utils.o
+prepare: $(OUTPUT)include/linux/iio
 
-%.o: %.c iio_utils.h
+LSIIO_IN := $(OUTPUT)lsiio-in.o
+$(LSIIO_IN): prepare FORCE
+        $(Q)$(MAKE) $(build)=lsiio
+$(OUTPUT)lsiio: $(LSIIO_IN)
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
-install:
-        - mkdir -p $(INSTALL_ROOT)/$(BINDIR)
-        - $(INSTALL_PROGRAM) "iio_event_monitor" "$(INSTALL_ROOT)/$(BINDIR)/iio_event_monitor"
-        - $(INSTALL_PROGRAM) "lsiio" "$(INSTALL_ROOT)/$(BINDIR)/lsiio"
-        - $(INSTALL_PROGRAM) "iio_generic_buffer" "$(INSTALL_ROOT)/$(BINDIR)/iio_generic_buffer"
+IIO_EVENT_MONITOR_IN := $(OUTPUT)iio_event_monitor-in.o
+$(IIO_EVENT_MONITOR_IN): prepare FORCE
+        $(Q)$(MAKE) $(build)=iio_event_monitor
+$(OUTPUT)iio_event_monitor: $(IIO_EVENT_MONITOR_IN)
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
-uninstall:
-        $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/iio_event_monitor"
-        $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/lsiio"
-        $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/iio_generic_buffer"
+IIO_GENERIC_BUFFER_IN := $(OUTPUT)iio_generic_buffer-in.o
+$(IIO_GENERIC_BUFFER_IN): prepare FORCE
+        $(Q)$(MAKE) $(build)=iio_generic_buffer
+$(OUTPUT)iio_generic_buffer: $(IIO_GENERIC_BUFFER_IN)
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
-.PHONY: clean
 clean:
-        rm -f *.o iio_event_monitor lsiio iio_generic_buffer
+        rm -f $(ALL_PROGRAMS)
+        rm -rf $(OUTPUT)include/linux/iio
+        find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+
+install: $(ALL_PROGRAMS)
+        install -d -m 755 $(DESTDIR)$(bindir);          \
+        for program in $(ALL_PROGRAMS); do              \
+                install $$program $(DESTDIR)$(bindir);  \
+        done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
index 5e9738f97bf3..4c1966f7c77a 100644
--- a/tools/include/asm-generic/atomic-gcc.h
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
 #define __TOOLS_ASM_GENERIC_ATOMIC_H
 
@@ -21,7 +22,7 @@
  */
 static inline int atomic_read(const atomic_t *v)
 {
-        return ACCESS_ONCE((v)->counter);
+        return READ_ONCE((v)->counter);
 }
 
 /**
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 0304600121da..9bce3b56b5e7 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_ASM_GENERIC_BITOPS_H
 #define __TOOLS_ASM_GENERIC_BITOPS_H
 
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
index b3accfdf24b9..9d1310519497 100644
--- a/tools/include/asm-generic/bitops/__ffs.h
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
 
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index a60a7ccb6782..03f721a8a2b1 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS___FLS_H_
 #define _ASM_GENERIC_BITOPS___FLS_H_
 
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
index 6a211f40665c..c2705e1d220d 100644
--- a/tools/include/asm-generic/bitops/arch_hweight.h
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 68b8c1516c5a..21c41ccd1266 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
 
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
index 0a7e06623470..149faeeeeaf2 100644
--- a/tools/include/asm-generic/bitops/const_hweight.h
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
index 5538ecdc964a..9311fadaaab2 100644
--- a/tools/include/asm-generic/bitops/find.h
+++ b/tools/include/asm-generic/bitops/find.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
 
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index 0576d1f42f43..753aecaab641 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_FLS_H_
 #define _ASM_GENERIC_BITOPS_FLS_H_
 
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index b097cf8444e3..866f2b2304ff 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_GENERIC_BITOPS_FLS64_H_
 #define _ASM_GENERIC_BITOPS_FLS64_H_
 
diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h
index 290120c01a8e..3e681982bcd1 100644
--- a/tools/include/asm-generic/bitops/hweight.h
+++ b/tools/include/asm-generic/bitops/hweight.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
 
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
index 45eca517efb3..8f2283052333 100644
--- a/tools/include/asm-generic/bitsperlong.h
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_GENERIC_BITS_PER_LONG
 #define __ASM_GENERIC_BITS_PER_LONG
 
diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h
new file mode 100644
index 000000000000..e4732d3c2998
--- /dev/null
+++ b/tools/include/asm-generic/hugetlb_encode.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size.  If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments.  The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments.  System call specific header files
+ * that use this encoding should include this file.  They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT       26
+#define HUGETLB_FLAG_ENCODE_MASK        0x3f
+
+#define HUGETLB_FLAG_ENCODE_64KB        (16 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB       (19 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB         (20 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB         (21 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB         (23 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB        (24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB       (28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB         (30 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB         (31 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB        (34 << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
diff --git a/tools/include/asm/alternative-asm.h b/tools/include/asm/alternative-asm.h
index 2a4d1bfa2988..b54bd860dff6 100644
--- a/tools/include/asm/alternative-asm.h
+++ b/tools/include/asm/alternative-asm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
 #define _TOOLS_ASM_ALTERNATIVE_ASM_H
 
diff --git a/tools/include/asm/atomic.h b/tools/include/asm/atomic.h
index 70794f538a86..8c9bfffd4191 100644
--- a/tools/include/asm/atomic.h
+++ b/tools/include/asm/atomic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_ASM_ATOMIC_H
 #define __TOOLS_LINUX_ASM_ATOMIC_H
 
diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h
index ac66ac594685..391d942536e5 100644
--- a/tools/include/asm/barrier.h
+++ b/tools/include/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #if defined(__i386__) || defined(__x86_64__)
 #include "../../arch/x86/include/asm/barrier.h"
 #elif defined(__arm__)
diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h
index 4790f047a89c..bbd75ac8b202 100644
--- a/tools/include/asm/bug.h
+++ b/tools/include/asm/bug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_ASM_BUG_H
 #define _TOOLS_ASM_BUG_H
 
diff --git a/tools/include/asm/export.h b/tools/include/asm/export.h
new file mode 100644
index 000000000000..2cb1a0d83035
--- /dev/null
+++ b/tools/include/asm/export.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_ASM_EXPORT_H
+#define _TOOLS_ASM_EXPORT_H
+
+#define EXPORT_SYMBOL(x)
+#define EXPORT_SYMBOL_GPL(x)
+
+#endif /* _TOOLS_ASM_EXPORT_H */
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
index 9f21fc2b092b..00a6c4ca562b 100644
--- a/tools/include/linux/atomic.h
+++ b/tools/include/linux/atomic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_ATOMIC_H
 #define __TOOLS_LINUX_ATOMIC_H
 
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index e8b9f518e36b..ca160270fdfa 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_BITOPS_H
 #define _PERF_BITOPS_H
 
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 969db1981868..acc704bd3998 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_BITOPS_H_
 #define _TOOLS_LINUX_BITOPS_H_
 
diff --git a/tools/include/linux/bug.h b/tools/include/linux/bug.h
index 8e4a4f49135d..85f80258a15f 100644
--- a/tools/include/linux/bug.h
+++ b/tools/include/linux/bug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_PERF_LINUX_BUG_H
 #define _TOOLS_PERF_LINUX_BUG_H
 
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index bd39b2090ad1..a3a4427441bf 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
 #endif
@@ -21,11 +22,14 @@
 #define __must_be_array(a)      BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
 #define  noinline       __attribute__((noinline))
-
+#ifndef __packed
 #define __packed        __attribute__((packed))
-
+#endif
+#ifndef __noreturn
 #define __noreturn      __attribute__((noreturn))
-
+#endif
+#ifndef __aligned
 #define __aligned(x)    __attribute__((aligned(x)))
+#endif
 #define __printf(a, b)  __attribute__((format(printf, a, b)))
 #define __scanf(a, b)   __attribute__((format(scanf, a, b)))
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index d7a5604c38d7..07fd03c74a77 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index 7d410260661b..edfeaba95429 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -24,6 +24,12 @@
 /* ETMv3.5/PTM's ETMCR config bit */
 #define ETM_OPT_CYCACC  12
 #define ETM_OPT_TS      28
+#define ETM_OPT_RETSTK  29
+
+/* ETMv4 CONFIGR programming bits for the ETM OPTs */
+#define ETM4_CFG_BIT_CYCACC     4
+#define ETM4_CFG_BIT_TS         11
+#define ETM4_CFG_BIT_RETSTK     12
 
 static inline int coresight_get_trace_id(int cpu)
 {
diff --git a/tools/include/linux/debug_locks.h b/tools/include/linux/debug_locks.h
index 61cc7f501168..72d595ce764a 100644
--- a/tools/include/linux/debug_locks.h
+++ b/tools/include/linux/debug_locks.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
 #define _LIBLOCKDEP_DEBUG_LOCKS_H_
 
diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h
index abf0478a8fb2..7a8b61ad44cb 100644
--- a/tools/include/linux/err.h
+++ b/tools/include/linux/err.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_ERR_H
 #define __TOOLS_LINUX_ERR_H
 
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 4ce25d43e8e3..c5e512da8d8a 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Linux Socket Filter Data Structures
  */
diff --git a/tools/include/linux/hardirq.h b/tools/include/linux/hardirq.h
index c8f3f8f58729..b25580b6a9be 100644
--- a/tools/include/linux/hardirq.h
+++ b/tools/include/linux/hardirq.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
 #define _LIBLOCKDEP_LINUX_HARDIRQ_H_
 
diff --git a/tools/include/linux/hashtable.h b/tools/include/linux/hashtable.h
index 251eabf2a05e..434dd5ac6d71 100644
--- a/tools/include/linux/hashtable.h
+++ b/tools/include/linux/hashtable.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Statically sized hash table implementation
  * (C) 2012  Sasha Levin <levinsasha928@gmail.com>
diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h
index df77669cfe1c..e734da3e5b33 100644
--- a/tools/include/linux/irqflags.h
+++ b/tools/include/linux/irqflags.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
 #define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
 
diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
index 582cc1e5f3a4..89ca6fe257cc 100644
--- a/tools/include/linux/kallsyms.h
+++ b/tools/include/linux/kallsyms.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_LINUX_KALLSYMS_H_
 #define _LIBLOCKDEP_LINUX_KALLSYMS_H_
 
diff --git a/tools/include/linux/kern_levels.h b/tools/include/linux/kern_levels.h
index 3b9bade28698..778ecb984480 100644
--- a/tools/include/linux/kern_levels.h
+++ b/tools/include/linux/kern_levels.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __KERN_LEVELS_H__
 #define __KERN_LEVELS_H__
 
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 77d2e94ca5df..0ad884452c5c 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_KERNEL_H
 #define __TOOLS_LINUX_KERNEL_H
 
diff --git a/tools/include/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h
index 94d598bc6abe..ea32a7d3cf1b 100644
--- a/tools/include/linux/kmemcheck.h
+++ b/tools/include/linux/kmemcheck.h
@@ -1,8 +1 @@
-#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_
-#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_
-
-static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
-}
-
-#endif
+/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h
index 1da423820ad4..b2fc48d5478c 100644
--- a/tools/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_LINUX_LIST_H
 #define __TOOLS_LINUX_LIST_H
 
diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h
index 8da3e8effafa..940c1b075659 100644
--- a/tools/include/linux/lockdep.h
+++ b/tools/include/linux/lockdep.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_LOCKDEP_H_
 #define _LIBLOCKDEP_LOCKDEP_H_
 
diff --git a/tools/include/linux/module.h b/tools/include/linux/module.h
index 07055db296f3..2c999abf68e7 100644
--- a/tools/include/linux/module.h
+++ b/tools/include/linux/module.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_LINUX_MODULE_H_
 #define _LIBLOCKDEP_LINUX_MODULE_H_
 
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
index 51334edec506..9fdcd3eaac3b 100644
--- a/tools/include/linux/poison.h
+++ b/tools/include/linux/poison.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_POISON_H
 #define _LINUX_POISON_H
 
@@ -14,6 +15,10 @@
 # define POISON_POINTER_DELTA 0
 #endif
 
+#ifdef __cplusplus
+#define LIST_POISON1  NULL
+#define LIST_POISON2  NULL
+#else
 /*
  * These are non-NULL pointers that will result in page faults
  * under normal circumstances, used to verify that nobody uses
@@ -21,6 +26,7 @@
  */
 #define LIST_POISON1  ((void *) 0x100 + POISON_POINTER_DELTA)
 #define LIST_POISON2  ((void *) 0x200 + POISON_POINTER_DELTA)
+#endif
 
 /********** include/linux/timer.h **********/
 /*
diff --git a/tools/include/linux/rcu.h b/tools/include/linux/rcu.h
index 5080649dad04..7d02527e5bce 100644
--- a/tools/include/linux/rcu.h
+++ b/tools/include/linux/rcu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_RCU_H_
 #define _LIBLOCKDEP_RCU_H_
 
diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h
index a0177c1f55b1..36cb29bc57c2 100644
--- a/tools/include/linux/refcount.h
+++ b/tools/include/linux/refcount.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_REFCOUNT_H
 #define _TOOLS_LINUX_REFCOUNT_H
 
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 417cda4f793f..4ed569fcb139 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_SPINLOCK_H_
 #define __LINUX_SPINLOCK_H_
 
diff --git a/tools/include/linux/stacktrace.h b/tools/include/linux/stacktrace.h
index 39aecc6b19d1..ae343ac35bfa 100644
--- a/tools/include/linux/stacktrace.h
+++ b/tools/include/linux/stacktrace.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_
 #define _LIBLOCKDEP_LINUX_STACKTRACE_H_
 
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index d62b56cf8c12..6c3e2cc274c5 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -1,8 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_STRING_H_
 #define _TOOLS_LINUX_STRING_H_
 
-
 #include <linux/types.h>        /* for size_t */
+#include <string.h>
 
 void *memdup(const void *src, size_t len);
 
@@ -18,6 +19,14 @@ extern size_t strlcpy(char *dest, const char *src, size_t size);
 
 char *str_error_r(int errnum, char *buf, size_t buflen);
 
-int prefixcmp(const char *str, const char *prefix);
+/**
+ * strstarts - does @str start with @prefix?
+ * @str: string to examine
+ * @prefix: prefix to look for.
+ */
+static inline bool strstarts(const char *str, const char *prefix)
+{
+        return strncmp(str, prefix, strlen(prefix)) == 0;
+}
 
 #endif /* _LINUX_STRING_H_ */
diff --git a/tools/include/linux/stringify.h b/tools/include/linux/stringify.h
index 841cec8ed525..60e2c187da2c 100644
--- a/tools/include/linux/stringify.h
+++ b/tools/include/linux/stringify.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_STRINGIFY_H
 #define __LINUX_STRINGIFY_H
 
diff --git a/tools/include/linux/time64.h b/tools/include/linux/time64.h
index df9265483d65..55fa644b95fd 100644
--- a/tools/include/linux/time64.h
+++ b/tools/include/linux/time64.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_TIME64_H
 #define _TOOLS_LINUX_TIME64_H
 
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index 77a28a26a670..154eb4e3ca7c 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LINUX_TYPES_H_
 #define _TOOLS_LINUX_TYPES_H_
 
diff --git a/tools/include/linux/unaligned/packed_struct.h b/tools/include/linux/unaligned/packed_struct.h
index c0d817de4df2..dbd93c7df2e1 100644
--- a/tools/include/linux/unaligned/packed_struct.h
+++ b/tools/include/linux/unaligned/packed_struct.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H
 #define _LINUX_UNALIGNED_PACKED_STRUCT_H
 
diff --git a/tools/include/tools/be_byteshift.h b/tools/include/tools/be_byteshift.h
index 84c17d836578..f7d1d1698938 100644
--- a/tools/include/tools/be_byteshift.h
+++ b/tools/include/tools/be_byteshift.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_BE_BYTESHIFT_H
 #define _TOOLS_BE_BYTESHIFT_H
 
diff --git a/tools/include/tools/endian.h b/tools/include/tools/endian.h
index 8001194008da..c67888fd427e 100644
--- a/tools/include/tools/endian.h
+++ b/tools/include/tools/endian.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_ENDIAN_H
 #define _TOOLS_ENDIAN_H
 
diff --git a/tools/include/tools/le_byteshift.h b/tools/include/tools/le_byteshift.h
index 8fe9f2488ec7..dc8565f39717 100644
--- a/tools/include/tools/le_byteshift.h
+++ b/tools/include/tools/le_byteshift.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TOOLS_LE_BYTESHIFT_H
 #define _TOOLS_LE_BYTESHIFT_H
 
diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
new file mode 100644
index 000000000000..ac190958c981
--- /dev/null
+++ b/tools/include/uapi/asm-generic/fcntl.h
@@ -0,0 +1,220 @@
+#ifndef _ASM_GENERIC_FCNTL_H
+#define _ASM_GENERIC_FCNTL_H
+
+#include <linux/types.h>
+
+/*
+ * FMODE_EXEC is 0x20
+ * FMODE_NONOTIFY is 0x4000000
+ * These cannot be used by userspace O_* until internal and external open
+ * flags are split.
+ * -Eric Paris
+ */
+
+/*
+ * When introducing new O_* bits, please check its uniqueness in fcntl_init().
+ */
+
+#define O_ACCMODE       00000003
+#define O_RDONLY        00000000
+#define O_WRONLY        00000001
+#define O_RDWR          00000002
+#ifndef O_CREAT
+#define O_CREAT         00000100        /* not fcntl */
+#endif
+#ifndef O_EXCL
+#define O_EXCL          00000200        /* not fcntl */
+#endif
+#ifndef O_NOCTTY
+#define O_NOCTTY        00000400        /* not fcntl */
+#endif
+#ifndef O_TRUNC
+#define O_TRUNC         00001000        /* not fcntl */
+#endif
+#ifndef O_APPEND
+#define O_APPEND        00002000
+#endif
+#ifndef O_NONBLOCK
+#define O_NONBLOCK      00004000
+#endif
+#ifndef O_DSYNC
+#define O_DSYNC         00010000        /* used to be O_SYNC, see below */
+#endif
+#ifndef FASYNC
+#define FASYNC          00020000        /* fcntl, for BSD compatibility */
+#endif
+#ifndef O_DIRECT
+#define O_DIRECT        00040000        /* direct disk access hint */
+#endif
+#ifndef O_LARGEFILE
+#define O_LARGEFILE     00100000
+#endif
+#ifndef O_DIRECTORY
+#define O_DIRECTORY     00200000        /* must be a directory */
+#endif
+#ifndef O_NOFOLLOW
+#define O_NOFOLLOW      00400000        /* don't follow links */
+#endif
+#ifndef O_NOATIME
+#define O_NOATIME       01000000
+#endif
+#ifndef O_CLOEXEC
+#define O_CLOEXEC       02000000        /* set close_on_exec */
+#endif
+
+/*
+ * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag.  We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics.  It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#ifndef O_SYNC
+#define __O_SYNC        04000000
+#define O_SYNC          (__O_SYNC|O_DSYNC)
+#endif
+
+#ifndef O_PATH
+#define O_PATH          010000000
+#endif
+
+#ifndef __O_TMPFILE
+#define __O_TMPFILE     020000000
+#endif
+
+/* a horrid kludge trying to make sure that this will fail on old kernels */
+#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
+#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)
+
+#ifndef O_NDELAY
+#define O_NDELAY        O_NONBLOCK
+#endif
+
+#define F_DUPFD         0       /* dup */
+#define F_GETFD         1       /* get close_on_exec */
+#define F_SETFD         2       /* set/clear close_on_exec */
+#define F_GETFL         3       /* get file->f_flags */
+#define F_SETFL         4       /* set file->f_flags */
+#ifndef F_GETLK
+#define F_GETLK         5
+#define F_SETLK         6
+#define F_SETLKW        7
+#endif
+#ifndef F_SETOWN
+#define F_SETOWN        8       /* for sockets. */
+#define F_GETOWN        9       /* for sockets. */
+#endif
+#ifndef F_SETSIG
+#define F_SETSIG        10      /* for sockets. */
+#define F_GETSIG        11      /* for sockets. */
+#endif
+
+#ifndef CONFIG_64BIT
+#ifndef F_GETLK64
+#define F_GETLK64       12      /*  using 'struct flock64' */
+#define F_SETLK64       13
+#define F_SETLKW64      14
+#endif
+#endif
+
+#ifndef F_SETOWN_EX
+#define F_SETOWN_EX     15
+#define F_GETOWN_EX     16
+#endif
+
+#ifndef F_GETOWNER_UIDS
+#define F_GETOWNER_UIDS 17
+#endif
+
+/*
+ * Open File Description Locks
+ *
+ * Usually record locks held by a process are released on *any* close and are
+ * not inherited across a fork().
+ *
+ * These cmd values will set locks that conflict with process-associated
+ * record  locks, but are "owned" by the open file description, not the
+ * process. This means that they are inherited across fork() like BSD (flock)
+ * locks, and they are only released automatically when the last reference to
+ * the the open file against which they were acquired is put.
+ */
+#define F_OFD_GETLK     36
+#define F_OFD_SETLK     37
+#define F_OFD_SETLKW    38
+
+#define F_OWNER_TID     0
+#define F_OWNER_PID     1
+#define F_OWNER_PGRP    2
+
+struct f_owner_ex {
+        int     type;
+        __kernel_pid_t  pid;
+};
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC      1       /* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#ifndef F_RDLCK
+#define F_RDLCK         0
+#define F_WRLCK         1
+#define F_UNLCK         2
+#endif
+
+/* for old implementation of bsd flock () */
+#ifndef F_EXLCK
+#define F_EXLCK         4       /* or 3 */
+#define F_SHLCK         8       /* or 4 */
+#endif
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH         1       /* shared lock */
+#define LOCK_EX         2       /* exclusive lock */
+#define LOCK_NB         4       /* or'd with one of the above to prevent
+                                   blocking */
+#define LOCK_UN         8       /* remove lock */
+
+#define LOCK_MAND       32      /* This is a mandatory flock ... */
+#define LOCK_READ       64      /* which allows concurrent read operations */
+#define LOCK_WRITE      128     /* which allows concurrent write operations */
+#define LOCK_RW         192     /* which allows concurrent read & write ops */
+
+#define F_LINUX_SPECIFIC_BASE   1024
+
+#ifndef HAVE_ARCH_STRUCT_FLOCK
+#ifndef __ARCH_FLOCK_PAD
+#define __ARCH_FLOCK_PAD
+#endif
+
+struct flock {
+        short   l_type;
+        short   l_whence;
+        __kernel_off_t  l_start;
+        __kernel_off_t  l_len;
+        __kernel_pid_t  l_pid;
+        __ARCH_FLOCK_PAD
+};
+#endif
+
+#ifndef HAVE_ARCH_STRUCT_FLOCK64
+#ifndef __ARCH_FLOCK64_PAD
+#define __ARCH_FLOCK64_PAD
+#endif
+
+struct flock64 {
+        short  l_type;
+        short  l_whence;
+        __kernel_loff_t l_start;
+        __kernel_loff_t l_len;
+        __kernel_pid_t  l_pid;
+        __ARCH_FLOCK64_PAD
+};
+#endif
+
+#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
new file mode 100644
index 000000000000..040651735662
--- /dev/null
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_IOCTLS_H
+#define __ASM_GENERIC_IOCTLS_H
+
+#include <linux/ioctl.h>
+
+/*
+ * These are the most common definitions for tty ioctl numbers.
+ * Most of them do not use the recommended _IOC(), but there is
+ * probably some source code out there hardcoding the number,
+ * so we might as well use them for all new platforms.
+ *
+ * The architectures that use different values here typically
+ * try to be compatible with some Unix variants for the same
+ * architecture.
+ */
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS          0x5401
+#define TCSETS          0x5402
+#define TCSETSW         0x5403
+#define TCSETSF         0x5404
+#define TCGETA          0x5405
+#define TCSETA          0x5406
+#define TCSETAW         0x5407
+#define TCSETAF         0x5408
+#define TCSBRK          0x5409
+#define TCXONC          0x540A
+#define TCFLSH          0x540B
+#define TIOCEXCL        0x540C
+#define TIOCNXCL        0x540D
+#define TIOCSCTTY       0x540E
+#define TIOCGPGRP       0x540F
+#define TIOCSPGRP       0x5410
+#define TIOCOUTQ        0x5411
+#define TIOCSTI         0x5412
+#define TIOCGWINSZ      0x5413
+#define TIOCSWINSZ      0x5414
+#define TIOCMGET        0x5415
+#define TIOCMBIS        0x5416
+#define TIOCMBIC        0x5417
+#define TIOCMSET        0x5418
+#define TIOCGSOFTCAR    0x5419
+#define TIOCSSOFTCAR    0x541A
+#define FIONREAD        0x541B
+#define TIOCINQ         FIONREAD
+#define TIOCLINUX       0x541C
+#define TIOCCONS        0x541D
+#define TIOCGSERIAL     0x541E
+#define TIOCSSERIAL     0x541F
+#define TIOCPKT         0x5420
+#define FIONBIO         0x5421
+#define TIOCNOTTY       0x5422
+#define TIOCSETD        0x5423
+#define TIOCGETD        0x5424
+#define TCSBRKP         0x5425  /* Needed for POSIX tcsendbreak() */
+#define TIOCSBRK        0x5427  /* BSD compatibility */
+#define TIOCCBRK        0x5428  /* BSD compatibility */
+#define TIOCGSID        0x5429  /* Return the session ID of FD */
+#define TCGETS2         _IOR('T', 0x2A, struct termios2)
+#define TCSETS2         _IOW('T', 0x2B, struct termios2)
+#define TCSETSW2        _IOW('T', 0x2C, struct termios2)
+#define TCSETSF2        _IOW('T', 0x2D, struct termios2)
+#define TIOCGRS485      0x542E
+#ifndef TIOCSRS485
+#define TIOCSRS485      0x542F
+#endif
+#define TIOCGPTN        _IOR('T', 0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK      _IOW('T', 0x31, int)  /* Lock/unlock Pty */
+#define TIOCGDEV        _IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */
+#define TCGETX          0x5432 /* SYS5 TCGETX compatibility */
+#define TCSETX          0x5433
+#define TCSETXF         0x5434
+#define TCSETXW         0x5435
+#define TIOCSIG         _IOW('T', 0x36, int)  /* pty: generate signal */
+#define TIOCVHANGUP     0x5437
+#define TIOCGPKT        _IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK      _IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL       _IOR('T', 0x40, int) /* Get exclusive mode state */
+#define TIOCGPTPEER     _IO('T', 0x41) /* Safely open the slave */
+
+#define FIONCLEX        0x5450
+#define FIOCLEX         0x5451
+#define FIOASYNC        0x5452
+#define TIOCSERCONFIG   0x5453
+#define TIOCSERGWILD    0x5454
+#define TIOCSERSWILD    0x5455
+#define TIOCGLCKTRMIOS  0x5456
+#define TIOCSLCKTRMIOS  0x5457
+#define TIOCSERGSTRUCT  0x5458 /* For debugging only */
+#define TIOCSERGETLSR   0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT      0x545C  /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
+
+/*
+ * Some arches already define FIOQSIZE due to a historical
+ * conflict with a Hayes modem-specific ioctl value.
+ */
+#ifndef FIOQSIZE
+# define FIOQSIZE       0x5460
+#endif
+
+/* Used for packet mode */
+#define TIOCPKT_DATA             0
+#define TIOCPKT_FLUSHREAD        1
+#define TIOCPKT_FLUSHWRITE       2
+#define TIOCPKT_STOP             4
+#define TIOCPKT_START            8
+#define TIOCPKT_NOSTOP          16
+#define TIOCPKT_DOSTOP          32
+#define TIOCPKT_IOCTL           64
+
+#define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
+
+#endif /* __ASM_GENERIC_IOCTLS_H */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 8c27db0c5c08..f8b134f5608f 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_MMAN_COMMON_H
 #define __ASM_GENERIC_MMAN_COMMON_H
 
@@ -16,6 +17,7 @@
 
 #define MAP_SHARED      0x01            /* Share changes */
 #define MAP_PRIVATE     0x02            /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03        /* share + validate extension flags */
 #define MAP_TYPE        0x0f            /* Mask for type of mapping */
 #define MAP_FIXED       0x10            /* Interpret addr exactly */
 #define MAP_ANONYMOUS   0x20            /* don't use a file */
@@ -58,20 +60,12 @@
                                            overrides the coredump filter bits */
 #define MADV_DODUMP     17              /* Clear the MADV_DONTDUMP flag */
 
+#define MADV_WIPEONFORK 18              /* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19              /* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE        0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT  26
-#define MAP_HUGE_MASK   0x3f
-
 #define PKEY_DISABLE_ACCESS     0x1
 #define PKEY_DISABLE_WRITE      0x2
 #define PKEY_ACCESS_MASK        (PKEY_DISABLE_ACCESS |\
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 10fa7857777f..2dffcbf705b3 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -1,7 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <uapi/asm-generic/mman-common.h>
+#include <asm-generic/mman-common.h>
 
 #define MAP_GROWSDOWN   0x0100          /* stack-like segment */
 #define MAP_DENYWRITE   0x0800          /* ETXTBSY */
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
new file mode 100644
index 000000000000..97677cd6964d
--- /dev/null
+++ b/tools/include/uapi/drm/drm.h
@@ -0,0 +1,955 @@
+/**
+ * \file drm.h
+ * Header for the Direct Rendering Manager
+ *
+ * \author Rickard E. (Rik) Faith <faith@valinux.com>
+ *
+ * \par Acknowledgments:
+ * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic \c cmpxchg.
+ */
+
+/*
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DRM_H_
+#define _DRM_H_
+
+#if defined(__KERNEL__)
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+typedef unsigned int drm_handle_t;
+
+#elif defined(__linux__)
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+typedef unsigned int drm_handle_t;
+
+#else /* One of the BSDs */
+
+#include <sys/ioccom.h>
+#include <sys/types.h>
+typedef int8_t   __s8;
+typedef uint8_t  __u8;
+typedef int16_t  __s16;
+typedef uint16_t __u16;
+typedef int32_t  __s32;
+typedef uint32_t __u32;
+typedef int64_t  __s64;
+typedef uint64_t __u64;
+typedef size_t   __kernel_size_t;
+typedef unsigned long drm_handle_t;
+
+#endif
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_NAME        "drm"     /**< Name in kernel, /dev, and /proc */
+#define DRM_MIN_ORDER   5         /**< At least 2^5 bytes = 32 bytes */
+#define DRM_MAX_ORDER   22        /**< Up to 2^22 bytes = 4MB */
+#define DRM_RAM_PERCENT 10        /**< How much system ram can we lock? */
+
+#define _DRM_LOCK_HELD  0x80000000U /**< Hardware lock is held */
+#define _DRM_LOCK_CONT  0x40000000U /**< Hardware lock is contended */
+#define _DRM_LOCK_IS_HELD(lock)    ((lock) & _DRM_LOCK_HELD)
+#define _DRM_LOCK_IS_CONT(lock)    ((lock) & _DRM_LOCK_CONT)
+#define _DRM_LOCKING_CONTEXT(lock) ((lock) & ~(_DRM_LOCK_HELD|_DRM_LOCK_CONT))
+
+typedef unsigned int drm_context_t;
+typedef unsigned int drm_drawable_t;
+typedef unsigned int drm_magic_t;
+
+/**
+ * Cliprect.
+ *
+ * \warning: If you change this structure, make sure you change
+ * XF86DRIClipRectRec in the server as well
+ *
+ * \note KW: Actually it's illegal to change either for
+ * backwards-compatibility reasons.
+ */
+struct drm_clip_rect {
+        unsigned short x1;
+        unsigned short y1;
+        unsigned short x2;
+        unsigned short y2;
+};
+
+/**
+ * Drawable information.
+ */
+struct drm_drawable_info {
+        unsigned int num_rects;
+        struct drm_clip_rect *rects;
+};
+
+/**
+ * Texture region,
+ */
+struct drm_tex_region {
+        unsigned char next;
+        unsigned char prev;
+        unsigned char in_use;
+        unsigned char padding;
+        unsigned int age;
+};
+
+/**
+ * Hardware lock.
+ *
+ * The lock structure is a simple cache-line aligned integer.  To avoid
+ * processor bus contention on a multiprocessor system, there should not be any
+ * other data stored in the same cache line.
+ */
+struct drm_hw_lock {
+        __volatile__ unsigned int lock;         /**< lock variable */
+        char padding[60];                       /**< Pad to cache line */
+};
+
+/**
+ * DRM_IOCTL_VERSION ioctl argument type.
+ *
+ * \sa drmGetVersion().
+ */
+struct drm_version {
+        int version_major;        /**< Major version */
+        int version_minor;        /**< Minor version */
+        int version_patchlevel;   /**< Patch level */
+        __kernel_size_t name_len;         /**< Length of name buffer */
+        char __user *name;        /**< Name of driver */
+        __kernel_size_t date_len;         /**< Length of date buffer */
+        char __user *date;        /**< User-space buffer to hold date */
+        __kernel_size_t desc_len;         /**< Length of desc buffer */
+        char __user *desc;        /**< User-space buffer to hold desc */
+};
+
+/**
+ * DRM_IOCTL_GET_UNIQUE ioctl argument type.
+ *
+ * \sa drmGetBusid() and drmSetBusId().
+ */
+struct drm_unique {
+        __kernel_size_t unique_len;       /**< Length of unique */
+        char __user *unique;      /**< Unique name for driver instantiation */
+};
+
+struct drm_list {
+        int count;                /**< Length of user-space structures */
+        struct drm_version __user *version;
+};
+
+struct drm_block {
+        int unused;
+};
+
+/**
+ * DRM_IOCTL_CONTROL ioctl argument type.
+ *
+ * \sa drmCtlInstHandler() and drmCtlUninstHandler().
+ */
+struct drm_control {
+        enum {
+                DRM_ADD_COMMAND,
+                DRM_RM_COMMAND,
+                DRM_INST_HANDLER,
+                DRM_UNINST_HANDLER
+        } func;
+        int irq;
+};
+
+/**
+ * Type of memory to map.
+ */
+enum drm_map_type {
+        _DRM_FRAME_BUFFER = 0,    /**< WC (no caching), no core dump */
+        _DRM_REGISTERS = 1,       /**< no caching, no core dump */
+        _DRM_SHM = 2,             /**< shared, cached */
+        _DRM_AGP = 3,             /**< AGP/GART */
+        _DRM_SCATTER_GATHER = 4,  /**< Scatter/gather memory for PCI DMA */
+        _DRM_CONSISTENT = 5       /**< Consistent memory for PCI DMA */
+};
+
+/**
+ * Memory mapping flags.
+ */
+enum drm_map_flags {
+        _DRM_RESTRICTED = 0x01,      /**< Cannot be mapped to user-virtual */
+        _DRM_READ_ONLY = 0x02,
+        _DRM_LOCKED = 0x04,          /**< shared, cached, locked */
+        _DRM_KERNEL = 0x08,          /**< kernel requires access */
+        _DRM_WRITE_COMBINING = 0x10, /**< use write-combining if available */
+        _DRM_CONTAINS_LOCK = 0x20,   /**< SHM page that contains lock */
+        _DRM_REMOVABLE = 0x40,       /**< Removable mapping */
+        _DRM_DRIVER = 0x80           /**< Managed by driver */
+};
+
+struct drm_ctx_priv_map {
+        unsigned int ctx_id;     /**< Context requesting private mapping */
+        void *handle;            /**< Handle of map */
+};
+
+/**
+ * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls
+ * argument type.
+ *
+ * \sa drmAddMap().
+ */
+struct drm_map {
+        unsigned long offset;    /**< Requested physical address (0 for SAREA)*/
+        unsigned long size;      /**< Requested physical size (bytes) */
+        enum drm_map_type type;  /**< Type of memory to map */
+        enum drm_map_flags flags;        /**< Flags */
+        void *handle;            /**< User-space: "Handle" to pass to mmap() */
+                                 /**< Kernel-space: kernel-virtual address */
+        int mtrr;                /**< MTRR slot used */
+        /*   Private data */
+};
+
+/**
+ * DRM_IOCTL_GET_CLIENT ioctl argument type.
+ */
+struct drm_client {
+        int idx;                /**< Which client desired? */
+        int auth;               /**< Is client authenticated? */
+        unsigned long pid;      /**< Process ID */
+        unsigned long uid;      /**< User ID */
+        unsigned long magic;    /**< Magic */
+        unsigned long iocs;     /**< Ioctl count */
+};
+
+enum drm_stat_type {
+        _DRM_STAT_LOCK,
+        _DRM_STAT_OPENS,
+        _DRM_STAT_CLOSES,
+        _DRM_STAT_IOCTLS,
+        _DRM_STAT_LOCKS,
+        _DRM_STAT_UNLOCKS,
+        _DRM_STAT_VALUE,        /**< Generic value */
+        _DRM_STAT_BYTE,         /**< Generic byte counter (1024bytes/K) */
+        _DRM_STAT_COUNT,        /**< Generic non-byte counter (1000/k) */
+
+        _DRM_STAT_IRQ,          /**< IRQ */
+        _DRM_STAT_PRIMARY,      /**< Primary DMA bytes */
+        _DRM_STAT_SECONDARY,    /**< Secondary DMA bytes */
+        _DRM_STAT_DMA,          /**< DMA */
+        _DRM_STAT_SPECIAL,      /**< Special DMA (e.g., priority or polled) */
+        _DRM_STAT_MISSED        /**< Missed DMA opportunity */
+            /* Add to the *END* of the list */
+};
+
+/**
+ * DRM_IOCTL_GET_STATS ioctl argument type.
+ */
+struct drm_stats {
+        unsigned long count;
+        struct {
+                unsigned long value;
+                enum drm_stat_type type;
+        } data[15];
+};
+
+/**
+ * Hardware locking flags.
+ */
+enum drm_lock_flags {
+        _DRM_LOCK_READY = 0x01,      /**< Wait until hardware is ready for DMA */
+        _DRM_LOCK_QUIESCENT = 0x02,  /**< Wait until hardware quiescent */
+        _DRM_LOCK_FLUSH = 0x04,      /**< Flush this context's DMA queue first */
+        _DRM_LOCK_FLUSH_ALL = 0x08,  /**< Flush all DMA queues first */
+        /* These *HALT* flags aren't supported yet
+           -- they will be used to support the
+           full-screen DGA-like mode. */
+        _DRM_HALT_ALL_QUEUES = 0x10, /**< Halt all current and future queues */
+        _DRM_HALT_CUR_QUEUES = 0x20  /**< Halt all current queues */
+};
+
+/**
+ * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type.
+ *
+ * \sa drmGetLock() and drmUnlock().
+ */
+struct drm_lock {
+        int context;
+        enum drm_lock_flags flags;
+};
+
+/**
+ * DMA flags
+ *
+ * \warning
+ * These values \e must match xf86drm.h.
+ *
+ * \sa drm_dma.
+ */
+enum drm_dma_flags {
+        /* Flags for DMA buffer dispatch */
+        _DRM_DMA_BLOCK = 0x01,        /**<
+                                       * Block until buffer dispatched.
+                                       *
+                                       * \note The buffer may not yet have
+                                       * been processed by the hardware --
+                                       * getting a hardware lock with the
+                                       * hardware quiescent will ensure
+                                       * that the buffer has been
+                                       * processed.
+                                       */
+        _DRM_DMA_WHILE_LOCKED = 0x02, /**< Dispatch while lock held */
+        _DRM_DMA_PRIORITY = 0x04,     /**< High priority dispatch */
+
+        /* Flags for DMA buffer request */
+        _DRM_DMA_WAIT = 0x10,         /**< Wait for free buffers */
+        _DRM_DMA_SMALLER_OK = 0x20,   /**< Smaller-than-requested buffers OK */
+        _DRM_DMA_LARGER_OK = 0x40     /**< Larger-than-requested buffers OK */
+};
+
+/**
+ * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type.
+ *
+ * \sa drmAddBufs().
+ */
+struct drm_buf_desc {
+        int count;               /**< Number of buffers of this size */
+        int size;                /**< Size in bytes */
+        int low_mark;            /**< Low water mark */
+        int high_mark;           /**< High water mark */
+        enum {
+                _DRM_PAGE_ALIGN = 0x01, /**< Align on page boundaries for DMA */
+                _DRM_AGP_BUFFER = 0x02, /**< Buffer is in AGP space */
+                _DRM_SG_BUFFER = 0x04,  /**< Scatter/gather memory buffer */
+                _DRM_FB_BUFFER = 0x08,  /**< Buffer is in frame buffer */
+                _DRM_PCI_BUFFER_RO = 0x10 /**< Map PCI DMA buffer read-only */
+        } flags;
+        unsigned long agp_start; /**<
+                                  * Start address of where the AGP buffers are
+                                  * in the AGP aperture
+                                  */
+};
+
+/**
+ * DRM_IOCTL_INFO_BUFS ioctl argument type.
+ */
+struct drm_buf_info {
+        int count;              /**< Entries in list */
+        struct drm_buf_desc __user *list;
+};
+
+/**
+ * DRM_IOCTL_FREE_BUFS ioctl argument type.
+ */
+struct drm_buf_free {
+        int count;
+        int __user *list;
+};
+
+/**
+ * Buffer information
+ *
+ * \sa drm_buf_map.
+ */
+struct drm_buf_pub {
+        int idx;                       /**< Index into the master buffer list */
+        int total;                     /**< Buffer size */
+        int used;                      /**< Amount of buffer in use (for DMA) */
+        void __user *address;          /**< Address of buffer */
+};
+
+/**
+ * DRM_IOCTL_MAP_BUFS ioctl argument type.
+ */
+struct drm_buf_map {
+        int count;              /**< Length of the buffer list */
+#ifdef __cplusplus
+        void __user *virt;
+#else
+        void __user *virtual;           /**< Mmap'd area in user-virtual */
+#endif
+        struct drm_buf_pub __user *list;        /**< Buffer information */
+};
+
+/**
+ * DRM_IOCTL_DMA ioctl argument type.
+ *
+ * Indices here refer to the offset into the buffer list in drm_buf_get.
+ *
+ * \sa drmDMA().
+ */
+struct drm_dma {
+        int context;                      /**< Context handle */
+        int send_count;                   /**< Number of buffers to send */
+        int __user *send_indices;         /**< List of handles to buffers */
+        int __user *send_sizes;           /**< Lengths of data to send */
+        enum drm_dma_flags flags;         /**< Flags */
+        int request_count;                /**< Number of buffers requested */
+        int request_size;                 /**< Desired size for buffers */
+        int __user *request_indices;      /**< Buffer information */
+        int __user *request_sizes;
+        int granted_count;                /**< Number of buffers granted */
+};
+
+enum drm_ctx_flags {
+        _DRM_CONTEXT_PRESERVED = 0x01,
+        _DRM_CONTEXT_2DONLY = 0x02
+};
+
+/**
+ * DRM_IOCTL_ADD_CTX ioctl argument type.
+ *
+ * \sa drmCreateContext() and drmDestroyContext().
+ */
+struct drm_ctx {
+        drm_context_t handle;
+        enum drm_ctx_flags flags;
+};
+
+/**
+ * DRM_IOCTL_RES_CTX ioctl argument type.
+ */
+struct drm_ctx_res {
+        int count;
+        struct drm_ctx __user *contexts;
+};
+
+/**
+ * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type.
+ */
+struct drm_draw {
+        drm_drawable_t handle;
+};
+
+/**
+ * DRM_IOCTL_UPDATE_DRAW ioctl argument type.
+ */
+typedef enum {
+        DRM_DRAWABLE_CLIPRECTS
+} drm_drawable_info_type_t;
+
+struct drm_update_draw {
+        drm_drawable_t handle;
+        unsigned int type;
+        unsigned int num;
+        unsigned long long data;
+};
+
+/**
+ * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type.
+ */
+struct drm_auth {
+        drm_magic_t magic;
+};
+
+/**
+ * DRM_IOCTL_IRQ_BUSID ioctl argument type.
+ *
+ * \sa drmGetInterruptFromBusID().
+ */
+struct drm_irq_busid {
+        int irq;        /**< IRQ number */
+        int busnum;     /**< bus number */
+        int devnum;     /**< device number */
+        int funcnum;    /**< function number */
+};
+
+enum drm_vblank_seq_type {
+        _DRM_VBLANK_ABSOLUTE = 0x0,     /**< Wait for specific vblank sequence number */
+        _DRM_VBLANK_RELATIVE = 0x1,     /**< Wait for given number of vblanks */
+        /* bits 1-6 are reserved for high crtcs */
+        _DRM_VBLANK_HIGH_CRTC_MASK = 0x0000003e,
+        _DRM_VBLANK_EVENT = 0x4000000,   /**< Send event instead of blocking */
+        _DRM_VBLANK_FLIP = 0x8000000,   /**< Scheduled buffer swap should flip */
+        _DRM_VBLANK_NEXTONMISS = 0x10000000,    /**< If missed, wait for next vblank */
+        _DRM_VBLANK_SECONDARY = 0x20000000,     /**< Secondary display controller */
+        _DRM_VBLANK_SIGNAL = 0x40000000 /**< Send signal instead of blocking, unsupported */
+};
+#define _DRM_VBLANK_HIGH_CRTC_SHIFT 1
+
+#define _DRM_VBLANK_TYPES_MASK (_DRM_VBLANK_ABSOLUTE | _DRM_VBLANK_RELATIVE)
+#define _DRM_VBLANK_FLAGS_MASK (_DRM_VBLANK_EVENT | _DRM_VBLANK_SIGNAL | \
+                                _DRM_VBLANK_SECONDARY | _DRM_VBLANK_NEXTONMISS)
+
+struct drm_wait_vblank_request {
+        enum drm_vblank_seq_type type;
+        unsigned int sequence;
+        unsigned long signal;
+};
+
+struct drm_wait_vblank_reply {
+        enum drm_vblank_seq_type type;
+        unsigned int sequence;
+        long tval_sec;
+        long tval_usec;
+};
+
+/**
+ * DRM_IOCTL_WAIT_VBLANK ioctl argument type.
+ *
+ * \sa drmWaitVBlank().
+ */
+union drm_wait_vblank {
+        struct drm_wait_vblank_request request;
+        struct drm_wait_vblank_reply reply;
+};
+
+#define _DRM_PRE_MODESET 1
+#define _DRM_POST_MODESET 2
+
+/**
+ * DRM_IOCTL_MODESET_CTL ioctl argument type
+ *
+ * \sa drmModesetCtl().
+ */
+struct drm_modeset_ctl {
+        __u32 crtc;
+        __u32 cmd;
+};
+
+/**
+ * DRM_IOCTL_AGP_ENABLE ioctl argument type.
+ *
+ * \sa drmAgpEnable().
+ */
+struct drm_agp_mode {
+        unsigned long mode;     /**< AGP mode */
+};
+
+/**
+ * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type.
+ *
+ * \sa drmAgpAlloc() and drmAgpFree().
+ */
+struct drm_agp_buffer {
+        unsigned long size;     /**< In bytes -- will round to page boundary */
+        unsigned long handle;   /**< Used for binding / unbinding */
+        unsigned long type;     /**< Type of memory to allocate */
+        unsigned long physical; /**< Physical used by i810 */
+};
+
+/**
+ * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type.
+ *
+ * \sa drmAgpBind() and drmAgpUnbind().
+ */
+struct drm_agp_binding {
+        unsigned long handle;   /**< From drm_agp_buffer */
+        unsigned long offset;   /**< In bytes -- will round to page boundary */
+};
+
+/**
+ * DRM_IOCTL_AGP_INFO ioctl argument type.
+ *
+ * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(),
+ * drmAgpBase(), drmAgpSize(), drmAgpMemoryUsed(), drmAgpMemoryAvail(),
+ * drmAgpVendorId() and drmAgpDeviceId().
+ */
+struct drm_agp_info {
+        int agp_version_major;
+        int agp_version_minor;
+        unsigned long mode;
+        unsigned long aperture_base;    /* physical address */
+        unsigned long aperture_size;    /* bytes */
+        unsigned long memory_allowed;   /* bytes */
+        unsigned long memory_used;
+
+        /* PCI information */
+        unsigned short id_vendor;
+        unsigned short id_device;
+};
+
+/**
+ * DRM_IOCTL_SG_ALLOC ioctl argument type.
+ */
+struct drm_scatter_gather {
+        unsigned long size;     /**< In bytes -- will round to page boundary */
+        unsigned long handle;   /**< Used for mapping / unmapping */
+};
+
+/**
+ * DRM_IOCTL_SET_VERSION ioctl argument type.
+ */
+struct drm_set_version {
+        int drm_di_major;
+        int drm_di_minor;
+        int drm_dd_major;
+        int drm_dd_minor;
+};
+
+/** DRM_IOCTL_GEM_CLOSE ioctl argument type */
+struct drm_gem_close {
+        /** Handle of the object to be closed. */
+        __u32 handle;
+        __u32 pad;
+};
+
+/** DRM_IOCTL_GEM_FLINK ioctl argument type */
+struct drm_gem_flink {
+        /** Handle for the object being named */
+        __u32 handle;
+
+        /** Returned global name */
+        __u32 name;
+};
+
+/** DRM_IOCTL_GEM_OPEN ioctl argument type */
+struct drm_gem_open {
+        /** Name of object being opened */
+        __u32 name;
+
+        /** Returned handle for the object */
+        __u32 handle;
+
+        /** Returned size of the object */
+        __u64 size;
+};
+
+#define DRM_CAP_DUMB_BUFFER             0x1
+#define DRM_CAP_VBLANK_HIGH_CRTC        0x2
+#define DRM_CAP_DUMB_PREFERRED_DEPTH    0x3
+#define DRM_CAP_DUMB_PREFER_SHADOW      0x4
+#define DRM_CAP_PRIME                   0x5
+#define  DRM_PRIME_CAP_IMPORT           0x1
+#define  DRM_PRIME_CAP_EXPORT           0x2
+#define DRM_CAP_TIMESTAMP_MONOTONIC     0x6
+#define DRM_CAP_ASYNC_PAGE_FLIP         0x7
+/*
+ * The CURSOR_WIDTH and CURSOR_HEIGHT capabilities return a valid widthxheight
+ * combination for the hardware cursor. The intention is that a hardware
+ * agnostic userspace can query a cursor plane size to use.
+ *
+ * Note that the cross-driver contract is to merely return a valid size;
+ * drivers are free to attach another meaning on top, eg. i915 returns the
+ * maximum plane size.
+ */
+#define DRM_CAP_CURSOR_WIDTH            0x8
+#define DRM_CAP_CURSOR_HEIGHT           0x9
+#define DRM_CAP_ADDFB2_MODIFIERS        0x10
+#define DRM_CAP_PAGE_FLIP_TARGET        0x11
+#define DRM_CAP_CRTC_IN_VBLANK_EVENT    0x12
+#define DRM_CAP_SYNCOBJ         0x13
+
+/** DRM_IOCTL_GET_CAP ioctl argument type */
+struct drm_get_cap {
+        __u64 capability;
+        __u64 value;
+};
+
+/**
+ * DRM_CLIENT_CAP_STEREO_3D
+ *
+ * if set to 1, the DRM core will expose the stereo 3D capabilities of the
+ * monitor by advertising the supported 3D layouts in the flags of struct
+ * drm_mode_modeinfo.
+ */
+#define DRM_CLIENT_CAP_STEREO_3D        1
+
+/**
+ * DRM_CLIENT_CAP_UNIVERSAL_PLANES
+ *
+ * If set to 1, the DRM core will expose all planes (overlay, primary, and
+ * cursor) to userspace.
+ */
+#define DRM_CLIENT_CAP_UNIVERSAL_PLANES  2
+
+/**
+ * DRM_CLIENT_CAP_ATOMIC
+ *
+ * If set to 1, the DRM core will expose atomic properties to userspace
+ */
+#define DRM_CLIENT_CAP_ATOMIC   3
+
+/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+struct drm_set_client_cap {
+        __u64 capability;
+        __u64 value;
+};
+
+#define DRM_RDWR O_RDWR
+#define DRM_CLOEXEC O_CLOEXEC
+struct drm_prime_handle {
+        __u32 handle;
+
+        /** Flags.. only applicable for handle->fd */
+        __u32 flags;
+
+        /** Returned dmabuf file descriptor */
+        __s32 fd;
+};
+
+struct drm_syncobj_create {
+        __u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
+        __u32 flags;
+};
+
+struct drm_syncobj_destroy {
+        __u32 handle;
+        __u32 pad;
+};
+
+#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0)
+struct drm_syncobj_handle {
+        __u32 handle;
+        __u32 flags;
+
+        __s32 fd;
+        __u32 pad;
+};
+
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+struct drm_syncobj_wait {
+        __u64 handles;
+        /* absolute timeout */
+        __s64 timeout_nsec;
+        __u32 count_handles;
+        __u32 flags;
+        __u32 first_signaled; /* only valid when not waiting all */
+        __u32 pad;
+};
+
+struct drm_syncobj_array {
+        __u64 handles;
+        __u32 count_handles;
+        __u32 pad;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#include "drm_mode.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_IOCTL_BASE                  'd'
+#define DRM_IO(nr)                      _IO(DRM_IOCTL_BASE,nr)
+#define DRM_IOR(nr,type)                _IOR(DRM_IOCTL_BASE,nr,type)
+#define DRM_IOW(nr,type)                _IOW(DRM_IOCTL_BASE,nr,type)
+#define DRM_IOWR(nr,type)               _IOWR(DRM_IOCTL_BASE,nr,type)
+
+#define DRM_IOCTL_VERSION               DRM_IOWR(0x00, struct drm_version)
+#define DRM_IOCTL_GET_UNIQUE            DRM_IOWR(0x01, struct drm_unique)
+#define DRM_IOCTL_GET_MAGIC             DRM_IOR( 0x02, struct drm_auth)
+#define DRM_IOCTL_IRQ_BUSID             DRM_IOWR(0x03, struct drm_irq_busid)
+#define DRM_IOCTL_GET_MAP               DRM_IOWR(0x04, struct drm_map)
+#define DRM_IOCTL_GET_CLIENT            DRM_IOWR(0x05, struct drm_client)
+#define DRM_IOCTL_GET_STATS             DRM_IOR( 0x06, struct drm_stats)
+#define DRM_IOCTL_SET_VERSION           DRM_IOWR(0x07, struct drm_set_version)
+#define DRM_IOCTL_MODESET_CTL           DRM_IOW(0x08, struct drm_modeset_ctl)
+#define DRM_IOCTL_GEM_CLOSE             DRM_IOW (0x09, struct drm_gem_close)
+#define DRM_IOCTL_GEM_FLINK             DRM_IOWR(0x0a, struct drm_gem_flink)
+#define DRM_IOCTL_GEM_OPEN              DRM_IOWR(0x0b, struct drm_gem_open)
+#define DRM_IOCTL_GET_CAP               DRM_IOWR(0x0c, struct drm_get_cap)
+#define DRM_IOCTL_SET_CLIENT_CAP        DRM_IOW( 0x0d, struct drm_set_client_cap)
+
+#define DRM_IOCTL_SET_UNIQUE            DRM_IOW( 0x10, struct drm_unique)
+#define DRM_IOCTL_AUTH_MAGIC            DRM_IOW( 0x11, struct drm_auth)
+#define DRM_IOCTL_BLOCK                 DRM_IOWR(0x12, struct drm_block)
+#define DRM_IOCTL_UNBLOCK               DRM_IOWR(0x13, struct drm_block)
+#define DRM_IOCTL_CONTROL               DRM_IOW( 0x14, struct drm_control)
+#define DRM_IOCTL_ADD_MAP               DRM_IOWR(0x15, struct drm_map)
+#define DRM_IOCTL_ADD_BUFS              DRM_IOWR(0x16, struct drm_buf_desc)
+#define DRM_IOCTL_MARK_BUFS             DRM_IOW( 0x17, struct drm_buf_desc)
+#define DRM_IOCTL_INFO_BUFS             DRM_IOWR(0x18, struct drm_buf_info)
+#define DRM_IOCTL_MAP_BUFS              DRM_IOWR(0x19, struct drm_buf_map)
+#define DRM_IOCTL_FREE_BUFS             DRM_IOW( 0x1a, struct drm_buf_free)
+
+#define DRM_IOCTL_RM_MAP                DRM_IOW( 0x1b, struct drm_map)
+
+#define DRM_IOCTL_SET_SAREA_CTX         DRM_IOW( 0x1c, struct drm_ctx_priv_map)
+#define DRM_IOCTL_GET_SAREA_CTX         DRM_IOWR(0x1d, struct drm_ctx_priv_map)
+
+#define DRM_IOCTL_SET_MASTER            DRM_IO(0x1e)
+#define DRM_IOCTL_DROP_MASTER           DRM_IO(0x1f)
+
+#define DRM_IOCTL_ADD_CTX               DRM_IOWR(0x20, struct drm_ctx)
+#define DRM_IOCTL_RM_CTX                DRM_IOWR(0x21, struct drm_ctx)
+#define DRM_IOCTL_MOD_CTX               DRM_IOW( 0x22, struct drm_ctx)
+#define DRM_IOCTL_GET_CTX               DRM_IOWR(0x23, struct drm_ctx)
+#define DRM_IOCTL_SWITCH_CTX            DRM_IOW( 0x24, struct drm_ctx)
+#define DRM_IOCTL_NEW_CTX               DRM_IOW( 0x25, struct drm_ctx)
+#define DRM_IOCTL_RES_CTX               DRM_IOWR(0x26, struct drm_ctx_res)
+#define DRM_IOCTL_ADD_DRAW              DRM_IOWR(0x27, struct drm_draw)
+#define DRM_IOCTL_RM_DRAW               DRM_IOWR(0x28, struct drm_draw)
+#define DRM_IOCTL_DMA                   DRM_IOWR(0x29, struct drm_dma)
+#define DRM_IOCTL_LOCK                  DRM_IOW( 0x2a, struct drm_lock)
+#define DRM_IOCTL_UNLOCK                DRM_IOW( 0x2b, struct drm_lock)
+#define DRM_IOCTL_FINISH                DRM_IOW( 0x2c, struct drm_lock)
+
+#define DRM_IOCTL_PRIME_HANDLE_TO_FD    DRM_IOWR(0x2d, struct drm_prime_handle)
+#define DRM_IOCTL_PRIME_FD_TO_HANDLE    DRM_IOWR(0x2e, struct drm_prime_handle)
+
+#define DRM_IOCTL_AGP_ACQUIRE           DRM_IO(  0x30)
+#define DRM_IOCTL_AGP_RELEASE           DRM_IO(  0x31)
+#define DRM_IOCTL_AGP_ENABLE            DRM_IOW( 0x32, struct drm_agp_mode)
+#define DRM_IOCTL_AGP_INFO              DRM_IOR( 0x33, struct drm_agp_info)
+#define DRM_IOCTL_AGP_ALLOC             DRM_IOWR(0x34, struct drm_agp_buffer)
+#define DRM_IOCTL_AGP_FREE              DRM_IOW( 0x35, struct drm_agp_buffer)
+#define DRM_IOCTL_AGP_BIND              DRM_IOW( 0x36, struct drm_agp_binding)
+#define DRM_IOCTL_AGP_UNBIND            DRM_IOW( 0x37, struct drm_agp_binding)
+
+#define DRM_IOCTL_SG_ALLOC              DRM_IOWR(0x38, struct drm_scatter_gather)
+#define DRM_IOCTL_SG_FREE               DRM_IOW( 0x39, struct drm_scatter_gather)
+
+#define DRM_IOCTL_WAIT_VBLANK           DRM_IOWR(0x3a, union drm_wait_vblank)
+
+#define DRM_IOCTL_UPDATE_DRAW           DRM_IOW(0x3f, struct drm_update_draw)
+
+#define DRM_IOCTL_MODE_GETRESOURCES     DRM_IOWR(0xA0, struct drm_mode_card_res)
+#define DRM_IOCTL_MODE_GETCRTC          DRM_IOWR(0xA1, struct drm_mode_crtc)
+#define DRM_IOCTL_MODE_SETCRTC          DRM_IOWR(0xA2, struct drm_mode_crtc)
+#define DRM_IOCTL_MODE_CURSOR           DRM_IOWR(0xA3, struct drm_mode_cursor)
+#define DRM_IOCTL_MODE_GETGAMMA         DRM_IOWR(0xA4, struct drm_mode_crtc_lut)
+#define DRM_IOCTL_MODE_SETGAMMA         DRM_IOWR(0xA5, struct drm_mode_crtc_lut)
+#define DRM_IOCTL_MODE_GETENCODER       DRM_IOWR(0xA6, struct drm_mode_get_encoder)
+#define DRM_IOCTL_MODE_GETCONNECTOR     DRM_IOWR(0xA7, struct drm_mode_get_connector)
+#define DRM_IOCTL_MODE_ATTACHMODE       DRM_IOWR(0xA8, struct drm_mode_mode_cmd) /* deprecated (never worked) */
+#define DRM_IOCTL_MODE_DETACHMODE       DRM_IOWR(0xA9, struct drm_mode_mode_cmd) /* deprecated (never worked) */
+
+#define DRM_IOCTL_MODE_GETPROPERTY      DRM_IOWR(0xAA, struct drm_mode_get_property)
+#define DRM_IOCTL_MODE_SETPROPERTY      DRM_IOWR(0xAB, struct drm_mode_connector_set_property)
+#define DRM_IOCTL_MODE_GETPROPBLOB      DRM_IOWR(0xAC, struct drm_mode_get_blob)
+#define DRM_IOCTL_MODE_GETFB            DRM_IOWR(0xAD, struct drm_mode_fb_cmd)
+#define DRM_IOCTL_MODE_ADDFB            DRM_IOWR(0xAE, struct drm_mode_fb_cmd)
+#define DRM_IOCTL_MODE_RMFB             DRM_IOWR(0xAF, unsigned int)
+#define DRM_IOCTL_MODE_PAGE_FLIP        DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
+#define DRM_IOCTL_MODE_DIRTYFB          DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
+
+#define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb)
+#define DRM_IOCTL_MODE_MAP_DUMB    DRM_IOWR(0xB3, struct drm_mode_map_dumb)
+#define DRM_IOCTL_MODE_DESTROY_DUMB    DRM_IOWR(0xB4, struct drm_mode_destroy_dumb)
+#define DRM_IOCTL_MODE_GETPLANERESOURCES DRM_IOWR(0xB5, struct drm_mode_get_plane_res)
+#define DRM_IOCTL_MODE_GETPLANE DRM_IOWR(0xB6, struct drm_mode_get_plane)
+#define DRM_IOCTL_MODE_SETPLANE DRM_IOWR(0xB7, struct drm_mode_set_plane)
+#define DRM_IOCTL_MODE_ADDFB2           DRM_IOWR(0xB8, struct drm_mode_fb_cmd2)
+#define DRM_IOCTL_MODE_OBJ_GETPROPERTIES        DRM_IOWR(0xB9, struct drm_mode_obj_get_properties)
+#define DRM_IOCTL_MODE_OBJ_SETPROPERTY  DRM_IOWR(0xBA, struct drm_mode_obj_set_property)
+#define DRM_IOCTL_MODE_CURSOR2          DRM_IOWR(0xBB, struct drm_mode_cursor2)
+#define DRM_IOCTL_MODE_ATOMIC           DRM_IOWR(0xBC, struct drm_mode_atomic)
+#define DRM_IOCTL_MODE_CREATEPROPBLOB   DRM_IOWR(0xBD, struct drm_mode_create_blob)
+#define DRM_IOCTL_MODE_DESTROYPROPBLOB  DRM_IOWR(0xBE, struct drm_mode_destroy_blob)
+
+#define DRM_IOCTL_SYNCOBJ_CREATE        DRM_IOWR(0xBF, struct drm_syncobj_create)
+#define DRM_IOCTL_SYNCOBJ_DESTROY       DRM_IOWR(0xC0, struct drm_syncobj_destroy)
+#define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD  DRM_IOWR(0xC1, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE  DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT          DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET         DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL        DRM_IOWR(0xC5, struct drm_syncobj_array)
+
+/**
+ * Device specific ioctls should only be in their respective headers
+ * The device specific ioctl range is from 0x40 to 0x9f.
+ * Generic IOCTLS restart at 0xA0.
+ *
+ * \sa drmCommandNone(), drmCommandRead(), drmCommandWrite(), and
+ * drmCommandReadWrite().
+ */
+#define DRM_COMMAND_BASE                0x40
+#define DRM_COMMAND_END                 0xA0
+
+/**
+ * Header for events written back to userspace on the drm fd.  The
+ * type defines the type of event, the length specifies the total
+ * length of the event (including the header), and user_data is
+ * typically a 64 bit value passed with the ioctl that triggered the
+ * event.  A read on the drm fd will always only return complete
+ * events, that is, if for example the read buffer is 100 bytes, and
+ * there are two 64 byte events pending, only one will be returned.
+ *
+ * Event types 0 - 0x7fffffff are generic drm events, 0x80000000 and
+ * up are chipset specific.
+ */
+struct drm_event {
+        __u32 type;
+        __u32 length;
+};
+
+#define DRM_EVENT_VBLANK 0x01
+#define DRM_EVENT_FLIP_COMPLETE 0x02
+
+struct drm_event_vblank {
+        struct drm_event base;
+        __u64 user_data;
+        __u32 tv_sec;
+        __u32 tv_usec;
+        __u32 sequence;
+        __u32 crtc_id; /* 0 on older kernels that do not support this */
+};
+
+/* typedef area */
+#ifndef __KERNEL__
+typedef struct drm_clip_rect drm_clip_rect_t;
+typedef struct drm_drawable_info drm_drawable_info_t;
+typedef struct drm_tex_region drm_tex_region_t;
+typedef struct drm_hw_lock drm_hw_lock_t;
+typedef struct drm_version drm_version_t;
+typedef struct drm_unique drm_unique_t;
+typedef struct drm_list drm_list_t;
+typedef struct drm_block drm_block_t;
+typedef struct drm_control drm_control_t;
+typedef enum drm_map_type drm_map_type_t;
+typedef enum drm_map_flags drm_map_flags_t;
+typedef struct drm_ctx_priv_map drm_ctx_priv_map_t;
+typedef struct drm_map drm_map_t;
+typedef struct drm_client drm_client_t;
+typedef enum drm_stat_type drm_stat_type_t;
+typedef struct drm_stats drm_stats_t;
+typedef enum drm_lock_flags drm_lock_flags_t;
+typedef struct drm_lock drm_lock_t;
+typedef enum drm_dma_flags drm_dma_flags_t;
+typedef struct drm_buf_desc drm_buf_desc_t;
+typedef struct drm_buf_info drm_buf_info_t;
+typedef struct drm_buf_free drm_buf_free_t;
+typedef struct drm_buf_pub drm_buf_pub_t;
+typedef struct drm_buf_map drm_buf_map_t;
+typedef struct drm_dma drm_dma_t;
+typedef union drm_wait_vblank drm_wait_vblank_t;
+typedef struct drm_agp_mode drm_agp_mode_t;
+typedef enum drm_ctx_flags drm_ctx_flags_t;
+typedef struct drm_ctx drm_ctx_t;
+typedef struct drm_ctx_res drm_ctx_res_t;
+typedef struct drm_draw drm_draw_t;
+typedef struct drm_update_draw drm_update_draw_t;
+typedef struct drm_auth drm_auth_t;
+typedef struct drm_irq_busid drm_irq_busid_t;
+typedef enum drm_vblank_seq_type drm_vblank_seq_type_t;
+
+typedef struct drm_agp_buffer drm_agp_buffer_t;
+typedef struct drm_agp_binding drm_agp_binding_t;
+typedef struct drm_agp_info drm_agp_info_t;
+typedef struct drm_scatter_gather drm_scatter_gather_t;
+typedef struct drm_set_version drm_set_version_t;
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
new file mode 100644
index 000000000000..9816590d3ad2
--- /dev/null
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -0,0 +1,1522 @@
+/*
+ * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
+ * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
+ * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _UAPI_I915_DRM_H_
+#define _UAPI_I915_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Please note that modifications to all structs defined here are
+ * subject to backwards-compatibility constraints.
+ */
+
+/**
+ * DOC: uevents generated by i915 on it's device node
+ *
+ * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
+ *      event from the gpu l3 cache. Additional information supplied is ROW,
+ *      BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *      track of these events and if a specific cache-line seems to have a
+ *      persistent error remap it with the l3 remapping tool supplied in
+ *      intel-gpu-tools.  The value supplied with the event is always 1.
+ *
+ * I915_ERROR_UEVENT - Generated upon error detection, currently only via
+ *      hangcheck. The error detection event is a good indicator of when things
+ *      began to go badly. The value supplied with the event is a 1 upon error
+ *      detection, and a 0 upon reset completion, signifying no more error
+ *      exists. NOTE: Disabling hangcheck or reset via module parameter will
+ *      cause the related events to not be seen.
+ *
+ * I915_RESET_UEVENT - Event is generated just before an attempt to reset the
+ *      the GPU. The value supplied with the event is always 1. NOTE: Disable
+ *      reset via module parameter will cause this event to not be seen.
+ */
+#define I915_L3_PARITY_UEVENT           "L3_PARITY_ERROR"
+#define I915_ERROR_UEVENT               "ERROR"
+#define I915_RESET_UEVENT               "RESET"
+
+/*
+ * MOCS indexes used for GPU surfaces, defining the cacheability of the
+ * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
+ */
+enum i915_mocs_table_index {
+        /*
+         * Not cached anywhere, coherency between CPU and GPU accesses is
+         * guaranteed.
+         */
+        I915_MOCS_UNCACHED,
+        /*
+         * Cacheability and coherency controlled by the kernel automatically
+         * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current
+         * usage of the surface (used for display scanout or not).
+         */
+        I915_MOCS_PTE,
+        /*
+         * Cached in all GPU caches available on the platform.
+         * Coherency between CPU and GPU accesses to the surface is not
+         * guaranteed without extra synchronization.
+         */
+        I915_MOCS_CACHED,
+};
+
+/* Each region is a minimum of 16k, and there are at most 255 of them.
+ */
+#define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use
+                                 * of chars for next/prev indices */
+#define I915_LOG_MIN_TEX_REGION_SIZE 14
+
+typedef struct _drm_i915_init {
+        enum {
+                I915_INIT_DMA = 0x01,
+                I915_CLEANUP_DMA = 0x02,
+                I915_RESUME_DMA = 0x03
+        } func;
+        unsigned int mmio_offset;
+        int sarea_priv_offset;
+        unsigned int ring_start;
+        unsigned int ring_end;
+        unsigned int ring_size;
+        unsigned int front_offset;
+        unsigned int back_offset;
+        unsigned int depth_offset;
+        unsigned int w;
+        unsigned int h;
+        unsigned int pitch;
+        unsigned int pitch_bits;
+        unsigned int back_pitch;
+        unsigned int depth_pitch;
+        unsigned int cpp;
+        unsigned int chipset;
+} drm_i915_init_t;
+
+typedef struct _drm_i915_sarea {
+        struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1];
+        int last_upload;        /* last time texture was uploaded */
+        int last_enqueue;       /* last time a buffer was enqueued */
+        int last_dispatch;      /* age of the most recently dispatched buffer */
+        int ctxOwner;           /* last context to upload state */
+        int texAge;
+        int pf_enabled;         /* is pageflipping allowed? */
+        int pf_active;
+        int pf_current_page;    /* which buffer is being displayed? */
+        int perf_boxes;         /* performance boxes to be displayed */
+        int width, height;      /* screen size in pixels */
+
+        drm_handle_t front_handle;
+        int front_offset;
+        int front_size;
+
+        drm_handle_t back_handle;
+        int back_offset;
+        int back_size;
+
+        drm_handle_t depth_handle;
+        int depth_offset;
+        int depth_size;
+
+        drm_handle_t tex_handle;
+        int tex_offset;
+        int tex_size;
+        int log_tex_granularity;
+        int pitch;
+        int rotation;           /* 0, 90, 180 or 270 */
+        int rotated_offset;
+        int rotated_size;
+        int rotated_pitch;
+        int virtualX, virtualY;
+
+        unsigned int front_tiled;
+        unsigned int back_tiled;
+        unsigned int depth_tiled;
+        unsigned int rotated_tiled;
+        unsigned int rotated2_tiled;
+
+        int pipeA_x;
+        int pipeA_y;
+        int pipeA_w;
+        int pipeA_h;
+        int pipeB_x;
+        int pipeB_y;
+        int pipeB_w;
+        int pipeB_h;
+
+        /* fill out some space for old userspace triple buffer */
+        drm_handle_t unused_handle;
+        __u32 unused1, unused2, unused3;
+
+        /* buffer object handles for static buffers. May change
+         * over the lifetime of the client.
+         */
+        __u32 front_bo_handle;
+        __u32 back_bo_handle;
+        __u32 unused_bo_handle;
+        __u32 depth_bo_handle;
+
+} drm_i915_sarea_t;
+
+/* due to userspace building against these headers we need some compat here */
+#define planeA_x pipeA_x
+#define planeA_y pipeA_y
+#define planeA_w pipeA_w
+#define planeA_h pipeA_h
+#define planeB_x pipeB_x
+#define planeB_y pipeB_y
+#define planeB_w pipeB_w
+#define planeB_h pipeB_h
+
+/* Flags for perf_boxes
+ */
+#define I915_BOX_RING_EMPTY    0x1
+#define I915_BOX_FLIP          0x2
+#define I915_BOX_WAIT          0x4
+#define I915_BOX_TEXTURE_LOAD  0x8
+#define I915_BOX_LOST_CONTEXT  0x10
+
+/*
+ * i915 specific ioctls.
+ *
+ * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie
+ * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset
+ * against DRM_COMMAND_BASE and should be between [0x0, 0x60).
+ */
+#define DRM_I915_INIT           0x00
+#define DRM_I915_FLUSH          0x01
+#define DRM_I915_FLIP           0x02
+#define DRM_I915_BATCHBUFFER    0x03
+#define DRM_I915_IRQ_EMIT       0x04
+#define DRM_I915_IRQ_WAIT       0x05
+#define DRM_I915_GETPARAM       0x06
+#define DRM_I915_SETPARAM       0x07
+#define DRM_I915_ALLOC          0x08
+#define DRM_I915_FREE           0x09
+#define DRM_I915_INIT_HEAP      0x0a
+#define DRM_I915_CMDBUFFER      0x0b
+#define DRM_I915_DESTROY_HEAP   0x0c
+#define DRM_I915_SET_VBLANK_PIPE        0x0d
+#define DRM_I915_GET_VBLANK_PIPE        0x0e
+#define DRM_I915_VBLANK_SWAP    0x0f
+#define DRM_I915_HWS_ADDR       0x11
+#define DRM_I915_GEM_INIT       0x13
+#define DRM_I915_GEM_EXECBUFFER 0x14
+#define DRM_I915_GEM_PIN        0x15
+#define DRM_I915_GEM_UNPIN      0x16
+#define DRM_I915_GEM_BUSY       0x17
+#define DRM_I915_GEM_THROTTLE   0x18
+#define DRM_I915_GEM_ENTERVT    0x19
+#define DRM_I915_GEM_LEAVEVT    0x1a
+#define DRM_I915_GEM_CREATE     0x1b
+#define DRM_I915_GEM_PREAD      0x1c
+#define DRM_I915_GEM_PWRITE     0x1d
+#define DRM_I915_GEM_MMAP       0x1e
+#define DRM_I915_GEM_SET_DOMAIN 0x1f
+#define DRM_I915_GEM_SW_FINISH  0x20
+#define DRM_I915_GEM_SET_TILING 0x21
+#define DRM_I915_GEM_GET_TILING 0x22
+#define DRM_I915_GEM_GET_APERTURE 0x23
+#define DRM_I915_GEM_MMAP_GTT   0x24
+#define DRM_I915_GET_PIPE_FROM_CRTC_ID  0x25
+#define DRM_I915_GEM_MADVISE    0x26
+#define DRM_I915_OVERLAY_PUT_IMAGE      0x27
+#define DRM_I915_OVERLAY_ATTRS  0x28
+#define DRM_I915_GEM_EXECBUFFER2        0x29
+#define DRM_I915_GEM_EXECBUFFER2_WR     DRM_I915_GEM_EXECBUFFER2
+#define DRM_I915_GET_SPRITE_COLORKEY    0x2a
+#define DRM_I915_SET_SPRITE_COLORKEY    0x2b
+#define DRM_I915_GEM_WAIT       0x2c
+#define DRM_I915_GEM_CONTEXT_CREATE     0x2d
+#define DRM_I915_GEM_CONTEXT_DESTROY    0x2e
+#define DRM_I915_GEM_SET_CACHING        0x2f
+#define DRM_I915_GEM_GET_CACHING        0x30
+#define DRM_I915_REG_READ               0x31
+#define DRM_I915_GET_RESET_STATS        0x32
+#define DRM_I915_GEM_USERPTR            0x33
+#define DRM_I915_GEM_CONTEXT_GETPARAM   0x34
+#define DRM_I915_GEM_CONTEXT_SETPARAM   0x35
+#define DRM_I915_PERF_OPEN              0x36
+#define DRM_I915_PERF_ADD_CONFIG        0x37
+#define DRM_I915_PERF_REMOVE_CONFIG     0x38
+
+#define DRM_IOCTL_I915_INIT             DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
+#define DRM_IOCTL_I915_FLUSH            DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
+#define DRM_IOCTL_I915_FLIP             DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP)
+#define DRM_IOCTL_I915_BATCHBUFFER      DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t)
+#define DRM_IOCTL_I915_IRQ_EMIT         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t)
+#define DRM_IOCTL_I915_IRQ_WAIT         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t)
+#define DRM_IOCTL_I915_GETPARAM         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t)
+#define DRM_IOCTL_I915_SETPARAM         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t)
+#define DRM_IOCTL_I915_ALLOC            DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t)
+#define DRM_IOCTL_I915_FREE             DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t)
+#define DRM_IOCTL_I915_INIT_HEAP        DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t)
+#define DRM_IOCTL_I915_CMDBUFFER        DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t)
+#define DRM_IOCTL_I915_DESTROY_HEAP     DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t)
+#define DRM_IOCTL_I915_SET_VBLANK_PIPE  DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
+#define DRM_IOCTL_I915_GET_VBLANK_PIPE  DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
+#define DRM_IOCTL_I915_VBLANK_SWAP      DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t)
+#define DRM_IOCTL_I915_HWS_ADDR         DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init)
+#define DRM_IOCTL_I915_GEM_INIT         DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER   DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2  DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR       DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_PIN          DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
+#define DRM_IOCTL_I915_GEM_UNPIN        DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
+#define DRM_IOCTL_I915_GEM_BUSY         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
+#define DRM_IOCTL_I915_GEM_SET_CACHING          DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching)
+#define DRM_IOCTL_I915_GEM_GET_CACHING          DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching)
+#define DRM_IOCTL_I915_GEM_THROTTLE     DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE)
+#define DRM_IOCTL_I915_GEM_ENTERVT      DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
+#define DRM_IOCTL_I915_GEM_LEAVEVT      DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
+#define DRM_IOCTL_I915_GEM_CREATE       DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
+#define DRM_IOCTL_I915_GEM_PREAD        DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
+#define DRM_IOCTL_I915_GEM_PWRITE       DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
+#define DRM_IOCTL_I915_GEM_MMAP         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
+#define DRM_IOCTL_I915_GEM_MMAP_GTT     DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_SET_DOMAIN   DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
+#define DRM_IOCTL_I915_GEM_SW_FINISH    DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
+#define DRM_IOCTL_I915_GEM_SET_TILING   DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
+#define DRM_IOCTL_I915_GEM_GET_TILING   DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
+#define DRM_IOCTL_I915_GEM_GET_APERTURE DRM_IOR  (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture)
+#define DRM_IOCTL_I915_GET_PIPE_FROM_CRTC_ID DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_PIPE_FROM_CRTC_ID, struct drm_i915_get_pipe_from_crtc_id)
+#define DRM_IOCTL_I915_GEM_MADVISE      DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise)
+#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE        DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image)
+#define DRM_IOCTL_I915_OVERLAY_ATTRS    DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
+#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GEM_WAIT         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
+#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE       DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
+#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY      DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
+#define DRM_IOCTL_I915_REG_READ                 DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
+#define DRM_IOCTL_I915_GET_RESET_STATS          DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
+#define DRM_IOCTL_I915_GEM_USERPTR                      DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
+#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM     DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM     DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_PERF_OPEN        DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG  DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG       DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+
+/* Allow drivers to submit batchbuffers directly to hardware, relying
+ * on the security mechanisms provided by hardware.
+ */
+typedef struct drm_i915_batchbuffer {
+        int start;              /* agp offset */
+        int used;               /* nr bytes in use */
+        int DR1;                /* hw flags for GFX_OP_DRAWRECT_INFO */
+        int DR4;                /* window origin for GFX_OP_DRAWRECT_INFO */
+        int num_cliprects;      /* mulitpass with multiple cliprects? */
+        struct drm_clip_rect __user *cliprects; /* pointer to userspace cliprects */
+} drm_i915_batchbuffer_t;
+
+/* As above, but pass a pointer to userspace buffer which can be
+ * validated by the kernel prior to sending to hardware.
+ */
+typedef struct _drm_i915_cmdbuffer {
+        char __user *buf;       /* pointer to userspace command buffer */
+        int sz;                 /* nr bytes in buf */
+        int DR1;                /* hw flags for GFX_OP_DRAWRECT_INFO */
+        int DR4;                /* window origin for GFX_OP_DRAWRECT_INFO */
+        int num_cliprects;      /* mulitpass with multiple cliprects? */
+        struct drm_clip_rect __user *cliprects; /* pointer to userspace cliprects */
+} drm_i915_cmdbuffer_t;
+
+/* Userspace can request & wait on irq's:
+ */
+typedef struct drm_i915_irq_emit {
+        int __user *irq_seq;
+} drm_i915_irq_emit_t;
+
+typedef struct drm_i915_irq_wait {
+        int irq_seq;
+} drm_i915_irq_wait_t;
+
+/* Ioctl to query kernel params:
+ */
+#define I915_PARAM_IRQ_ACTIVE            1
+#define I915_PARAM_ALLOW_BATCHBUFFER     2
+#define I915_PARAM_LAST_DISPATCH         3
+#define I915_PARAM_CHIPSET_ID            4
+#define I915_PARAM_HAS_GEM               5
+#define I915_PARAM_NUM_FENCES_AVAIL      6
+#define I915_PARAM_HAS_OVERLAY           7
+#define I915_PARAM_HAS_PAGEFLIPPING      8
+#define I915_PARAM_HAS_EXECBUF2          9
+#define I915_PARAM_HAS_BSD               10
+#define I915_PARAM_HAS_BLT               11
+#define I915_PARAM_HAS_RELAXED_FENCING   12
+#define I915_PARAM_HAS_COHERENT_RINGS    13
+#define I915_PARAM_HAS_EXEC_CONSTANTS    14
+#define I915_PARAM_HAS_RELAXED_DELTA     15
+#define I915_PARAM_HAS_GEN7_SOL_RESET    16
+#define I915_PARAM_HAS_LLC               17
+#define I915_PARAM_HAS_ALIASING_PPGTT    18
+#define I915_PARAM_HAS_WAIT_TIMEOUT      19
+#define I915_PARAM_HAS_SEMAPHORES        20
+#define I915_PARAM_HAS_PRIME_VMAP_FLUSH  21
+#define I915_PARAM_HAS_VEBOX             22
+#define I915_PARAM_HAS_SECURE_BATCHES    23
+#define I915_PARAM_HAS_PINNED_BATCHES    24
+#define I915_PARAM_HAS_EXEC_NO_RELOC     25
+#define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
+#define I915_PARAM_HAS_WT                27
+#define I915_PARAM_CMD_PARSER_VERSION    28
+#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29
+#define I915_PARAM_MMAP_VERSION          30
+#define I915_PARAM_HAS_BSD2              31
+#define I915_PARAM_REVISION              32
+#define I915_PARAM_SUBSLICE_TOTAL        33
+#define I915_PARAM_EU_TOTAL              34
+#define I915_PARAM_HAS_GPU_RESET         35
+#define I915_PARAM_HAS_RESOURCE_STREAMER 36
+#define I915_PARAM_HAS_EXEC_SOFTPIN      37
+#define I915_PARAM_HAS_POOLED_EU         38
+#define I915_PARAM_MIN_EU_IN_POOL        39
+#define I915_PARAM_MMAP_GTT_VERSION      40
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+ * priorities and the driver will attempt to execute batches in priority order.
+ */
+#define I915_PARAM_HAS_SCHEDULER         41
+#define I915_PARAM_HUC_STATUS            42
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
+ * synchronisation with implicit fencing on individual objects.
+ * See EXEC_OBJECT_ASYNC.
+ */
+#define I915_PARAM_HAS_EXEC_ASYNC        43
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support -
+ * both being able to pass in a sync_file fd to wait upon before executing,
+ * and being able to return a new sync_file fd that is signaled when the
+ * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE        44
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
+ * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * EXEC_OBJECT_CAPTURE.
+ */
+#define I915_PARAM_HAS_EXEC_CAPTURE      45
+
+#define I915_PARAM_SLICE_MASK            46
+
+/* Assuming it's uniform for each slice, this queries the mask of subslices
+ * per-slice for this system.
+ */
+#define I915_PARAM_SUBSLICE_MASK         47
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
+ * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
+ */
+#define I915_PARAM_HAS_EXEC_BATCH_FIRST  48
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
+typedef struct drm_i915_getparam {
+        __s32 param;
+        /*
+         * WARNING: Using pointers instead of fixed-size u64 means we need to write
+         * compat32 code. Don't repeat this mistake.
+         */
+        int __user *value;
+} drm_i915_getparam_t;
+
+/* Ioctl to set kernel params:
+ */
+#define I915_SETPARAM_USE_MI_BATCHBUFFER_START            1
+#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY             2
+#define I915_SETPARAM_ALLOW_BATCHBUFFER                   3
+#define I915_SETPARAM_NUM_USED_FENCES                     4
+
+typedef struct drm_i915_setparam {
+        int param;
+        int value;
+} drm_i915_setparam_t;
+
+/* A memory manager for regions of shared memory:
+ */
+#define I915_MEM_REGION_AGP 1
+
+typedef struct drm_i915_mem_alloc {
+        int region;
+        int alignment;
+        int size;
+        int __user *region_offset;      /* offset from start of fb or agp */
+} drm_i915_mem_alloc_t;
+
+typedef struct drm_i915_mem_free {
+        int region;
+        int region_offset;
+} drm_i915_mem_free_t;
+
+typedef struct drm_i915_mem_init_heap {
+        int region;
+        int size;
+        int start;
+} drm_i915_mem_init_heap_t;
+
+/* Allow memory manager to be torn down and re-initialized (eg on
+ * rotate):
+ */
+typedef struct drm_i915_mem_destroy_heap {
+        int region;
+} drm_i915_mem_destroy_heap_t;
+
+/* Allow X server to configure which pipes to monitor for vblank signals
+ */
+#define DRM_I915_VBLANK_PIPE_A  1
+#define DRM_I915_VBLANK_PIPE_B  2
+
+typedef struct drm_i915_vblank_pipe {
+        int pipe;
+} drm_i915_vblank_pipe_t;
+
+/* Schedule buffer swap at given vertical blank:
+ */
+typedef struct drm_i915_vblank_swap {
+        drm_drawable_t drawable;
+        enum drm_vblank_seq_type seqtype;
+        unsigned int sequence;
+} drm_i915_vblank_swap_t;
+
+typedef struct drm_i915_hws_addr {
+        __u64 addr;
+} drm_i915_hws_addr_t;
+
+struct drm_i915_gem_init {
+        /**
+         * Beginning offset in the GTT to be managed by the DRM memory
+         * manager.
+         */
+        __u64 gtt_start;
+        /**
+         * Ending offset in the GTT to be managed by the DRM memory
+         * manager.
+         */
+        __u64 gtt_end;
+};
+
+struct drm_i915_gem_create {
+        /**
+         * Requested size for the object.
+         *
+         * The (page-aligned) allocated size for the object will be returned.
+         */
+        __u64 size;
+        /**
+         * Returned handle for the object.
+         *
+         * Object handles are nonzero.
+         */
+        __u32 handle;
+        __u32 pad;
+};
+
+struct drm_i915_gem_pread {
+        /** Handle for the object being read. */
+        __u32 handle;
+        __u32 pad;
+        /** Offset into the object to read from */
+        __u64 offset;
+        /** Length of data to read */
+        __u64 size;
+        /**
+         * Pointer to write the data into.
+         *
+         * This is a fixed-size type for 32/64 compatibility.
+         */
+        __u64 data_ptr;
+};
+
+struct drm_i915_gem_pwrite {
+        /** Handle for the object being written to. */
+        __u32 handle;
+        __u32 pad;
+        /** Offset into the object to write to */
+        __u64 offset;
+        /** Length of data to write */
+        __u64 size;
+        /**
+         * Pointer to read the data from.
+         *
+         * This is a fixed-size type for 32/64 compatibility.
+         */
+        __u64 data_ptr;
+};
+
+struct drm_i915_gem_mmap {
+        /** Handle for the object being mapped. */
+        __u32 handle;
+        __u32 pad;
+        /** Offset in the object to map. */
+        __u64 offset;
+        /**
+         * Length of data to map.
+         *
+         * The value will be page-aligned.
+         */
+        __u64 size;
+        /**
+         * Returned pointer the data was mapped at.
+         *
+         * This is a fixed-size type for 32/64 compatibility.
+         */
+        __u64 addr_ptr;
+
+        /**
+         * Flags for extended behaviour.
+         *
+         * Added in version 2.
+         */
+        __u64 flags;
+#define I915_MMAP_WC 0x1
+};
+
+struct drm_i915_gem_mmap_gtt {
+        /** Handle for the object being mapped. */
+        __u32 handle;
+        __u32 pad;
+        /**
+         * Fake offset to use for subsequent mmap call
+         *
+         * This is a fixed-size type for 32/64 compatibility.
+         */
+        __u64 offset;
+};
+
+struct drm_i915_gem_set_domain {
+        /** Handle for the object */
+        __u32 handle;
+
+        /** New read domains */
+        __u32 read_domains;
+
+        /** New write domain */
+        __u32 write_domain;
+};
+
+struct drm_i915_gem_sw_finish {
+        /** Handle for the object */
+        __u32 handle;
+};
+
+struct drm_i915_gem_relocation_entry {
+        /**
+         * Handle of the buffer being pointed to by this relocation entry.
+         *
+         * It's appealing to make this be an index into the mm_validate_entry
+         * list to refer to the buffer, but this allows the driver to create
+         * a relocation list for state buffers and not re-write it per
+         * exec using the buffer.
+         */
+        __u32 target_handle;
+
+        /**
+         * Value to be added to the offset of the target buffer to make up
+         * the relocation entry.
+         */
+        __u32 delta;
+
+        /** Offset in the buffer the relocation entry will be written into */
+        __u64 offset;
+
+        /**
+         * Offset value of the target buffer that the relocation entry was last
+         * written as.
+         *
+         * If the buffer has the same offset as last time, we can skip syncing
+         * and writing the relocation.  This value is written back out by
+         * the execbuffer ioctl when the relocation is written.
+         */
+        __u64 presumed_offset;
+
+        /**
+         * Target memory domains read by this operation.
+         */
+        __u32 read_domains;
+
+        /**
+         * Target memory domains written by this operation.
+         *
+         * Note that only one domain may be written by the whole
+         * execbuffer operation, so that where there are conflicts,
+         * the application will get -EINVAL back.
+         */
+        __u32 write_domain;
+};
+
+/** @{
+ * Intel memory domains
+ *
+ * Most of these just align with the various caches in
+ * the system and are used to flush and invalidate as
+ * objects end up cached in different domains.
+ */
+/** CPU cache */
+#define I915_GEM_DOMAIN_CPU             0x00000001
+/** Render cache, used by 2D and 3D drawing */
+#define I915_GEM_DOMAIN_RENDER          0x00000002
+/** Sampler cache, used by texture engine */
+#define I915_GEM_DOMAIN_SAMPLER         0x00000004
+/** Command queue, used to load batch buffers */
+#define I915_GEM_DOMAIN_COMMAND         0x00000008
+/** Instruction cache, used by shader programs */
+#define I915_GEM_DOMAIN_INSTRUCTION     0x00000010
+/** Vertex address cache */
+#define I915_GEM_DOMAIN_VERTEX          0x00000020
+/** GTT domain - aperture and scanout */
+#define I915_GEM_DOMAIN_GTT             0x00000040
+/** WC domain - uncached access */
+#define I915_GEM_DOMAIN_WC              0x00000080
+/** @} */
+
+struct drm_i915_gem_exec_object {
+        /**
+         * User's handle for a buffer to be bound into the GTT for this
+         * operation.
+         */
+        __u32 handle;
+
+        /** Number of relocations to be performed on this buffer */
+        __u32 relocation_count;
+        /**
+         * Pointer to array of struct drm_i915_gem_relocation_entry containing
+         * the relocations to be performed in this buffer.
+         */
+        __u64 relocs_ptr;
+
+        /** Required alignment in graphics aperture */
+        __u64 alignment;
+
+        /**
+         * Returned value of the updated offset of the object, for future
+         * presumed_offset writes.
+         */
+        __u64 offset;
+};
+
+struct drm_i915_gem_execbuffer {
+        /**
+         * List of buffers to be validated with their relocations to be
+         * performend on them.
+         *
+         * This is a pointer to an array of struct drm_i915_gem_validate_entry.
+         *
+         * These buffers must be listed in an order such that all relocations
+         * a buffer is performing refer to buffers that have already appeared
+         * in the validate list.
+         */
+        __u64 buffers_ptr;
+        __u32 buffer_count;
+
+        /** Offset in the batchbuffer to start execution from. */
+        __u32 batch_start_offset;
+        /** Bytes used in batchbuffer from batch_start_offset */
+        __u32 batch_len;
+        __u32 DR1;
+        __u32 DR4;
+        __u32 num_cliprects;
+        /** This is a struct drm_clip_rect *cliprects */
+        __u64 cliprects_ptr;
+};
+
+struct drm_i915_gem_exec_object2 {
+        /**
+         * User's handle for a buffer to be bound into the GTT for this
+         * operation.
+         */
+        __u32 handle;
+
+        /** Number of relocations to be performed on this buffer */
+        __u32 relocation_count;
+        /**
+         * Pointer to array of struct drm_i915_gem_relocation_entry containing
+         * the relocations to be performed in this buffer.
+         */
+        __u64 relocs_ptr;
+
+        /** Required alignment in graphics aperture */
+        __u64 alignment;
+
+        /**
+         * When the EXEC_OBJECT_PINNED flag is specified this is populated by
+         * the user with the GTT offset at which this object will be pinned.
+         * When the I915_EXEC_NO_RELOC flag is specified this must contain the
+         * presumed_offset of the object.
+         * During execbuffer2 the kernel populates it with the value of the
+         * current GTT offset of the object, for future presumed_offset writes.
+         */
+        __u64 offset;
+
+#define EXEC_OBJECT_NEEDS_FENCE          (1<<0)
+#define EXEC_OBJECT_NEEDS_GTT            (1<<1)
+#define EXEC_OBJECT_WRITE                (1<<2)
+#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
+#define EXEC_OBJECT_PINNED               (1<<4)
+#define EXEC_OBJECT_PAD_TO_SIZE          (1<<5)
+/* The kernel implicitly tracks GPU activity on all GEM objects, and
+ * synchronises operations with outstanding rendering. This includes
+ * rendering on other devices if exported via dma-buf. However, sometimes
+ * this tracking is too coarse and the user knows better. For example,
+ * if the object is split into non-overlapping ranges shared between different
+ * clients or engines (i.e. suballocating objects), the implicit tracking
+ * by kernel assumes that each operation affects the whole object rather
+ * than an individual range, causing needless synchronisation between clients.
+ * The kernel will also forgo any CPU cache flushes prior to rendering from
+ * the object as the client is expected to be also handling such domain
+ * tracking.
+ *
+ * The kernel maintains the implicit tracking in order to manage resources
+ * used by the GPU - this flag only disables the synchronisation prior to
+ * rendering with this object in this execbuf.
+ *
+ * Opting out of implicit synhronisation requires the user to do its own
+ * explicit tracking to avoid rendering corruption. See, for example,
+ * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
+ */
+#define EXEC_OBJECT_ASYNC               (1<<6)
+/* Request that the contents of this execobject be copied into the error
+ * state upon a GPU hang involving this batch for post-mortem debugging.
+ * These buffers are recorded in no particular order as "user" in
+ * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see
+ * if the kernel supports this flag.
+ */
+#define EXEC_OBJECT_CAPTURE             (1<<7)
+/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1)
+        __u64 flags;
+
+        union {
+                __u64 rsvd1;
+                __u64 pad_to_size;
+        };
+        __u64 rsvd2;
+};
+
+struct drm_i915_gem_exec_fence {
+        /**
+         * User's handle for a drm_syncobj to wait on or signal.
+         */
+        __u32 handle;
+
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
+        __u32 flags;
+};
+
+struct drm_i915_gem_execbuffer2 {
+        /**
+         * List of gem_exec_object2 structs
+         */
+        __u64 buffers_ptr;
+        __u32 buffer_count;
+
+        /** Offset in the batchbuffer to start execution from. */
+        __u32 batch_start_offset;
+        /** Bytes used in batchbuffer from batch_start_offset */
+        __u32 batch_len;
+        __u32 DR1;
+        __u32 DR4;
+        __u32 num_cliprects;
+        /**
+         * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+         * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+         * struct drm_i915_gem_exec_fence *fences.
+         */
+        __u64 cliprects_ptr;
+#define I915_EXEC_RING_MASK              (7<<0)
+#define I915_EXEC_DEFAULT                (0<<0)
+#define I915_EXEC_RENDER                 (1<<0)
+#define I915_EXEC_BSD                    (2<<0)
+#define I915_EXEC_BLT                    (3<<0)
+#define I915_EXEC_VEBOX                  (4<<0)
+
+/* Used for switching the constants addressing mode on gen4+ RENDER ring.
+ * Gen6+ only supports relative addressing to dynamic state (default) and
+ * absolute addressing.
+ *
+ * These flags are ignored for the BSD and BLT rings.
+ */
+#define I915_EXEC_CONSTANTS_MASK        (3<<6)
+#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
+#define I915_EXEC_CONSTANTS_ABSOLUTE    (1<<6)
+#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
+        __u64 flags;
+        __u64 rsvd1; /* now used for context info */
+        __u64 rsvd2;
+};
+
+/** Resets the SO write offset registers for transform feedback on gen7. */
+#define I915_EXEC_GEN7_SOL_RESET        (1<<8)
+
+/** Request a privileged ("secure") batch buffer. Note only available for
+ * DRM_ROOT_ONLY | DRM_MASTER processes.
+ */
+#define I915_EXEC_SECURE                (1<<9)
+
+/** Inform the kernel that the batch is and will always be pinned. This
+ * negates the requirement for a workaround to be performed to avoid
+ * an incoherent CS (such as can be found on 830/845). If this flag is
+ * not passed, the kernel will endeavour to make sure the batch is
+ * coherent with the CS before execution. If this flag is passed,
+ * userspace assumes the responsibility for ensuring the same.
+ */
+#define I915_EXEC_IS_PINNED             (1<<10)
+
+/** Provide a hint to the kernel that the command stream and auxiliary
+ * state buffers already holds the correct presumed addresses and so the
+ * relocation process may be skipped if no buffers need to be moved in
+ * preparation for the execbuffer.
+ */
+#define I915_EXEC_NO_RELOC              (1<<11)
+
+/** Use the reloc.handle as an index into the exec object array rather
+ * than as the per-file handle.
+ */
+#define I915_EXEC_HANDLE_LUT            (1<<12)
+
+/** Used for switching BSD rings on the platforms with two BSD rings */
+#define I915_EXEC_BSD_SHIFT      (13)
+#define I915_EXEC_BSD_MASK       (3 << I915_EXEC_BSD_SHIFT)
+/* default ping-pong mode */
+#define I915_EXEC_BSD_DEFAULT    (0 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING1      (1 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING2      (2 << I915_EXEC_BSD_SHIFT)
+
+/** Tell the kernel that the batchbuffer is processed by
+ *  the resource streamer.
+ */
+#define I915_EXEC_RESOURCE_STREAMER     (1<<15)
+
+/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_IN              (1<<16)
+
+/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd
+ * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given
+ * to the caller, and it should be close() after use. (The fd is a regular
+ * file descriptor and will be cleaned up on process termination. It holds
+ * a reference to the request, but nothing else.)
+ *
+ * The sync_file fd can be combined with other sync_file and passed either
+ * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip
+ * will only occur after this request completes), or to other devices.
+ *
+ * Using I915_EXEC_FENCE_OUT requires use of
+ * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written
+ * back to userspace. Failure to do so will cause the out-fence to always
+ * be reported as zero, and the real fence fd to be leaked.
+ */
+#define I915_EXEC_FENCE_OUT             (1<<17)
+
+/*
+ * Traditionally the execbuf ioctl has only considered the final element in
+ * the execobject[] to be the executable batch. Often though, the client
+ * will known the batch object prior to construction and being able to place
+ * it into the execobject[] array first can simplify the relocation tracking.
+ * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the
+ * execobject[] as the * batch instead (the default is to use the last
+ * element).
+ */
+#define I915_EXEC_BATCH_FIRST           (1<<18)
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
+
+#define I915_EXEC_CONTEXT_ID_MASK       (0xffffffff)
+#define i915_execbuffer2_set_context_id(eb2, context) \
+        (eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
+#define i915_execbuffer2_get_context_id(eb2) \
+        ((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)
+
+struct drm_i915_gem_pin {
+        /** Handle of the buffer to be pinned. */
+        __u32 handle;
+        __u32 pad;
+
+        /** alignment required within the aperture */
+        __u64 alignment;
+
+        /** Returned GTT offset of the buffer. */
+        __u64 offset;
+};
+
+struct drm_i915_gem_unpin {
+        /** Handle of the buffer to be unpinned. */
+        __u32 handle;
+        __u32 pad;
+};
+
+struct drm_i915_gem_busy {
+        /** Handle of the buffer to check for busy */
+        __u32 handle;
+
+        /** Return busy status
+         *
+         * A return of 0 implies that the object is idle (after
+         * having flushed any pending activity), and a non-zero return that
+         * the object is still in-flight on the GPU. (The GPU has not yet
+         * signaled completion for all pending requests that reference the
+         * object.) An object is guaranteed to become idle eventually (so
+         * long as no new GPU commands are executed upon it). Due to the
+         * asynchronous nature of the hardware, an object reported
+         * as busy may become idle before the ioctl is completed.
+         *
+         * Furthermore, if the object is busy, which engine is busy is only
+         * provided as a guide. There are race conditions which prevent the
+         * report of which engines are busy from being always accurate.
+         * However, the converse is not true. If the object is idle, the
+         * result of the ioctl, that all engines are idle, is accurate.
+         *
+         * The returned dword is split into two fields to indicate both
+         * the engines on which the object is being read, and the
+         * engine on which it is currently being written (if any).
+         *
+         * The low word (bits 0:15) indicate if the object is being written
+         * to by any engine (there can only be one, as the GEM implicit
+         * synchronisation rules force writes to be serialised). Only the
+         * engine for the last write is reported.
+         *
+         * The high word (bits 16:31) are a bitmask of which engines are
+         * currently reading from the object. Multiple engines may be
+         * reading from the object simultaneously.
+         *
+         * The value of each engine is the same as specified in the
+         * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc.
+         * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to
+         * the I915_EXEC_RENDER engine for execution, and so it is never
+         * reported as active itself. Some hardware may have parallel
+         * execution engines, e.g. multiple media engines, which are
+         * mapped to the same identifier in the EXECBUFFER2 ioctl and
+         * so are not separately reported for busyness.
+         *
+         * Caveat emptor:
+         * Only the boolean result of this query is reliable; that is whether
+         * the object is idle or busy. The report of which engines are busy
+         * should be only used as a heuristic.
+         */
+        __u32 busy;
+};
+
+/**
+ * I915_CACHING_NONE
+ *
+ * GPU access is not coherent with cpu caches. Default for machines without an
+ * LLC.
+ */
+#define I915_CACHING_NONE               0
+/**
+ * I915_CACHING_CACHED
+ *
+ * GPU access is coherent with cpu caches and furthermore the data is cached in
+ * last-level caches shared between cpu cores and the gpu GT. Default on
+ * machines with HAS_LLC.
+ */
+#define I915_CACHING_CACHED             1
+/**
+ * I915_CACHING_DISPLAY
+ *
+ * Special GPU caching mode which is coherent with the scanout engines.
+ * Transparently falls back to I915_CACHING_NONE on platforms where no special
+ * cache mode (like write-through or gfdt flushing) is available. The kernel
+ * automatically sets this mode when using a buffer as a scanout target.
+ * Userspace can manually set this mode to avoid a costly stall and clflush in
+ * the hotpath of drawing the first frame.
+ */
+#define I915_CACHING_DISPLAY            2
+
+struct drm_i915_gem_caching {
+        /**
+         * Handle of the buffer to set/get the caching level of. */
+        __u32 handle;
+
+        /**
+         * Cacheing level to apply or return value
+         *
+         * bits0-15 are for generic caching control (i.e. the above defined
+         * values). bits16-31 are reserved for platform-specific variations
+         * (e.g. l3$ caching on gen7). */
+        __u32 caching;
+};
+
+#define I915_TILING_NONE        0
+#define I915_TILING_X           1
+#define I915_TILING_Y           2
+#define I915_TILING_LAST        I915_TILING_Y
+
+#define I915_BIT_6_SWIZZLE_NONE         0
+#define I915_BIT_6_SWIZZLE_9            1
+#define I915_BIT_6_SWIZZLE_9_10         2
+#define I915_BIT_6_SWIZZLE_9_11         3
+#define I915_BIT_6_SWIZZLE_9_10_11      4
+/* Not seen by userland */
+#define I915_BIT_6_SWIZZLE_UNKNOWN      5
+/* Seen by userland. */
+#define I915_BIT_6_SWIZZLE_9_17         6
+#define I915_BIT_6_SWIZZLE_9_10_17      7
+
+struct drm_i915_gem_set_tiling {
+        /** Handle of the buffer to have its tiling state updated */
+        __u32 handle;
+
+        /**
+         * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+         * I915_TILING_Y).
+         *
+         * This value is to be set on request, and will be updated by the
+         * kernel on successful return with the actual chosen tiling layout.
+         *
+         * The tiling mode may be demoted to I915_TILING_NONE when the system
+         * has bit 6 swizzling that can't be managed correctly by GEM.
+         *
+         * Buffer contents become undefined when changing tiling_mode.
+         */
+        __u32 tiling_mode;
+
+        /**
+         * Stride in bytes for the object when in I915_TILING_X or
+         * I915_TILING_Y.
+         */
+        __u32 stride;
+
+        /**
+         * Returned address bit 6 swizzling required for CPU access through
+         * mmap mapping.
+         */
+        __u32 swizzle_mode;
+};
+
+struct drm_i915_gem_get_tiling {
+        /** Handle of the buffer to get tiling state for. */
+        __u32 handle;
+
+        /**
+         * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+         * I915_TILING_Y).
+         */
+        __u32 tiling_mode;
+
+        /**
+         * Returned address bit 6 swizzling required for CPU access through
+         * mmap mapping.
+         */
+        __u32 swizzle_mode;
+
+        /**
+         * Returned address bit 6 swizzling required for CPU access through
+         * mmap mapping whilst bound.
+         */
+        __u32 phys_swizzle_mode;
+};
+
+struct drm_i915_gem_get_aperture {
+        /** Total size of the aperture used by i915_gem_execbuffer, in bytes */
+        __u64 aper_size;
+
+        /**
+         * Available space in the aperture used by i915_gem_execbuffer, in
+         * bytes
+         */
+        __u64 aper_available_size;
+};
+
+struct drm_i915_get_pipe_from_crtc_id {
+        /** ID of CRTC being requested **/
+        __u32 crtc_id;
+
+        /** pipe of requested CRTC **/
+        __u32 pipe;
+};
+
+#define I915_MADV_WILLNEED 0
+#define I915_MADV_DONTNEED 1
+#define __I915_MADV_PURGED 2 /* internal state */
+
+struct drm_i915_gem_madvise {
+        /** Handle of the buffer to change the backing store advice */
+        __u32 handle;
+
+        /* Advice: either the buffer will be needed again in the near future,
+         *         or wont be and could be discarded under memory pressure.
+         */
+        __u32 madv;
+
+        /** Whether the backing store still exists. */
+        __u32 retained;
+};
+
+/* flags */
+#define I915_OVERLAY_TYPE_MASK          0xff
+#define I915_OVERLAY_YUV_PLANAR         0x01
+#define I915_OVERLAY_YUV_PACKED         0x02
+#define I915_OVERLAY_RGB                0x03
+
+#define I915_OVERLAY_DEPTH_MASK         0xff00
+#define I915_OVERLAY_RGB24              0x1000
+#define I915_OVERLAY_RGB16              0x2000
+#define I915_OVERLAY_RGB15              0x3000
+#define I915_OVERLAY_YUV422             0x0100
+#define I915_OVERLAY_YUV411             0x0200
+#define I915_OVERLAY_YUV420             0x0300
+#define I915_OVERLAY_YUV410             0x0400
+
+#define I915_OVERLAY_SWAP_MASK          0xff0000
+#define I915_OVERLAY_NO_SWAP            0x000000
+#define I915_OVERLAY_UV_SWAP            0x010000
+#define I915_OVERLAY_Y_SWAP             0x020000
+#define I915_OVERLAY_Y_AND_UV_SWAP      0x030000
+
+#define I915_OVERLAY_FLAGS_MASK         0xff000000
+#define I915_OVERLAY_ENABLE             0x01000000
+
+struct drm_intel_overlay_put_image {
+        /* various flags and src format description */
+        __u32 flags;
+        /* source picture description */
+        __u32 bo_handle;
+        /* stride values and offsets are in bytes, buffer relative */
+        __u16 stride_Y; /* stride for packed formats */
+        __u16 stride_UV;
+        __u32 offset_Y; /* offset for packet formats */
+        __u32 offset_U;
+        __u32 offset_V;
+        /* in pixels */
+        __u16 src_width;
+        __u16 src_height;
+        /* to compensate the scaling factors for partially covered surfaces */
+        __u16 src_scan_width;
+        __u16 src_scan_height;
+        /* output crtc description */
+        __u32 crtc_id;
+        __u16 dst_x;
+        __u16 dst_y;
+        __u16 dst_width;
+        __u16 dst_height;
+};
+
+/* flags */
+#define I915_OVERLAY_UPDATE_ATTRS       (1<<0)
+#define I915_OVERLAY_UPDATE_GAMMA       (1<<1)
+#define I915_OVERLAY_DISABLE_DEST_COLORKEY      (1<<2)
+struct drm_intel_overlay_attrs {
+        __u32 flags;
+        __u32 color_key;
+        __s32 brightness;
+        __u32 contrast;
+        __u32 saturation;
+        __u32 gamma0;
+        __u32 gamma1;
+        __u32 gamma2;
+        __u32 gamma3;
+        __u32 gamma4;
+        __u32 gamma5;
+};
+
+/*
+ * Intel sprite handling
+ *
+ * Color keying works with a min/mask/max tuple.  Both source and destination
+ * color keying is allowed.
+ *
+ * Source keying:
+ * Sprite pixels within the min & max values, masked against the color channels
+ * specified in the mask field, will be transparent.  All other pixels will
+ * be displayed on top of the primary plane.  For RGB surfaces, only the min
+ * and mask fields will be used; ranged compares are not allowed.
+ *
+ * Destination keying:
+ * Primary plane pixels that match the min value, masked against the color
+ * channels specified in the mask field, will be replaced by corresponding
+ * pixels from the sprite plane.
+ *
+ * Note that source & destination keying are exclusive; only one can be
+ * active on a given plane.
+ */
+
+#define I915_SET_COLORKEY_NONE          (1<<0) /* disable color key matching */
+#define I915_SET_COLORKEY_DESTINATION   (1<<1)
+#define I915_SET_COLORKEY_SOURCE        (1<<2)
+struct drm_intel_sprite_colorkey {
+        __u32 plane_id;
+        __u32 min_value;
+        __u32 channel_mask;
+        __u32 max_value;
+        __u32 flags;
+};
+
+struct drm_i915_gem_wait {
+        /** Handle of BO we shall wait on */
+        __u32 bo_handle;
+        __u32 flags;
+        /** Number of nanoseconds to wait, Returns time remaining. */
+        __s64 timeout_ns;
+};
+
+struct drm_i915_gem_context_create {
+        /*  output: id of new context*/
+        __u32 ctx_id;
+        __u32 pad;
+};
+
+struct drm_i915_gem_context_destroy {
+        __u32 ctx_id;
+        __u32 pad;
+};
+
+struct drm_i915_reg_read {
+        /*
+         * Register offset.
+         * For 64bit wide registers where the upper 32bits don't immediately
+         * follow the lower 32bits, the offset of the lower 32bits must
+         * be specified
+         */
+        __u64 offset;
+        __u64 val; /* Return value */
+};
+/* Known registers:
+ *
+ * Render engine timestamp - 0x2358 + 64bit - gen7+
+ * - Note this register returns an invalid value if using the default
+ *   single instruction 8byte read, in order to workaround that use
+ *   offset (0x2538 | 1) instead.
+ *
+ */
+
+struct drm_i915_reset_stats {
+        __u32 ctx_id;
+        __u32 flags;
+
+        /* All resets since boot/module reload, for all contexts */
+        __u32 reset_count;
+
+        /* Number of batches lost when active in GPU, for this context */
+        __u32 batch_active;
+
+        /* Number of batches lost pending for execution, for this context */
+        __u32 batch_pending;
+
+        __u32 pad;
+};
+
+struct drm_i915_gem_userptr {
+        __u64 user_ptr;
+        __u64 user_size;
+        __u32 flags;
+#define I915_USERPTR_READ_ONLY 0x1
+#define I915_USERPTR_UNSYNCHRONIZED 0x80000000
+        /**
+         * Returned handle for the object.
+         *
+         * Object handles are nonzero.
+         */
+        __u32 handle;
+};
+
+struct drm_i915_gem_context_param {
+        __u32 ctx_id;
+        __u32 size;
+        __u64 param;
+#define I915_CONTEXT_PARAM_BAN_PERIOD   0x1
+#define I915_CONTEXT_PARAM_NO_ZEROMAP   0x2
+#define I915_CONTEXT_PARAM_GTT_SIZE     0x3
+#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE     0x4
+#define I915_CONTEXT_PARAM_BANNABLE     0x5
+        __u64 value;
+};
+
+enum drm_i915_oa_format {
+        I915_OA_FORMAT_A13 = 1,     /* HSW only */
+        I915_OA_FORMAT_A29,         /* HSW only */
+        I915_OA_FORMAT_A13_B8_C8,   /* HSW only */
+        I915_OA_FORMAT_B4_C8,       /* HSW only */
+        I915_OA_FORMAT_A45_B8_C8,   /* HSW only */
+        I915_OA_FORMAT_B4_C8_A16,   /* HSW only */
+        I915_OA_FORMAT_C4_B8,       /* HSW+ */
+
+        /* Gen8+ */
+        I915_OA_FORMAT_A12,
+        I915_OA_FORMAT_A12_B8_C8,
+        I915_OA_FORMAT_A32u40_A4u32_B8_C8,
+
+        I915_OA_FORMAT_MAX          /* non-ABI */
+};
+
+enum drm_i915_perf_property_id {
+        /**
+         * Open the stream for a specific context handle (as used with
+         * execbuffer2). A stream opened for a specific context this way
+         * won't typically require root privileges.
+         */
+        DRM_I915_PERF_PROP_CTX_HANDLE = 1,
+
+        /**
+         * A value of 1 requests the inclusion of raw OA unit reports as
+         * part of stream samples.
+         */
+        DRM_I915_PERF_PROP_SAMPLE_OA,
+
+        /**
+         * The value specifies which set of OA unit metrics should be
+         * be configured, defining the contents of any OA unit reports.
+         */
+        DRM_I915_PERF_PROP_OA_METRICS_SET,
+
+        /**
+         * The value specifies the size and layout of OA unit reports.
+         */
+        DRM_I915_PERF_PROP_OA_FORMAT,
+
+        /**
+         * Specifying this property implicitly requests periodic OA unit
+         * sampling and (at least on Haswell) the sampling frequency is derived
+         * from this exponent as follows:
+         *
+         *   80ns * 2^(period_exponent + 1)
+         */
+        DRM_I915_PERF_PROP_OA_EXPONENT,
+
+        DRM_I915_PERF_PROP_MAX /* non-ABI */
+};
+
+struct drm_i915_perf_open_param {
+        __u32 flags;
+#define I915_PERF_FLAG_FD_CLOEXEC       (1<<0)
+#define I915_PERF_FLAG_FD_NONBLOCK      (1<<1)
+#define I915_PERF_FLAG_DISABLED         (1<<2)
+
+        /** The number of u64 (id, value) pairs */
+        __u32 num_properties;
+
+        /**
+         * Pointer to array of u64 (id, value) pairs configuring the stream
+         * to open.
+         */
+        __u64 properties_ptr;
+};
+
+/**
+ * Enable data capture for a stream that was either opened in a disabled state
+ * via I915_PERF_FLAG_DISABLED or was later disabled via
+ * I915_PERF_IOCTL_DISABLE.
+ *
+ * It is intended to be cheaper to disable and enable a stream than it may be
+ * to close and re-open a stream with the same configuration.
+ *
+ * It's undefined whether any pending data for the stream will be lost.
+ */
+#define I915_PERF_IOCTL_ENABLE  _IO('i', 0x0)
+
+/**
+ * Disable data capture for a stream.
+ *
+ * It is an error to try and read a stream that is disabled.
+ */
+#define I915_PERF_IOCTL_DISABLE _IO('i', 0x1)
+
+/**
+ * Common to all i915 perf records
+ */
+struct drm_i915_perf_record_header {
+        __u32 type;
+        __u16 pad;
+        __u16 size;
+};
+
+enum drm_i915_perf_record_type {
+
+        /**
+         * Samples are the work horse record type whose contents are extensible
+         * and defined when opening an i915 perf stream based on the given
+         * properties.
+         *
+         * Boolean properties following the naming convention
+         * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in
+         * every sample.
+         *
+         * The order of these sample properties given by userspace has no
+         * affect on the ordering of data within a sample. The order is
+         * documented here.
+         *
+         * struct {
+         *     struct drm_i915_perf_record_header header;
+         *
+         *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
+         * };
+         */
+        DRM_I915_PERF_RECORD_SAMPLE = 1,
+
+        /*
+         * Indicates that one or more OA reports were not written by the
+         * hardware. This can happen for example if an MI_REPORT_PERF_COUNT
+         * command collides with periodic sampling - which would be more likely
+         * at higher sampling frequencies.
+         */
+        DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,
+
+        /**
+         * An error occurred that resulted in all pending OA reports being lost.
+         */
+        DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3,
+
+        DRM_I915_PERF_RECORD_MAX /* non-ABI */
+};
+
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+        /** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+        char uuid[36];
+
+        __u32 n_mux_regs;
+        __u32 n_boolean_regs;
+        __u32 n_flex_regs;
+
+        __u64 __user mux_regs_ptr;
+        __u64 __user boolean_regs_ptr;
+        __u64 __user flex_regs_ptr;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_I915_DRM_H_ */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ce2988be4f0e..4c223ab30293 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  *
  * This program is free software; you can redistribute it and/or
@@ -30,9 +31,14 @@
 #define BPF_FROM_LE     BPF_TO_LE
 #define BPF_FROM_BE     BPF_TO_BE
 
+/* jmp encodings */
 #define BPF_JNE         0x50    /* jump != */
+#define BPF_JLT         0xa0    /* LT is unsigned, '<' */
+#define BPF_JLE         0xb0    /* LE is unsigned, '<=' */
 #define BPF_JSGT        0x60    /* SGT is signed '>', GT in x86 */
 #define BPF_JSGE        0x70    /* SGE is signed '>=', GE in x86 */
+#define BPF_JSLT        0xc0    /* SLT is signed, '<' */
+#define BPF_JSLE        0xd0    /* SLE is signed, '<=' */
 #define BPF_CALL        0x80    /* function call */
 #define BPF_EXIT        0x90    /* function return */
 
@@ -87,6 +93,7 @@ enum bpf_cmd {
         BPF_PROG_GET_FD_BY_ID,
         BPF_MAP_GET_FD_BY_ID,
         BPF_OBJ_GET_INFO_BY_FD,
+        BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {
@@ -104,6 +111,9 @@ enum bpf_map_type {
         BPF_MAP_TYPE_LPM_TRIE,
         BPF_MAP_TYPE_ARRAY_OF_MAPS,
         BPF_MAP_TYPE_HASH_OF_MAPS,
+        BPF_MAP_TYPE_DEVMAP,
+        BPF_MAP_TYPE_SOCKMAP,
+        BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
@@ -121,6 +131,8 @@ enum bpf_prog_type {
         BPF_PROG_TYPE_LWT_OUT,
         BPF_PROG_TYPE_LWT_XMIT,
         BPF_PROG_TYPE_SOCK_OPS,
+        BPF_PROG_TYPE_SK_SKB,
+        BPF_PROG_TYPE_CGROUP_DEVICE,
 };
 
 enum bpf_attach_type {
@@ -128,16 +140,55 @@ enum bpf_attach_type {
         BPF_CGROUP_INET_EGRESS,
         BPF_CGROUP_INET_SOCK_CREATE,
         BPF_CGROUP_SOCK_OPS,
+        BPF_SK_SKB_STREAM_PARSER,
+        BPF_SK_SKB_STREAM_VERDICT,
+        BPF_CGROUP_DEVICE,
         __MAX_BPF_ATTACH_TYPE
 };
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ *    cgrp2 (OVERRIDE prog C) ->
+ *      cgrp3 (MULTI prog D) ->
+ *        cgrp4 (OVERRIDE prog E) ->
+ *          cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
  */
 #define BPF_F_ALLOW_OVERRIDE    (1U << 0)
+#define BPF_F_ALLOW_MULTI       (1U << 1)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -153,6 +204,7 @@ enum bpf_attach_type {
 #define BPF_NOEXIST     1 /* create new element if it didn't exist */
 #define BPF_EXIST       2 /* update existing element */
 
+/* flags for BPF_MAP_CREATE command */
 #define BPF_F_NO_PREALLOC       (1U << 0)
 /* Instead of having one common LRU list in the
  * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
@@ -161,6 +213,17 @@ enum bpf_attach_type {
  * across different LRU lists.
  */
 #define BPF_F_NO_COMMON_LRU     (1U << 1)
+/* Specify numa node during map creation */
+#define BPF_F_NUMA_NODE         (1U << 2)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE   (1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY            (1U << 3)
+#define BPF_F_WRONLY            (1U << 4)
 
 union bpf_attr {
         struct { /* anonymous struct used by BPF_MAP_CREATE command */
@@ -168,8 +231,14 @@ union bpf_attr {
                 __u32   key_size;       /* size of key in bytes */
                 __u32   value_size;     /* size of value in bytes */
                 __u32   max_entries;    /* max number of entries in a map */
-                __u32   map_flags;      /* prealloc or not */
+                __u32   map_flags;      /* BPF_MAP_CREATE related
+                                         * flags defined above.
+                                         */
                 __u32   inner_map_fd;   /* fd pointing to the inner map */
+                __u32   numa_node;      /* numa node (effective only if
+                                         * BPF_F_NUMA_NODE is set).
+                                         */
+                char    map_name[BPF_OBJ_NAME_LEN];
         };
 
         struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -192,11 +261,14 @@ union bpf_attr {
                 __aligned_u64   log_buf;        /* user supplied buffer */
                 __u32           kern_version;   /* checked when prog_type=kprobe */
                 __u32           prog_flags;
+                char            prog_name[BPF_OBJ_NAME_LEN];
+                __u32           prog_ifindex;   /* ifindex of netdev to prep for */
         };
 
         struct { /* anonymous struct used by BPF_OBJ_* commands */
                 __aligned_u64   pathname;
                 __u32           bpf_fd;
+                __u32           file_flags;
         };
 
         struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -224,6 +296,7 @@ union bpf_attr {
                         __u32           map_id;
                 };
                 __u32           next_id;
+                __u32           open_flags;
         };
 
         struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -231,6 +304,15 @@ union bpf_attr {
                 __u32           info_len;
                 __aligned_u64   info;
         } info;
+
+        struct { /* anonymous struct used by BPF_PROG_QUERY command */
+                __u32           target_fd;      /* container object to query */
+                __u32           attach_type;
+                __u32           query_flags;
+                __u32           attach_flags;
+                __aligned_u64   prog_ids;
+                __u32           prog_cnt;
+        } query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -294,7 +376,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
@@ -344,9 +426,20 @@ union bpf_attr {
  * int bpf_redirect(ifindex, flags)
  *     redirect to another netdev
  *     @ifindex: ifindex of the net device
- *     @flags: bit 0 - if set, redirect to ingress instead of egress
- *             other bits - reserved
- *     Return: TC_ACT_REDIRECT
+ *     @flags:
+ *        cls_bpf:
+ *          bit 0 - if set, redirect to ingress instead of egress
+ *          other bits - reserved
+ *        xdp_bpf:
+ *          all bits - reserved
+ *     Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
+ *             xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
+ * int bpf_redirect_map(map, key, flags)
+ *     redirect to endpoint in map
+ *     @map: pointer to dev map
+ *     @key: index in map to lookup
+ *     @flags: --
+ *     Return: XDP_REDIRECT on success or XDP_ABORT on error
  *
  * u32 bpf_get_route_realm(skb)
  *     retrieve a dst's tclassid
@@ -524,12 +617,22 @@ union bpf_attr {
  * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
  *     Calls setsockopt. Not all opts are available, only those with
  *     integer optvals plus TCP_CONGESTION.
- *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     Supported levels: SOL_SOCKET and IPPROTO_TCP
  *     @bpf_socket: pointer to bpf_socket
- *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @level: SOL_SOCKET or IPPROTO_TCP
  *     @optname: option name
  *     @optval: pointer to option value
- *     @optlen: length of optval in byes
+ *     @optlen: length of optval in bytes
+ *     Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls getsockopt. Not all opts are available.
+ *     Supported levels: IPPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -539,6 +642,41 @@ union bpf_attr {
  *     @mode: operation mode (enum bpf_adj_room_mode)
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
+ *
+ * int bpf_sk_redirect_map(map, key, flags)
+ *     Redirect skb to a sock in map using key as a lookup key for the
+ *     sock in map.
+ *     @map: pointer to sockmap
+ *     @key: key to lookup sock in map
+ *     @flags: reserved for future use
+ *     Return: SK_PASS
+ *
+ * int bpf_sock_map_update(skops, map, key, flags)
+ *      @skops: pointer to bpf_sock_ops
+ *      @map: pointer to sockmap to update
+ *      @key: key to insert/update sock in map
+ *      @flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ *     Adjust the xdp_md.data_meta by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data_meta
+ *     Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ *     read perf event counter value and perf event enabled/running time
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ *     read perf prog attached perf event counter and enabled/running time
+ *     @ctx: pointer to ctx
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return : 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)           \
         FN(unspec),                     \
@@ -591,7 +729,14 @@ union bpf_attr {
         FN(get_socket_uid),             \
         FN(set_hash),                   \
         FN(setsockopt),                 \
-        FN(skb_adjust_room),
+        FN(skb_adjust_room),            \
+        FN(redirect_map),               \
+        FN(sk_redirect_map),            \
+        FN(sock_map_update),            \
+        FN(xdp_adjust_meta),            \
+        FN(perf_event_read_value),      \
+        FN(perf_prog_read_value),       \
+        FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -635,7 +780,9 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX              (1ULL << 1)
 #define BPF_F_DONT_FRAGMENT             (1ULL << 2)
 
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
 #define BPF_F_INDEX_MASK                0xffffffffULL
 #define BPF_F_CURRENT_CPU               BPF_F_INDEX_MASK
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -643,7 +790,7 @@ enum bpf_func_id {
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
-        BPF_ADJ_ROOM_NET_OPTS,
+        BPF_ADJ_ROOM_NET,
 };
 
 /* user accessible mirror of in-kernel sk_buff.
@@ -668,6 +815,18 @@ struct __sk_buff {
         __u32 data;
         __u32 data_end;
         __u32 napi_id;
+
+        /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
+        __u32 family;
+        __u32 remote_ip4;       /* Stored in network byte order */
+        __u32 local_ip4;        /* Stored in network byte order */
+        __u32 remote_ip6[4];    /* Stored in network byte order */
+        __u32 local_ip6[4];     /* Stored in network byte order */
+        __u32 remote_port;      /* Stored in network byte order */
+        __u32 local_port;       /* stored in host byte order */
+        /* ... here. */
+
+        __u32 data_meta;
 };
 
 struct bpf_tunnel_key {
@@ -703,20 +862,23 @@ struct bpf_sock {
         __u32 family;
         __u32 type;
         __u32 protocol;
+        __u32 mark;
+        __u32 priority;
 };
 
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
- * return codes are reserved for future use. Unknown return codes will result
- * in packet drop.
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
  */
 enum xdp_action {
         XDP_ABORTED = 0,
         XDP_DROP,
         XDP_PASS,
         XDP_TX,
+        XDP_REDIRECT,
 };
 
 /* user accessible metadata for XDP packet hook
@@ -725,6 +887,12 @@ enum xdp_action {
 struct xdp_md {
         __u32 data;
         __u32 data_end;
+        __u32 data_meta;
+};
+
+enum sk_action {
+        SK_DROP = 0,
+        SK_PASS,
 };
 
 #define BPF_TAG_SIZE    8
@@ -737,6 +905,11 @@ struct bpf_prog_info {
         __u32 xlated_prog_len;
         __aligned_u64 jited_prog_insns;
         __aligned_u64 xlated_prog_insns;
+        __u64 load_time;        /* ns since boottime */
+        __u32 created_by_uid;
+        __u32 nr_map_ids;
+        __aligned_u64 map_ids;
+        char name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -746,10 +919,13 @@ struct bpf_map_info {
         __u32 value_size;
         __u32 max_entries;
         __u32 map_flags;
+        char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
  * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
  * New fields can only be added at the end of this structure
  */
 struct bpf_sock_ops {
@@ -759,12 +935,12 @@ struct bpf_sock_ops {
                 __u32 replylong[4];
         };
         __u32 family;
-        __u32 remote_ip4;
-        __u32 local_ip4;
-        __u32 remote_ip6[4];
-        __u32 local_ip6[4];
-        __u32 remote_port;
-        __u32 local_port;
+        __u32 remote_ip4;       /* Stored in network byte order */
+        __u32 local_ip4;        /* Stored in network byte order */
+        __u32 remote_ip6[4];    /* Stored in network byte order */
+        __u32 local_ip6[4];     /* Stored in network byte order */
+        __u32 remote_port;      /* Stored in network byte order */
+        __u32 local_port;       /* stored in host byte order */
 };
 
 /* List of known BPF sock_ops operators.
@@ -793,9 +969,35 @@ enum {
         BPF_SOCK_OPS_NEEDS_ECN,         /* If connection's congestion control
                                          * needs ECN
                                          */
+        BPF_SOCK_OPS_BASE_RTT,          /* Get base RTT. The correct value is
+                                         * based on the path and may be
+                                         * dependent on the congestion control
+                                         * algorithm. In general it indicates
+                                         * a congestion threshold. RTTs above
+                                         * this indicate congestion
+                                         */
 };
 
 #define TCP_BPF_IW              1001    /* Set TCP initial congestion window */
 #define TCP_BPF_SNDCWND_CLAMP   1002    /* Set sndcwnd_clamp */
 
+struct bpf_perf_event_value {
+        __u64 counter;
+        __u64 enabled;
+        __u64 running;
+};
+
+#define BPF_DEVCG_ACC_MKNOD     (1ULL << 0)
+#define BPF_DEVCG_ACC_READ      (1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE     (1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK     (1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR      (1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+        __u32 access_type; /* (access << 16) | type */
+        __u32 major;
+        __u32 minor;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h
index a5c220e0828f..18be90725ab0 100644
--- a/tools/include/uapi/linux/bpf_common.h
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI__LINUX_BPF_COMMON_H__
 #define _UAPI__LINUX_BPF_COMMON_H__
 
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 813afd6eee71..6448cdd9a350 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_FCNTL_H
 #define _UAPI_LINUX_FCNTL_H
 
@@ -43,6 +44,27 @@
 /* (1U << 31) is reserved for signed error codes */
 
 /*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT           (F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT           (F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT      (F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT      (F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWF_WRITE_LIFE_NOT_SET  0
+#define RWH_WRITE_LIFE_NONE     1
+#define RWH_WRITE_LIFE_SHORT    2
+#define RWH_WRITE_LIFE_MEDIUM   3
+#define RWH_WRITE_LIFE_LONG     4
+#define RWH_WRITE_LIFE_EXTREME  5
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS       0x00000001      /* File accessed */
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
index 2b65efd19a46..965e4d8606d8 100644
--- a/tools/include/uapi/linux/hw_breakpoint.h
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_HW_BREAKPOINT_H
 #define _UAPI_LINUX_HW_BREAKPOINT_H
 
diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h
new file mode 100644
index 000000000000..481e103da78e
--- /dev/null
+++ b/tools/include/uapi/linux/kcmp.h
@@ -0,0 +1,27 @@
+#ifndef _UAPI_LINUX_KCMP_H
+#define _UAPI_LINUX_KCMP_H
+
+#include <linux/types.h>
+
+/* Comparison type */
+enum kcmp_type {
+        KCMP_FILE,
+        KCMP_VM,
+        KCMP_FILES,
+        KCMP_FS,
+        KCMP_SIGHAND,
+        KCMP_IO,
+        KCMP_SYSVSEM,
+        KCMP_EPOLL_TFD,
+
+        KCMP_TYPES,
+};
+
+/* Slot for KCMP_EPOLL_TFD */
+struct kcmp_epoll_slot {
+        __u32 efd;              /* epoll file descriptor */
+        __u32 tfd;              /* target file number */
+        __u32 toff;             /* target offset within same numbered sequence */
+};
+
+#endif /* _UAPI_LINUX_KCMP_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
new file mode 100644
index 000000000000..7e99999d6236
--- /dev/null
+++ b/tools/include/uapi/linux/kvm.h
@@ -0,0 +1,1421 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_KVM_H
+#define __LINUX_KVM_H
+
+/*
+ * Userspace interface for /dev/kvm - kernel based virtual machine
+ *
+ * Note: you must update KVM_API_VERSION if you change this interface.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <asm/kvm.h>
+
+#define KVM_API_VERSION 12
+
+/* *** Deprecated interfaces *** */
+
+#define KVM_TRC_SHIFT           16
+
+#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
+#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
+
+#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
+#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
+#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
+
+#define KVM_TRC_HEAD_SIZE       12
+#define KVM_TRC_CYCLE_SIZE      8
+#define KVM_TRC_EXTRA_MAX       7
+
+#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
+#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
+#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
+#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
+#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
+#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
+#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
+#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
+#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
+#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
+#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
+#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
+#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
+#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
+#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
+#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
+#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
+#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
+#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
+#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
+#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
+#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
+#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
+#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
+
+struct kvm_user_trace_setup {
+        __u32 buf_size;
+        __u32 buf_nr;
+};
+
+#define __KVM_DEPRECATED_MAIN_W_0x06 \
+        _IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
+#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
+#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
+
+#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
+
+struct kvm_breakpoint {
+        __u32 enabled;
+        __u32 padding;
+        __u64 address;
+};
+
+struct kvm_debug_guest {
+        __u32 enabled;
+        __u32 pad;
+        struct kvm_breakpoint breakpoints[4];
+        __u32 singlestep;
+};
+
+#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
+
+/* *** End of deprecated interfaces *** */
+
+
+/* for KVM_CREATE_MEMORY_REGION */
+struct kvm_memory_region {
+        __u32 slot;
+        __u32 flags;
+        __u64 guest_phys_addr;
+        __u64 memory_size; /* bytes */
+};
+
+/* for KVM_SET_USER_MEMORY_REGION */
+struct kvm_userspace_memory_region {
+        __u32 slot;
+        __u32 flags;
+        __u64 guest_phys_addr;
+        __u64 memory_size; /* bytes */
+        __u64 userspace_addr; /* start of the userspace allocated memory */
+};
+
+/*
+ * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
+ * other bits are reserved for kvm internal use which are defined in
+ * include/linux/kvm_host.h.
+ */
+#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
+#define KVM_MEM_READONLY        (1UL << 1)
+
+/* for KVM_IRQ_LINE */
+struct kvm_irq_level {
+        /*
+         * ACPI gsi notion of irq.
+         * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
+         * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
+         * For ARM: See Documentation/virtual/kvm/api.txt
+         */
+        union {
+                __u32 irq;
+                __s32 status;
+        };
+        __u32 level;
+};
+
+
+struct kvm_irqchip {
+        __u32 chip_id;
+        __u32 pad;
+        union {
+                char dummy[512];  /* reserving space */
+#ifdef __KVM_HAVE_PIT
+                struct kvm_pic_state pic;
+#endif
+#ifdef __KVM_HAVE_IOAPIC
+                struct kvm_ioapic_state ioapic;
+#endif
+        } chip;
+};
+
+/* for KVM_CREATE_PIT2 */
+struct kvm_pit_config {
+        __u32 flags;
+        __u32 pad[15];
+};
+
+#define KVM_PIT_SPEAKER_DUMMY     1
+
+struct kvm_s390_skeys {
+        __u64 start_gfn;
+        __u64 count;
+        __u64 skeydata_addr;
+        __u32 flags;
+        __u32 reserved[9];
+};
+
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ *             pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ *        in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+        __u64 start_gfn;
+        __u32 count;
+        __u32 flags;
+        union {
+                __u64 remaining;
+                __u64 mask;
+        };
+        __u64 values;
+};
+
+struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC          1
+#define KVM_EXIT_HYPERV_HCALL          2
+        __u32 type;
+        union {
+                struct {
+                        __u32 msr;
+                        __u64 control;
+                        __u64 evt_page;
+                        __u64 msg_page;
+                } synic;
+                struct {
+                        __u64 input;
+                        __u64 result;
+                        __u64 params[2];
+                } hcall;
+        } u;
+};
+
+#define KVM_S390_GET_SKEYS_NONE   1
+#define KVM_S390_SKEYS_MAX        1048576
+
+#define KVM_EXIT_UNKNOWN          0
+#define KVM_EXIT_EXCEPTION        1
+#define KVM_EXIT_IO               2
+#define KVM_EXIT_HYPERCALL        3
+#define KVM_EXIT_DEBUG            4
+#define KVM_EXIT_HLT              5
+#define KVM_EXIT_MMIO             6
+#define KVM_EXIT_IRQ_WINDOW_OPEN  7
+#define KVM_EXIT_SHUTDOWN         8
+#define KVM_EXIT_FAIL_ENTRY       9
+#define KVM_EXIT_INTR             10
+#define KVM_EXIT_SET_TPR          11
+#define KVM_EXIT_TPR_ACCESS       12
+#define KVM_EXIT_S390_SIEIC       13
+#define KVM_EXIT_S390_RESET       14
+#define KVM_EXIT_DCR              15 /* deprecated */
+#define KVM_EXIT_NMI              16
+#define KVM_EXIT_INTERNAL_ERROR   17
+#define KVM_EXIT_OSI              18
+#define KVM_EXIT_PAPR_HCALL       19
+#define KVM_EXIT_S390_UCONTROL    20
+#define KVM_EXIT_WATCHDOG         21
+#define KVM_EXIT_S390_TSCH        22
+#define KVM_EXIT_EPR              23
+#define KVM_EXIT_SYSTEM_EVENT     24
+#define KVM_EXIT_S390_STSI        25
+#define KVM_EXIT_IOAPIC_EOI       26
+#define KVM_EXIT_HYPERV           27
+
+/* For KVM_EXIT_INTERNAL_ERROR */
+/* Emulate instruction failed. */
+#define KVM_INTERNAL_ERROR_EMULATION    1
+/* Encounter unexpected simultaneous exceptions. */
+#define KVM_INTERNAL_ERROR_SIMUL_EX     2
+/* Encounter unexpected vm-exit due to delivery event. */
+#define KVM_INTERNAL_ERROR_DELIVERY_EV  3
+
+/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
+struct kvm_run {
+        /* in */
+        __u8 request_interrupt_window;
+        __u8 immediate_exit;
+        __u8 padding1[6];
+
+        /* out */
+        __u32 exit_reason;
+        __u8 ready_for_interrupt_injection;
+        __u8 if_flag;
+        __u16 flags;
+
+        /* in (pre_kvm_run), out (post_kvm_run) */
+        __u64 cr8;
+        __u64 apic_base;
+
+#ifdef __KVM_S390
+        /* the processor status word for s390 */
+        __u64 psw_mask; /* psw upper half */
+        __u64 psw_addr; /* psw lower half */
+#endif
+        union {
+                /* KVM_EXIT_UNKNOWN */
+                struct {
+                        __u64 hardware_exit_reason;
+                } hw;
+                /* KVM_EXIT_FAIL_ENTRY */
+                struct {
+                        __u64 hardware_entry_failure_reason;
+                } fail_entry;
+                /* KVM_EXIT_EXCEPTION */
+                struct {
+                        __u32 exception;
+                        __u32 error_code;
+                } ex;
+                /* KVM_EXIT_IO */
+                struct {
+#define KVM_EXIT_IO_IN  0
+#define KVM_EXIT_IO_OUT 1
+                        __u8 direction;
+                        __u8 size; /* bytes */
+                        __u16 port;
+                        __u32 count;
+                        __u64 data_offset; /* relative to kvm_run start */
+                } io;
+                /* KVM_EXIT_DEBUG */
+                struct {
+                        struct kvm_debug_exit_arch arch;
+                } debug;
+                /* KVM_EXIT_MMIO */
+                struct {
+                        __u64 phys_addr;
+                        __u8  data[8];
+                        __u32 len;
+                        __u8  is_write;
+                } mmio;
+                /* KVM_EXIT_HYPERCALL */
+                struct {
+                        __u64 nr;
+                        __u64 args[6];
+                        __u64 ret;
+                        __u32 longmode;
+                        __u32 pad;
+                } hypercall;
+                /* KVM_EXIT_TPR_ACCESS */
+                struct {
+                        __u64 rip;
+                        __u32 is_write;
+                        __u32 pad;
+                } tpr_access;
+                /* KVM_EXIT_S390_SIEIC */
+                struct {
+                        __u8 icptcode;
+                        __u16 ipa;
+                        __u32 ipb;
+                } s390_sieic;
+                /* KVM_EXIT_S390_RESET */
+#define KVM_S390_RESET_POR       1
+#define KVM_S390_RESET_CLEAR     2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT  8
+#define KVM_S390_RESET_IPL       16
+                __u64 s390_reset_flags;
+                /* KVM_EXIT_S390_UCONTROL */
+                struct {
+                        __u64 trans_exc_code;
+                        __u32 pgm_code;
+                } s390_ucontrol;
+                /* KVM_EXIT_DCR (deprecated) */
+                struct {
+                        __u32 dcrn;
+                        __u32 data;
+                        __u8  is_write;
+                } dcr;
+                /* KVM_EXIT_INTERNAL_ERROR */
+                struct {
+                        __u32 suberror;
+                        /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */
+                        __u32 ndata;
+                        __u64 data[16];
+                } internal;
+                /* KVM_EXIT_OSI */
+                struct {
+                        __u64 gprs[32];
+                } osi;
+                /* KVM_EXIT_PAPR_HCALL */
+                struct {
+                        __u64 nr;
+                        __u64 ret;
+                        __u64 args[9];
+                } papr_hcall;
+                /* KVM_EXIT_S390_TSCH */
+                struct {
+                        __u16 subchannel_id;
+                        __u16 subchannel_nr;
+                        __u32 io_int_parm;
+                        __u32 io_int_word;
+                        __u32 ipb;
+                        __u8 dequeued;
+                } s390_tsch;
+                /* KVM_EXIT_EPR */
+                struct {
+                        __u32 epr;
+                } epr;
+                /* KVM_EXIT_SYSTEM_EVENT */
+                struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN       1
+#define KVM_SYSTEM_EVENT_RESET          2
+#define KVM_SYSTEM_EVENT_CRASH          3
+                        __u32 type;
+                        __u64 flags;
+                } system_event;
+                /* KVM_EXIT_S390_STSI */
+                struct {
+                        __u64 addr;
+                        __u8 ar;
+                        __u8 reserved;
+                        __u8 fc;
+                        __u8 sel1;
+                        __u16 sel2;
+                } s390_stsi;
+                /* KVM_EXIT_IOAPIC_EOI */
+                struct {
+                        __u8 vector;
+                } eoi;
+                /* KVM_EXIT_HYPERV */
+                struct kvm_hyperv_exit hyperv;
+                /* Fix the size of the union. */
+                char padding[256];
+        };
+
+        /*
+         * shared registers between kvm and userspace.
+         * kvm_valid_regs specifies the register classes set by the host
+         * kvm_dirty_regs specified the register classes dirtied by userspace
+         * struct kvm_sync_regs is architecture specific, as well as the
+         * bits for kvm_valid_regs and kvm_dirty_regs
+         */
+        __u64 kvm_valid_regs;
+        __u64 kvm_dirty_regs;
+        union {
+                struct kvm_sync_regs regs;
+                char padding[2048];
+        } s;
+};
+
+/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
+
+struct kvm_coalesced_mmio_zone {
+        __u64 addr;
+        __u32 size;
+        __u32 pad;
+};
+
+struct kvm_coalesced_mmio {
+        __u64 phys_addr;
+        __u32 len;
+        __u32 pad;
+        __u8  data[8];
+};
+
+struct kvm_coalesced_mmio_ring {
+        __u32 first, last;
+        struct kvm_coalesced_mmio coalesced_mmio[0];
+};
+
+#define KVM_COALESCED_MMIO_MAX \
+        ((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \
+         sizeof(struct kvm_coalesced_mmio))
+
+/* for KVM_TRANSLATE */
+struct kvm_translation {
+        /* in */
+        __u64 linear_address;
+
+        /* out */
+        __u64 physical_address;
+        __u8  valid;
+        __u8  writeable;
+        __u8  usermode;
+        __u8  pad[5];
+};
+
+/* for KVM_S390_MEM_OP */
+struct kvm_s390_mem_op {
+        /* in */
+        __u64 gaddr;            /* the guest address */
+        __u64 flags;            /* flags */
+        __u32 size;             /* amount of bytes */
+        __u32 op;               /* type of operation */
+        __u64 buf;              /* buffer in userspace */
+        __u8 ar;                /* the access register number */
+        __u8 reserved[31];      /* should be set to 0 */
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ     0
+#define KVM_S390_MEMOP_LOGICAL_WRITE    1
+/* flags for kvm_s390_mem_op->flags */
+#define KVM_S390_MEMOP_F_CHECK_ONLY             (1ULL << 0)
+#define KVM_S390_MEMOP_F_INJECT_EXCEPTION       (1ULL << 1)
+
+/* for KVM_INTERRUPT */
+struct kvm_interrupt {
+        /* in */
+        __u32 irq;
+};
+
+/* for KVM_GET_DIRTY_LOG */
+struct kvm_dirty_log {
+        __u32 slot;
+        __u32 padding1;
+        union {
+                void __user *dirty_bitmap; /* one bit per page */
+                __u64 padding2;
+        };
+};
+
+/* for KVM_SET_SIGNAL_MASK */
+struct kvm_signal_mask {
+        __u32 len;
+        __u8  sigset[0];
+};
+
+/* for KVM_TPR_ACCESS_REPORTING */
+struct kvm_tpr_access_ctl {
+        __u32 enabled;
+        __u32 flags;
+        __u32 reserved[8];
+};
+
+/* for KVM_SET_VAPIC_ADDR */
+struct kvm_vapic_addr {
+        __u64 vapic_addr;
+};
+
+/* for KVM_SET_MP_STATE */
+
+/* not all states are valid on all architectures */
+#define KVM_MP_STATE_RUNNABLE          0
+#define KVM_MP_STATE_UNINITIALIZED     1
+#define KVM_MP_STATE_INIT_RECEIVED     2
+#define KVM_MP_STATE_HALTED            3
+#define KVM_MP_STATE_SIPI_RECEIVED     4
+#define KVM_MP_STATE_STOPPED           5
+#define KVM_MP_STATE_CHECK_STOP        6
+#define KVM_MP_STATE_OPERATING         7
+#define KVM_MP_STATE_LOAD              8
+
+struct kvm_mp_state {
+        __u32 mp_state;
+};
+
+struct kvm_s390_psw {
+        __u64 mask;
+        __u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP              0xfffe0000u
+#define KVM_S390_PROGRAM_INT            0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX        0xfffe0002u
+#define KVM_S390_RESTART                0xfffe0003u
+#define KVM_S390_INT_PFAULT_INIT        0xfffe0004u
+#define KVM_S390_INT_PFAULT_DONE        0xfffe0005u
+#define KVM_S390_MCHK                   0xfffe1000u
+#define KVM_S390_INT_CLOCK_COMP         0xffff1004u
+#define KVM_S390_INT_CPU_TIMER          0xffff1005u
+#define KVM_S390_INT_VIRTIO             0xffff2603u
+#define KVM_S390_INT_SERVICE            0xffff2401u
+#define KVM_S390_INT_EMERGENCY          0xffff1201u
+#define KVM_S390_INT_EXTERNAL_CALL      0xffff1202u
+/* Anything below 0xfffe0000u is taken by INT_IO */
+#define KVM_S390_INT_IO(ai,cssid,ssid,schid)   \
+        (((schid)) |                           \
+         ((ssid) << 16) |                      \
+         ((cssid) << 18) |                     \
+         ((ai) << 26))
+#define KVM_S390_INT_IO_MIN             0x00000000u
+#define KVM_S390_INT_IO_MAX             0xfffdffffu
+#define KVM_S390_INT_IO_AI_MASK         0x04000000u
+
+
+struct kvm_s390_interrupt {
+        __u32 type;
+        __u32 parm;
+        __u64 parm64;
+};
+
+struct kvm_s390_io_info {
+        __u16 subchannel_id;
+        __u16 subchannel_nr;
+        __u32 io_int_parm;
+        __u32 io_int_word;
+};
+
+struct kvm_s390_ext_info {
+        __u32 ext_params;
+        __u32 pad;
+        __u64 ext_params2;
+};
+
+struct kvm_s390_pgm_info {
+        __u64 trans_exc_code;
+        __u64 mon_code;
+        __u64 per_address;
+        __u32 data_exc_code;
+        __u16 code;
+        __u16 mon_class_nr;
+        __u8 per_code;
+        __u8 per_atmid;
+        __u8 exc_access_id;
+        __u8 per_access_id;
+        __u8 op_access_id;
+#define KVM_S390_PGM_FLAGS_ILC_VALID    0x01
+#define KVM_S390_PGM_FLAGS_ILC_0        0x02
+#define KVM_S390_PGM_FLAGS_ILC_1        0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK     0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND    0x08
+        __u8 flags;
+        __u8 pad[2];
+};
+
+struct kvm_s390_prefix_info {
+        __u32 address;
+};
+
+struct kvm_s390_extcall_info {
+        __u16 code;
+};
+
+struct kvm_s390_emerg_info {
+        __u16 code;
+};
+
+#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
+struct kvm_s390_stop_info {
+        __u32 flags;
+};
+
+struct kvm_s390_mchk_info {
+        __u64 cr14;
+        __u64 mcic;
+        __u64 failing_storage_address;
+        __u32 ext_damage_code;
+        __u32 pad;
+        __u8 fixed_logout[16];
+};
+
+struct kvm_s390_irq {
+        __u64 type;
+        union {
+                struct kvm_s390_io_info io;
+                struct kvm_s390_ext_info ext;
+                struct kvm_s390_pgm_info pgm;
+                struct kvm_s390_emerg_info emerg;
+                struct kvm_s390_extcall_info extcall;
+                struct kvm_s390_prefix_info prefix;
+                struct kvm_s390_stop_info stop;
+                struct kvm_s390_mchk_info mchk;
+                char reserved[64];
+        } u;
+};
+
+struct kvm_s390_irq_state {
+        __u64 buf;
+        __u32 flags;
+        __u32 len;
+        __u32 reserved[4];
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+
+#define KVM_GUESTDBG_ENABLE             0x00000001
+#define KVM_GUESTDBG_SINGLESTEP         0x00000002
+
+struct kvm_guest_debug {
+        __u32 control;
+        __u32 pad;
+        struct kvm_guest_debug_arch arch;
+};
+
+enum {
+        kvm_ioeventfd_flag_nr_datamatch,
+        kvm_ioeventfd_flag_nr_pio,
+        kvm_ioeventfd_flag_nr_deassign,
+        kvm_ioeventfd_flag_nr_virtio_ccw_notify,
+        kvm_ioeventfd_flag_nr_fast_mmio,
+        kvm_ioeventfd_flag_nr_max,
+};
+
+#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
+#define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
+#define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
+#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+        (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
+
+#define KVM_IOEVENTFD_VALID_FLAG_MASK  ((1 << kvm_ioeventfd_flag_nr_max) - 1)
+
+struct kvm_ioeventfd {
+        __u64 datamatch;
+        __u64 addr;        /* legal pio/mmio address */
+        __u32 len;         /* 1, 2, 4, or 8 bytes; or 0 to ignore length */
+        __s32 fd;
+        __u32 flags;
+        __u8  pad[36];
+};
+
+/* for KVM_ENABLE_CAP */
+struct kvm_enable_cap {
+        /* in */
+        __u32 cap;
+        __u32 flags;
+        __u64 args[4];
+        __u8  pad[64];
+};
+
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
+
+struct kvm_ppc_pvinfo {
+        /* out */
+        __u32 flags;
+        __u32 hcall[4];
+        __u8  pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ       8
+
+struct kvm_ppc_one_page_size {
+        __u32 page_shift;       /* Page shift (or 0) */
+        __u32 pte_enc;          /* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+        __u32 page_shift;       /* Base page shift of segment (or 0) */
+        __u32 slb_enc;          /* SLB encoding for BookS */
+        struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL         0x00000001
+#define KVM_PPC_1T_SEGMENTS             0x00000002
+
+struct kvm_ppc_smmu_info {
+        __u64 flags;
+        __u32 slb_size;
+        __u16 data_keys;        /* # storage keys supported for data */
+        __u16 instr_keys;       /* # storage keys supported for instructions */
+        struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+        __u64 flags;
+        __u32 shift;
+        __u32 pad;
+};
+
+#define KVMIO 0xAE
+
+/* machine type bits, to be used as argument to KVM_CREATE_VM */
+#define KVM_VM_S390_UCONTROL    1
+
+/* on ppc, 0 indicate default, 1 should force HV and 2 PR */
+#define KVM_VM_PPC_HV 1
+#define KVM_VM_PPC_PR 2
+
+/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
+#define KVM_VM_MIPS_TE          0
+#define KVM_VM_MIPS_VZ          1
+
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
+/*
+ * ioctls for /dev/kvm fds:
+ */
+#define KVM_GET_API_VERSION       _IO(KVMIO,   0x00)
+#define KVM_CREATE_VM             _IO(KVMIO,   0x01) /* returns a VM fd */
+#define KVM_GET_MSR_INDEX_LIST    _IOWR(KVMIO, 0x02, struct kvm_msr_list)
+
+#define KVM_S390_ENABLE_SIE       _IO(KVMIO,   0x06)
+/*
+ * Check if a kvm extension is available.  Argument is extension number,
+ * return is 1 (yes) or 0 (no, sorry).
+ */
+#define KVM_CHECK_EXTENSION       _IO(KVMIO,   0x03)
+/*
+ * Get size for mmap(vcpu_fd)
+ */
+#define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
+#define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
+#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
+#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
+#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID    _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+
+/*
+ * Extension capability list.
+ */
+#define KVM_CAP_IRQCHIP   0
+#define KVM_CAP_HLT       1
+#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2
+#define KVM_CAP_USER_MEMORY 3
+#define KVM_CAP_SET_TSS_ADDR 4
+#define KVM_CAP_VAPIC 6
+#define KVM_CAP_EXT_CPUID 7
+#define KVM_CAP_CLOCKSOURCE 8
+#define KVM_CAP_NR_VCPUS 9       /* returns recommended max vcpus per vm */
+#define KVM_CAP_NR_MEMSLOTS 10   /* returns max memory slots per vm */
+#define KVM_CAP_PIT 11
+#define KVM_CAP_NOP_IO_DELAY 12
+#define KVM_CAP_PV_MMU 13
+#define KVM_CAP_MP_STATE 14
+#define KVM_CAP_COALESCED_MMIO 15
+#define KVM_CAP_SYNC_MMU 16  /* Changes to host mmap are reflected in guest */
+#define KVM_CAP_IOMMU 18
+/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
+#define KVM_CAP_USER_NMI 22
+#ifdef __KVM_HAVE_GUEST_DEBUG
+#define KVM_CAP_SET_GUEST_DEBUG 23
+#endif
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_REINJECT_CONTROL 24
+#endif
+#define KVM_CAP_IRQ_ROUTING 25
+#define KVM_CAP_IRQ_INJECT_STATUS 26
+#define KVM_CAP_ASSIGN_DEV_IRQ 29
+/* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
+#ifdef __KVM_HAVE_MCE
+#define KVM_CAP_MCE 31
+#endif
+#define KVM_CAP_IRQFD 32
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_PIT2 33
+#endif
+#define KVM_CAP_SET_BOOT_CPU_ID 34
+#ifdef __KVM_HAVE_PIT_STATE2
+#define KVM_CAP_PIT_STATE2 35
+#endif
+#define KVM_CAP_IOEVENTFD 36
+#define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
+#ifdef __KVM_HAVE_XEN_HVM
+#define KVM_CAP_XEN_HVM 38
+#endif
+#define KVM_CAP_ADJUST_CLOCK 39
+#define KVM_CAP_INTERNAL_ERROR_DATA 40
+#ifdef __KVM_HAVE_VCPU_EVENTS
+#define KVM_CAP_VCPU_EVENTS 41
+#endif
+#define KVM_CAP_S390_PSW 42
+#define KVM_CAP_PPC_SEGSTATE 43
+#define KVM_CAP_HYPERV 44
+#define KVM_CAP_HYPERV_VAPIC 45
+#define KVM_CAP_HYPERV_SPIN 46
+#define KVM_CAP_PCI_SEGMENT 47
+#define KVM_CAP_PPC_PAIRED_SINGLES 48
+#define KVM_CAP_INTR_SHADOW 49
+#ifdef __KVM_HAVE_DEBUGREGS
+#define KVM_CAP_DEBUGREGS 50
+#endif
+#define KVM_CAP_X86_ROBUST_SINGLESTEP 51
+#define KVM_CAP_PPC_OSI 52
+#define KVM_CAP_PPC_UNSET_IRQ 53
+#define KVM_CAP_ENABLE_CAP 54
+#ifdef __KVM_HAVE_XSAVE
+#define KVM_CAP_XSAVE 55
+#endif
+#ifdef __KVM_HAVE_XCRS
+#define KVM_CAP_XCRS 56
+#endif
+#define KVM_CAP_PPC_GET_PVINFO 57
+#define KVM_CAP_PPC_IRQ_LEVEL 58
+#define KVM_CAP_ASYNC_PF 59
+#define KVM_CAP_TSC_CONTROL 60
+#define KVM_CAP_GET_TSC_KHZ 61
+#define KVM_CAP_PPC_BOOKE_SREGS 62
+#define KVM_CAP_SPAPR_TCE 63
+#define KVM_CAP_PPC_SMT 64
+#define KVM_CAP_PPC_RMA 65
+#define KVM_CAP_MAX_VCPUS 66       /* returns max vcpus per vm */
+#define KVM_CAP_PPC_HIOR 67
+#define KVM_CAP_PPC_PAPR 68
+#define KVM_CAP_SW_TLB 69
+#define KVM_CAP_ONE_REG 70
+#define KVM_CAP_S390_GMAP 71
+#define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_S390_UCONTROL 73
+#define KVM_CAP_SYNC_REGS 74
+#define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_KVMCLOCK_CTRL 76
+#define KVM_CAP_SIGNAL_MSI 77
+#define KVM_CAP_PPC_GET_SMMU_INFO 78
+#define KVM_CAP_S390_COW 79
+#define KVM_CAP_PPC_ALLOC_HTAB 80
+#define KVM_CAP_READONLY_MEM 81
+#define KVM_CAP_IRQFD_RESAMPLE 82
+#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_HTAB_FD 84
+#define KVM_CAP_S390_CSS_SUPPORT 85
+#define KVM_CAP_PPC_EPR 86
+#define KVM_CAP_ARM_PSCI 87
+#define KVM_CAP_ARM_SET_DEVICE_ADDR 88
+#define KVM_CAP_DEVICE_CTRL 89
+#define KVM_CAP_IRQ_MPIC 90
+#define KVM_CAP_PPC_RTAS 91
+#define KVM_CAP_IRQ_XICS 92
+#define KVM_CAP_ARM_EL1_32BIT 93
+#define KVM_CAP_SPAPR_MULTITCE 94
+#define KVM_CAP_EXT_EMUL_CPUID 95
+#define KVM_CAP_HYPERV_TIME 96
+#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
+#define KVM_CAP_ENABLE_CAP_VM 98
+#define KVM_CAP_S390_IRQCHIP 99
+#define KVM_CAP_IOEVENTFD_NO_LENGTH 100
+#define KVM_CAP_VM_ATTRIBUTES 101
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_PPC_FIXUP_HCALL 103
+#define KVM_CAP_PPC_ENABLE_HCALL 104
+#define KVM_CAP_CHECK_EXTENSION_VM 105
+#define KVM_CAP_S390_USER_SIGP 106
+#define KVM_CAP_S390_VECTOR_REGISTERS 107
+#define KVM_CAP_S390_MEM_OP 108
+#define KVM_CAP_S390_USER_STSI 109
+#define KVM_CAP_S390_SKEYS 110
+#define KVM_CAP_MIPS_FPU 111
+#define KVM_CAP_MIPS_MSA 112
+#define KVM_CAP_S390_INJECT_IRQ 113
+#define KVM_CAP_S390_IRQ_STATE 114
+#define KVM_CAP_PPC_HWRNG 115
+#define KVM_CAP_DISABLE_QUIRKS 116
+#define KVM_CAP_X86_SMM 117
+#define KVM_CAP_MULTI_ADDRESS_SPACE 118
+#define KVM_CAP_GUEST_DEBUG_HW_BPS 119
+#define KVM_CAP_GUEST_DEBUG_HW_WPS 120
+#define KVM_CAP_SPLIT_IRQCHIP 121
+#define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_HYPERV_SYNIC 123
+#define KVM_CAP_S390_RI 124
+#define KVM_CAP_SPAPR_TCE_64 125
+#define KVM_CAP_ARM_PMU_V3 126
+#define KVM_CAP_VCPU_ATTRIBUTES 127
+#define KVM_CAP_MAX_VCPU_ID 128
+#define KVM_CAP_X2APIC_API 129
+#define KVM_CAP_S390_USER_INSTR0 130
+#define KVM_CAP_MSI_DEVID 131
+#define KVM_CAP_PPC_HTM 132
+#define KVM_CAP_SPAPR_RESIZE_HPT 133
+#define KVM_CAP_PPC_MMU_RADIX 134
+#define KVM_CAP_PPC_MMU_HASH_V3 135
+#define KVM_CAP_IMMEDIATE_EXIT 136
+#define KVM_CAP_MIPS_VZ 137
+#define KVM_CAP_MIPS_TE 138
+#define KVM_CAP_MIPS_64BIT 139
+#define KVM_CAP_S390_GS 140
+#define KVM_CAP_S390_AIS 141
+#define KVM_CAP_SPAPR_TCE_VFIO 142
+#define KVM_CAP_X86_GUEST_MWAIT 143
+#define KVM_CAP_ARM_USER_IRQ 144
+#define KVM_CAP_S390_CMMA_MIGRATION 145
+#define KVM_CAP_PPC_FWNMI 146
+#define KVM_CAP_PPC_SMT_POSSIBLE 147
+#define KVM_CAP_HYPERV_SYNIC2 148
+#define KVM_CAP_HYPERV_VP_INDEX 149
+
+#ifdef KVM_CAP_IRQ_ROUTING
+
+struct kvm_irq_routing_irqchip {
+        __u32 irqchip;
+        __u32 pin;
+};
+
+struct kvm_irq_routing_msi {
+        __u32 address_lo;
+        __u32 address_hi;
+        __u32 data;
+        union {
+                __u32 pad;
+                __u32 devid;
+        };
+};
+
+struct kvm_irq_routing_s390_adapter {
+        __u64 ind_addr;
+        __u64 summary_addr;
+        __u64 ind_offset;
+        __u32 summary_offset;
+        __u32 adapter_id;
+};
+
+struct kvm_irq_routing_hv_sint {
+        __u32 vcpu;
+        __u32 sint;
+};
+
+/* gsi routing entry types */
+#define KVM_IRQ_ROUTING_IRQCHIP 1
+#define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
+
+struct kvm_irq_routing_entry {
+        __u32 gsi;
+        __u32 type;
+        __u32 flags;
+        __u32 pad;
+        union {
+                struct kvm_irq_routing_irqchip irqchip;
+                struct kvm_irq_routing_msi msi;
+                struct kvm_irq_routing_s390_adapter adapter;
+                struct kvm_irq_routing_hv_sint hv_sint;
+                __u32 pad[8];
+        } u;
+};
+
+struct kvm_irq_routing {
+        __u32 nr;
+        __u32 flags;
+        struct kvm_irq_routing_entry entries[0];
+};
+
+#endif
+
+#ifdef KVM_CAP_MCE
+/* x86 MCE */
+struct kvm_x86_mce {
+        __u64 status;
+        __u64 addr;
+        __u64 misc;
+        __u64 mcg_status;
+        __u8 bank;
+        __u8 pad1[7];
+        __u64 pad2[3];
+};
+#endif
+
+#ifdef KVM_CAP_XEN_HVM
+struct kvm_xen_hvm_config {
+        __u32 flags;
+        __u32 msr;
+        __u64 blob_addr_32;
+        __u64 blob_addr_64;
+        __u8 blob_size_32;
+        __u8 blob_size_64;
+        __u8 pad2[30];
+};
+#endif
+
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+/*
+ * Available with KVM_CAP_IRQFD_RESAMPLE
+ *
+ * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
+ * the irqfd to operate in resampling mode for level triggered interrupt
+ * emulation.  See Documentation/virtual/kvm/api.txt.
+ */
+#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
+
+struct kvm_irqfd {
+        __u32 fd;
+        __u32 gsi;
+        __u32 flags;
+        __u32 resamplefd;
+        __u8  pad[16];
+};
+
+/* For KVM_CAP_ADJUST_CLOCK */
+
+/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
+#define KVM_CLOCK_TSC_STABLE            2
+
+struct kvm_clock_data {
+        __u64 clock;
+        __u32 flags;
+        __u32 pad[9];
+};
+
+/* For KVM_CAP_SW_TLB */
+
+#define KVM_MMU_FSL_BOOKE_NOHV          0
+#define KVM_MMU_FSL_BOOKE_HV            1
+
+struct kvm_config_tlb {
+        __u64 params;
+        __u64 array;
+        __u32 mmu_type;
+        __u32 array_len;
+};
+
+struct kvm_dirty_tlb {
+        __u64 bitmap;
+        __u32 num_dirty;
+};
+
+/* Available with KVM_CAP_ONE_REG */
+
+#define KVM_REG_ARCH_MASK       0xff00000000000000ULL
+#define KVM_REG_GENERIC         0x0000000000000000ULL
+
+/*
+ * Architecture specific registers are to be defined in arch headers and
+ * ORed with the arch identifier.
+ */
+#define KVM_REG_PPC             0x1000000000000000ULL
+#define KVM_REG_X86             0x2000000000000000ULL
+#define KVM_REG_IA64            0x3000000000000000ULL
+#define KVM_REG_ARM             0x4000000000000000ULL
+#define KVM_REG_S390            0x5000000000000000ULL
+#define KVM_REG_ARM64           0x6000000000000000ULL
+#define KVM_REG_MIPS            0x7000000000000000ULL
+
+#define KVM_REG_SIZE_SHIFT      52
+#define KVM_REG_SIZE_MASK       0x00f0000000000000ULL
+#define KVM_REG_SIZE_U8         0x0000000000000000ULL
+#define KVM_REG_SIZE_U16        0x0010000000000000ULL
+#define KVM_REG_SIZE_U32        0x0020000000000000ULL
+#define KVM_REG_SIZE_U64        0x0030000000000000ULL
+#define KVM_REG_SIZE_U128       0x0040000000000000ULL
+#define KVM_REG_SIZE_U256       0x0050000000000000ULL
+#define KVM_REG_SIZE_U512       0x0060000000000000ULL
+#define KVM_REG_SIZE_U1024      0x0070000000000000ULL
+
+struct kvm_reg_list {
+        __u64 n; /* number of regs */
+        __u64 reg[0];
+};
+
+struct kvm_one_reg {
+        __u64 id;
+        __u64 addr;
+};
+
+#define KVM_MSI_VALID_DEVID     (1U << 0)
+struct kvm_msi {
+        __u32 address_lo;
+        __u32 address_hi;
+        __u32 data;
+        __u32 flags;
+        __u32 devid;
+        __u8  pad[12];
+};
+
+struct kvm_arm_device_addr {
+        __u64 id;
+        __u64 addr;
+};
+
+/*
+ * Device control API, available with KVM_CAP_DEVICE_CTRL
+ */
+#define KVM_CREATE_DEVICE_TEST          1
+
+struct kvm_create_device {
+        __u32   type;   /* in: KVM_DEV_TYPE_xxx */
+        __u32   fd;     /* out: device handle */
+        __u32   flags;  /* in: KVM_CREATE_DEVICE_xxx */
+};
+
+struct kvm_device_attr {
+        __u32   flags;          /* no flags currently defined */
+        __u32   group;          /* device-defined */
+        __u64   attr;           /* group-defined */
+        __u64   addr;           /* userspace address of attr data */
+};
+
+#define  KVM_DEV_VFIO_GROUP                     1
+#define   KVM_DEV_VFIO_GROUP_ADD                        1
+#define   KVM_DEV_VFIO_GROUP_DEL                        2
+#define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE              3
+
+enum kvm_device_type {
+        KVM_DEV_TYPE_FSL_MPIC_20        = 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20        KVM_DEV_TYPE_FSL_MPIC_20
+        KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42        KVM_DEV_TYPE_FSL_MPIC_42
+        KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS               KVM_DEV_TYPE_XICS
+        KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO               KVM_DEV_TYPE_VFIO
+        KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2        KVM_DEV_TYPE_ARM_VGIC_V2
+        KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC               KVM_DEV_TYPE_FLIC
+        KVM_DEV_TYPE_ARM_VGIC_V3,
+#define KVM_DEV_TYPE_ARM_VGIC_V3        KVM_DEV_TYPE_ARM_VGIC_V3
+        KVM_DEV_TYPE_ARM_VGIC_ITS,
+#define KVM_DEV_TYPE_ARM_VGIC_ITS       KVM_DEV_TYPE_ARM_VGIC_ITS
+        KVM_DEV_TYPE_MAX,
+};
+
+struct kvm_vfio_spapr_tce {
+        __s32   groupfd;
+        __s32   tablefd;
+};
+
+/*
+ * ioctls for VM fds
+ */
+#define KVM_SET_MEMORY_REGION     _IOW(KVMIO,  0x40, struct kvm_memory_region)
+/*
+ * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
+ * a vcpu fd.
+ */
+#define KVM_CREATE_VCPU           _IO(KVMIO,   0x41)
+#define KVM_GET_DIRTY_LOG         _IOW(KVMIO,  0x42, struct kvm_dirty_log)
+/* KVM_SET_MEMORY_ALIAS is obsolete: */
+#define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO,  0x43, struct kvm_memory_alias)
+#define KVM_SET_NR_MMU_PAGES      _IO(KVMIO,   0x44)
+#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)
+#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
+                                        struct kvm_userspace_memory_region)
+#define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
+#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+
+/* enable ucontrol for s390 */
+struct kvm_s390_ucas_mapping {
+        __u64 user_addr;
+        __u64 vcpu_addr;
+        __u64 length;
+};
+#define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
+#define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+#define KVM_S390_VCPU_FAULT      _IOW(KVMIO, 0x52, unsigned long)
+
+/* Device model IOC */
+#define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)
+#define KVM_IRQ_LINE              _IOW(KVMIO,  0x61, struct kvm_irq_level)
+#define KVM_GET_IRQCHIP           _IOWR(KVMIO, 0x62, struct kvm_irqchip)
+#define KVM_SET_IRQCHIP           _IOR(KVMIO,  0x63, struct kvm_irqchip)
+#define KVM_CREATE_PIT            _IO(KVMIO,   0x64)
+#define KVM_GET_PIT               _IOWR(KVMIO, 0x65, struct kvm_pit_state)
+#define KVM_SET_PIT               _IOR(KVMIO,  0x66, struct kvm_pit_state)
+#define KVM_IRQ_LINE_STATUS       _IOWR(KVMIO, 0x67, struct kvm_irq_level)
+#define KVM_REGISTER_COALESCED_MMIO \
+                        _IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
+#define KVM_UNREGISTER_COALESCED_MMIO \
+                        _IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
+#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
+                                       struct kvm_assigned_pci_dev)
+#define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
+/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
+#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
+#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
+#define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
+#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
+                                       struct kvm_assigned_pci_dev)
+#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
+                                       struct kvm_assigned_msix_nr)
+#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
+                                       struct kvm_assigned_msix_entry)
+#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
+#define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
+#define KVM_CREATE_PIT2           _IOW(KVMIO,  0x77, struct kvm_pit_config)
+#define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
+#define KVM_IOEVENTFD             _IOW(KVMIO,  0x79, struct kvm_ioeventfd)
+#define KVM_XEN_HVM_CONFIG        _IOW(KVMIO,  0x7a, struct kvm_xen_hvm_config)
+#define KVM_SET_CLOCK             _IOW(KVMIO,  0x7b, struct kvm_clock_data)
+#define KVM_GET_CLOCK             _IOR(KVMIO,  0x7c, struct kvm_clock_data)
+/* Available with KVM_CAP_PIT_STATE2 */
+#define KVM_GET_PIT2              _IOR(KVMIO,  0x9f, struct kvm_pit_state2)
+#define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
+/* Available with KVM_CAP_PPC_GET_PVINFO */
+#define KVM_PPC_GET_PVINFO        _IOW(KVMIO,  0xa1, struct kvm_ppc_pvinfo)
+/* Available with KVM_CAP_TSC_CONTROL */
+#define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
+#define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
+/* Available with KVM_CAP_PCI_2_3 */
+#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
+                                       struct kvm_assigned_pci_dev)
+/* Available with KVM_CAP_SIGNAL_MSI */
+#define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
+/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
+#define KVM_PPC_GET_SMMU_INFO     _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
+/* Available with KVM_CAP_PPC_ALLOC_HTAB */
+#define KVM_PPC_ALLOCATE_HTAB     _IOWR(KVMIO, 0xa7, __u32)
+#define KVM_CREATE_SPAPR_TCE      _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
+#define KVM_CREATE_SPAPR_TCE_64   _IOW(KVMIO,  0xa8, \
+                                       struct kvm_create_spapr_tce_64)
+/* Available with KVM_CAP_RMA */
+#define KVM_ALLOCATE_RMA          _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD       _IOW(KVMIO,  0xaa, struct kvm_get_htab_fd)
+/* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */
+#define KVM_ARM_SET_DEVICE_ADDR   _IOW(KVMIO,  0xab, struct kvm_arm_device_addr)
+/* Available with KVM_CAP_PPC_RTAS */
+#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO,  0xac, struct kvm_rtas_token_args)
+/* Available with KVM_CAP_SPAPR_RESIZE_HPT */
+#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
+#define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
+/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+#define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
+/* Available with KVM_CAP_PPC_RADIX_MMU */
+#define KVM_PPC_GET_RMMU_INFO     _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
+
+/* ioctl for vm fd */
+#define KVM_CREATE_DEVICE         _IOWR(KVMIO,  0xe0, struct kvm_create_device)
+
+/* ioctls for fds returned by KVM_CREATE_DEVICE */
+#define KVM_SET_DEVICE_ATTR       _IOW(KVMIO,  0xe1, struct kvm_device_attr)
+#define KVM_GET_DEVICE_ATTR       _IOW(KVMIO,  0xe2, struct kvm_device_attr)
+#define KVM_HAS_DEVICE_ATTR       _IOW(KVMIO,  0xe3, struct kvm_device_attr)
+
+/*
+ * ioctls for vcpu fds
+ */
+#define KVM_RUN                   _IO(KVMIO,   0x80)
+#define KVM_GET_REGS              _IOR(KVMIO,  0x81, struct kvm_regs)
+#define KVM_SET_REGS              _IOW(KVMIO,  0x82, struct kvm_regs)
+#define KVM_GET_SREGS             _IOR(KVMIO,  0x83, struct kvm_sregs)
+#define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
+#define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
+#define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
+/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
+#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
+#define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
+#define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
+#define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
+#define KVM_SET_SIGNAL_MASK       _IOW(KVMIO,  0x8b, struct kvm_signal_mask)
+#define KVM_GET_FPU               _IOR(KVMIO,  0x8c, struct kvm_fpu)
+#define KVM_SET_FPU               _IOW(KVMIO,  0x8d, struct kvm_fpu)
+#define KVM_GET_LAPIC             _IOR(KVMIO,  0x8e, struct kvm_lapic_state)
+#define KVM_SET_LAPIC             _IOW(KVMIO,  0x8f, struct kvm_lapic_state)
+#define KVM_SET_CPUID2            _IOW(KVMIO,  0x90, struct kvm_cpuid2)
+#define KVM_GET_CPUID2            _IOWR(KVMIO, 0x91, struct kvm_cpuid2)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_TPR_ACCESS_REPORTING  _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_SET_VAPIC_ADDR        _IOW(KVMIO,  0x93, struct kvm_vapic_addr)
+/* valid for virtual machine (for floating interrupt)_and_ vcpu */
+#define KVM_S390_INTERRUPT        _IOW(KVMIO,  0x94, struct kvm_s390_interrupt)
+/* store status for s390 */
+#define KVM_S390_STORE_STATUS_NOADDR    (-1ul)
+#define KVM_S390_STORE_STATUS_PREFIXED  (-2ul)
+#define KVM_S390_STORE_STATUS     _IOW(KVMIO,  0x95, unsigned long)
+/* initial ipl psw for s390 */
+#define KVM_S390_SET_INITIAL_PSW  _IOW(KVMIO,  0x96, struct kvm_s390_psw)
+/* initial reset for s390 */
+#define KVM_S390_INITIAL_RESET    _IO(KVMIO,   0x97)
+#define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
+#define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
+/* Available with KVM_CAP_USER_NMI */
+#define KVM_NMI                   _IO(KVMIO,   0x9a)
+/* Available with KVM_CAP_SET_GUEST_DEBUG */
+#define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
+/* MCE for x86 */
+#define KVM_X86_SETUP_MCE         _IOW(KVMIO,  0x9c, __u64)
+#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO,  0x9d, __u64)
+#define KVM_X86_SET_MCE           _IOW(KVMIO,  0x9e, struct kvm_x86_mce)
+/* Available with KVM_CAP_VCPU_EVENTS */
+#define KVM_GET_VCPU_EVENTS       _IOR(KVMIO,  0x9f, struct kvm_vcpu_events)
+#define KVM_SET_VCPU_EVENTS       _IOW(KVMIO,  0xa0, struct kvm_vcpu_events)
+/* Available with KVM_CAP_DEBUGREGS */
+#define KVM_GET_DEBUGREGS         _IOR(KVMIO,  0xa1, struct kvm_debugregs)
+#define KVM_SET_DEBUGREGS         _IOW(KVMIO,  0xa2, struct kvm_debugregs)
+/*
+ * vcpu version available with KVM_ENABLE_CAP
+ * vm version available with KVM_CAP_ENABLE_CAP_VM
+ */
+#define KVM_ENABLE_CAP            _IOW(KVMIO,  0xa3, struct kvm_enable_cap)
+/* Available with KVM_CAP_XSAVE */
+#define KVM_GET_XSAVE             _IOR(KVMIO,  0xa4, struct kvm_xsave)
+#define KVM_SET_XSAVE             _IOW(KVMIO,  0xa5, struct kvm_xsave)
+/* Available with KVM_CAP_XCRS */
+#define KVM_GET_XCRS              _IOR(KVMIO,  0xa6, struct kvm_xcrs)
+#define KVM_SET_XCRS              _IOW(KVMIO,  0xa7, struct kvm_xcrs)
+/* Available with KVM_CAP_SW_TLB */
+#define KVM_DIRTY_TLB             _IOW(KVMIO,  0xaa, struct kvm_dirty_tlb)
+/* Available with KVM_CAP_ONE_REG */
+#define KVM_GET_ONE_REG           _IOW(KVMIO,  0xab, struct kvm_one_reg)
+#define KVM_SET_ONE_REG           _IOW(KVMIO,  0xac, struct kvm_one_reg)
+/* VM is being stopped by host */
+#define KVM_KVMCLOCK_CTRL         _IO(KVMIO,   0xad)
+#define KVM_ARM_VCPU_INIT         _IOW(KVMIO,  0xae, struct kvm_vcpu_init)
+#define KVM_ARM_PREFERRED_TARGET  _IOR(KVMIO,  0xaf, struct kvm_vcpu_init)
+#define KVM_GET_REG_LIST          _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
+/* Available with KVM_CAP_S390_MEM_OP */
+#define KVM_S390_MEM_OP           _IOW(KVMIO,  0xb1, struct kvm_s390_mem_op)
+/* Available with KVM_CAP_S390_SKEYS */
+#define KVM_S390_GET_SKEYS      _IOW(KVMIO, 0xb2, struct kvm_s390_skeys)
+#define KVM_S390_SET_SKEYS      _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
+/* Available with KVM_CAP_S390_INJECT_IRQ */
+#define KVM_S390_IRQ              _IOW(KVMIO,  0xb4, struct kvm_s390_irq)
+/* Available with KVM_CAP_S390_IRQ_STATE */
+#define KVM_S390_SET_IRQ_STATE    _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state)
+#define KVM_S390_GET_IRQ_STATE    _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
+/* Available with KVM_CAP_X86_SMM */
+#define KVM_SMI                   _IO(KVMIO,   0xb7)
+/* Available with KVM_CAP_S390_CMMA_MIGRATION */
+#define KVM_S390_GET_CMMA_BITS      _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU     (1 << 0)
+#define KVM_DEV_ASSIGN_PCI_2_3          (1 << 1)
+#define KVM_DEV_ASSIGN_MASK_INTX        (1 << 2)
+
+struct kvm_assigned_pci_dev {
+        __u32 assigned_dev_id;
+        __u32 busnr;
+        __u32 devfn;
+        __u32 flags;
+        __u32 segnr;
+        union {
+                __u32 reserved[11];
+        };
+};
+
+#define KVM_DEV_IRQ_HOST_INTX    (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI     (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX    (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX   (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI    (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX   (1 << 10)
+
+#define KVM_DEV_IRQ_HOST_MASK    0x00ff
+#define KVM_DEV_IRQ_GUEST_MASK   0xff00
+
+struct kvm_assigned_irq {
+        __u32 assigned_dev_id;
+        __u32 host_irq; /* ignored (legacy field) */
+        __u32 guest_irq;
+        __u32 flags;
+        union {
+                __u32 reserved[12];
+        };
+};
+
+struct kvm_assigned_msix_nr {
+        __u32 assigned_dev_id;
+        __u16 entry_nr;
+        __u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV            256
+struct kvm_assigned_msix_entry {
+        __u32 assigned_dev_id;
+        __u32 gsi;
+        __u16 entry; /* The index of entry in the MSI-X table */
+        __u16 padding[3];
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+
+/* Available with KVM_CAP_ARM_USER_IRQ */
+
+/* Bits for run->s.regs.device_irq_level */
+#define KVM_ARM_DEV_EL1_VTIMER          (1 << 0)
+#define KVM_ARM_DEV_EL1_PTIMER          (1 << 1)
+#define KVM_ARM_DEV_PMU                 (1 << 2)
+
+#endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 81d8edf11789..bfd5938fede6 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -1,7 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_MMAN_H
 #define _UAPI_LINUX_MMAN_H
 
-#include <uapi/asm/mman.h>
+#include <asm/mman.h>
+#include <asm-generic/hugetlb_encode.h>
 
 #define MREMAP_MAYMOVE  1
 #define MREMAP_FIXED    2
@@ -10,4 +12,25 @@
 #define OVERCOMMIT_ALWAYS               1
 #define OVERCOMMIT_NEVER                2
 
+/*
+ * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h.
+ * All known huge page size encodings are provided here.  It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system.  See mmap(2) man page for details.
+ */
+#define MAP_HUGE_SHIFT  HUGETLB_FLAG_ENCODE_SHIFT
+#define MAP_HUGE_MASK   HUGETLB_FLAG_ENCODE_MASK
+
+#define MAP_HUGE_64KB   HUGETLB_FLAG_ENCODE_64KB
+#define MAP_HUGE_512KB  HUGETLB_FLAG_ENCODE_512KB
+#define MAP_HUGE_1MB    HUGETLB_FLAG_ENCODE_1MB
+#define MAP_HUGE_2MB    HUGETLB_FLAG_ENCODE_2MB
+#define MAP_HUGE_8MB    HUGETLB_FLAG_ENCODE_8MB
+#define MAP_HUGE_16MB   HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_256MB  HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_1GB    HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB    HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB   HUGETLB_FLAG_ENCODE_16GB
+
 #endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b1c0b187acfe..362493a2f950 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Performance events:
  *
@@ -139,8 +140,9 @@ enum perf_event_sample_format {
         PERF_SAMPLE_IDENTIFIER                  = 1U << 16,
         PERF_SAMPLE_TRANSACTION                 = 1U << 17,
         PERF_SAMPLE_REGS_INTR                   = 1U << 18,
+        PERF_SAMPLE_PHYS_ADDR                   = 1U << 19,
 
-        PERF_SAMPLE_MAX = 1U << 19,             /* non-ABI */
+        PERF_SAMPLE_MAX = 1U << 20,             /* non-ABI */
 };
 
 /*
@@ -174,6 +176,8 @@ enum perf_branch_sample_type_shift {
         PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT       = 14, /* no flags */
         PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT      = 15, /* no cycles */
 
+        PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT      = 16, /* save branch type */
+
         PERF_SAMPLE_BRANCH_MAX_SHIFT            /* non-ABI */
 };
 
@@ -198,9 +202,30 @@ enum perf_branch_sample_type {
         PERF_SAMPLE_BRANCH_NO_FLAGS     = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
         PERF_SAMPLE_BRANCH_NO_CYCLES    = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
 
+        PERF_SAMPLE_BRANCH_TYPE_SAVE    =
+                1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
+
         PERF_SAMPLE_BRANCH_MAX          = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
+/*
+ * Common flow change classification
+ */
+enum {
+        PERF_BR_UNKNOWN         = 0,    /* unknown */
+        PERF_BR_COND            = 1,    /* conditional */
+        PERF_BR_UNCOND          = 2,    /* unconditional  */
+        PERF_BR_IND             = 3,    /* indirect */
+        PERF_BR_CALL            = 4,    /* function call */
+        PERF_BR_IND_CALL        = 5,    /* indirect function call */
+        PERF_BR_RET             = 6,    /* function return */
+        PERF_BR_SYSCALL         = 7,    /* syscall */
+        PERF_BR_SYSRET          = 8,    /* syscall return */
+        PERF_BR_COND_CALL       = 9,    /* conditional function call */
+        PERF_BR_COND_RET        = 10,   /* conditional function return */
+        PERF_BR_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
         (PERF_SAMPLE_BRANCH_USER|\
          PERF_SAMPLE_BRANCH_KERNEL|\
@@ -791,6 +816,7 @@ enum perf_event_type {
          *      { u64                   transaction; } && PERF_SAMPLE_TRANSACTION
          *      { u64                   abi; # enum perf_sample_regs_abi
          *        u64                   regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+         *      { u64                   phys_addr;} && PERF_SAMPLE_PHYS_ADDR
          * };
          */
         PERF_RECORD_SAMPLE                      = 9,
@@ -931,14 +957,20 @@ union perf_mem_data_src {
                         mem_snoop:5,    /* snoop mode */
                         mem_lock:2,     /* lock instr */
                         mem_dtlb:7,     /* tlb access */
-                        mem_rsvd:31;
+                        mem_lvl_num:4,  /* memory hierarchy level number */
+                        mem_remote:1,   /* remote */
+                        mem_snoopx:2,   /* snoop mode, ext */
+                        mem_rsvd:24;
         };
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
         __u64 val;
         struct {
-                __u64   mem_rsvd:31,
+                __u64   mem_rsvd:24,
+                        mem_snoopx:2,   /* snoop mode, ext */
+                        mem_remote:1,   /* remote */
+                        mem_lvl_num:4,  /* memory hierarchy level number */
                         mem_dtlb:7,     /* tlb access */
                         mem_lock:2,     /* lock instr */
                         mem_snoop:5,    /* snoop mode */
@@ -975,6 +1007,22 @@ union perf_mem_data_src {
 #define PERF_MEM_LVL_UNC        0x2000 /* Uncached memory */
 #define PERF_MEM_LVL_SHIFT      5
 
+#define PERF_MEM_REMOTE_REMOTE  0x01  /* Remote */
+#define PERF_MEM_REMOTE_SHIFT   37
+
+#define PERF_MEM_LVLNUM_L1      0x01 /* L1 */
+#define PERF_MEM_LVLNUM_L2      0x02 /* L2 */
+#define PERF_MEM_LVLNUM_L3      0x03 /* L3 */
+#define PERF_MEM_LVLNUM_L4      0x04 /* L4 */
+/* 5-0xa available */
+#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
+#define PERF_MEM_LVLNUM_LFB     0x0c /* LFB */
+#define PERF_MEM_LVLNUM_RAM     0x0d /* RAM */
+#define PERF_MEM_LVLNUM_PMEM    0x0e /* PMEM */
+#define PERF_MEM_LVLNUM_NA      0x0f /* N/A */
+
+#define PERF_MEM_LVLNUM_SHIFT   33
+
 /* snoop mode */
 #define PERF_MEM_SNOOP_NA       0x01 /* not available */
 #define PERF_MEM_SNOOP_NONE     0x02 /* no snoop */
@@ -983,6 +1031,10 @@ union perf_mem_data_src {
 #define PERF_MEM_SNOOP_HITM     0x10 /* snoop hit modified */
 #define PERF_MEM_SNOOP_SHIFT    19
 
+#define PERF_MEM_SNOOPX_FWD     0x01 /* forward */
+/* 1 free */
+#define PERF_MEM_SNOOPX_SHIFT   37
+
 /* locked instruction */
 #define PERF_MEM_LOCK_NA        0x01 /* not available */
 #define PERF_MEM_LOCK_LOCKED    0x02 /* locked transaction */
@@ -1015,6 +1067,7 @@ union perf_mem_data_src {
  *     in_tx: running in a hardware transaction
  *     abort: aborting a hardware transaction
  *    cycles: cycles from last branch (or 0 if not supported)
+ *      type: branch type
  */
 struct perf_branch_entry {
         __u64   from;
@@ -1024,7 +1077,8 @@ struct perf_branch_entry {
                 in_tx:1,    /* in transaction */
                 abort:1,    /* transaction abort */
                 cycles:16,  /* cycle count to last branch */
-                reserved:44;
+                type:4,     /* branch type */
+                reserved:40;
 };
 
 #endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
new file mode 100644
index 000000000000..a8d0759a9e40
--- /dev/null
+++ b/tools/include/uapi/linux/prctl.h
@@ -0,0 +1,200 @@
+#ifndef _LINUX_PRCTL_H
+#define _LINUX_PRCTL_H
+
+#include <linux/types.h>
+
+/* Values to pass as first argument to prctl() */
+
+#define PR_SET_PDEATHSIG  1  /* Second arg is a signal */
+#define PR_GET_PDEATHSIG  2  /* Second arg is a ptr to return the signal */
+
+/* Get/set current->mm->dumpable */
+#define PR_GET_DUMPABLE   3
+#define PR_SET_DUMPABLE   4
+
+/* Get/set unaligned access control bits (if meaningful) */
+#define PR_GET_UNALIGN    5
+#define PR_SET_UNALIGN    6
+# define PR_UNALIGN_NOPRINT     1       /* silently fix up unaligned user accesses */
+# define PR_UNALIGN_SIGBUS      2       /* generate SIGBUS on unaligned user access */
+
+/* Get/set whether or not to drop capabilities on setuid() away from
+ * uid 0 (as per security/commoncap.c) */
+#define PR_GET_KEEPCAPS   7
+#define PR_SET_KEEPCAPS   8
+
+/* Get/set floating-point emulation control bits (if meaningful) */
+#define PR_GET_FPEMU  9
+#define PR_SET_FPEMU 10
+# define PR_FPEMU_NOPRINT       1       /* silently emulate fp operations accesses */
+# define PR_FPEMU_SIGFPE        2       /* don't emulate fp operations, send SIGFPE instead */
+
+/* Get/set floating-point exception mode (if meaningful) */
+#define PR_GET_FPEXC    11
+#define PR_SET_FPEXC    12
+# define PR_FP_EXC_SW_ENABLE    0x80    /* Use FPEXC for FP exception enables */
+# define PR_FP_EXC_DIV          0x010000        /* floating point divide by zero */
+# define PR_FP_EXC_OVF          0x020000        /* floating point overflow */
+# define PR_FP_EXC_UND          0x040000        /* floating point underflow */
+# define PR_FP_EXC_RES          0x080000        /* floating point inexact result */
+# define PR_FP_EXC_INV          0x100000        /* floating point invalid operation */
+# define PR_FP_EXC_DISABLED     0       /* FP exceptions disabled */
+# define PR_FP_EXC_NONRECOV     1       /* async non-recoverable exc. mode */
+# define PR_FP_EXC_ASYNC        2       /* async recoverable exception mode */
+# define PR_FP_EXC_PRECISE      3       /* precise exception mode */
+
+/* Get/set whether we use statistical process timing or accurate timestamp
+ * based process timing */
+#define PR_GET_TIMING   13
+#define PR_SET_TIMING   14
+# define PR_TIMING_STATISTICAL  0       /* Normal, traditional,
+                                                   statistical process timing */
+# define PR_TIMING_TIMESTAMP    1       /* Accurate timestamp based
+                                                   process timing */
+
+#define PR_SET_NAME    15               /* Set process name */
+#define PR_GET_NAME    16               /* Get process name */
+
+/* Get/set process endian */
+#define PR_GET_ENDIAN   19
+#define PR_SET_ENDIAN   20
+# define PR_ENDIAN_BIG          0
+# define PR_ENDIAN_LITTLE       1       /* True little endian mode */
+# define PR_ENDIAN_PPC_LITTLE   2       /* "PowerPC" pseudo little endian */
+
+/* Get/set process seccomp mode */
+#define PR_GET_SECCOMP  21
+#define PR_SET_SECCOMP  22
+
+/* Get/set the capability bounding set (as per security/commoncap.c) */
+#define PR_CAPBSET_READ 23
+#define PR_CAPBSET_DROP 24
+
+/* Get/set the process' ability to use the timestamp counter instruction */
+#define PR_GET_TSC 25
+#define PR_SET_TSC 26
+# define PR_TSC_ENABLE          1       /* allow the use of the timestamp counter */
+# define PR_TSC_SIGSEGV         2       /* throw a SIGSEGV instead of reading the TSC */
+
+/* Get/set securebits (as per security/commoncap.c) */
+#define PR_GET_SECUREBITS 27
+#define PR_SET_SECUREBITS 28
+
+/*
+ * Get/set the timerslack as used by poll/select/nanosleep
+ * A value of 0 means "use default"
+ */
+#define PR_SET_TIMERSLACK 29
+#define PR_GET_TIMERSLACK 30
+
+#define PR_TASK_PERF_EVENTS_DISABLE             31
+#define PR_TASK_PERF_EVENTS_ENABLE              32
+
+/*
+ * Set early/late kill mode for hwpoison memory corruption.
+ * This influences when the process gets killed on a memory corruption.
+ */
+#define PR_MCE_KILL     33
+# define PR_MCE_KILL_CLEAR   0
+# define PR_MCE_KILL_SET     1
+
+# define PR_MCE_KILL_LATE    0
+# define PR_MCE_KILL_EARLY   1
+# define PR_MCE_KILL_DEFAULT 2
+
+#define PR_MCE_KILL_GET 34
+
+/*
+ * Tune up process memory map specifics.
+ */
+#define PR_SET_MM               35
+# define PR_SET_MM_START_CODE           1
+# define PR_SET_MM_END_CODE             2
+# define PR_SET_MM_START_DATA           3
+# define PR_SET_MM_END_DATA             4
+# define PR_SET_MM_START_STACK          5
+# define PR_SET_MM_START_BRK            6
+# define PR_SET_MM_BRK                  7
+# define PR_SET_MM_ARG_START            8
+# define PR_SET_MM_ARG_END              9
+# define PR_SET_MM_ENV_START            10
+# define PR_SET_MM_ENV_END              11
+# define PR_SET_MM_AUXV                 12
+# define PR_SET_MM_EXE_FILE             13
+# define PR_SET_MM_MAP                  14
+# define PR_SET_MM_MAP_SIZE             15
+
+/*
+ * This structure provides new memory descriptor
+ * map which mostly modifies /proc/pid/stat[m]
+ * output for a task. This mostly done in a
+ * sake of checkpoint/restore functionality.
+ */
+struct prctl_mm_map {
+        __u64   start_code;             /* code section bounds */
+        __u64   end_code;
+        __u64   start_data;             /* data section bounds */
+        __u64   end_data;
+        __u64   start_brk;              /* heap for brk() syscall */
+        __u64   brk;
+        __u64   start_stack;            /* stack starts at */
+        __u64   arg_start;              /* command line arguments bounds */
+        __u64   arg_end;
+        __u64   env_start;              /* environment variables bounds */
+        __u64   env_end;
+        __u64   *auxv;                  /* auxiliary vector */
+        __u32   auxv_size;              /* vector size */
+        __u32   exe_fd;                 /* /proc/$pid/exe link file */
+};
+
+/*
+ * Set specific pid that is allowed to ptrace the current task.
+ * A value of 0 mean "no process".
+ */
+#define PR_SET_PTRACER 0x59616d61
+# define PR_SET_PTRACER_ANY ((unsigned long)-1)
+
+#define PR_SET_CHILD_SUBREAPER  36
+#define PR_GET_CHILD_SUBREAPER  37
+
+/*
+ * If no_new_privs is set, then operations that grant new privileges (i.e.
+ * execve) will either fail or not grant them.  This affects suid/sgid,
+ * file capabilities, and LSMs.
+ *
+ * Operations that merely manipulate or drop existing privileges (setresuid,
+ * capset, etc.) will still work.  Drop those privileges if you want them gone.
+ *
+ * Changing LSM security domain is considered a new privilege.  So, for example,
+ * asking selinux for a specific new context (e.g. with runcon) will result
+ * in execve returning -EPERM.
+ *
+ * See Documentation/prctl/no_new_privs.txt for more details.
+ */
+#define PR_SET_NO_NEW_PRIVS     38
+#define PR_GET_NO_NEW_PRIVS     39
+
+#define PR_GET_TID_ADDRESS      40
+
+#define PR_SET_THP_DISABLE      41
+#define PR_GET_THP_DISABLE      42
+
+/*
+ * Tell the kernel to start/stop helping userspace manage bounds tables.
+ */
+#define PR_MPX_ENABLE_MANAGEMENT  43
+#define PR_MPX_DISABLE_MANAGEMENT 44
+
+#define PR_SET_FP_MODE          45
+#define PR_GET_FP_MODE          46
+# define PR_FP_MODE_FR          (1 << 0)        /* 64b FP registers */
+# define PR_FP_MODE_FRE         (1 << 1)        /* 32b compatibility */
+
+/* Control the ambient capability set */
+#define PR_CAP_AMBIENT                  47
+# define PR_CAP_AMBIENT_IS_SET          1
+# define PR_CAP_AMBIENT_RAISE           2
+# define PR_CAP_AMBIENT_LOWER           3
+# define PR_CAP_AMBIENT_CLEAR_ALL       4
+
+#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
new file mode 100644
index 000000000000..30a9e51bbb1e
--- /dev/null
+++ b/tools/include/uapi/linux/sched.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SCHED_H
+#define _UAPI_LINUX_SCHED_H
+
+/*
+ * cloning flags:
+ */
+#define CSIGNAL         0x000000ff      /* signal mask to be sent at exit */
+#define CLONE_VM        0x00000100      /* set if VM shared between processes */
+#define CLONE_FS        0x00000200      /* set if fs info shared between processes */
+#define CLONE_FILES     0x00000400      /* set if open files shared between processes */
+#define CLONE_SIGHAND   0x00000800      /* set if signal handlers and blocked signals shared */
+#define CLONE_PTRACE    0x00002000      /* set if we want to let tracing continue on the child too */
+#define CLONE_VFORK     0x00004000      /* set if the parent wants the child to wake it up on mm_release */
+#define CLONE_PARENT    0x00008000      /* set if we want to have the same parent as the cloner */
+#define CLONE_THREAD    0x00010000      /* Same thread group? */
+#define CLONE_NEWNS     0x00020000      /* New mount namespace group */
+#define CLONE_SYSVSEM   0x00040000      /* share system V SEM_UNDO semantics */
+#define CLONE_SETTLS    0x00080000      /* create a new TLS for the child */
+#define CLONE_PARENT_SETTID     0x00100000      /* set the TID in the parent */
+#define CLONE_CHILD_CLEARTID    0x00200000      /* clear the TID in the child */
+#define CLONE_DETACHED          0x00400000      /* Unused, ignored */
+#define CLONE_UNTRACED          0x00800000      /* set if the tracing process can't force CLONE_PTRACE on this clone */
+#define CLONE_CHILD_SETTID      0x01000000      /* set the TID in the child */
+#define CLONE_NEWCGROUP         0x02000000      /* New cgroup namespace */
+#define CLONE_NEWUTS            0x04000000      /* New utsname namespace */
+#define CLONE_NEWIPC            0x08000000      /* New ipc namespace */
+#define CLONE_NEWUSER           0x10000000      /* New user namespace */
+#define CLONE_NEWPID            0x20000000      /* New pid namespace */
+#define CLONE_NEWNET            0x40000000      /* New network namespace */
+#define CLONE_IO                0x80000000      /* Clone io context */
+
+/*
+ * Scheduling policies
+ */
+#define SCHED_NORMAL            0
+#define SCHED_FIFO              1
+#define SCHED_RR                2
+#define SCHED_BATCH             3
+/* SCHED_ISO: reserved but not implemented yet */
+#define SCHED_IDLE              5
+#define SCHED_DEADLINE          6
+
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK     0x40000000
+
+/*
+ * For the sched_{set,get}attr() calls
+ */
+#define SCHED_FLAG_RESET_ON_FORK        0x01
+#define SCHED_FLAG_RECLAIM              0x02
+
+#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 17b10304c393..7b35e98d3c58 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_STAT_H
 #define _UAPI_LINUX_STAT_H
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
new file mode 100644
index 000000000000..c51f8e5cc608
--- /dev/null
+++ b/tools/include/uapi/linux/vhost.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_vring_state {
+        unsigned int index;
+        unsigned int num;
+};
+
+struct vhost_vring_file {
+        unsigned int index;
+        int fd; /* Pass -1 to unbind from file. */
+
+};
+
+struct vhost_vring_addr {
+        unsigned int index;
+        /* Option flags. */
+        unsigned int flags;
+        /* Flag values: */
+        /* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+        /* Start of array of descriptors (virtually contiguous) */
+        __u64 desc_user_addr;
+        /* Used structure address. Must be 32 bit aligned */
+        __u64 used_user_addr;
+        /* Available structure address. Must be 16 bit aligned */
+        __u64 avail_user_addr;
+        /* Logging support. */
+        /* Log writes to used structure, at offset calculated from specified
+         * address. Address must be 32 bit aligned. */
+        __u64 log_guest_addr;
+};
+
+/* no alignment requirement */
+struct vhost_iotlb_msg {
+        __u64 iova;
+        __u64 size;
+        __u64 uaddr;
+#define VHOST_ACCESS_RO      0x1
+#define VHOST_ACCESS_WO      0x2
+#define VHOST_ACCESS_RW      0x3
+        __u8 perm;
+#define VHOST_IOTLB_MISS           1
+#define VHOST_IOTLB_UPDATE         2
+#define VHOST_IOTLB_INVALIDATE     3
+#define VHOST_IOTLB_ACCESS_FAIL    4
+        __u8 type;
+};
+
+#define VHOST_IOTLB_MSG 0x1
+
+struct vhost_msg {
+        int type;
+        union {
+                struct vhost_iotlb_msg iotlb;
+                __u8 padding[64];
+        };
+};
+
+struct vhost_memory_region {
+        __u64 guest_phys_addr;
+        __u64 memory_size; /* bytes */
+        __u64 userspace_addr;
+        __u64 flags_padding; /* No flags are currently specified. */
+};
+
+/* All region addresses and sizes must be 4K aligned. */
+#define VHOST_PAGE_SIZE 0x1000
+
+struct vhost_memory {
+        __u32 nregions;
+        __u32 padding;
+        struct vhost_memory_region regions[0];
+};
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility.  Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES      _IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES      _IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor.  This
+ * must be called before any other vhost command.  Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE     _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
+ * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
+ * The byte order cannot be changed while the device is active: trying to do so
+ * returns -EBUSY.
+ * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
+ * set.
+ * Not all kernel configurations support this ioctl, but all configurations that
+ * support SET also support GET.
+ */
+#define VHOST_VRING_LITTLE_ENDIAN 0
+#define VHOST_VRING_BIG_ENDIAN 1
+#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
+#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+/* Set busy loop timeout (in us) */
+#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23,       \
+                                         struct vhost_vring_state)
+/* Get busy loop timeout (in us) */
+#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,       \
+                                         struct vhost_vring_state)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit.  Pass fd -1 to unbind from the socket and the transmit
+ * device.  This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* Feature bits */
+/* Log all write descriptors. Can be changed while device is active. */
+#define VHOST_F_LOG_ALL 26
+/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
+#define VHOST_NET_F_VIRTIO_NET_HDR 27
+
+/* VHOST_SCSI specific definitions */
+
+/*
+ * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
+ *
+ * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
+ *            RFC-v2 vhost-scsi userspace.  Add GET_ABI_VERSION ioctl usage
+ * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
+ *            All the targets under vhost_wwpn can be seen and used by guset.
+ */
+
+#define VHOST_SCSI_ABI_VERSION  1
+
+struct vhost_scsi_target {
+        int abi_version;
+        char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
+        unsigned short vhost_tpgt;
+        unsigned short reserved;
+};
+
+#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
+#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
+/* Changing this breaks userspace. */
+#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
+/* Set and get the events missed flag */
+#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
+#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
+
+/* VHOST_VSOCK specific defines */
+
+#define VHOST_VSOCK_SET_GUEST_CID       _IOW(VHOST_VIRTIO, 0x60, __u64)
+#define VHOST_VSOCK_SET_RUNNING         _IOW(VHOST_VIRTIO, 0x61, int)
+
+#endif
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
new file mode 100644
index 000000000000..c227ccba60ae
--- /dev/null
+++ b/tools/include/uapi/sound/asound.h
@@ -0,0 +1,1027 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  Advanced Linux Sound Architecture - ALSA - Driver
+ *  Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>,
+ *                             Abramo Bagnara <abramo@alsa-project.org>
+ *
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+
+#ifndef _UAPI__SOUND_ASOUND_H
+#define _UAPI__SOUND_ASOUND_H
+
+#if defined(__KERNEL__) || defined(__linux__)
+#include <linux/types.h>
+#else
+#include <sys/ioctl.h>
+#endif
+
+#ifndef __KERNEL__
+#include <stdlib.h>
+#endif
+
+/*
+ *  protocol version
+ */
+
+#define SNDRV_PROTOCOL_VERSION(major, minor, subminor) (((major)<<16)|((minor)<<8)|(subminor))
+#define SNDRV_PROTOCOL_MAJOR(version) (((version)>>16)&0xffff)
+#define SNDRV_PROTOCOL_MINOR(version) (((version)>>8)&0xff)
+#define SNDRV_PROTOCOL_MICRO(version) ((version)&0xff)
+#define SNDRV_PROTOCOL_INCOMPATIBLE(kversion, uversion) \
+        (SNDRV_PROTOCOL_MAJOR(kversion) != SNDRV_PROTOCOL_MAJOR(uversion) || \
+         (SNDRV_PROTOCOL_MAJOR(kversion) == SNDRV_PROTOCOL_MAJOR(uversion) && \
+           SNDRV_PROTOCOL_MINOR(kversion) != SNDRV_PROTOCOL_MINOR(uversion)))
+
+/****************************************************************************
+ *                                                                          *
+ *        Digital audio interface                                           *
+ *                                                                          *
+ ****************************************************************************/
+
+struct snd_aes_iec958 {
+        unsigned char status[24];       /* AES/IEC958 channel status bits */
+        unsigned char subcode[147];     /* AES/IEC958 subcode bits */
+        unsigned char pad;              /* nothing */
+        unsigned char dig_subframe[4];  /* AES/IEC958 subframe bits */
+};
+
+/****************************************************************************
+ *                                                                          *
+ *        CEA-861 Audio InfoFrame. Used in HDMI and DisplayPort             *
+ *                                                                          *
+ ****************************************************************************/
+
+struct snd_cea_861_aud_if {
+        unsigned char db1_ct_cc; /* coding type and channel count */
+        unsigned char db2_sf_ss; /* sample frequency and size */
+        unsigned char db3; /* not used, all zeros */
+        unsigned char db4_ca; /* channel allocation code */
+        unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */
+};
+
+/****************************************************************************
+ *                                                                          *
+ *      Section for driver hardware dependent interface - /dev/snd/hw?      *
+ *                                                                          *
+ ****************************************************************************/
+
+#define SNDRV_HWDEP_VERSION             SNDRV_PROTOCOL_VERSION(1, 0, 1)
+
+enum {
+        SNDRV_HWDEP_IFACE_OPL2 = 0,
+        SNDRV_HWDEP_IFACE_OPL3,
+        SNDRV_HWDEP_IFACE_OPL4,
+        SNDRV_HWDEP_IFACE_SB16CSP,      /* Creative Signal Processor */
+        SNDRV_HWDEP_IFACE_EMU10K1,      /* FX8010 processor in EMU10K1 chip */
+        SNDRV_HWDEP_IFACE_YSS225,       /* Yamaha FX processor */
+        SNDRV_HWDEP_IFACE_ICS2115,      /* Wavetable synth */
+        SNDRV_HWDEP_IFACE_SSCAPE,       /* Ensoniq SoundScape ISA card (MC68EC000) */
+        SNDRV_HWDEP_IFACE_VX,           /* Digigram VX cards */
+        SNDRV_HWDEP_IFACE_MIXART,       /* Digigram miXart cards */
+        SNDRV_HWDEP_IFACE_USX2Y,        /* Tascam US122, US224 & US428 usb */
+        SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */
+        SNDRV_HWDEP_IFACE_BLUETOOTH,    /* Bluetooth audio */
+        SNDRV_HWDEP_IFACE_USX2Y_PCM,    /* Tascam US122, US224 & US428 rawusb pcm */
+        SNDRV_HWDEP_IFACE_PCXHR,        /* Digigram PCXHR */
+        SNDRV_HWDEP_IFACE_SB_RC,        /* SB Extigy/Audigy2NX remote control */
+        SNDRV_HWDEP_IFACE_HDA,          /* HD-audio */
+        SNDRV_HWDEP_IFACE_USB_STREAM,   /* direct access to usb stream */
+        SNDRV_HWDEP_IFACE_FW_DICE,      /* TC DICE FireWire device */
+        SNDRV_HWDEP_IFACE_FW_FIREWORKS, /* Echo Audio Fireworks based device */
+        SNDRV_HWDEP_IFACE_FW_BEBOB,     /* BridgeCo BeBoB based device */
+        SNDRV_HWDEP_IFACE_FW_OXFW,      /* Oxford OXFW970/971 based device */
+        SNDRV_HWDEP_IFACE_FW_DIGI00X,   /* Digidesign Digi 002/003 family */
+        SNDRV_HWDEP_IFACE_FW_TASCAM,    /* TASCAM FireWire series */
+        SNDRV_HWDEP_IFACE_LINE6,        /* Line6 USB processors */
+        SNDRV_HWDEP_IFACE_FW_MOTU,      /* MOTU FireWire series */
+        SNDRV_HWDEP_IFACE_FW_FIREFACE,  /* RME Fireface series */
+
+        /* Don't forget to change the following: */
+        SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_FIREFACE
+};
+
+struct snd_hwdep_info {
+        unsigned int device;            /* WR: device number */
+        int card;                       /* R: card number */
+        unsigned char id[64];           /* ID (user selectable) */
+        unsigned char name[80];         /* hwdep name */
+        int iface;                      /* hwdep interface */
+        unsigned char reserved[64];     /* reserved for future */
+};
+
+/* generic DSP loader */
+struct snd_hwdep_dsp_status {
+        unsigned int version;           /* R: driver-specific version */
+        unsigned char id[32];           /* R: driver-specific ID string */
+        unsigned int num_dsps;          /* R: number of DSP images to transfer */
+        unsigned int dsp_loaded;        /* R: bit flags indicating the loaded DSPs */
+        unsigned int chip_ready;        /* R: 1 = initialization finished */
+        unsigned char reserved[16];     /* reserved for future use */
+};
+
+struct snd_hwdep_dsp_image {
+        unsigned int index;             /* W: DSP index */
+        unsigned char name[64];         /* W: ID (e.g. file name) */
+        unsigned char __user *image;    /* W: binary image */
+        size_t length;                  /* W: size of image in bytes */
+        unsigned long driver_data;      /* W: driver-specific data */
+};
+
+#define SNDRV_HWDEP_IOCTL_PVERSION      _IOR ('H', 0x00, int)
+#define SNDRV_HWDEP_IOCTL_INFO          _IOR ('H', 0x01, struct snd_hwdep_info)
+#define SNDRV_HWDEP_IOCTL_DSP_STATUS    _IOR('H', 0x02, struct snd_hwdep_dsp_status)
+#define SNDRV_HWDEP_IOCTL_DSP_LOAD      _IOW('H', 0x03, struct snd_hwdep_dsp_image)
+
+/*****************************************************************************
+ *                                                                           *
+ *             Digital Audio (PCM) interface - /dev/snd/pcm??                *
+ *                                                                           *
+ *****************************************************************************/
+
+#define SNDRV_PCM_VERSION               SNDRV_PROTOCOL_VERSION(2, 0, 14)
+
+typedef unsigned long snd_pcm_uframes_t;
+typedef signed long snd_pcm_sframes_t;
+
+enum {
+        SNDRV_PCM_CLASS_GENERIC = 0,    /* standard mono or stereo device */
+        SNDRV_PCM_CLASS_MULTI,          /* multichannel device */
+        SNDRV_PCM_CLASS_MODEM,          /* software modem class */
+        SNDRV_PCM_CLASS_DIGITIZER,      /* digitizer class */
+        /* Don't forget to change the following: */
+        SNDRV_PCM_CLASS_LAST = SNDRV_PCM_CLASS_DIGITIZER,
+};
+
+enum {
+        SNDRV_PCM_SUBCLASS_GENERIC_MIX = 0, /* mono or stereo subdevices are mixed together */
+        SNDRV_PCM_SUBCLASS_MULTI_MIX,   /* multichannel subdevices are mixed together */
+        /* Don't forget to change the following: */
+        SNDRV_PCM_SUBCLASS_LAST = SNDRV_PCM_SUBCLASS_MULTI_MIX,
+};
+
+enum {
+        SNDRV_PCM_STREAM_PLAYBACK = 0,
+        SNDRV_PCM_STREAM_CAPTURE,
+        SNDRV_PCM_STREAM_LAST = SNDRV_PCM_STREAM_CAPTURE,
+};
+
+typedef int __bitwise snd_pcm_access_t;
+#define SNDRV_PCM_ACCESS_MMAP_INTERLEAVED       ((__force snd_pcm_access_t) 0) /* interleaved mmap */
+#define SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED    ((__force snd_pcm_access_t) 1) /* noninterleaved mmap */
+#define SNDRV_PCM_ACCESS_MMAP_COMPLEX           ((__force snd_pcm_access_t) 2) /* complex mmap */
+#define SNDRV_PCM_ACCESS_RW_INTERLEAVED         ((__force snd_pcm_access_t) 3) /* readi/writei */
+#define SNDRV_PCM_ACCESS_RW_NONINTERLEAVED      ((__force snd_pcm_access_t) 4) /* readn/writen */
+#define SNDRV_PCM_ACCESS_LAST           SNDRV_PCM_ACCESS_RW_NONINTERLEAVED
+
+typedef int __bitwise snd_pcm_format_t;
+#define SNDRV_PCM_FORMAT_S8     ((__force snd_pcm_format_t) 0)
+#define SNDRV_PCM_FORMAT_U8     ((__force snd_pcm_format_t) 1)
+#define SNDRV_PCM_FORMAT_S16_LE ((__force snd_pcm_format_t) 2)
+#define SNDRV_PCM_FORMAT_S16_BE ((__force snd_pcm_format_t) 3)
+#define SNDRV_PCM_FORMAT_U16_LE ((__force snd_pcm_format_t) 4)
+#define SNDRV_PCM_FORMAT_U16_BE ((__force snd_pcm_format_t) 5)
+#define SNDRV_PCM_FORMAT_S24_LE ((__force snd_pcm_format_t) 6) /* low three bytes */
+#define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */
+#define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */
+#define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */
+#define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10)
+#define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11)
+#define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12)
+#define SNDRV_PCM_FORMAT_U32_BE ((__force snd_pcm_format_t) 13)
+#define SNDRV_PCM_FORMAT_FLOAT_LE       ((__force snd_pcm_format_t) 14) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_FLOAT_BE       ((__force snd_pcm_format_t) 15) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_FLOAT64_LE     ((__force snd_pcm_format_t) 16) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_FLOAT64_BE     ((__force snd_pcm_format_t) 17) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE ((__force snd_pcm_format_t) 18) /* IEC-958 subframe, Little Endian */
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE ((__force snd_pcm_format_t) 19) /* IEC-958 subframe, Big Endian */
+#define SNDRV_PCM_FORMAT_MU_LAW         ((__force snd_pcm_format_t) 20)
+#define SNDRV_PCM_FORMAT_A_LAW          ((__force snd_pcm_format_t) 21)
+#define SNDRV_PCM_FORMAT_IMA_ADPCM      ((__force snd_pcm_format_t) 22)
+#define SNDRV_PCM_FORMAT_MPEG           ((__force snd_pcm_format_t) 23)
+#define SNDRV_PCM_FORMAT_GSM            ((__force snd_pcm_format_t) 24)
+#define SNDRV_PCM_FORMAT_SPECIAL        ((__force snd_pcm_format_t) 31)
+#define SNDRV_PCM_FORMAT_S24_3LE        ((__force snd_pcm_format_t) 32) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S24_3BE        ((__force snd_pcm_format_t) 33) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U24_3LE        ((__force snd_pcm_format_t) 34) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U24_3BE        ((__force snd_pcm_format_t) 35) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S20_3LE        ((__force snd_pcm_format_t) 36) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S20_3BE        ((__force snd_pcm_format_t) 37) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U20_3LE        ((__force snd_pcm_format_t) 38) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U20_3BE        ((__force snd_pcm_format_t) 39) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S18_3LE        ((__force snd_pcm_format_t) 40) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S18_3BE        ((__force snd_pcm_format_t) 41) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U18_3LE        ((__force snd_pcm_format_t) 42) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U18_3BE        ((__force snd_pcm_format_t) 43) /* in three bytes */
+#define SNDRV_PCM_FORMAT_G723_24        ((__force snd_pcm_format_t) 44) /* 8 samples in 3 bytes */
+#define SNDRV_PCM_FORMAT_G723_24_1B     ((__force snd_pcm_format_t) 45) /* 1 sample in 1 byte */
+#define SNDRV_PCM_FORMAT_G723_40        ((__force snd_pcm_format_t) 46) /* 8 Samples in 5 bytes */
+#define SNDRV_PCM_FORMAT_G723_40_1B     ((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */
+#define SNDRV_PCM_FORMAT_DSD_U8         ((__force snd_pcm_format_t) 48) /* DSD, 1-byte samples DSD (x8) */
+#define SNDRV_PCM_FORMAT_DSD_U16_LE     ((__force snd_pcm_format_t) 49) /* DSD, 2-byte samples DSD (x16), little endian */
+#define SNDRV_PCM_FORMAT_DSD_U32_LE     ((__force snd_pcm_format_t) 50) /* DSD, 4-byte samples DSD (x32), little endian */
+#define SNDRV_PCM_FORMAT_DSD_U16_BE     ((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */
+#define SNDRV_PCM_FORMAT_DSD_U32_BE     ((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */
+#define SNDRV_PCM_FORMAT_LAST           SNDRV_PCM_FORMAT_DSD_U32_BE
+
+#ifdef SNDRV_LITTLE_ENDIAN
+#define SNDRV_PCM_FORMAT_S16            SNDRV_PCM_FORMAT_S16_LE
+#define SNDRV_PCM_FORMAT_U16            SNDRV_PCM_FORMAT_U16_LE
+#define SNDRV_PCM_FORMAT_S24            SNDRV_PCM_FORMAT_S24_LE
+#define SNDRV_PCM_FORMAT_U24            SNDRV_PCM_FORMAT_U24_LE
+#define SNDRV_PCM_FORMAT_S32            SNDRV_PCM_FORMAT_S32_LE
+#define SNDRV_PCM_FORMAT_U32            SNDRV_PCM_FORMAT_U32_LE
+#define SNDRV_PCM_FORMAT_FLOAT          SNDRV_PCM_FORMAT_FLOAT_LE
+#define SNDRV_PCM_FORMAT_FLOAT64        SNDRV_PCM_FORMAT_FLOAT64_LE
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
+#endif
+#ifdef SNDRV_BIG_ENDIAN
+#define SNDRV_PCM_FORMAT_S16            SNDRV_PCM_FORMAT_S16_BE
+#define SNDRV_PCM_FORMAT_U16            SNDRV_PCM_FORMAT_U16_BE
+#define SNDRV_PCM_FORMAT_S24            SNDRV_PCM_FORMAT_S24_BE
+#define SNDRV_PCM_FORMAT_U24            SNDRV_PCM_FORMAT_U24_BE
+#define SNDRV_PCM_FORMAT_S32            SNDRV_PCM_FORMAT_S32_BE
+#define SNDRV_PCM_FORMAT_U32            SNDRV_PCM_FORMAT_U32_BE
+#define SNDRV_PCM_FORMAT_FLOAT          SNDRV_PCM_FORMAT_FLOAT_BE
+#define SNDRV_PCM_FORMAT_FLOAT64        SNDRV_PCM_FORMAT_FLOAT64_BE
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
+#endif
+
+typedef int __bitwise snd_pcm_subformat_t;
+#define SNDRV_PCM_SUBFORMAT_STD         ((__force snd_pcm_subformat_t) 0)
+#define SNDRV_PCM_SUBFORMAT_LAST        SNDRV_PCM_SUBFORMAT_STD
+
+#define SNDRV_PCM_INFO_MMAP             0x00000001      /* hardware supports mmap */
+#define SNDRV_PCM_INFO_MMAP_VALID       0x00000002      /* period data are valid during transfer */
+#define SNDRV_PCM_INFO_DOUBLE           0x00000004      /* Double buffering needed for PCM start/stop */
+#define SNDRV_PCM_INFO_BATCH            0x00000010      /* double buffering */
+#define SNDRV_PCM_INFO_SYNC_APPLPTR     0x00000020      /* need the explicit sync of appl_ptr update */
+#define SNDRV_PCM_INFO_INTERLEAVED      0x00000100      /* channels are interleaved */
+#define SNDRV_PCM_INFO_NONINTERLEAVED   0x00000200      /* channels are not interleaved */
+#define SNDRV_PCM_INFO_COMPLEX          0x00000400      /* complex frame organization (mmap only) */
+#define SNDRV_PCM_INFO_BLOCK_TRANSFER   0x00010000      /* hardware transfer block of samples */
+#define SNDRV_PCM_INFO_OVERRANGE        0x00020000      /* hardware supports ADC (capture) overrange detection */
+#define SNDRV_PCM_INFO_RESUME           0x00040000      /* hardware supports stream resume after suspend */
+#define SNDRV_PCM_INFO_PAUSE            0x00080000      /* pause ioctl is supported */
+#define SNDRV_PCM_INFO_HALF_DUPLEX      0x00100000      /* only half duplex */
+#define SNDRV_PCM_INFO_JOINT_DUPLEX     0x00200000      /* playback and capture stream are somewhat correlated */
+#define SNDRV_PCM_INFO_SYNC_START       0x00400000      /* pcm support some kind of sync go */
+#define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP 0x00800000      /* period wakeup can be disabled */
+#define SNDRV_PCM_INFO_HAS_WALL_CLOCK   0x01000000      /* (Deprecated)has audio wall clock for audio/system time sync */
+#define SNDRV_PCM_INFO_HAS_LINK_ATIME              0x01000000  /* report hardware link audio time, reset on startup */
+#define SNDRV_PCM_INFO_HAS_LINK_ABSOLUTE_ATIME     0x02000000  /* report absolute hardware link audio time, not reset on startup */
+#define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME    0x04000000  /* report estimated link audio time */
+#define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000  /* report synchronized audio/system time */
+
+#define SNDRV_PCM_INFO_DRAIN_TRIGGER    0x40000000              /* internal kernel flag - trigger in drain */
+#define SNDRV_PCM_INFO_FIFO_IN_FRAMES   0x80000000      /* internal kernel flag - FIFO size is in frames */
+
+
+
+typedef int __bitwise snd_pcm_state_t;
+#define SNDRV_PCM_STATE_OPEN            ((__force snd_pcm_state_t) 0) /* stream is open */
+#define SNDRV_PCM_STATE_SETUP           ((__force snd_pcm_state_t) 1) /* stream has a setup */
+#define SNDRV_PCM_STATE_PREPARED        ((__force snd_pcm_state_t) 2) /* stream is ready to start */
+#define SNDRV_PCM_STATE_RUNNING         ((__force snd_pcm_state_t) 3) /* stream is running */
+#define SNDRV_PCM_STATE_XRUN            ((__force snd_pcm_state_t) 4) /* stream reached an xrun */
+#define SNDRV_PCM_STATE_DRAINING        ((__force snd_pcm_state_t) 5) /* stream is draining */
+#define SNDRV_PCM_STATE_PAUSED          ((__force snd_pcm_state_t) 6) /* stream is paused */
+#define SNDRV_PCM_STATE_SUSPENDED       ((__force snd_pcm_state_t) 7) /* hardware is suspended */
+#define SNDRV_PCM_STATE_DISCONNECTED    ((__force snd_pcm_state_t) 8) /* hardware is disconnected */
+#define SNDRV_PCM_STATE_LAST            SNDRV_PCM_STATE_DISCONNECTED
+
+enum {
+        SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
+        SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
+        SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
+};
+
+union snd_pcm_sync_id {
+        unsigned char id[16];
+        unsigned short id16[8];
+        unsigned int id32[4];
+};
+
+struct snd_pcm_info {
+        unsigned int device;            /* RO/WR (control): device number */
+        unsigned int subdevice;         /* RO/WR (control): subdevice number */
+        int stream;                     /* RO/WR (control): stream direction */
+        int card;                       /* R: card number */
+        unsigned char id[64];           /* ID (user selectable) */
+        unsigned char name[80];         /* name of this device */
+        unsigned char subname[32];      /* subdevice name */
+        int dev_class;                  /* SNDRV_PCM_CLASS_* */
+        int dev_subclass;               /* SNDRV_PCM_SUBCLASS_* */
+        unsigned int subdevices_count;
+        unsigned int subdevices_avail;
+        union snd_pcm_sync_id sync;     /* hardware synchronization ID */
+        unsigned char reserved[64];     /* reserved for future... */
+};
+
+typedef int snd_pcm_hw_param_t;
+#define SNDRV_PCM_HW_PARAM_ACCESS       0       /* Access type */
+#define SNDRV_PCM_HW_PARAM_FORMAT       1       /* Format */
+#define SNDRV_PCM_HW_PARAM_SUBFORMAT    2       /* Subformat */
+#define SNDRV_PCM_HW_PARAM_FIRST_MASK   SNDRV_PCM_HW_PARAM_ACCESS
+#define SNDRV_PCM_HW_PARAM_LAST_MASK    SNDRV_PCM_HW_PARAM_SUBFORMAT
+
+#define SNDRV_PCM_HW_PARAM_SAMPLE_BITS  8       /* Bits per sample */
+#define SNDRV_PCM_HW_PARAM_FRAME_BITS   9       /* Bits per frame */
+#define SNDRV_PCM_HW_PARAM_CHANNELS     10      /* Channels */
+#define SNDRV_PCM_HW_PARAM_RATE         11      /* Approx rate */
+#define SNDRV_PCM_HW_PARAM_PERIOD_TIME  12      /* Approx distance between
+                                                 * interrupts in us
+                                                 */
+#define SNDRV_PCM_HW_PARAM_PERIOD_SIZE  13      /* Approx frames between
+                                                 * interrupts
+                                                 */
+#define SNDRV_PCM_HW_PARAM_PERIOD_BYTES 14      /* Approx bytes between
+                                                 * interrupts
+                                                 */
+#define SNDRV_PCM_HW_PARAM_PERIODS      15      /* Approx interrupts per
+                                                 * buffer
+                                                 */
+#define SNDRV_PCM_HW_PARAM_BUFFER_TIME  16      /* Approx duration of buffer
+                                                 * in us
+                                                 */
+#define SNDRV_PCM_HW_PARAM_BUFFER_SIZE  17      /* Size of buffer in frames */
+#define SNDRV_PCM_HW_PARAM_BUFFER_BYTES 18      /* Size of buffer in bytes */
+#define SNDRV_PCM_HW_PARAM_TICK_TIME    19      /* Approx tick duration in us */
+#define SNDRV_PCM_HW_PARAM_FIRST_INTERVAL       SNDRV_PCM_HW_PARAM_SAMPLE_BITS
+#define SNDRV_PCM_HW_PARAM_LAST_INTERVAL        SNDRV_PCM_HW_PARAM_TICK_TIME
+
+#define SNDRV_PCM_HW_PARAMS_NORESAMPLE  (1<<0)  /* avoid rate resampling */
+#define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER       (1<<1)  /* export buffer */
+#define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP    (1<<2)  /* disable period wakeups */
+
+struct snd_interval {
+        unsigned int min, max;
+        unsigned int openmin:1,
+                     openmax:1,
+                     integer:1,
+                     empty:1;
+};
+
+#define SNDRV_MASK_MAX  256
+
+struct snd_mask {
+        __u32 bits[(SNDRV_MASK_MAX+31)/32];
+};
+
+struct snd_pcm_hw_params {
+        unsigned int flags;
+        struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK -
+                               SNDRV_PCM_HW_PARAM_FIRST_MASK + 1];
+        struct snd_mask mres[5];        /* reserved masks */
+        struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL -
+                                        SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1];
+        struct snd_interval ires[9];    /* reserved intervals */
+        unsigned int rmask;             /* W: requested masks */
+        unsigned int cmask;             /* R: changed masks */
+        unsigned int info;              /* R: Info flags for returned setup */
+        unsigned int msbits;            /* R: used most significant bits */
+        unsigned int rate_num;          /* R: rate numerator */
+        unsigned int rate_den;          /* R: rate denominator */
+        snd_pcm_uframes_t fifo_size;    /* R: chip FIFO size in frames */
+        unsigned char reserved[64];     /* reserved for future */
+};
+
+enum {
+        SNDRV_PCM_TSTAMP_NONE = 0,
+        SNDRV_PCM_TSTAMP_ENABLE,
+        SNDRV_PCM_TSTAMP_LAST = SNDRV_PCM_TSTAMP_ENABLE,
+};
+
+struct snd_pcm_sw_params {
+        int tstamp_mode;                        /* timestamp mode */
+        unsigned int period_step;
+        unsigned int sleep_min;                 /* min ticks to sleep */
+        snd_pcm_uframes_t avail_min;            /* min avail frames for wakeup */
+        snd_pcm_uframes_t xfer_align;           /* obsolete: xfer size need to be a multiple */
+        snd_pcm_uframes_t start_threshold;      /* min hw_avail frames for automatic start */
+        snd_pcm_uframes_t stop_threshold;       /* min avail frames for automatic stop */
+        snd_pcm_uframes_t silence_threshold;    /* min distance from noise for silence filling */
+        snd_pcm_uframes_t silence_size;         /* silence block size */
+        snd_pcm_uframes_t boundary;             /* pointers wrap point */
+        unsigned int proto;                     /* protocol version */
+        unsigned int tstamp_type;               /* timestamp type (req. proto >= 2.0.12) */
+        unsigned char reserved[56];             /* reserved for future */
+};
+
+struct snd_pcm_channel_info {
+        unsigned int channel;
+        __kernel_off_t offset;          /* mmap offset */
+        unsigned int first;             /* offset to first sample in bits */
+        unsigned int step;              /* samples distance in bits */
+};
+
+enum {
+        /*
+         *  first definition for backwards compatibility only,
+         *  maps to wallclock/link time for HDAudio playback and DEFAULT/DMA time for everything else
+         */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_COMPAT = 0,
+
+        /* timestamp definitions */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_DEFAULT = 1,           /* DMA time, reported as per hw_ptr */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK = 2,              /* link time reported by sample or wallclock counter, reset on startup */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_ABSOLUTE = 3,     /* link time reported by sample or wallclock counter, not reset on startup */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_ESTIMATED = 4,    /* link time estimated indirectly */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED = 5, /* link time synchronized with system time */
+        SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED
+};
+
+struct snd_pcm_status {
+        snd_pcm_state_t state;          /* stream state */
+        struct timespec trigger_tstamp; /* time when stream was started/stopped/paused */
+        struct timespec tstamp;         /* reference timestamp */
+        snd_pcm_uframes_t appl_ptr;     /* appl ptr */
+        snd_pcm_uframes_t hw_ptr;       /* hw ptr */
+        snd_pcm_sframes_t delay;        /* current delay in frames */
+        snd_pcm_uframes_t avail;        /* number of frames available */
+        snd_pcm_uframes_t avail_max;    /* max frames available on hw since last status */
+        snd_pcm_uframes_t overrange;    /* count of ADC (capture) overrange detections from last status */
+        snd_pcm_state_t suspended_state; /* suspended stream state */
+        __u32 audio_tstamp_data;         /* needed for 64-bit alignment, used for configs/report to/from userspace */
+        struct timespec audio_tstamp;   /* sample counter, wall clock, PHC or on-demand sync'ed */
+        struct timespec driver_tstamp;  /* useful in case reference system tstamp is reported with delay */
+        __u32 audio_tstamp_accuracy;    /* in ns units, only valid if indicated in audio_tstamp_data */
+        unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */
+};
+
+struct snd_pcm_mmap_status {
+        snd_pcm_state_t state;          /* RO: state - SNDRV_PCM_STATE_XXXX */
+        int pad1;                       /* Needed for 64 bit alignment */
+        snd_pcm_uframes_t hw_ptr;       /* RO: hw ptr (0...boundary-1) */
+        struct timespec tstamp;         /* Timestamp */
+        snd_pcm_state_t suspended_state; /* RO: suspended stream state */
+        struct timespec audio_tstamp;   /* from sample counter or wall clock */
+};
+
+struct snd_pcm_mmap_control {
+        snd_pcm_uframes_t appl_ptr;     /* RW: appl ptr (0...boundary-1) */
+        snd_pcm_uframes_t avail_min;    /* RW: min available frames for wakeup */
+};
+
+#define SNDRV_PCM_SYNC_PTR_HWSYNC       (1<<0)  /* execute hwsync */
+#define SNDRV_PCM_SYNC_PTR_APPL         (1<<1)  /* get appl_ptr from driver (r/w op) */
+#define SNDRV_PCM_SYNC_PTR_AVAIL_MIN    (1<<2)  /* get avail_min from driver */
+
+struct snd_pcm_sync_ptr {
+        unsigned int flags;
+        union {
+                struct snd_pcm_mmap_status status;
+                unsigned char reserved[64];
+        } s;
+        union {
+                struct snd_pcm_mmap_control control;
+                unsigned char reserved[64];
+        } c;
+};
+
+struct snd_xferi {
+        snd_pcm_sframes_t result;
+        void __user *buf;
+        snd_pcm_uframes_t frames;
+};
+
+struct snd_xfern {
+        snd_pcm_sframes_t result;
+        void __user * __user *bufs;
+        snd_pcm_uframes_t frames;
+};
+
+enum {
+        SNDRV_PCM_TSTAMP_TYPE_GETTIMEOFDAY = 0, /* gettimeofday equivalent */
+        SNDRV_PCM_TSTAMP_TYPE_MONOTONIC,        /* posix_clock_monotonic equivalent */
+        SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW,    /* monotonic_raw (no NTP) */
+        SNDRV_PCM_TSTAMP_TYPE_LAST = SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW,
+};
+
+/* channel positions */
+enum {
+        SNDRV_CHMAP_UNKNOWN = 0,
+        SNDRV_CHMAP_NA,         /* N/A, silent */
+        SNDRV_CHMAP_MONO,       /* mono stream */
+        /* this follows the alsa-lib mixer channel value + 3 */
+        SNDRV_CHMAP_FL,         /* front left */
+        SNDRV_CHMAP_FR,         /* front right */
+        SNDRV_CHMAP_RL,         /* rear left */
+        SNDRV_CHMAP_RR,         /* rear right */
+        SNDRV_CHMAP_FC,         /* front center */
+        SNDRV_CHMAP_LFE,        /* LFE */
+        SNDRV_CHMAP_SL,         /* side left */
+        SNDRV_CHMAP_SR,         /* side right */
+        SNDRV_CHMAP_RC,         /* rear center */
+        /* new definitions */
+        SNDRV_CHMAP_FLC,        /* front left center */
+        SNDRV_CHMAP_FRC,        /* front right center */
+        SNDRV_CHMAP_RLC,        /* rear left center */
+        SNDRV_CHMAP_RRC,        /* rear right center */
+        SNDRV_CHMAP_FLW,        /* front left wide */
+        SNDRV_CHMAP_FRW,        /* front right wide */
+        SNDRV_CHMAP_FLH,        /* front left high */
+        SNDRV_CHMAP_FCH,        /* front center high */
+        SNDRV_CHMAP_FRH,        /* front right high */
+        SNDRV_CHMAP_TC,         /* top center */
+        SNDRV_CHMAP_TFL,        /* top front left */
+        SNDRV_CHMAP_TFR,        /* top front right */
+        SNDRV_CHMAP_TFC,        /* top front center */
+        SNDRV_CHMAP_TRL,        /* top rear left */
+        SNDRV_CHMAP_TRR,        /* top rear right */
+        SNDRV_CHMAP_TRC,        /* top rear center */
+        /* new definitions for UAC2 */
+        SNDRV_CHMAP_TFLC,       /* top front left center */
+        SNDRV_CHMAP_TFRC,       /* top front right center */
+        SNDRV_CHMAP_TSL,        /* top side left */
+        SNDRV_CHMAP_TSR,        /* top side right */
+        SNDRV_CHMAP_LLFE,       /* left LFE */
+        SNDRV_CHMAP_RLFE,       /* right LFE */
+        SNDRV_CHMAP_BC,         /* bottom center */
+        SNDRV_CHMAP_BLC,        /* bottom left center */
+        SNDRV_CHMAP_BRC,        /* bottom right center */
+        SNDRV_CHMAP_LAST = SNDRV_CHMAP_BRC,
+};
+
+#define SNDRV_CHMAP_POSITION_MASK       0xffff
+#define SNDRV_CHMAP_PHASE_INVERSE       (0x01 << 16)
+#define SNDRV_CHMAP_DRIVER_SPEC         (0x02 << 16)
+
+#define SNDRV_PCM_IOCTL_PVERSION        _IOR('A', 0x00, int)
+#define SNDRV_PCM_IOCTL_INFO            _IOR('A', 0x01, struct snd_pcm_info)
+#define SNDRV_PCM_IOCTL_TSTAMP          _IOW('A', 0x02, int)
+#define SNDRV_PCM_IOCTL_TTSTAMP         _IOW('A', 0x03, int)
+#define SNDRV_PCM_IOCTL_USER_PVERSION   _IOW('A', 0x04, int)
+#define SNDRV_PCM_IOCTL_HW_REFINE       _IOWR('A', 0x10, struct snd_pcm_hw_params)
+#define SNDRV_PCM_IOCTL_HW_PARAMS       _IOWR('A', 0x11, struct snd_pcm_hw_params)
+#define SNDRV_PCM_IOCTL_HW_FREE         _IO('A', 0x12)
+#define SNDRV_PCM_IOCTL_SW_PARAMS       _IOWR('A', 0x13, struct snd_pcm_sw_params)
+#define SNDRV_PCM_IOCTL_STATUS          _IOR('A', 0x20, struct snd_pcm_status)
+#define SNDRV_PCM_IOCTL_DELAY           _IOR('A', 0x21, snd_pcm_sframes_t)
+#define SNDRV_PCM_IOCTL_HWSYNC          _IO('A', 0x22)
+#define SNDRV_PCM_IOCTL_SYNC_PTR        _IOWR('A', 0x23, struct snd_pcm_sync_ptr)
+#define SNDRV_PCM_IOCTL_STATUS_EXT      _IOWR('A', 0x24, struct snd_pcm_status)
+#define SNDRV_PCM_IOCTL_CHANNEL_INFO    _IOR('A', 0x32, struct snd_pcm_channel_info)
+#define SNDRV_PCM_IOCTL_PREPARE         _IO('A', 0x40)
+#define SNDRV_PCM_IOCTL_RESET           _IO('A', 0x41)
+#define SNDRV_PCM_IOCTL_START           _IO('A', 0x42)
+#define SNDRV_PCM_IOCTL_DROP            _IO('A', 0x43)
+#define SNDRV_PCM_IOCTL_DRAIN           _IO('A', 0x44)
+#define SNDRV_PCM_IOCTL_PAUSE           _IOW('A', 0x45, int)
+#define SNDRV_PCM_IOCTL_REWIND          _IOW('A', 0x46, snd_pcm_uframes_t)
+#define SNDRV_PCM_IOCTL_RESUME          _IO('A', 0x47)
+#define SNDRV_PCM_IOCTL_XRUN            _IO('A', 0x48)
+#define SNDRV_PCM_IOCTL_FORWARD         _IOW('A', 0x49, snd_pcm_uframes_t)
+#define SNDRV_PCM_IOCTL_WRITEI_FRAMES   _IOW('A', 0x50, struct snd_xferi)
+#define SNDRV_PCM_IOCTL_READI_FRAMES    _IOR('A', 0x51, struct snd_xferi)
+#define SNDRV_PCM_IOCTL_WRITEN_FRAMES   _IOW('A', 0x52, struct snd_xfern)
+#define SNDRV_PCM_IOCTL_READN_FRAMES    _IOR('A', 0x53, struct snd_xfern)
+#define SNDRV_PCM_IOCTL_LINK            _IOW('A', 0x60, int)
+#define SNDRV_PCM_IOCTL_UNLINK          _IO('A', 0x61)
+
+/*****************************************************************************
+ *                                                                           *
+ *                            MIDI v1.0 interface                            *
+ *                                                                           *
+ *****************************************************************************/
+
+/*
+ *  Raw MIDI section - /dev/snd/midi??
+ */
+
+#define SNDRV_RAWMIDI_VERSION           SNDRV_PROTOCOL_VERSION(2, 0, 0)
+
+enum {
+        SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
+        SNDRV_RAWMIDI_STREAM_INPUT,
+        SNDRV_RAWMIDI_STREAM_LAST = SNDRV_RAWMIDI_STREAM_INPUT,
+};
+
+#define SNDRV_RAWMIDI_INFO_OUTPUT               0x00000001
+#define SNDRV_RAWMIDI_INFO_INPUT                0x00000002
+#define SNDRV_RAWMIDI_INFO_DUPLEX               0x00000004
+
+struct snd_rawmidi_info {
+        unsigned int device;            /* RO/WR (control): device number */
+        unsigned int subdevice;         /* RO/WR (control): subdevice number */
+        int stream;                     /* WR: stream */
+        int card;                       /* R: card number */
+        unsigned int flags;             /* SNDRV_RAWMIDI_INFO_XXXX */
+        unsigned char id[64];           /* ID (user selectable) */
+        unsigned char name[80];         /* name of device */
+        unsigned char subname[32];      /* name of active or selected subdevice */
+        unsigned int subdevices_count;
+        unsigned int subdevices_avail;
+        unsigned char reserved[64];     /* reserved for future use */
+};
+
+struct snd_rawmidi_params {
+        int stream;
+        size_t buffer_size;             /* queue size in bytes */
+        size_t avail_min;               /* minimum avail bytes for wakeup */
+        unsigned int no_active_sensing: 1; /* do not send active sensing byte in close() */
+        unsigned char reserved[16];     /* reserved for future use */
+};
+
+struct snd_rawmidi_status {
+        int stream;
+        struct timespec tstamp;         /* Timestamp */
+        size_t avail;                   /* available bytes */
+        size_t xruns;                   /* count of overruns since last status (in bytes) */
+        unsigned char reserved[16];     /* reserved for future use */
+};
+
+#define SNDRV_RAWMIDI_IOCTL_PVERSION    _IOR('W', 0x00, int)
+#define SNDRV_RAWMIDI_IOCTL_INFO        _IOR('W', 0x01, struct snd_rawmidi_info)
+#define SNDRV_RAWMIDI_IOCTL_PARAMS      _IOWR('W', 0x10, struct snd_rawmidi_params)
+#define SNDRV_RAWMIDI_IOCTL_STATUS      _IOWR('W', 0x20, struct snd_rawmidi_status)
+#define SNDRV_RAWMIDI_IOCTL_DROP        _IOW('W', 0x30, int)
+#define SNDRV_RAWMIDI_IOCTL_DRAIN       _IOW('W', 0x31, int)
+
+/*
+ *  Timer section - /dev/snd/timer
+ */
+
+#define SNDRV_TIMER_VERSION             SNDRV_PROTOCOL_VERSION(2, 0, 6)
+
+enum {
+        SNDRV_TIMER_CLASS_NONE = -1,
+        SNDRV_TIMER_CLASS_SLAVE = 0,
+        SNDRV_TIMER_CLASS_GLOBAL,
+        SNDRV_TIMER_CLASS_CARD,
+        SNDRV_TIMER_CLASS_PCM,
+        SNDRV_TIMER_CLASS_LAST = SNDRV_TIMER_CLASS_PCM,
+};
+
+/* slave timer classes */
+enum {
+        SNDRV_TIMER_SCLASS_NONE = 0,
+        SNDRV_TIMER_SCLASS_APPLICATION,
+        SNDRV_TIMER_SCLASS_SEQUENCER,           /* alias */
+        SNDRV_TIMER_SCLASS_OSS_SEQUENCER,       /* alias */
+        SNDRV_TIMER_SCLASS_LAST = SNDRV_TIMER_SCLASS_OSS_SEQUENCER,
+};
+
+/* global timers (device member) */
+#define SNDRV_TIMER_GLOBAL_SYSTEM       0
+#define SNDRV_TIMER_GLOBAL_RTC          1       /* unused */
+#define SNDRV_TIMER_GLOBAL_HPET         2
+#define SNDRV_TIMER_GLOBAL_HRTIMER      3
+
+/* info flags */
+#define SNDRV_TIMER_FLG_SLAVE           (1<<0)  /* cannot be controlled */
+
+struct snd_timer_id {
+        int dev_class;
+        int dev_sclass;
+        int card;
+        int device;
+        int subdevice;
+};
+
+struct snd_timer_ginfo {
+        struct snd_timer_id tid;        /* requested timer ID */
+        unsigned int flags;             /* timer flags - SNDRV_TIMER_FLG_* */
+        int card;                       /* card number */
+        unsigned char id[64];           /* timer identification */
+        unsigned char name[80];         /* timer name */
+        unsigned long reserved0;        /* reserved for future use */
+        unsigned long resolution;       /* average period resolution in ns */
+        unsigned long resolution_min;   /* minimal period resolution in ns */
+        unsigned long resolution_max;   /* maximal period resolution in ns */
+        unsigned int clients;           /* active timer clients */
+        unsigned char reserved[32];
+};
+
+struct snd_timer_gparams {
+        struct snd_timer_id tid;        /* requested timer ID */
+        unsigned long period_num;       /* requested precise period duration (in seconds) - numerator */
+        unsigned long period_den;       /* requested precise period duration (in seconds) - denominator */
+        unsigned char reserved[32];
+};
+
+struct snd_timer_gstatus {
+        struct snd_timer_id tid;        /* requested timer ID */
+        unsigned long resolution;       /* current period resolution in ns */
+        unsigned long resolution_num;   /* precise current period resolution (in seconds) - numerator */
+        unsigned long resolution_den;   /* precise current period resolution (in seconds) - denominator */
+        unsigned char reserved[32];
+};
+
+struct snd_timer_select {
+        struct snd_timer_id id; /* bind to timer ID */
+        unsigned char reserved[32];     /* reserved */
+};
+
+struct snd_timer_info {
+        unsigned int flags;             /* timer flags - SNDRV_TIMER_FLG_* */
+        int card;                       /* card number */
+        unsigned char id[64];           /* timer identificator */
+        unsigned char name[80];         /* timer name */
+        unsigned long reserved0;        /* reserved for future use */
+        unsigned long resolution;       /* average period resolution in ns */
+        unsigned char reserved[64];     /* reserved */
+};
+
+#define SNDRV_TIMER_PSFLG_AUTO          (1<<0)  /* auto start, otherwise one-shot */
+#define SNDRV_TIMER_PSFLG_EXCLUSIVE     (1<<1)  /* exclusive use, precise start/stop/pause/continue */
+#define SNDRV_TIMER_PSFLG_EARLY_EVENT   (1<<2)  /* write early event to the poll queue */
+
+struct snd_timer_params {
+        unsigned int flags;             /* flags - SNDRV_MIXER_PSFLG_* */
+        unsigned int ticks;             /* requested resolution in ticks */
+        unsigned int queue_size;        /* total size of queue (32-1024) */
+        unsigned int reserved0;         /* reserved, was: failure locations */
+        unsigned int filter;            /* event filter (bitmask of SNDRV_TIMER_EVENT_*) */
+        unsigned char reserved[60];     /* reserved */
+};
+
+struct snd_timer_status {
+        struct timespec tstamp;         /* Timestamp - last update */
+        unsigned int resolution;        /* current period resolution in ns */
+        unsigned int lost;              /* counter of master tick lost */
+        unsigned int overrun;           /* count of read queue overruns */
+        unsigned int queue;             /* used queue size */
+        unsigned char reserved[64];     /* reserved */
+};
+
+#define SNDRV_TIMER_IOCTL_PVERSION      _IOR('T', 0x00, int)
+#define SNDRV_TIMER_IOCTL_NEXT_DEVICE   _IOWR('T', 0x01, struct snd_timer_id)
+#define SNDRV_TIMER_IOCTL_TREAD         _IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_GINFO         _IOWR('T', 0x03, struct snd_timer_ginfo)
+#define SNDRV_TIMER_IOCTL_GPARAMS       _IOW('T', 0x04, struct snd_timer_gparams)
+#define SNDRV_TIMER_IOCTL_GSTATUS       _IOWR('T', 0x05, struct snd_timer_gstatus)
+#define SNDRV_TIMER_IOCTL_SELECT        _IOW('T', 0x10, struct snd_timer_select)
+#define SNDRV_TIMER_IOCTL_INFO          _IOR('T', 0x11, struct snd_timer_info)
+#define SNDRV_TIMER_IOCTL_PARAMS        _IOW('T', 0x12, struct snd_timer_params)
+#define SNDRV_TIMER_IOCTL_STATUS        _IOR('T', 0x14, struct snd_timer_status)
+/* The following four ioctls are changed since 1.0.9 due to confliction */
+#define SNDRV_TIMER_IOCTL_START         _IO('T', 0xa0)
+#define SNDRV_TIMER_IOCTL_STOP          _IO('T', 0xa1)
+#define SNDRV_TIMER_IOCTL_CONTINUE      _IO('T', 0xa2)
+#define SNDRV_TIMER_IOCTL_PAUSE         _IO('T', 0xa3)
+
+struct snd_timer_read {
+        unsigned int resolution;
+        unsigned int ticks;
+};
+
+enum {
+        SNDRV_TIMER_EVENT_RESOLUTION = 0,       /* val = resolution in ns */
+        SNDRV_TIMER_EVENT_TICK,                 /* val = ticks */
+        SNDRV_TIMER_EVENT_START,                /* val = resolution in ns */
+        SNDRV_TIMER_EVENT_STOP,                 /* val = 0 */
+        SNDRV_TIMER_EVENT_CONTINUE,             /* val = resolution in ns */
+        SNDRV_TIMER_EVENT_PAUSE,                /* val = 0 */
+        SNDRV_TIMER_EVENT_EARLY,                /* val = 0, early event */
+        SNDRV_TIMER_EVENT_SUSPEND,              /* val = 0 */
+        SNDRV_TIMER_EVENT_RESUME,               /* val = resolution in ns */
+        /* master timer events for slave timer instances */
+        SNDRV_TIMER_EVENT_MSTART = SNDRV_TIMER_EVENT_START + 10,
+        SNDRV_TIMER_EVENT_MSTOP = SNDRV_TIMER_EVENT_STOP + 10,
+        SNDRV_TIMER_EVENT_MCONTINUE = SNDRV_TIMER_EVENT_CONTINUE + 10,
+        SNDRV_TIMER_EVENT_MPAUSE = SNDRV_TIMER_EVENT_PAUSE + 10,
+        SNDRV_TIMER_EVENT_MSUSPEND = SNDRV_TIMER_EVENT_SUSPEND + 10,
+        SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
+};
+
+struct snd_timer_tread {
+        int event;
+        struct timespec tstamp;
+        unsigned int val;
+};
+
+/****************************************************************************
+ *                                                                          *
+ *        Section for driver control interface - /dev/snd/control?          *
+ *                                                                          *
+ ****************************************************************************/
+
+#define SNDRV_CTL_VERSION               SNDRV_PROTOCOL_VERSION(2, 0, 7)
+
+struct snd_ctl_card_info {
+        int card;                       /* card number */
+        int pad;                        /* reserved for future (was type) */
+        unsigned char id[16];           /* ID of card (user selectable) */
+        unsigned char driver[16];       /* Driver name */
+        unsigned char name[32];         /* Short name of soundcard */
+        unsigned char longname[80];     /* name + info text about soundcard */
+        unsigned char reserved_[16];    /* reserved for future (was ID of mixer) */
+        unsigned char mixername[80];    /* visual mixer identification */
+        unsigned char components[128];  /* card components / fine identification, delimited with one space (AC97 etc..) */
+};
+
+typedef int __bitwise snd_ctl_elem_type_t;
+#define SNDRV_CTL_ELEM_TYPE_NONE        ((__force snd_ctl_elem_type_t) 0) /* invalid */
+#define SNDRV_CTL_ELEM_TYPE_BOOLEAN     ((__force snd_ctl_elem_type_t) 1) /* boolean type */
+#define SNDRV_CTL_ELEM_TYPE_INTEGER     ((__force snd_ctl_elem_type_t) 2) /* integer type */
+#define SNDRV_CTL_ELEM_TYPE_ENUMERATED  ((__force snd_ctl_elem_type_t) 3) /* enumerated type */
+#define SNDRV_CTL_ELEM_TYPE_BYTES       ((__force snd_ctl_elem_type_t) 4) /* byte array */
+#define SNDRV_CTL_ELEM_TYPE_IEC958      ((__force snd_ctl_elem_type_t) 5) /* IEC958 (S/PDIF) setup */
+#define SNDRV_CTL_ELEM_TYPE_INTEGER64   ((__force snd_ctl_elem_type_t) 6) /* 64-bit integer type */
+#define SNDRV_CTL_ELEM_TYPE_LAST        SNDRV_CTL_ELEM_TYPE_INTEGER64
+
+typedef int __bitwise snd_ctl_elem_iface_t;
+#define SNDRV_CTL_ELEM_IFACE_CARD       ((__force snd_ctl_elem_iface_t) 0) /* global control */
+#define SNDRV_CTL_ELEM_IFACE_HWDEP      ((__force snd_ctl_elem_iface_t) 1) /* hardware dependent device */
+#define SNDRV_CTL_ELEM_IFACE_MIXER      ((__force snd_ctl_elem_iface_t) 2) /* virtual mixer device */
+#define SNDRV_CTL_ELEM_IFACE_PCM        ((__force snd_ctl_elem_iface_t) 3) /* PCM device */
+#define SNDRV_CTL_ELEM_IFACE_RAWMIDI    ((__force snd_ctl_elem_iface_t) 4) /* RawMidi device */
+#define SNDRV_CTL_ELEM_IFACE_TIMER      ((__force snd_ctl_elem_iface_t) 5) /* timer device */
+#define SNDRV_CTL_ELEM_IFACE_SEQUENCER  ((__force snd_ctl_elem_iface_t) 6) /* sequencer client */
+#define SNDRV_CTL_ELEM_IFACE_LAST       SNDRV_CTL_ELEM_IFACE_SEQUENCER
+
+#define SNDRV_CTL_ELEM_ACCESS_READ              (1<<0)
+#define SNDRV_CTL_ELEM_ACCESS_WRITE             (1<<1)
+#define SNDRV_CTL_ELEM_ACCESS_READWRITE         (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
+#define SNDRV_CTL_ELEM_ACCESS_VOLATILE          (1<<2)  /* control value may be changed without a notification */
+#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP         (1<<3)  /* when was control changed */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_READ          (1<<4)  /* TLV read is possible */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE         (1<<5)  /* TLV write is possible */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE     (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
+#define SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND       (1<<6)  /* TLV command is possible */
+#define SNDRV_CTL_ELEM_ACCESS_INACTIVE          (1<<8)  /* control does actually nothing, but may be updated */
+#define SNDRV_CTL_ELEM_ACCESS_LOCK              (1<<9)  /* write lock */
+#define SNDRV_CTL_ELEM_ACCESS_OWNER             (1<<10) /* write lock owner */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK      (1<<28) /* kernel use a TLV callback */
+#define SNDRV_CTL_ELEM_ACCESS_USER              (1<<29) /* user space element */
+/* bits 30 and 31 are obsoleted (for indirect access) */
+
+/* for further details see the ACPI and PCI power management specification */
+#define SNDRV_CTL_POWER_D0              0x0000  /* full On */
+#define SNDRV_CTL_POWER_D1              0x0100  /* partial On */
+#define SNDRV_CTL_POWER_D2              0x0200  /* partial On */
+#define SNDRV_CTL_POWER_D3              0x0300  /* Off */
+#define SNDRV_CTL_POWER_D3hot           (SNDRV_CTL_POWER_D3|0x0000)     /* Off, with power */
+#define SNDRV_CTL_POWER_D3cold          (SNDRV_CTL_POWER_D3|0x0001)     /* Off, without power */
+
+#define SNDRV_CTL_ELEM_ID_NAME_MAXLEN   44
+
+struct snd_ctl_elem_id {
+        unsigned int numid;             /* numeric identifier, zero = invalid */
+        snd_ctl_elem_iface_t iface;     /* interface identifier */
+        unsigned int device;            /* device/client number */
+        unsigned int subdevice;         /* subdevice (substream) number */
+        unsigned char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];              /* ASCII name of item */
+        unsigned int index;             /* index of item */
+};
+
+struct snd_ctl_elem_list {
+        unsigned int offset;            /* W: first element ID to get */
+        unsigned int space;             /* W: count of element IDs to get */
+        unsigned int used;              /* R: count of element IDs set */
+        unsigned int count;             /* R: count of all elements */
+        struct snd_ctl_elem_id __user *pids; /* R: IDs */
+        unsigned char reserved[50];
+};
+
+struct snd_ctl_elem_info {
+        struct snd_ctl_elem_id id;      /* W: element ID */
+        snd_ctl_elem_type_t type;       /* R: value type - SNDRV_CTL_ELEM_TYPE_* */
+        unsigned int access;            /* R: value access (bitmask) - SNDRV_CTL_ELEM_ACCESS_* */
+        unsigned int count;             /* count of values */
+        __kernel_pid_t owner;           /* owner's PID of this control */
+        union {
+                struct {
+                        long min;               /* R: minimum value */
+                        long max;               /* R: maximum value */
+                        long step;              /* R: step (0 variable) */
+                } integer;
+                struct {
+                        long long min;          /* R: minimum value */
+                        long long max;          /* R: maximum value */
+                        long long step;         /* R: step (0 variable) */
+                } integer64;
+                struct {
+                        unsigned int items;     /* R: number of items */
+                        unsigned int item;      /* W: item number */
+                        char name[64];          /* R: value name */
+                        __u64 names_ptr;        /* W: names list (ELEM_ADD only) */
+                        unsigned int names_length;
+                } enumerated;
+                unsigned char reserved[128];
+        } value;
+        union {
+                unsigned short d[4];            /* dimensions */
+                unsigned short *d_ptr;          /* indirect - obsoleted */
+        } dimen;
+        unsigned char reserved[64-4*sizeof(unsigned short)];
+};
+
+struct snd_ctl_elem_value {
+        struct snd_ctl_elem_id id;      /* W: element ID */
+        unsigned int indirect: 1;       /* W: indirect access - obsoleted */
+        union {
+                union {
+                        long value[128];
+                        long *value_ptr;        /* obsoleted */
+                } integer;
+                union {
+                        long long value[64];
+                        long long *value_ptr;   /* obsoleted */
+                } integer64;
+                union {
+                        unsigned int item[128];
+                        unsigned int *item_ptr; /* obsoleted */
+                } enumerated;
+                union {
+                        unsigned char data[512];
+                        unsigned char *data_ptr;        /* obsoleted */
+                } bytes;
+                struct snd_aes_iec958 iec958;
+        } value;                /* RO */
+        struct timespec tstamp;
+        unsigned char reserved[128-sizeof(struct timespec)];
+};
+
+struct snd_ctl_tlv {
+        unsigned int numid;     /* control element numeric identification */
+        unsigned int length;    /* in bytes aligned to 4 */
+        unsigned int tlv[0];    /* first TLV */
+};
+
+#define SNDRV_CTL_IOCTL_PVERSION        _IOR('U', 0x00, int)
+#define SNDRV_CTL_IOCTL_CARD_INFO       _IOR('U', 0x01, struct snd_ctl_card_info)
+#define SNDRV_CTL_IOCTL_ELEM_LIST       _IOWR('U', 0x10, struct snd_ctl_elem_list)
+#define SNDRV_CTL_IOCTL_ELEM_INFO       _IOWR('U', 0x11, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_READ       _IOWR('U', 0x12, struct snd_ctl_elem_value)
+#define SNDRV_CTL_IOCTL_ELEM_WRITE      _IOWR('U', 0x13, struct snd_ctl_elem_value)
+#define SNDRV_CTL_IOCTL_ELEM_LOCK       _IOW('U', 0x14, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_ELEM_UNLOCK     _IOW('U', 0x15, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_SUBSCRIBE_EVENTS _IOWR('U', 0x16, int)
+#define SNDRV_CTL_IOCTL_ELEM_ADD        _IOWR('U', 0x17, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_REPLACE    _IOWR('U', 0x18, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_REMOVE     _IOWR('U', 0x19, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_TLV_READ        _IOWR('U', 0x1a, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_TLV_WRITE       _IOWR('U', 0x1b, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_TLV_COMMAND     _IOWR('U', 0x1c, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_HWDEP_NEXT_DEVICE _IOWR('U', 0x20, int)
+#define SNDRV_CTL_IOCTL_HWDEP_INFO      _IOR('U', 0x21, struct snd_hwdep_info)
+#define SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE _IOR('U', 0x30, int)
+#define SNDRV_CTL_IOCTL_PCM_INFO        _IOWR('U', 0x31, struct snd_pcm_info)
+#define SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE _IOW('U', 0x32, int)
+#define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int)
+#define SNDRV_CTL_IOCTL_RAWMIDI_INFO    _IOWR('U', 0x41, struct snd_rawmidi_info)
+#define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int)
+#define SNDRV_CTL_IOCTL_POWER           _IOWR('U', 0xd0, int)
+#define SNDRV_CTL_IOCTL_POWER_STATE     _IOR('U', 0xd1, int)
+
+/*
+ *  Read interface.
+ */
+
+enum sndrv_ctl_event_type {
+        SNDRV_CTL_EVENT_ELEM = 0,
+        SNDRV_CTL_EVENT_LAST = SNDRV_CTL_EVENT_ELEM,
+};
+
+#define SNDRV_CTL_EVENT_MASK_VALUE      (1<<0)  /* element value was changed */
+#define SNDRV_CTL_EVENT_MASK_INFO       (1<<1)  /* element info was changed */
+#define SNDRV_CTL_EVENT_MASK_ADD        (1<<2)  /* element was added */
+#define SNDRV_CTL_EVENT_MASK_TLV        (1<<3)  /* element TLV tree was changed */
+#define SNDRV_CTL_EVENT_MASK_REMOVE     (~0U)   /* element was removed */
+
+struct snd_ctl_event {
+        int type;       /* event type - SNDRV_CTL_EVENT_* */
+        union {
+                struct {
+                        unsigned int mask;
+                        struct snd_ctl_elem_id id;
+                } elem;
+                unsigned char data8[60];
+        } data;
+};
+
+/*
+ *  Control names
+ */
+
+#define SNDRV_CTL_NAME_NONE                             ""
+#define SNDRV_CTL_NAME_PLAYBACK                         "Playback "
+#define SNDRV_CTL_NAME_CAPTURE                          "Capture "
+
+#define SNDRV_CTL_NAME_IEC958_NONE                      ""
+#define SNDRV_CTL_NAME_IEC958_SWITCH                    "Switch"
+#define SNDRV_CTL_NAME_IEC958_VOLUME                    "Volume"
+#define SNDRV_CTL_NAME_IEC958_DEFAULT                   "Default"
+#define SNDRV_CTL_NAME_IEC958_MASK                      "Mask"
+#define SNDRV_CTL_NAME_IEC958_CON_MASK                  "Con Mask"
+#define SNDRV_CTL_NAME_IEC958_PRO_MASK                  "Pro Mask"
+#define SNDRV_CTL_NAME_IEC958_PCM_STREAM                "PCM Stream"
+#define SNDRV_CTL_NAME_IEC958(expl,direction,what)      "IEC958 " expl SNDRV_CTL_NAME_##direction SNDRV_CTL_NAME_IEC958_##what
+
+#endif /* _UAPI__SOUND_ASOUND_H */
diff --git a/tools/kvm/kvm_stat/Makefile b/tools/kvm/kvm_stat/Makefile
index 5b1cba57e3b3..c3e36c60d477 100644
--- a/tools/kvm/kvm_stat/Makefile
+++ b/tools/kvm/kvm_stat/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 include ../../scripts/Makefile.include
 include ../../scripts/utilities.mak
 BINDIR=usr/bin
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index dd8f00cfb8b4..217cf6f95c36 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -19,9 +19,11 @@ Three different ways of output formatting are available:
 
 The data is sampled from the KVM's debugfs entries and its perf events.
 """
+from __future__ import print_function
 
 import curses
 import sys
+import locale
 import os
 import time
 import optparse
@@ -225,6 +227,8 @@ IOCTL_NUMBERS = {
     'RESET':       0x00002403,
 }
 
+ENCODING = locale.getpreferredencoding(False)
+
 
 class Arch(object):
     """Encapsulates global architecture specific data.
@@ -474,7 +478,7 @@ class Provider(object):
     @staticmethod
     def is_field_wanted(fields_filter, field):
         """Indicate whether field is valid according to fields_filter."""
-        if not fields_filter:
+        if not fields_filter or fields_filter == "help":
             return True
         return re.match(fields_filter, field) is not None
 
@@ -666,7 +670,7 @@ class TracepointProvider(Provider):
         """Returns 'event name: current value' for all enabled events."""
         ret = defaultdict(int)
         for group in self.group_leaders:
-            for name, val in group.read().iteritems():
+            for name, val in group.read().items():
                 if name in self._fields:
                     ret[name] += val
         return ret
@@ -955,7 +959,7 @@ class Tui(object):
         except:
             raise Exception
         for line in child.stdout:
-            line = line.lstrip().split(' ', 1)
+            line = line.decode(ENCODING).lstrip().split(' ', 1)
             # perform a sanity check before calling the more expensive
             # function to possibly extract the guest name
             if ' -name ' in line[1]:
@@ -1005,7 +1009,7 @@ class Tui(object):
         name = ''
         try:
             line = open('/proc/{}/cmdline'
-                        .format(pid), 'rb').read().split('\0')
+                        .format(pid), 'r').read().split('\0')
             parms = line[line.index('-name') + 1].split(',')
             while '' in parms:
                 # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results
@@ -1170,7 +1174,7 @@ class Tui(object):
                                .format(self.stats.fields_filter))
             self.screen.addstr(3, 0, "New regex: ")
             curses.echo()
-            regex = self.screen.getstr()
+            regex = self.screen.getstr().decode(ENCODING)
             curses.noecho()
             if len(regex) == 0:
                 self.stats.fields_filter = DEFAULT_REGEX
@@ -1204,7 +1208,7 @@ class Tui(object):
 
             curses.echo()
             self.screen.addstr(3, 0, "Pid [0 or pid]: ")
-            pid = self.screen.getstr()
+            pid = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
             try:
@@ -1233,7 +1237,7 @@ class Tui(object):
             self.screen.addstr(2, 0, 'Change delay from %.1fs to ' %
                                self._delay_regular)
             curses.echo()
-            val = self.screen.getstr()
+            val = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
             try:
@@ -1273,7 +1277,7 @@ class Tui(object):
             self.print_all_gnames(7)
             curses.echo()
             self.screen.addstr(3, 0, "Guest [ENTER or guest]: ")
-            gname = self.screen.getstr()
+            gname = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
             if not gname:
@@ -1369,25 +1373,25 @@ def batch(stats):
         s = stats.get()
         for key in sorted(s.keys()):
             values = s[key]
-            print '%-42s%10d%10d' % (key, values[0], values[1])
+            print('%-42s%10d%10d' % (key, values[0], values[1]))
     except KeyboardInterrupt:
         pass
 
 
 def log(stats):
     """Prints statistics as reiterating key block, multiple value blocks."""
-    keys = sorted(stats.get().iterkeys())
+    keys = sorted(stats.get().keys())
 
     def banner():
         for k in keys:
-            print '%s' % k,
-        print
+            print(k, end=' ')
+        print()
 
     def statline():
         s = stats.get()
         for k in keys:
-            print ' %9d' % s[k][1],
-        print
+            print(' %9d' % s[k][1], end=' ')
+        print()
     line = 0
     banner_repeat = 20
     while True:
@@ -1413,8 +1417,8 @@ performance.
 
 Requirements:
 - Access to:
-    /sys/kernel/debug/kvm
-    /sys/kernel/debug/trace/events/*
+    %s
+    %s/events/*
     /proc/pid/task
 - /proc/sys/kernel/perf_event_paranoid < 1 if user has no
   CAP_SYS_ADMIN and perf events are used.
@@ -1434,7 +1438,7 @@ Interactive Commands:
    s     set update interval
    x     toggle reporting of stats for individual child trace events
 Press any other key to refresh statistics immediately.
-"""
+""" % (PATH_DEBUGFS_KVM, PATH_DEBUGFS_TRACING)
 
     class PlainHelpFormatter(optparse.IndentedHelpFormatter):
         def format_description(self, description):
@@ -1496,7 +1500,8 @@ Press any other key to refresh statistics immediately.
                          action='store',
                          default=DEFAULT_REGEX,
                          dest='fields',
-                         help='fields to display (regex)',
+                         help='''fields to display (regex)
+                                 "-f help" for a list of available events''',
                          )
     optparser.add_option('-p', '--pid',
                          action='store',
@@ -1559,6 +1564,17 @@ def main():
 
     stats = Stats(options)
 
+    if options.fields == "help":
+        event_list = "\n"
+        s = stats.get()
+        for key in s.keys():
+            if key.find('(') != -1:
+                key = key[0:key.find('(')]
+            if event_list.find('\n' + key + '\n') == -1:
+                event_list += key + '\n'
+        sys.stdout.write(event_list)
+        return ""
+
     if options.log:
         log(stats)
     elif not options.once:
diff --git a/tools/laptop/dslm/Makefile b/tools/laptop/dslm/Makefile
index ff613b31730b..90f512c4e2bb 100644
--- a/tools/laptop/dslm/Makefile
+++ b/tools/laptop/dslm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC := $(CROSS_COMPILE)gcc
 CFLAGS := -I../../usr/include
 
diff --git a/tools/laptop/freefall/Makefile b/tools/laptop/freefall/Makefile
index 48c6c9328419..5f758c489a20 100644
--- a/tools/laptop/freefall/Makefile
+++ b/tools/laptop/freefall/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 PREFIX ?= /usr
 SBINDIR ?= sbin
 INSTALL ?= install
diff --git a/tools/leds/Makefile b/tools/leds/Makefile
index 078b666fd78b..c379af003807 100644
--- a/tools/leds/Makefile
+++ b/tools/leds/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for LEDs tools
 
 CC = $(CROSS_COMPILE)gcc
diff --git a/tools/leds/led_hw_brightness_mon.c b/tools/leds/led_hw_brightness_mon.c
index 64642ccfe442..eb65ae988839 100644
--- a/tools/leds/led_hw_brightness_mon.c
+++ b/tools/leds/led_hw_brightness_mon.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * led_hw_brightness_mon.c
  *
diff --git a/tools/leds/uledmon.c b/tools/leds/uledmon.c
index 25cbc7acf50a..c15a39c1f271 100644
--- a/tools/leds/uledmon.c
+++ b/tools/leds/uledmon.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * uledmon.c
  *
diff --git a/tools/lguest/.gitignore b/tools/lguest/.gitignore
deleted file mode 100644
index 8d9a8383a52e..000000000000
--- a/tools/lguest/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-lguest
-include
diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile
deleted file mode 100644
index d04599a79802..000000000000
--- a/tools/lguest/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude
-
-all: lguest
-
-include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h
-        mkdir -p include/linux 2>&1 || true
-        ln -sf ../../../../include/uapi/linux/virtio_types.h $@
-
-lguest: include/linux/virtio_types.h
-
-clean:
-        rm -f lguest
-        rm -rf include
diff --git a/tools/lguest/extract b/tools/lguest/extract
deleted file mode 100644
index 7730bb6e4b94..000000000000
--- a/tools/lguest/extract
+++ /dev/null
@@ -1,58 +0,0 @@
-#! /bin/sh
-
-set -e
-
-PREFIX=$1
-shift
-
-trap 'rm -r $TMPDIR' 0
-TMPDIR=`mktemp -d`
-
-exec 3>/dev/null
-for f; do
-    while IFS="
-" read -r LINE; do
-        case "$LINE" in
-            *$PREFIX:[0-9]*:\**)
-                NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"`
-                if [ -f $TMPDIR/$NUM ]; then
-                    echo "$TMPDIR/$NUM already exits prior to $f"
-                    exit 1
-                fi
-                exec 3>>$TMPDIR/$NUM
-                echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM
-                /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3
-                ;;
-            *$PREFIX:[0-9]*)
-                NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"`
-                if [ -f $TMPDIR/$NUM ]; then
-                    echo "$TMPDIR/$NUM already exits prior to $f"
-                    exit 1
-                fi
-                exec 3>>$TMPDIR/$NUM
-                echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM
-                /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3
-                ;;
-            *:\**)
-                /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3
-                echo >&3
-                exec 3>/dev/null
-                ;;
-            *)
-                /bin/echo "$LINE" >&3
-                ;;
-        esac
-    done < $f
-    echo >&3
-    exec 3>/dev/null
-done
-
-LASTFILE=""
-for f in $TMPDIR/*; do
-    if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then
-        LASTFILE=$(cat $TMPDIR/.$(basename $f) )
-        echo "[ $LASTFILE ]"
-    fi
-    cat $f
-done
-
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
deleted file mode 100644
index 897cd6f3f687..000000000000
--- a/tools/lguest/lguest.c
+++ /dev/null
@@ -1,3420 +0,0 @@
-/*P:100
- * This is the Launcher code, a simple program which lays out the "physical"
- * memory for the new Guest by mapping the kernel image and the virtual
- * devices, then opens /dev/lguest to tell the kernel about the Guest and
- * control it.
-:*/
-#define _LARGEFILE64_SOURCE
-#define _GNU_SOURCE
-#include <stdio.h>
-#include <string.h>
-#include <unistd.h>
-#include <err.h>
-#include <stdint.h>
-#include <stdlib.h>
-#include <elf.h>
-#include <sys/mman.h>
-#include <sys/param.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <sys/wait.h>
-#include <sys/eventfd.h>
-#include <fcntl.h>
-#include <stdbool.h>
-#include <errno.h>
-#include <ctype.h>
-#include <sys/socket.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
-#include <time.h>
-#include <netinet/in.h>
-#include <net/if.h>
-#include <linux/sockios.h>
-#include <linux/if_tun.h>
-#include <sys/uio.h>
-#include <termios.h>
-#include <getopt.h>
-#include <assert.h>
-#include <sched.h>
-#include <limits.h>
-#include <stddef.h>
-#include <signal.h>
-#include <pwd.h>
-#include <grp.h>
-#include <sys/user.h>
-#include <linux/pci_regs.h>
-
-#ifndef VIRTIO_F_ANY_LAYOUT
-#define VIRTIO_F_ANY_LAYOUT             27
-#endif
-
-/*L:110
- * We can ignore the 43 include files we need for this program, but I do want
- * to draw attention to the use of kernel-style types.
- *
- * As Linus said, "C is a Spartan language, and so should your naming be."  I
- * like these abbreviations, so we define them here.  Note that u64 is always
- * unsigned long long, which works on all Linux systems: this means that we can
- * use %llu in printf for any u64.
- */
-typedef unsigned long long u64;
-typedef uint32_t u32;
-typedef uint16_t u16;
-typedef uint8_t u8;
-/*:*/
-
-#define VIRTIO_CONFIG_NO_LEGACY
-#define VIRTIO_PCI_NO_LEGACY
-#define VIRTIO_BLK_NO_LEGACY
-#define VIRTIO_NET_NO_LEGACY
-
-/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */
-#include "../../include/uapi/linux/virtio_config.h"
-#include "../../include/uapi/linux/virtio_net.h"
-#include "../../include/uapi/linux/virtio_blk.h"
-#include "../../include/uapi/linux/virtio_console.h"
-#include "../../include/uapi/linux/virtio_rng.h"
-#include <linux/virtio_ring.h>
-#include "../../include/uapi/linux/virtio_pci.h"
-#include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
-
-#define BRIDGE_PFX "bridge:"
-#ifndef SIOCBRADDIF
-#define SIOCBRADDIF     0x89a2          /* add interface to bridge      */
-#endif
-/* We can have up to 256 pages for devices. */
-#define DEVICE_PAGES 256
-/* This will occupy 3 pages: it must be a power of 2. */
-#define VIRTQUEUE_NUM 256
-
-/*L:120
- * verbose is both a global flag and a macro.  The C preprocessor allows
- * this, and although I wouldn't recommend it, it works quite nicely here.
- */
-static bool verbose;
-#define verbose(args...) \
-        do { if (verbose) printf(args); } while(0)
-/*:*/
-
-/* The pointer to the start of guest memory. */
-static void *guest_base;
-/* The maximum guest physical address allowed, and maximum possible. */
-static unsigned long guest_limit, guest_max, guest_mmio;
-/* The /dev/lguest file descriptor. */
-static int lguest_fd;
-
-/* a per-cpu variable indicating whose vcpu is currently running */
-static unsigned int __thread cpu_id;
-
-/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */
-#define MAX_PCI_DEVICES 32
-
-/* This is our list of devices. */
-struct device_list {
-        /* Counter to assign interrupt numbers. */
-        unsigned int next_irq;
-
-        /* Counter to print out convenient device numbers. */
-        unsigned int device_num;
-
-        /* PCI devices. */
-        struct device *pci[MAX_PCI_DEVICES];
-};
-
-/* The list of Guest devices, based on command line arguments. */
-static struct device_list devices;
-
-/*
- * Just like struct virtio_pci_cfg_cap in uapi/linux/virtio_pci.h,
- * but uses a u32 explicitly for the data.
- */
-struct virtio_pci_cfg_cap_u32 {
-        struct virtio_pci_cap cap;
-        u32 pci_cfg_data; /* Data for BAR access. */
-};
-
-struct virtio_pci_mmio {
-        struct virtio_pci_common_cfg cfg;
-        u16 notify;
-        u8 isr;
-        u8 padding;
-        /* Device-specific configuration follows this. */
-};
-
-/* This is the layout (little-endian) of the PCI config space. */
-struct pci_config {
-        u16 vendor_id, device_id;
-        u16 command, status;
-        u8 revid, prog_if, subclass, class;
-        u8 cacheline_size, lat_timer, header_type, bist;
-        u32 bar[6];
-        u32 cardbus_cis_ptr;
-        u16 subsystem_vendor_id, subsystem_device_id;
-        u32 expansion_rom_addr;
-        u8 capabilities, reserved1[3];
-        u32 reserved2;
-        u8 irq_line, irq_pin, min_grant, max_latency;
-
-        /* Now, this is the linked capability list. */
-        struct virtio_pci_cap common;
-        struct virtio_pci_notify_cap notify;
-        struct virtio_pci_cap isr;
-        struct virtio_pci_cap device;
-        struct virtio_pci_cfg_cap_u32 cfg_access;
-};
-
-/* The device structure describes a single device. */
-struct device {
-        /* The name of this device, for --verbose. */
-        const char *name;
-
-        /* Any queues attached to this device */
-        struct virtqueue *vq;
-
-        /* Is it operational */
-        bool running;
-
-        /* Has it written FEATURES_OK but not re-checked it? */
-        bool wrote_features_ok;
-
-        /* PCI configuration */
-        union {
-                struct pci_config config;
-                u32 config_words[sizeof(struct pci_config) / sizeof(u32)];
-        };
-
-        /* Features we offer, and those accepted. */
-        u64 features, features_accepted;
-
-        /* Device-specific config hangs off the end of this. */
-        struct virtio_pci_mmio *mmio;
-
-        /* PCI MMIO resources (all in BAR0) */
-        size_t mmio_size;
-        u32 mmio_addr;
-
-        /* Device-specific data. */
-        void *priv;
-};
-
-/* The virtqueue structure describes a queue attached to a device. */
-struct virtqueue {
-        struct virtqueue *next;
-
-        /* Which device owns me. */
-        struct device *dev;
-
-        /* Name for printing errors. */
-        const char *name;
-
-        /* The actual ring of buffers. */
-        struct vring vring;
-
-        /* The information about this virtqueue (we only use queue_size on) */
-        struct virtio_pci_common_cfg pci_config;
-
-        /* Last available index we saw. */
-        u16 last_avail_idx;
-
-        /* How many are used since we sent last irq? */
-        unsigned int pending_used;
-
-        /* Eventfd where Guest notifications arrive. */
-        int eventfd;
-
-        /* Function for the thread which is servicing this virtqueue. */
-        void (*service)(struct virtqueue *vq);
-        pid_t thread;
-};
-
-/* Remember the arguments to the program so we can "reboot" */
-static char **main_args;
-
-/* The original tty settings to restore on exit. */
-static struct termios orig_term;
-
-/*
- * We have to be careful with barriers: our devices are all run in separate
- * threads and so we need to make sure that changes visible to the Guest happen
- * in precise order.
- */
-#define wmb() __asm__ __volatile__("" : : : "memory")
-#define rmb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory")
-#define mb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory")
-
-/* Wrapper for the last available index.  Makes it easier to change. */
-#define lg_last_avail(vq)       ((vq)->last_avail_idx)
-
-/*
- * The virtio configuration space is defined to be little-endian.  x86 is
- * little-endian too, but it's nice to be explicit so we have these helpers.
- */
-#define cpu_to_le16(v16) (v16)
-#define cpu_to_le32(v32) (v32)
-#define cpu_to_le64(v64) (v64)
-#define le16_to_cpu(v16) (v16)
-#define le32_to_cpu(v32) (v32)
-#define le64_to_cpu(v64) (v64)
-
-/*
- * A real device would ignore weird/non-compliant driver behaviour.  We
- * stop and flag it, to help debugging Linux problems.
- */
-#define bad_driver(d, fmt, ...) \
-        errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__)
-#define bad_driver_vq(vq, fmt, ...)                            \
-        errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \
-             vq->name, ## __VA_ARGS__)
-
-/* Is this iovec empty? */
-static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
-{
-        unsigned int i;
-
-        for (i = 0; i < num_iov; i++)
-                if (iov[i].iov_len)
-                        return false;
-        return true;
-}
-
-/* Take len bytes from the front of this iovec. */
-static void iov_consume(struct device *d,
-                        struct iovec iov[], unsigned num_iov,
-                        void *dest, unsigned len)
-{
-        unsigned int i;
-
-        for (i = 0; i < num_iov; i++) {
-                unsigned int used;
-
-                used = iov[i].iov_len < len ? iov[i].iov_len : len;
-                if (dest) {
-                        memcpy(dest, iov[i].iov_base, used);
-                        dest += used;
-                }
-                iov[i].iov_base += used;
-                iov[i].iov_len -= used;
-                len -= used;
-        }
-        if (len != 0)
-                bad_driver(d, "iovec too short!");
-}
-
-/*L:100
- * The Launcher code itself takes us out into userspace, that scary place where
- * pointers run wild and free!  Unfortunately, like most userspace programs,
- * it's quite boring (which is why everyone likes to hack on the kernel!).
- * Perhaps if you make up an Lguest Drinking Game at this point, it will get
- * you through this section.  Or, maybe not.
- *
- * The Launcher sets up a big chunk of memory to be the Guest's "physical"
- * memory and stores it in "guest_base".  In other words, Guest physical ==
- * Launcher virtual with an offset.
- *
- * This can be tough to get your head around, but usually it just means that we
- * use these trivial conversion functions when the Guest gives us its
- * "physical" addresses:
- */
-static void *from_guest_phys(unsigned long addr)
-{
-        return guest_base + addr;
-}
-
-static unsigned long to_guest_phys(const void *addr)
-{
-        return (addr - guest_base);
-}
-
-/*L:130
- * Loading the Kernel.
- *
- * We start with couple of simple helper routines.  open_or_die() avoids
- * error-checking code cluttering the callers:
- */
-static int open_or_die(const char *name, int flags)
-{
-        int fd = open(name, flags);
-        if (fd < 0)
-                err(1, "Failed to open %s", name);
-        return fd;
-}
-
-/* map_zeroed_pages() takes a number of pages. */
-static void *map_zeroed_pages(unsigned int num)
-{
-        int fd = open_or_die("/dev/zero", O_RDONLY);
-        void *addr;
-
-        /*
-         * We use a private mapping (ie. if we write to the page, it will be
-         * copied). We allocate an extra two pages PROT_NONE to act as guard
-         * pages against read/write attempts that exceed allocated space.
-         */
-        addr = mmap(NULL, getpagesize() * (num+2),
-                    PROT_NONE, MAP_PRIVATE, fd, 0);
-
-        if (addr == MAP_FAILED)
-                err(1, "Mmapping %u pages of /dev/zero", num);
-
-        if (mprotect(addr + getpagesize(), getpagesize() * num,
-                     PROT_READ|PROT_WRITE) == -1)
-                err(1, "mprotect rw %u pages failed", num);
-
-        /*
-         * One neat mmap feature is that you can close the fd, and it
-         * stays mapped.
-         */
-        close(fd);
-
-        /* Return address after PROT_NONE page */
-        return addr + getpagesize();
-}
-
-/* Get some bytes which won't be mapped into the guest. */
-static unsigned long get_mmio_region(size_t size)
-{
-        unsigned long addr = guest_mmio;
-        size_t i;
-
-        if (!size)
-                return addr;
-
-        /* Size has to be a power of 2 (and multiple of 16) */
-        for (i = 1; i < size; i <<= 1);
-
-        guest_mmio += i;
-
-        return addr;
-}
-
-/*
- * This routine is used to load the kernel or initrd.  It tries mmap, but if
- * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries),
- * it falls back to reading the memory in.
- */
-static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
-{
-        ssize_t r;
-
-        /*
-         * We map writable even though for some segments are marked read-only.
-         * The kernel really wants to be writable: it patches its own
-         * instructions.
-         *
-         * MAP_PRIVATE means that the page won't be copied until a write is
-         * done to it.  This allows us to share untouched memory between
-         * Guests.
-         */
-        if (mmap(addr, len, PROT_READ|PROT_WRITE,
-                 MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
-                return;
-
-        /* pread does a seek and a read in one shot: saves a few lines. */
-        r = pread(fd, addr, len, offset);
-        if (r != len)
-                err(1, "Reading offset %lu len %lu gave %zi", offset, len, r);
-}
-
-/*
- * This routine takes an open vmlinux image, which is in ELF, and maps it into
- * the Guest memory.  ELF = Embedded Linking Format, which is the format used
- * by all modern binaries on Linux including the kernel.
- *
- * The ELF headers give *two* addresses: a physical address, and a virtual
- * address.  We use the physical address; the Guest will map itself to the
- * virtual address.
- *
- * We return the starting address.
- */
-static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
-{
-        Elf32_Phdr phdr[ehdr->e_phnum];
-        unsigned int i;
-
-        /*
-         * Sanity checks on the main ELF header: an x86 executable with a
-         * reasonable number of correctly-sized program headers.
-         */
-        if (ehdr->e_type != ET_EXEC
-            || ehdr->e_machine != EM_386
-            || ehdr->e_phentsize != sizeof(Elf32_Phdr)
-            || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr))
-                errx(1, "Malformed elf header");
-
-        /*
-         * An ELF executable contains an ELF header and a number of "program"
-         * headers which indicate which parts ("segments") of the program to
-         * load where.
-         */
-
-        /* We read in all the program headers at once: */
-        if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0)
-                err(1, "Seeking to program headers");
-        if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr))
-                err(1, "Reading program headers");
-
-        /*
-         * Try all the headers: there are usually only three.  A read-only one,
-         * a read-write one, and a "note" section which we don't load.
-         */
-        for (i = 0; i < ehdr->e_phnum; i++) {
-                /* If this isn't a loadable segment, we ignore it */
-                if (phdr[i].p_type != PT_LOAD)
-                        continue;
-
-                verbose("Section %i: size %i addr %p\n",
-                        i, phdr[i].p_memsz, (void *)phdr[i].p_paddr);
-
-                /* We map this section of the file at its physical address. */
-                map_at(elf_fd, from_guest_phys(phdr[i].p_paddr),
-                       phdr[i].p_offset, phdr[i].p_filesz);
-        }
-
-        /* The entry point is given in the ELF header. */
-        return ehdr->e_entry;
-}
-
-/*L:150
- * A bzImage, unlike an ELF file, is not meant to be loaded.  You're supposed
- * to jump into it and it will unpack itself.  We used to have to perform some
- * hairy magic because the unpacking code scared me.
- *
- * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote
- * a small patch to jump over the tricky bits in the Guest, so now we just read
- * the funky header so we know where in the file to load, and away we go!
- */
-static unsigned long load_bzimage(int fd)
-{
-        struct boot_params boot;
-        int r;
-        /* Modern bzImages get loaded at 1M. */
-        void *p = from_guest_phys(0x100000);
-
-        /*
-         * Go back to the start of the file and read the header.  It should be
-         * a Linux boot header (see Documentation/x86/boot.txt)
-         */
-        lseek(fd, 0, SEEK_SET);
-        read(fd, &boot, sizeof(boot));
-
-        /* Inside the setup_hdr, we expect the magic "HdrS" */
-        if (memcmp(&boot.hdr.header, "HdrS", 4) != 0)
-                errx(1, "This doesn't look like a bzImage to me");
-
-        /* Skip over the extra sectors of the header. */
-        lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET);
-
-        /* Now read everything into memory. in nice big chunks. */
-        while ((r = read(fd, p, 65536)) > 0)
-                p += r;
-
-        /* Finally, code32_start tells us where to enter the kernel. */
-        return boot.hdr.code32_start;
-}
-
-/*L:140
- * Loading the kernel is easy when it's a "vmlinux", but most kernels
- * come wrapped up in the self-decompressing "bzImage" format.  With a little
- * work, we can load those, too.
- */
-static unsigned long load_kernel(int fd)
-{
-        Elf32_Ehdr hdr;
-
-        /* Read in the first few bytes. */
-        if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr))
-                err(1, "Reading kernel");
-
-        /* If it's an ELF file, it starts with "\177ELF" */
-        if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0)
-                return map_elf(fd, &hdr);
-
-        /* Otherwise we assume it's a bzImage, and try to load it. */
-        return load_bzimage(fd);
-}
-
-/*
- * This is a trivial little helper to align pages.  Andi Kleen hated it because
- * it calls getpagesize() twice: "it's dumb code."
- *
- * Kernel guys get really het up about optimization, even when it's not
- * necessary.  I leave this code as a reaction against that.
- */
-static inline unsigned long page_align(unsigned long addr)
-{
-        /* Add upwards and truncate downwards. */
-        return ((addr + getpagesize()-1) & ~(getpagesize()-1));
-}
-
-/*L:180
- * An "initial ram disk" is a disk image loaded into memory along with the
- * kernel which the kernel can use to boot from without needing any drivers.
- * Most distributions now use this as standard: the initrd contains the code to
- * load the appropriate driver modules for the current machine.
- *
- * Importantly, James Morris works for RedHat, and Fedora uses initrds for its
- * kernels.  He sent me this (and tells me when I break it).
- */
-static unsigned long load_initrd(const char *name, unsigned long mem)
-{
-        int ifd;
-        struct stat st;
-        unsigned long len;
-
-        ifd = open_or_die(name, O_RDONLY);
-        /* fstat() is needed to get the file size. */
-        if (fstat(ifd, &st) < 0)
-                err(1, "fstat() on initrd '%s'", name);
-
-        /*
-         * We map the initrd at the top of memory, but mmap wants it to be
-         * page-aligned, so we round the size up for that.
-         */
-        len = page_align(st.st_size);
-        map_at(ifd, from_guest_phys(mem - len), 0, st.st_size);
-        /*
-         * Once a file is mapped, you can close the file descriptor.  It's a
-         * little odd, but quite useful.
-         */
-        close(ifd);
-        verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len);
-
-        /* We return the initrd size. */
-        return len;
-}
-/*:*/
-
-/*
- * Simple routine to roll all the commandline arguments together with spaces
- * between them.
- */
-static void concat(char *dst, char *args[])
-{
-        unsigned int i, len = 0;
-
-        for (i = 0; args[i]; i++) {
-                if (i) {
-                        strcat(dst+len, " ");
-                        len++;
-                }
-                strcpy(dst+len, args[i]);
-                len += strlen(args[i]);
-        }
-        /* In case it's empty. */
-        dst[len] = '\0';
-}
-
-/*L:185
- * This is where we actually tell the kernel to initialize the Guest.  We
- * saw the arguments it expects when we looked at initialize() in lguest_user.c:
- * the base of Guest "physical" memory, the top physical page to allow and the
- * entry point for the Guest.
- */
-static void tell_kernel(unsigned long start)
-{
-        unsigned long args[] = { LHREQ_INITIALIZE,
-                                 (unsigned long)guest_base,
-                                 guest_limit / getpagesize(), start,
-                                 (guest_mmio+getpagesize()-1) / getpagesize() };
-        verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n",
-                guest_base, guest_base + guest_limit,
-                guest_limit, guest_mmio);
-        lguest_fd = open_or_die("/dev/lguest", O_RDWR);
-        if (write(lguest_fd, args, sizeof(args)) < 0)
-                err(1, "Writing to /dev/lguest");
-}
-/*:*/
-
-/*L:200
- * Device Handling.
- *
- * When the Guest gives us a buffer, it sends an array of addresses and sizes.
- * We need to make sure it's not trying to reach into the Launcher itself, so
- * we have a convenient routine which checks it and exits with an error message
- * if something funny is going on:
- */
-static void *_check_pointer(struct device *d,
-                            unsigned long addr, unsigned int size,
-                            unsigned int line)
-{
-        /*
-         * Check if the requested address and size exceeds the allocated memory,
-         * or addr + size wraps around.
-         */
-        if ((addr + size) > guest_limit || (addr + size) < addr)
-                bad_driver(d, "%s:%i: Invalid address %#lx",
-                           __FILE__, line, addr);
-        /*
-         * We return a pointer for the caller's convenience, now we know it's
-         * safe to use.
-         */
-        return from_guest_phys(addr);
-}
-/* A macro which transparently hands the line number to the real function. */
-#define check_pointer(d,addr,size) _check_pointer(d, addr, size, __LINE__)
-
-/*
- * Each buffer in the virtqueues is actually a chain of descriptors.  This
- * function returns the next descriptor in the chain, or vq->vring.num if we're
- * at the end.
- */
-static unsigned next_desc(struct device *d, struct vring_desc *desc,
-                          unsigned int i, unsigned int max)
-{
-        unsigned int next;
-
-        /* If this descriptor says it doesn't chain, we're done. */
-        if (!(desc[i].flags & VRING_DESC_F_NEXT))
-                return max;
-
-        /* Check they're not leading us off end of descriptors. */
-        next = desc[i].next;
-        /* Make sure compiler knows to grab that: we don't want it changing! */
-        wmb();
-
-        if (next >= max)
-                bad_driver(d, "Desc next is %u", next);
-
-        return next;
-}
-
-/*
- * This actually sends the interrupt for this virtqueue, if we've used a
- * buffer.
- */
-static void trigger_irq(struct virtqueue *vq)
-{
-        unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line };
-
-        /* Don't inform them if nothing used. */
-        if (!vq->pending_used)
-                return;
-        vq->pending_used = 0;
-
-        /*
-         * 2.4.7.1:
-         *
-         *  If the VIRTIO_F_EVENT_IDX feature bit is not negotiated:
-         *    The driver MUST set flags to 0 or 1. 
-         */
-        if (vq->vring.avail->flags > 1)
-                bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags);
-
-        /*
-         * 2.4.7.2:
-         *
-         *  If the VIRTIO_F_EVENT_IDX feature bit is not negotiated:
-         *
-         *     - The device MUST ignore the used_event value.
-         *     - After the device writes a descriptor index into the used ring:
-         *         - If flags is 1, the device SHOULD NOT send an interrupt.
-         *         - If flags is 0, the device MUST send an interrupt.
-         */
-        if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
-                return;
-        }
-
-        /*
-         * 4.1.4.5.1:
-         *
-         *  If MSI-X capability is disabled, the device MUST set the Queue
-         *  Interrupt bit in ISR status before sending a virtqueue notification
-         *  to the driver.
-         */
-        vq->dev->mmio->isr = 0x1;
-
-        /* Send the Guest an interrupt tell them we used something up. */
-        if (write(lguest_fd, buf, sizeof(buf)) != 0)
-                err(1, "Triggering irq %i", vq->dev->config.irq_line);
-}
-
-/*
- * This looks in the virtqueue for the first available buffer, and converts
- * it to an iovec for convenient access.  Since descriptors consist of some
- * number of output then some number of input descriptors, it's actually two
- * iovecs, but we pack them into one and note how many of each there were.
- *
- * This function waits if necessary, and returns the descriptor number found.
- */
-static unsigned wait_for_vq_desc(struct virtqueue *vq,
-                                 struct iovec iov[],
-                                 unsigned int *out_num, unsigned int *in_num)
-{
-        unsigned int i, head, max;
-        struct vring_desc *desc;
-        u16 last_avail = lg_last_avail(vq);
-
-        /*
-         * 2.4.7.1:
-         *
-         *   The driver MUST handle spurious interrupts from the device.
-         *
-         * That's why this is a while loop.
-         */
-
-        /* There's nothing available? */
-        while (last_avail == vq->vring.avail->idx) {
-                u64 event;
-
-                /*
-                 * Since we're about to sleep, now is a good time to tell the
-                 * Guest about what we've used up to now.
-                 */
-                trigger_irq(vq);
-
-                /* OK, now we need to know about added descriptors. */
-                vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
-
-                /*
-                 * They could have slipped one in as we were doing that: make
-                 * sure it's written, then check again.
-                 */
-                mb();
-                if (last_avail != vq->vring.avail->idx) {
-                        vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
-                        break;
-                }
-
-                /* Nothing new?  Wait for eventfd to tell us they refilled. */
-                if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event))
-                        errx(1, "Event read failed?");
-
-                /* We don't need to be notified again. */
-                vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
-        }
-
-        /* Check it isn't doing very strange things with descriptor numbers. */
-        if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
-                bad_driver_vq(vq, "Guest moved used index from %u to %u",
-                              last_avail, vq->vring.avail->idx);
-
-        /* 
-         * Make sure we read the descriptor number *after* we read the ring
-         * update; don't let the cpu or compiler change the order.
-         */
-        rmb();
-
-        /*
-         * Grab the next descriptor number they're advertising, and increment
-         * the index we've seen.
-         */
-        head = vq->vring.avail->ring[last_avail % vq->vring.num];
-        lg_last_avail(vq)++;
-
-        /* If their number is silly, that's a fatal mistake. */
-        if (head >= vq->vring.num)
-                bad_driver_vq(vq, "Guest says index %u is available", head);
-
-        /* When we start there are none of either input nor output. */
-        *out_num = *in_num = 0;
-
-        max = vq->vring.num;
-        desc = vq->vring.desc;
-        i = head;
-
-        /*
-         * We have to read the descriptor after we read the descriptor number,
-         * but there's a data dependency there so the CPU shouldn't reorder
-         * that: no rmb() required.
-         */
-
-        do {
-                /*
-                 * If this is an indirect entry, then this buffer contains a
-                 * descriptor table which we handle as if it's any normal
-                 * descriptor chain.
-                 */
-                if (desc[i].flags & VRING_DESC_F_INDIRECT) {
-                        /* 2.4.5.3.1:
-                         *
-                         *  The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT
-                         *  flag unless the VIRTIO_F_INDIRECT_DESC feature was
-                         *  negotiated.
-                         */
-                        if (!(vq->dev->features_accepted &
-                              (1<<VIRTIO_RING_F_INDIRECT_DESC)))
-                                bad_driver_vq(vq, "vq indirect not negotiated");
-
-                        /*
-                         * 2.4.5.3.1:
-                         *
-                         *   The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT
-                         *   flag within an indirect descriptor (ie. only one
-                         *   table per descriptor).
-                         */
-                        if (desc != vq->vring.desc)
-                                bad_driver_vq(vq, "Indirect within indirect");
-
-                        /*
-                         * Proposed update VIRTIO-134 spells this out:
-                         *
-                         *   A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT
-                         *   and VIRTQ_DESC_F_NEXT in flags.
-                         */
-                        if (desc[i].flags & VRING_DESC_F_NEXT)
-                                bad_driver_vq(vq, "indirect and next together");
-
-                        if (desc[i].len % sizeof(struct vring_desc))
-                                bad_driver_vq(vq,
-                                              "Invalid size for indirect table");
-                        /*
-                         * 2.4.5.3.2:
-                         *
-                         *  The device MUST ignore the write-only flag
-                         *  (flags&VIRTQ_DESC_F_WRITE) in the descriptor that
-                         *  refers to an indirect table.
-                         *
-                         * We ignore it here: :)
-                         */
-
-                        max = desc[i].len / sizeof(struct vring_desc);
-                        desc = check_pointer(vq->dev, desc[i].addr, desc[i].len);
-                        i = 0;
-
-                        /* 2.4.5.3.1:
-                         *
-                         *  A driver MUST NOT create a descriptor chain longer
-                         *  than the Queue Size of the device.
-                         */
-                        if (max > vq->pci_config.queue_size)
-                                bad_driver_vq(vq,
-                                              "indirect has too many entries");
-                }
-
-                /* Grab the first descriptor, and check it's OK. */
-                iov[*out_num + *in_num].iov_len = desc[i].len;
-                iov[*out_num + *in_num].iov_base
-                        = check_pointer(vq->dev, desc[i].addr, desc[i].len);
-                /* If this is an input descriptor, increment that count. */
-                if (desc[i].flags & VRING_DESC_F_WRITE)
-                        (*in_num)++;
-                else {
-                        /*
-                         * If it's an output descriptor, they're all supposed
-                         * to come before any input descriptors.
-                         */
-                        if (*in_num)
-                                bad_driver_vq(vq,
-                                              "Descriptor has out after in");
-                        (*out_num)++;
-                }
-
-                /* If we've got too many, that implies a descriptor loop. */
-                if (*out_num + *in_num > max)
-                        bad_driver_vq(vq, "Looped descriptor");
-        } while ((i = next_desc(vq->dev, desc, i, max)) != max);
-
-        return head;
-}
-
-/*
- * After we've used one of their buffers, we tell the Guest about it.  Sometime
- * later we'll want to send them an interrupt using trigger_irq(); note that
- * wait_for_vq_desc() does that for us if it has to wait.
- */
-static void add_used(struct virtqueue *vq, unsigned int head, int len)
-{
-        struct vring_used_elem *used;
-
-        /*
-         * The virtqueue contains a ring of used buffers.  Get a pointer to the
-         * next entry in that used ring.
-         */
-        used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num];
-        used->id = head;
-        used->len = len;
-        /* Make sure buffer is written before we update index. */
-        wmb();
-        vq->vring.used->idx++;
-        vq->pending_used++;
-}
-
-/* And here's the combo meal deal.  Supersize me! */
-static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len)
-{
-        add_used(vq, head, len);
-        trigger_irq(vq);
-}
-
-/*
- * The Console
- *
- * We associate some data with the console for our exit hack.
- */
-struct console_abort {
-        /* How many times have they hit ^C? */
-        int count;
-        /* When did they start? */
-        struct timeval start;
-};
-
-/* This is the routine which handles console input (ie. stdin). */
-static void console_input(struct virtqueue *vq)
-{
-        int len;
-        unsigned int head, in_num, out_num;
-        struct console_abort *abort = vq->dev->priv;
-        struct iovec iov[vq->vring.num];
-
-        /* Make sure there's a descriptor available. */
-        head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
-        if (out_num)
-                bad_driver_vq(vq, "Output buffers in console in queue?");
-
-        /* Read into it.  This is where we usually wait. */
-        len = readv(STDIN_FILENO, iov, in_num);
-        if (len <= 0) {
-                /* Ran out of input? */
-                warnx("Failed to get console input, ignoring console.");
-                /*
-                 * For simplicity, dying threads kill the whole Launcher.  So
-                 * just nap here.
-                 */
-                for (;;)
-                        pause();
-        }
-
-        /* Tell the Guest we used a buffer. */
-        add_used_and_trigger(vq, head, len);
-
-        /*
-         * Three ^C within one second?  Exit.
-         *
-         * This is such a hack, but works surprisingly well.  Each ^C has to
-         * be in a buffer by itself, so they can't be too fast.  But we check
-         * that we get three within about a second, so they can't be too
-         * slow.
-         */
-        if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) {
-                abort->count = 0;
-                return;
-        }
-
-        abort->count++;
-        if (abort->count == 1)
-                gettimeofday(&abort->start, NULL);
-        else if (abort->count == 3) {
-                struct timeval now;
-                gettimeofday(&now, NULL);
-                /* Kill all Launcher processes with SIGINT, like normal ^C */
-                if (now.tv_sec <= abort->start.tv_sec+1)
-                        kill(0, SIGINT);
-                abort->count = 0;
-        }
-}
-
-/* This is the routine which handles console output (ie. stdout). */
-static void console_output(struct virtqueue *vq)
-{
-        unsigned int head, out, in;
-        struct iovec iov[vq->vring.num];
-
-        /* We usually wait in here, for the Guest to give us something. */
-        head = wait_for_vq_desc(vq, iov, &out, &in);
-        if (in)
-                bad_driver_vq(vq, "Input buffers in console output queue?");
-
-        /* writev can return a partial write, so we loop here. */
-        while (!iov_empty(iov, out)) {
-                int len = writev(STDOUT_FILENO, iov, out);
-                if (len <= 0) {
-                        warn("Write to stdout gave %i (%d)", len, errno);
-                        break;
-                }
-                iov_consume(vq->dev, iov, out, NULL, len);
-        }
-
-        /*
-         * We're finished with that buffer: if we're going to sleep,
-         * wait_for_vq_desc() will prod the Guest with an interrupt.
-         */
-        add_used(vq, head, 0);
-}
-
-/*
- * The Network
- *
- * Handling output for network is also simple: we get all the output buffers
- * and write them to /dev/net/tun.
- */
-struct net_info {
-        int tunfd;
-};
-
-static void net_output(struct virtqueue *vq)
-{
-        struct net_info *net_info = vq->dev->priv;
-        unsigned int head, out, in;
-        struct iovec iov[vq->vring.num];
-
-        /* We usually wait in here for the Guest to give us a packet. */
-        head = wait_for_vq_desc(vq, iov, &out, &in);
-        if (in)
-                bad_driver_vq(vq, "Input buffers in net output queue?");
-        /*
-         * Send the whole thing through to /dev/net/tun.  It expects the exact
-         * same format: what a coincidence!
-         */
-        if (writev(net_info->tunfd, iov, out) < 0)
-                warnx("Write to tun failed (%d)?", errno);
-
-        /*
-         * Done with that one; wait_for_vq_desc() will send the interrupt if
-         * all packets are processed.
-         */
-        add_used(vq, head, 0);
-}
-
-/*
- * Handling network input is a bit trickier, because I've tried to optimize it.
- *
- * First we have a helper routine which tells is if from this file descriptor
- * (ie. the /dev/net/tun device) will block:
- */
-static bool will_block(int fd)
-{
-        fd_set fdset;
-        struct timeval zero = { 0, 0 };
-        FD_ZERO(&fdset);
-        FD_SET(fd, &fdset);
-        return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
-}
-
-/*
- * This handles packets coming in from the tun device to our Guest.  Like all
- * service routines, it gets called again as soon as it returns, so you don't
- * see a while(1) loop here.
- */
-static void net_input(struct virtqueue *vq)
-{
-        int len;
-        unsigned int head, out, in;
-        struct iovec iov[vq->vring.num];
-        struct net_info *net_info = vq->dev->priv;
-
-        /*
-         * Get a descriptor to write an incoming packet into.  This will also
-         * send an interrupt if they're out of descriptors.
-         */
-        head = wait_for_vq_desc(vq, iov, &out, &in);
-        if (out)
-                bad_driver_vq(vq, "Output buffers in net input queue?");
-
-        /*
-         * If it looks like we'll block reading from the tun device, send them
-         * an interrupt.
-         */
-        if (vq->pending_used && will_block(net_info->tunfd))
-                trigger_irq(vq);
-
-        /*
-         * Read in the packet.  This is where we normally wait (when there's no
-         * incoming network traffic).
-         */
-        len = readv(net_info->tunfd, iov, in);
-        if (len <= 0)
-                warn("Failed to read from tun (%d).", errno);
-
-        /*
-         * Mark that packet buffer as used, but don't interrupt here.  We want
-         * to wait until we've done as much work as we can.
-         */
-        add_used(vq, head, len);
-}
-/*:*/
-
-/* This is the helper to create threads: run the service routine in a loop. */
-static int do_thread(void *_vq)
-{
-        struct virtqueue *vq = _vq;
-
-        for (;;)
-                vq->service(vq);
-        return 0;
-}
-
-/*
- * When a child dies, we kill our entire process group with SIGTERM.  This
- * also has the side effect that the shell restores the console for us!
- */
-static void kill_launcher(int signal)
-{
-        kill(0, SIGTERM);
-}
-
-static void reset_vq_pci_config(struct virtqueue *vq)
-{
-        vq->pci_config.queue_size = VIRTQUEUE_NUM;
-        vq->pci_config.queue_enable = 0;
-}
-
-static void reset_device(struct device *dev)
-{
-        struct virtqueue *vq;
-
-        verbose("Resetting device %s\n", dev->name);
-
-        /* Clear any features they've acked. */
-        dev->features_accepted = 0;
-
-        /* We're going to be explicitly killing threads, so ignore them. */
-        signal(SIGCHLD, SIG_IGN);
-
-        /*
-         * 4.1.4.3.1:
-         *
-         *   The device MUST present a 0 in queue_enable on reset. 
-         *
-         * This means we set it here, and reset the saved ones in every vq.
-         */
-        dev->mmio->cfg.queue_enable = 0;
-
-        /* Get rid of the virtqueue threads */
-        for (vq = dev->vq; vq; vq = vq->next) {
-                vq->last_avail_idx = 0;
-                reset_vq_pci_config(vq);
-                if (vq->thread != (pid_t)-1) {
-                        kill(vq->thread, SIGTERM);
-                        waitpid(vq->thread, NULL, 0);
-                        vq->thread = (pid_t)-1;
-                }
-        }
-        dev->running = false;
-        dev->wrote_features_ok = false;
-
-        /* Now we care if threads die. */
-        signal(SIGCHLD, (void *)kill_launcher);
-}
-
-static void cleanup_devices(void)
-{
-        unsigned int i;
-
-        for (i = 1; i < MAX_PCI_DEVICES; i++) {
-                struct device *d = devices.pci[i];
-                if (!d)
-                        continue;
-                reset_device(d);
-        }
-
-        /* If we saved off the original terminal settings, restore them now. */
-        if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
-                tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
-}
-
-/*L:217
- * We do PCI.  This is mainly done to let us test the kernel virtio PCI
- * code.
- */
-
-/* Linux expects a PCI host bridge: ours is a dummy, and first on the bus. */
-static struct device pci_host_bridge;
-
-static void init_pci_host_bridge(void)
-{
-        pci_host_bridge.name = "PCI Host Bridge";
-        pci_host_bridge.config.class = 0x06; /* bridge */
-        pci_host_bridge.config.subclass = 0; /* host bridge */
-        devices.pci[0] = &pci_host_bridge;
-}
-
-/* The IO ports used to read the PCI config space. */
-#define PCI_CONFIG_ADDR 0xCF8
-#define PCI_CONFIG_DATA 0xCFC
-
-/*
- * Not really portable, but does help readability: this is what the Guest
- * writes to the PCI_CONFIG_ADDR IO port.
- */
-union pci_config_addr {
-        struct {
-                unsigned mbz: 2;
-                unsigned offset: 6;
-                unsigned funcnum: 3;
-                unsigned devnum: 5;
-                unsigned busnum: 8;
-                unsigned reserved: 7;
-                unsigned enabled : 1;
-        } bits;
-        u32 val;
-};
-
-/*
- * We cache what they wrote to the address port, so we know what they're
- * talking about when they access the data port.
- */
-static union pci_config_addr pci_config_addr;
-
-static struct device *find_pci_device(unsigned int index)
-{
-        return devices.pci[index];
-}
-
-/* PCI can do 1, 2 and 4 byte reads; we handle that here. */
-static void ioread(u16 off, u32 v, u32 mask, u32 *val)
-{
-        assert(off < 4);
-        assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF);
-        *val = (v >> (off * 8)) & mask;
-}
-
-/* PCI can do 1, 2 and 4 byte writes; we handle that here. */
-static void iowrite(u16 off, u32 v, u32 mask, u32 *dst)
-{
-        assert(off < 4);
-        assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF);
-        *dst &= ~(mask << (off * 8));
-        *dst |= (v & mask) << (off * 8);
-}
-
-/*
- * Where PCI_CONFIG_DATA accesses depends on the previous write to
- * PCI_CONFIG_ADDR.
- */
-static struct device *dev_and_reg(u32 *reg)
-{
-        if (!pci_config_addr.bits.enabled)
-                return NULL;
-
-        if (pci_config_addr.bits.funcnum != 0)
-                return NULL;
-
-        if (pci_config_addr.bits.busnum != 0)
-                return NULL;
-
-        if (pci_config_addr.bits.offset * 4 >= sizeof(struct pci_config))
-                return NULL;
-
-        *reg = pci_config_addr.bits.offset;
-        return find_pci_device(pci_config_addr.bits.devnum);
-}
-
-/*
- * We can get invalid combinations of values while they're writing, so we
- * only fault if they try to write with some invalid bar/offset/length.
- */
-static bool valid_bar_access(struct device *d,
-                             struct virtio_pci_cfg_cap_u32 *cfg_access)
-{
-        /* We only have 1 bar (BAR0) */
-        if (cfg_access->cap.bar != 0)
-                return false;
-
-        /* Check it's within BAR0. */
-        if (cfg_access->cap.offset >= d->mmio_size
-            || cfg_access->cap.offset + cfg_access->cap.length > d->mmio_size)
-                return false;
-
-        /* Check length is 1, 2 or 4. */
-        if (cfg_access->cap.length != 1
-            && cfg_access->cap.length != 2
-            && cfg_access->cap.length != 4)
-                return false;
-
-        /*
-         * 4.1.4.7.2:
-         *
-         *  The driver MUST NOT write a cap.offset which is not a multiple of
-         *  cap.length (ie. all accesses MUST be aligned).
-         */
-        if (cfg_access->cap.offset % cfg_access->cap.length != 0)
-                return false;
-
-        /* Return pointer into word in BAR0. */
-        return true;
-}
-
-/* Is this accessing the PCI config address port?. */
-static bool is_pci_addr_port(u16 port)
-{
-        return port >= PCI_CONFIG_ADDR && port < PCI_CONFIG_ADDR + 4;
-}
-
-static bool pci_addr_iowrite(u16 port, u32 mask, u32 val)
-{
-        iowrite(port - PCI_CONFIG_ADDR, val, mask,
-                &pci_config_addr.val);
-        verbose("PCI%s: %#x/%x: bus %u dev %u func %u reg %u\n",
-                pci_config_addr.bits.enabled ? "" : " DISABLED",
-                val, mask,
-                pci_config_addr.bits.busnum,
-                pci_config_addr.bits.devnum,
-                pci_config_addr.bits.funcnum,
-                pci_config_addr.bits.offset);
-        return true;
-}
-
-static void pci_addr_ioread(u16 port, u32 mask, u32 *val)
-{
-        ioread(port - PCI_CONFIG_ADDR, pci_config_addr.val, mask, val);
-}
-
-/* Is this accessing the PCI config data port?. */
-static bool is_pci_data_port(u16 port)
-{
-        return port >= PCI_CONFIG_DATA && port < PCI_CONFIG_DATA + 4;
-}
-
-static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask);
-
-static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
-{
-        u32 reg, portoff;
-        struct device *d = dev_and_reg(&reg);
-
-        /* Complain if they don't belong to a device. */
-        if (!d)
-                return false;
-
-        /* They can do 1 byte writes, etc. */
-        portoff = port - PCI_CONFIG_DATA;
-
-        /*
-         * PCI uses a weird way to determine the BAR size: the OS
-         * writes all 1's, and sees which ones stick.
-         */
-        if (&d->config_words[reg] == &d->config.bar[0]) {
-                int i;
-
-                iowrite(portoff, val, mask, &d->config.bar[0]);
-                for (i = 0; (1 << i) < d->mmio_size; i++)
-                        d->config.bar[0] &= ~(1 << i);
-                return true;
-        } else if ((&d->config_words[reg] > &d->config.bar[0]
-                    && &d->config_words[reg] <= &d->config.bar[6])
-                   || &d->config_words[reg] == &d->config.expansion_rom_addr) {
-                /* Allow writing to any other BAR, or expansion ROM */
-                iowrite(portoff, val, mask, &d->config_words[reg]);
-                return true;
-                /* We let them override latency timer and cacheline size */
-        } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
-                /* Only let them change the first two fields. */
-                if (mask == 0xFFFFFFFF)
-                        mask = 0xFFFF;
-                iowrite(portoff, val, mask, &d->config_words[reg]);
-                return true;
-        } else if (&d->config_words[reg] == (void *)&d->config.command
-                   && mask == 0xFFFF) {
-                /* Ignore command writes. */
-                return true;
-        } else if (&d->config_words[reg]
-                   == (void *)&d->config.cfg_access.cap.bar
-                   || &d->config_words[reg]
-                   == &d->config.cfg_access.cap.length
-                   || &d->config_words[reg]
-                   == &d->config.cfg_access.cap.offset) {
-
-                /*
-                 * The VIRTIO_PCI_CAP_PCI_CFG capability
-                 * provides a backdoor to access the MMIO
-                 * regions without mapping them.  Weird, but
-                 * useful.
-                 */
-                iowrite(portoff, val, mask, &d->config_words[reg]);
-                return true;
-        } else if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) {
-                u32 write_mask;
-
-                /*
-                 * 4.1.4.7.1:
-                 *
-                 *  Upon detecting driver write access to pci_cfg_data, the
-                 *  device MUST execute a write access at offset cap.offset at
-                 *  BAR selected by cap.bar using the first cap.length bytes
-                 *  from pci_cfg_data.
-                 */
-
-                /* Must be bar 0 */
-                if (!valid_bar_access(d, &d->config.cfg_access))
-                        return false;
-
-                iowrite(portoff, val, mask, &d->config.cfg_access.pci_cfg_data);
-
-                /*
-                 * Now emulate a write.  The mask we use is set by
-                 * len, *not* this write!
-                 */
-                write_mask = (1ULL<<(8*d->config.cfg_access.cap.length)) - 1;
-                verbose("Window writing %#x/%#x to bar %u, offset %u len %u\n",
-                        d->config.cfg_access.pci_cfg_data, write_mask,
-                        d->config.cfg_access.cap.bar,
-                        d->config.cfg_access.cap.offset,
-                        d->config.cfg_access.cap.length);
-
-                emulate_mmio_write(d, d->config.cfg_access.cap.offset,
-                                   d->config.cfg_access.pci_cfg_data,
-                                   write_mask);
-                return true;
-        }
-
-        /*
-         * 4.1.4.1:
-         *
-         *  The driver MUST NOT write into any field of the capability
-         *  structure, with the exception of those with cap_type
-         *  VIRTIO_PCI_CAP_PCI_CFG...
-         */
-        return false;
-}
-
-static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask);
-
-static void pci_data_ioread(u16 port, u32 mask, u32 *val)
-{
-        u32 reg;
-        struct device *d = dev_and_reg(&reg);
-
-        if (!d)
-                return;
-
-        /* Read through the PCI MMIO access window is special */
-        if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) {
-                u32 read_mask;
-
-                /*
-                 * 4.1.4.7.1:
-                 *
-                 *  Upon detecting driver read access to pci_cfg_data, the
-                 *  device MUST execute a read access of length cap.length at
-                 *  offset cap.offset at BAR selected by cap.bar and store the
-                 *  first cap.length bytes in pci_cfg_data.
-                 */
-                /* Must be bar 0 */
-                if (!valid_bar_access(d, &d->config.cfg_access))
-                        bad_driver(d,
-                             "Invalid cfg_access to bar%u, offset %u len %u",
-                             d->config.cfg_access.cap.bar,
-                             d->config.cfg_access.cap.offset,
-                             d->config.cfg_access.cap.length);
-
-                /*
-                 * Read into the window.  The mask we use is set by
-                 * len, *not* this read!
-                 */
-                read_mask = (1ULL<<(8*d->config.cfg_access.cap.length))-1;
-                d->config.cfg_access.pci_cfg_data
-                        = emulate_mmio_read(d,
-                                            d->config.cfg_access.cap.offset,
-                                            read_mask);
-                verbose("Window read %#x/%#x from bar %u, offset %u len %u\n",
-                        d->config.cfg_access.pci_cfg_data, read_mask,
-                        d->config.cfg_access.cap.bar,
-                        d->config.cfg_access.cap.offset,
-                        d->config.cfg_access.cap.length);
-        }
-        ioread(port - PCI_CONFIG_DATA, d->config_words[reg], mask, val);
-}
-
-/*L:216
- * This is where we emulate a handful of Guest instructions.  It's ugly
- * and we used to do it in the kernel but it grew over time.
- */
-
-/*
- * We use the ptrace syscall's pt_regs struct to talk about registers
- * to lguest: these macros convert the names to the offsets.
- */
-#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name))
-#define setreg(name, val) \
-        setreg_off(offsetof(struct user_regs_struct, name), (val))
-
-static u32 getreg_off(size_t offset)
-{
-        u32 r;
-        unsigned long args[] = { LHREQ_GETREG, offset };
-
-        if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
-                err(1, "Getting register %u", offset);
-        if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r))
-                err(1, "Reading register %u", offset);
-
-        return r;
-}
-
-static void setreg_off(size_t offset, u32 val)
-{
-        unsigned long args[] = { LHREQ_SETREG, offset, val };
-
-        if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
-                err(1, "Setting register %u", offset);
-}
-
-/* Get register by instruction encoding */
-static u32 getreg_num(unsigned regnum, u32 mask)
-{
-        /* 8 bit ops use regnums 4-7 for high parts of word */
-        if (mask == 0xFF && (regnum & 0x4))
-                return getreg_num(regnum & 0x3, 0xFFFF) >> 8;
-
-        switch (regnum) {
-        case 0: return getreg(eax) & mask;
-        case 1: return getreg(ecx) & mask;
-        case 2: return getreg(edx) & mask;
-        case 3: return getreg(ebx) & mask;
-        case 4: return getreg(esp) & mask;
-        case 5: return getreg(ebp) & mask;
-        case 6: return getreg(esi) & mask;
-        case 7: return getreg(edi) & mask;
-        }
-        abort();
-}
-
-/* Set register by instruction encoding */
-static void setreg_num(unsigned regnum, u32 val, u32 mask)
-{
-        /* Don't try to set bits out of range */
-        assert(~(val & ~mask));
-
-        /* 8 bit ops use regnums 4-7 for high parts of word */
-        if (mask == 0xFF && (regnum & 0x4)) {
-                /* Construct the 16 bits we want. */
-                val = (val << 8) | getreg_num(regnum & 0x3, 0xFF);
-                setreg_num(regnum & 0x3, val, 0xFFFF);
-                return;
-        }
-
-        switch (regnum) {
-        case 0: setreg(eax, val | (getreg(eax) & ~mask)); return;
-        case 1: setreg(ecx, val | (getreg(ecx) & ~mask)); return;
-        case 2: setreg(edx, val | (getreg(edx) & ~mask)); return;
-        case 3: setreg(ebx, val | (getreg(ebx) & ~mask)); return;
-        case 4: setreg(esp, val | (getreg(esp) & ~mask)); return;
-        case 5: setreg(ebp, val | (getreg(ebp) & ~mask)); return;
-        case 6: setreg(esi, val | (getreg(esi) & ~mask)); return;
-        case 7: setreg(edi, val | (getreg(edi) & ~mask)); return;
-        }
-        abort();
-}
-
-/* Get bytes of displacement appended to instruction, from r/m encoding */
-static u32 insn_displacement_len(u8 mod_reg_rm)
-{
-        /* Switch on the mod bits */
-        switch (mod_reg_rm >> 6) {
-        case 0:
-                /* If mod == 0, and r/m == 101, 16-bit displacement follows */
-                if ((mod_reg_rm & 0x7) == 0x5)
-                        return 2;
-                /* Normally, mod == 0 means no literal displacement */
-                return 0;
-        case 1:
-                /* One byte displacement */
-                return 1;
-        case 2:
-                /* Four byte displacement */
-                return 4;
-        case 3:
-                /* Register mode */
-                return 0;
-        }
-        abort();
-}
-
-static void emulate_insn(const u8 insn[])
-{
-        unsigned long args[] = { LHREQ_TRAP, 13 };
-        unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access;
-        unsigned int eax, port, mask;
-        /*
-         * Default is to return all-ones on IO port reads, which traditionally
-         * means "there's nothing there".
-         */
-        u32 val = 0xFFFFFFFF;
-
-        /*
-         * This must be the Guest kernel trying to do something, not userspace!
-         * The bottom two bits of the CS segment register are the privilege
-         * level.
-         */
-        if ((getreg(xcs) & 3) != 0x1)
-                goto no_emulate;
-
-        /* Decoding x86 instructions is icky. */
-
-        /*
-         * Around 2.6.33, the kernel started using an emulation for the
-         * cmpxchg8b instruction in early boot on many configurations.  This
-         * code isn't paravirtualized, and it tries to disable interrupts.
-         * Ignore it, which will Mostly Work.
-         */
-        if (insn[insnlen] == 0xfa) {
-                /* "cli", or Clear Interrupt Enable instruction.  Skip it. */
-                insnlen = 1;
-                goto skip_insn;
-        }
-
-        /*
-         * 0x66 is an "operand prefix".  It means a 16, not 32 bit in/out.
-         */
-        if (insn[insnlen] == 0x66) {
-                small_operand = 1;
-                /* The instruction is 1 byte so far, read the next byte. */
-                insnlen = 1;
-        }
-
-        /* If the lower bit isn't set, it's a single byte access */
-        byte_access = !(insn[insnlen] & 1);
-
-        /*
-         * Now we can ignore the lower bit and decode the 4 opcodes
-         * we need to emulate.
-         */
-        switch (insn[insnlen] & 0xFE) {
-        case 0xE4: /* in     <next byte>,%al */
-                port = insn[insnlen+1];
-                insnlen += 2;
-                in = 1;
-                break;
-        case 0xEC: /* in     (%dx),%al */
-                port = getreg(edx) & 0xFFFF;
-                insnlen += 1;
-                in = 1;
-                break;
-        case 0xE6: /* out    %al,<next byte> */
-                port = insn[insnlen+1];
-                insnlen += 2;
-                break;
-        case 0xEE: /* out    %al,(%dx) */
-                port = getreg(edx) & 0xFFFF;
-                insnlen += 1;
-                break;
-        default:
-                /* OK, we don't know what this is, can't emulate. */
-                goto no_emulate;
-        }
-
-        /* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */
-        if (byte_access)
-                mask = 0xFF;
-        else if (small_operand)
-                mask = 0xFFFF;
-        else
-                mask = 0xFFFFFFFF;
-
-        /*
-         * If it was an "IN" instruction, they expect the result to be read
-         * into %eax, so we change %eax.
-         */
-        eax = getreg(eax);
-
-        if (in) {
-                /* This is the PS/2 keyboard status; 1 means ready for output */
-                if (port == 0x64)
-                        val = 1;
-                else if (is_pci_addr_port(port))
-                        pci_addr_ioread(port, mask, &val);
-                else if (is_pci_data_port(port))
-                        pci_data_ioread(port, mask, &val);
-
-                /* Clear the bits we're about to read */
-                eax &= ~mask;
-                /* Copy bits in from val. */
-                eax |= val & mask;
-                /* Now update the register. */
-                setreg(eax, eax);
-        } else {
-                if (is_pci_addr_port(port)) {
-                        if (!pci_addr_iowrite(port, mask, eax))
-                                goto bad_io;
-                } else if (is_pci_data_port(port)) {
-                        if (!pci_data_iowrite(port, mask, eax))
-                                goto bad_io;
-                }
-                /* There are many other ports, eg. CMOS clock, serial
-                 * and parallel ports, so we ignore them all. */
-        }
-
-        verbose("IO %s of %x to %u: %#08x\n",
-                in ? "IN" : "OUT", mask, port, eax);
-skip_insn:
-        /* Finally, we've "done" the instruction, so move past it. */
-        setreg(eip, getreg(eip) + insnlen);
-        return;
-
-bad_io:
-        warnx("Attempt to %s port %u (%#x mask)",
-              in ? "read from" : "write to", port, mask);
-
-no_emulate:
-        /* Inject trap into Guest. */
-        if (write(lguest_fd, args, sizeof(args)) < 0)
-                err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip));
-}
-
-static struct device *find_mmio_region(unsigned long paddr, u32 *off)
-{
-        unsigned int i;
-
-        for (i = 1; i < MAX_PCI_DEVICES; i++) {
-                struct device *d = devices.pci[i];
-
-                if (!d)
-                        continue;
-                if (paddr < d->mmio_addr)
-                        continue;
-                if (paddr >= d->mmio_addr + d->mmio_size)
-                        continue;
-                *off = paddr - d->mmio_addr;
-                return d;
-        }
-        return NULL;
-}
-
-/* FIXME: Use vq array. */
-static struct virtqueue *vq_by_num(struct device *d, u32 num)
-{
-        struct virtqueue *vq = d->vq;
-
-        while (num-- && vq)
-                vq = vq->next;
-
-        return vq;
-}
-
-static void save_vq_config(const struct virtio_pci_common_cfg *cfg,
-                           struct virtqueue *vq)
-{
-        vq->pci_config = *cfg;
-}
-
-static void restore_vq_config(struct virtio_pci_common_cfg *cfg,
-                              struct virtqueue *vq)
-{
-        /* Only restore the per-vq part */
-        size_t off = offsetof(struct virtio_pci_common_cfg, queue_size);
-
-        memcpy((void *)cfg + off, (void *)&vq->pci_config + off,
-               sizeof(*cfg) - off);
-}
-
-/*
- * 4.1.4.3.2:
- *
- *  The driver MUST configure the other virtqueue fields before
- *  enabling the virtqueue with queue_enable.
- *
- * When they enable the virtqueue, we check that their setup is valid.
- */
-static void check_virtqueue(struct device *d, struct virtqueue *vq)
-{
-        /* Because lguest is 32 bit, all the descriptor high bits must be 0 */
-        if (vq->pci_config.queue_desc_hi
-            || vq->pci_config.queue_avail_hi
-            || vq->pci_config.queue_used_hi)
-                bad_driver_vq(vq, "invalid 64-bit queue address");
-
-        /*
-         * 2.4.1:
-         *
-         *  The driver MUST ensure that the physical address of the first byte
-         *  of each virtqueue part is a multiple of the specified alignment
-         *  value in the above table.
-         */
-        if (vq->pci_config.queue_desc_lo % 16
-            || vq->pci_config.queue_avail_lo % 2
-            || vq->pci_config.queue_used_lo % 4)
-                bad_driver_vq(vq, "invalid alignment in queue addresses");
-
-        /* Initialize the virtqueue and check they're all in range. */
-        vq->vring.num = vq->pci_config.queue_size;
-        vq->vring.desc = check_pointer(vq->dev,
-                                       vq->pci_config.queue_desc_lo,
-                                       sizeof(*vq->vring.desc) * vq->vring.num);
-        vq->vring.avail = check_pointer(vq->dev,
-                                        vq->pci_config.queue_avail_lo,
-                                        sizeof(*vq->vring.avail)
-                                        + (sizeof(vq->vring.avail->ring[0])
-                                           * vq->vring.num));
-        vq->vring.used = check_pointer(vq->dev,
-                                       vq->pci_config.queue_used_lo,
-                                       sizeof(*vq->vring.used)
-                                       + (sizeof(vq->vring.used->ring[0])
-                                          * vq->vring.num));
-
-        /*
-         * 2.4.9.1:
-         *
-         *   The driver MUST initialize flags in the used ring to 0
-         *   when allocating the used ring.
-         */
-        if (vq->vring.used->flags != 0)
-                bad_driver_vq(vq, "invalid initial used.flags %#x",
-                              vq->vring.used->flags);
-}
-
-static void start_virtqueue(struct virtqueue *vq)
-{
-        /*
-         * Create stack for thread.  Since the stack grows upwards, we point
-         * the stack pointer to the end of this region.
-         */
-        char *stack = malloc(32768);
-
-        /* Create a zero-initialized eventfd. */
-        vq->eventfd = eventfd(0, 0);
-        if (vq->eventfd < 0)
-                err(1, "Creating eventfd");
-
-        /*
-         * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so
-         * we get a signal if it dies.
-         */
-        vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
-        if (vq->thread == (pid_t)-1)
-                err(1, "Creating clone");
-}
-
-static void start_virtqueues(struct device *d)
-{
-        struct virtqueue *vq;
-
-        for (vq = d->vq; vq; vq = vq->next) {
-                if (vq->pci_config.queue_enable)
-                        start_virtqueue(vq);
-        }
-}
-
-static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask)
-{
-        struct virtqueue *vq;
-
-        switch (off) {
-        case offsetof(struct virtio_pci_mmio, cfg.device_feature_select):
-                /*
-                 * 4.1.4.3.1:
-                 *
-                 * The device MUST present the feature bits it is offering in
-                 * device_feature, starting at bit device_feature_select ∗ 32
-                 * for any device_feature_select written by the driver
-                 */
-                if (val == 0)
-                        d->mmio->cfg.device_feature = d->features;
-                else if (val == 1)
-                        d->mmio->cfg.device_feature = (d->features >> 32);
-                else
-                        d->mmio->cfg.device_feature = 0;
-                goto feature_write_through32;
-        case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select):
-                if (val > 1)
-                        bad_driver(d, "Unexpected driver select %u", val);
-                goto feature_write_through32;
-        case offsetof(struct virtio_pci_mmio, cfg.guest_feature):
-                if (d->mmio->cfg.guest_feature_select == 0) {
-                        d->features_accepted &= ~((u64)0xFFFFFFFF);
-                        d->features_accepted |= val;
-                } else {
-                        assert(d->mmio->cfg.guest_feature_select == 1);
-                        d->features_accepted &= 0xFFFFFFFF;
-                        d->features_accepted |= ((u64)val) << 32;
-                }
-                /*
-                 * 2.2.1:
-                 *
-                 *   The driver MUST NOT accept a feature which the device did
-                 *   not offer
-                 */
-                if (d->features_accepted & ~d->features)
-                        bad_driver(d, "over-accepted features %#llx of %#llx",
-                                   d->features_accepted, d->features);
-                goto feature_write_through32;
-        case offsetof(struct virtio_pci_mmio, cfg.device_status): {
-                u8 prev;
-
-                verbose("%s: device status -> %#x\n", d->name, val);
-                /*
-                 * 4.1.4.3.1:
-                 * 
-                 *  The device MUST reset when 0 is written to device_status,
-                 *  and present a 0 in device_status once that is done.
-                 */
-                if (val == 0) {
-                        reset_device(d);
-                        goto write_through8;
-                }
-
-                /* 2.1.1: The driver MUST NOT clear a device status bit. */
-                if (d->mmio->cfg.device_status & ~val)
-                        bad_driver(d, "unset of device status bit %#x -> %#x",
-                                   d->mmio->cfg.device_status, val);
-
-                /*
-                 * 2.1.2:
-                 *
-                 *  The device MUST NOT consume buffers or notify the driver
-                 *  before DRIVER_OK.
-                 */
-                if (val & VIRTIO_CONFIG_S_DRIVER_OK
-                    && !(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK))
-                        start_virtqueues(d);
-
-                /*
-                 * 3.1.1:
-                 *
-                 *   The driver MUST follow this sequence to initialize a device:
-                 *   - Reset the device.
-                 *   - Set the ACKNOWLEDGE status bit: the guest OS has
-                 *     notice the device.
-                 *   - Set the DRIVER status bit: the guest OS knows how
-                 *     to drive the device.
-                 *   - Read device feature bits, and write the subset
-                 *     of feature bits understood by the OS and driver
-                 *     to the device. During this step the driver MAY
-                 *     read (but MUST NOT write) the device-specific
-                 *     configuration fields to check that it can
-                 *     support the device before accepting it.
-                 *   - Set the FEATURES_OK status bit.  The driver
-                 *     MUST not accept new feature bits after this
-                 *     step.
-                 *   - Re-read device status to ensure the FEATURES_OK
-                 *     bit is still set: otherwise, the device does
-                 *     not support our subset of features and the
-                 *     device is unusable.
-                 *   - Perform device-specific setup, including
-                 *     discovery of virtqueues for the device,
-                 *     optional per-bus setup, reading and possibly
-                 *     writing the device’s virtio configuration
-                 *     space, and population of virtqueues.
-                 *   - Set the DRIVER_OK status bit. At this point the
-                 *     device is “live”.
-                 */
-                prev = 0;
-                switch (val & ~d->mmio->cfg.device_status) {
-                case VIRTIO_CONFIG_S_DRIVER_OK:
-                        prev |= VIRTIO_CONFIG_S_FEATURES_OK; /* fall thru */
-                case VIRTIO_CONFIG_S_FEATURES_OK:
-                        prev |= VIRTIO_CONFIG_S_DRIVER; /* fall thru */
-                case VIRTIO_CONFIG_S_DRIVER:
-                        prev |= VIRTIO_CONFIG_S_ACKNOWLEDGE; /* fall thru */
-                case VIRTIO_CONFIG_S_ACKNOWLEDGE:
-                        break;
-                default:
-                        bad_driver(d, "unknown device status bit %#x -> %#x",
-                                   d->mmio->cfg.device_status, val);
-                }
-                if (d->mmio->cfg.device_status != prev)
-                        bad_driver(d, "unexpected status transition %#x -> %#x",
-                                   d->mmio->cfg.device_status, val);
-
-                /* If they just wrote FEATURES_OK, we make sure they read */
-                switch (val & ~d->mmio->cfg.device_status) {
-                case VIRTIO_CONFIG_S_FEATURES_OK:
-                        d->wrote_features_ok = true;
-                        break;
-                case VIRTIO_CONFIG_S_DRIVER_OK:
-                        if (d->wrote_features_ok)
-                                bad_driver(d, "did not re-read FEATURES_OK");
-                        break;
-                }
-                goto write_through8;
-        }
-        case offsetof(struct virtio_pci_mmio, cfg.queue_select):
-                vq = vq_by_num(d, val);
-                /*
-                 * 4.1.4.3.1:
-                 *
-                 *  The device MUST present a 0 in queue_size if the virtqueue
-                 *  corresponding to the current queue_select is unavailable.
-                 */
-                if (!vq) {
-                        d->mmio->cfg.queue_size = 0;
-                        goto write_through16;
-                }
-                /* Save registers for old vq, if it was a valid vq */
-                if (d->mmio->cfg.queue_size)
-                        save_vq_config(&d->mmio->cfg,
-                                       vq_by_num(d, d->mmio->cfg.queue_select));
-                /* Restore the registers for the queue they asked for */
-                restore_vq_config(&d->mmio->cfg, vq);
-                goto write_through16;
-        case offsetof(struct virtio_pci_mmio, cfg.queue_size):
-                /*
-                 * 4.1.4.3.2:
-                 *
-                 *  The driver MUST NOT write a value which is not a power of 2
-                 *  to queue_size.
-                 */
-                if (val & (val-1))
-                        bad_driver(d, "invalid queue size %u", val);
-                if (d->mmio->cfg.queue_enable)
-                        bad_driver(d, "changing queue size on live device");
-                goto write_through16;
-        case offsetof(struct virtio_pci_mmio, cfg.queue_msix_vector):
-                bad_driver(d, "attempt to set MSIX vector to %u", val);
-        case offsetof(struct virtio_pci_mmio, cfg.queue_enable): {
-                struct virtqueue *vq = vq_by_num(d, d->mmio->cfg.queue_select);
-
-                /*
-                 * 4.1.4.3.2:
-                 *
-                 *  The driver MUST NOT write a 0 to queue_enable.
-                 */
-                if (val != 1)
-                        bad_driver(d, "setting queue_enable to %u", val);
-
-                /*
-                 * 3.1.1:
-                 *
-                 *  7. Perform device-specific setup, including discovery of
-                 *     virtqueues for the device, optional per-bus setup,
-                 *     reading and possibly writing the device’s virtio
-                 *     configuration space, and population of virtqueues.
-                 *  8. Set the DRIVER_OK status bit.
-                 *
-                 * All our devices require all virtqueues to be enabled, so
-                 * they should have done that before setting DRIVER_OK.
-                 */
-                if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)
-                        bad_driver(d, "enabling vq after DRIVER_OK");
-
-                d->mmio->cfg.queue_enable = val;
-                save_vq_config(&d->mmio->cfg, vq);
-                check_virtqueue(d, vq);
-                goto write_through16;
-        }
-        case offsetof(struct virtio_pci_mmio, cfg.queue_notify_off):
-                bad_driver(d, "attempt to write to queue_notify_off");
-        case offsetof(struct virtio_pci_mmio, cfg.queue_desc_lo):
-        case offsetof(struct virtio_pci_mmio, cfg.queue_desc_hi):
-        case offsetof(struct virtio_pci_mmio, cfg.queue_avail_lo):
-        case offsetof(struct virtio_pci_mmio, cfg.queue_avail_hi):
-        case offsetof(struct virtio_pci_mmio, cfg.queue_used_lo):
-        case offsetof(struct virtio_pci_mmio, cfg.queue_used_hi):
-                /*
-                 * 4.1.4.3.2:
-                 *
-                 *  The driver MUST configure the other virtqueue fields before
-                 *  enabling the virtqueue with queue_enable.
-                 */
-                if (d->mmio->cfg.queue_enable)
-                        bad_driver(d, "changing queue on live device");
-
-                /*
-                 * 3.1.1:
-                 *
-                 *  The driver MUST follow this sequence to initialize a device:
-                 *...
-                 *  5. Set the FEATURES_OK status bit. The driver MUST not
-                 *  accept new feature bits after this step.
-                 */
-                if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK))
-                        bad_driver(d, "setting up vq before FEATURES_OK");
-
-                /*
-                 *  6. Re-read device status to ensure the FEATURES_OK bit is
-                 *     still set...
-                 */
-                if (d->wrote_features_ok)
-                        bad_driver(d, "didn't re-read FEATURES_OK before setup");
-
-                goto write_through32;
-        case offsetof(struct virtio_pci_mmio, notify):
-                vq = vq_by_num(d, val);
-                if (!vq)
-                        bad_driver(d, "Invalid vq notification on %u", val);
-                /* Notify the process handling this vq by adding 1 to eventfd */
-                write(vq->eventfd, "\1\0\0\0\0\0\0\0", 8);
-                goto write_through16;
-        case offsetof(struct virtio_pci_mmio, isr):
-                bad_driver(d, "Unexpected write to isr");
-        /* Weird corner case: write to emerg_wr of console */
-        case sizeof(struct virtio_pci_mmio)
-                + offsetof(struct virtio_console_config, emerg_wr):
-                if (strcmp(d->name, "console") == 0) {
-                        char c = val;
-                        write(STDOUT_FILENO, &c, 1);
-                        goto write_through32;
-                }
-                /* Fall through... */
-        default:
-                /*
-                 * 4.1.4.3.2:
-                 *
-                 *   The driver MUST NOT write to device_feature, num_queues,
-                 *   config_generation or queue_notify_off.
-                 */
-                bad_driver(d, "Unexpected write to offset %u", off);
-        }
-
-feature_write_through32:
-        /*
-         * 3.1.1:
-         *
-         *   The driver MUST follow this sequence to initialize a device:
-         *...
-         *   - Set the DRIVER status bit: the guest OS knows how
-         *     to drive the device.
-         *   - Read device feature bits, and write the subset
-         *     of feature bits understood by the OS and driver
-         *     to the device.
-         *...
-         *   - Set the FEATURES_OK status bit. The driver MUST not
-         *     accept new feature bits after this step.
-         */
-        if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
-                bad_driver(d, "feature write before VIRTIO_CONFIG_S_DRIVER");
-        if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK)
-                bad_driver(d, "feature write after VIRTIO_CONFIG_S_FEATURES_OK");
-
-        /*
-         * 4.1.3.1:
-         *
-         *  The driver MUST access each field using the “natural” access
-         *  method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for
-         *  16-bit fields and 8-bit accesses for 8-bit fields.
-         */
-write_through32:
-        if (mask != 0xFFFFFFFF) {
-                bad_driver(d, "non-32-bit write to offset %u (%#x)",
-                           off, getreg(eip));
-                return;
-        }
-        memcpy((char *)d->mmio + off, &val, 4);
-        return;
-
-write_through16:
-        if (mask != 0xFFFF)
-                bad_driver(d, "non-16-bit write to offset %u (%#x)",
-                           off, getreg(eip));
-        memcpy((char *)d->mmio + off, &val, 2);
-        return;
-
-write_through8:
-        if (mask != 0xFF)
-                bad_driver(d, "non-8-bit write to offset %u (%#x)",
-                           off, getreg(eip));
-        memcpy((char *)d->mmio + off, &val, 1);
-        return;
-}
-
-static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask)
-{
-        u8 isr;
-        u32 val = 0;
-
-        switch (off) {
-        case offsetof(struct virtio_pci_mmio, cfg.device_feature_select):
-        case offsetof(struct virtio_pci_mmio, cfg.device_feature):
-        case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select):
-        case offsetof(struct virtio_pci_mmio, cfg.guest_feature):
-                /*
-                 * 3.1.1:
-                 *
-                 *   The driver MUST follow this sequence to initialize a device:
-                 *...
-                 *   - Set the DRIVER status bit: the guest OS knows how
-                 *     to drive the device.
-                 *   - Read device feature bits, and write the subset
-                 *     of feature bits understood by the OS and driver
-                 *     to the device.
-                 */
-                if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
-                        bad_driver(d,
-                                   "feature read before VIRTIO_CONFIG_S_DRIVER");
-                goto read_through32;
-        case offsetof(struct virtio_pci_mmio, cfg.msix_config):
-                bad_driver(d, "read of msix_config");
-        case offsetof(struct virtio_pci_mmio, cfg.num_queues):
-                goto read_through16;
-        case offsetof(struct virtio_pci_mmio, cfg.device_status):
-                /* As they did read, any write of FEATURES_OK is now fine. */
-                d->wrote_features_ok = false;
-                goto read_through8;
-        case offsetof(struct virtio_pci_mmio, cfg.config_generation):
-                /*
-                 * 4.1.4.3.1:
-                 *
-                 *  The device MUST present a changed config_generation after
-                 *  the driver has read a device-specific configuration value
-                 *  which has changed since any part of the device-specific
-                 *  configuration was last read.
-                 *
-                 * This is simple: none of our devices change config, so this
-                 * is always 0.
-                 */
-                goto read_through8;
-        case offsetof(struct virtio_pci_mmio, notify):
-                /*
-                 * 3.1.1:
-                 *
-                 *   The driver MUST NOT notify the device before setting
-                 *   DRIVER_OK.
-                 */
-                if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK))
-                        bad_driver(d, "notify before VIRTIO_CONFIG_S_DRIVER_OK");
-                goto read_through16;
-        case offsetof(struct virtio_pci_mmio, isr):
-                if (mask != 0xFF)
-                        bad_driver(d, "non-8-bit read from offset %u (%#x)",
-                                   off, getreg(eip));
-                isr = d->mmio->isr;
-                /*
-                 * 4.1.4.5.1:
-                 *
-                 *  The device MUST reset ISR status to 0 on driver read. 
-                 */
-                d->mmio->isr = 0;
-                return isr;
-        case offsetof(struct virtio_pci_mmio, padding):
-                bad_driver(d, "read from padding (%#x)", getreg(eip));
-        default:
-                /* Read from device config space, beware unaligned overflow */
-                if (off > d->mmio_size - 4)
-                        bad_driver(d, "read past end (%#x)", getreg(eip));
-
-                /*
-                 * 3.1.1:
-                 *  The driver MUST follow this sequence to initialize a device:
-                 *...
-                 *  3. Set the DRIVER status bit: the guest OS knows how to
-                 *  drive the device.
-                 *  4. Read device feature bits, and write the subset of
-                 *  feature bits understood by the OS and driver to the
-                 *  device. During this step the driver MAY read (but MUST NOT
-                 *  write) the device-specific configuration fields to check
-                 *  that it can support the device before accepting it.
-                 */
-                if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
-                        bad_driver(d,
-                                   "config read before VIRTIO_CONFIG_S_DRIVER");
-
-                if (mask == 0xFFFFFFFF)
-                        goto read_through32;
-                else if (mask == 0xFFFF)
-                        goto read_through16;
-                else
-                        goto read_through8;
-        }
-
-        /*
-         * 4.1.3.1:
-         *
-         *  The driver MUST access each field using the “natural” access
-         *  method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for
-         *  16-bit fields and 8-bit accesses for 8-bit fields.
-         */
-read_through32:
-        if (mask != 0xFFFFFFFF)
-                bad_driver(d, "non-32-bit read to offset %u (%#x)",
-                           off, getreg(eip));
-        memcpy(&val, (char *)d->mmio + off, 4);
-        return val;
-
-read_through16:
-        if (mask != 0xFFFF)
-                bad_driver(d, "non-16-bit read to offset %u (%#x)",
-                           off, getreg(eip));
-        memcpy(&val, (char *)d->mmio + off, 2);
-        return val;
-
-read_through8:
-        if (mask != 0xFF)
-                bad_driver(d, "non-8-bit read to offset %u (%#x)",
-                           off, getreg(eip));
-        memcpy(&val, (char *)d->mmio + off, 1);
-        return val;
-}
-
-static void emulate_mmio(unsigned long paddr, const u8 *insn)
-{
-        u32 val, off, mask = 0xFFFFFFFF, insnlen = 0;
-        struct device *d = find_mmio_region(paddr, &off);
-        unsigned long args[] = { LHREQ_TRAP, 14 };
-
-        if (!d) {
-                warnx("MMIO touching %#08lx (not a device)", paddr);
-                goto reinject;
-        }
-
-        /* Prefix makes it a 16 bit op */
-        if (insn[0] == 0x66) {
-                mask = 0xFFFF;
-                insnlen++;
-        }
-
-        /* iowrite */
-        if (insn[insnlen] == 0x89) {
-                /* Next byte is r/m byte: bits 3-5 are register. */
-                val = getreg_num((insn[insnlen+1] >> 3) & 0x7, mask);
-                emulate_mmio_write(d, off, val, mask);
-                insnlen += 2 + insn_displacement_len(insn[insnlen+1]);
-        } else if (insn[insnlen] == 0x8b) { /* ioread */
-                /* Next byte is r/m byte: bits 3-5 are register. */
-                val = emulate_mmio_read(d, off, mask);
-                setreg_num((insn[insnlen+1] >> 3) & 0x7, val, mask);
-                insnlen += 2 + insn_displacement_len(insn[insnlen+1]);
-        } else if (insn[0] == 0x88) { /* 8-bit iowrite */
-                mask = 0xff;
-                /* Next byte is r/m byte: bits 3-5 are register. */
-                val = getreg_num((insn[1] >> 3) & 0x7, mask);
-                emulate_mmio_write(d, off, val, mask);
-                insnlen = 2 + insn_displacement_len(insn[1]);
-        } else if (insn[0] == 0x8a) { /* 8-bit ioread */
-                mask = 0xff;
-                val = emulate_mmio_read(d, off, mask);
-                setreg_num((insn[1] >> 3) & 0x7, val, mask);
-                insnlen = 2 + insn_displacement_len(insn[1]);
-        } else {
-                warnx("Unknown MMIO instruction touching %#08lx:"
-                     " %02x %02x %02x %02x at %u",
-                     paddr, insn[0], insn[1], insn[2], insn[3], getreg(eip));
-        reinject:
-                /* Inject trap into Guest. */
-                if (write(lguest_fd, args, sizeof(args)) < 0)
-                        err(1, "Reinjecting trap 14 for fault at %#x",
-                            getreg(eip));
-                return;
-        }
-
-        /* Finally, we've "done" the instruction, so move past it. */
-        setreg(eip, getreg(eip) + insnlen);
-}
-
-/*L:190
- * Device Setup
- *
- * All devices need a descriptor so the Guest knows it exists, and a "struct
- * device" so the Launcher can keep track of it.  We have common helper
- * routines to allocate and manage them.
- */
-static void add_pci_virtqueue(struct device *dev,
-                              void (*service)(struct virtqueue *),
-                              const char *name)
-{
-        struct virtqueue **i, *vq = malloc(sizeof(*vq));
-
-        /* Initialize the virtqueue */
-        vq->next = NULL;
-        vq->last_avail_idx = 0;
-        vq->dev = dev;
-        vq->name = name;
-
-        /*
-         * This is the routine the service thread will run, and its Process ID
-         * once it's running.
-         */
-        vq->service = service;
-        vq->thread = (pid_t)-1;
-
-        /* Initialize the configuration. */
-        reset_vq_pci_config(vq);
-        vq->pci_config.queue_notify_off = 0;
-
-        /* Add one to the number of queues */
-        vq->dev->mmio->cfg.num_queues++;
-
-        /*
-         * Add to tail of list, so dev->vq is first vq, dev->vq->next is
-         * second.
-         */
-        for (i = &dev->vq; *i; i = &(*i)->next);
-        *i = vq;
-}
-
-/* The Guest accesses the feature bits via the PCI common config MMIO region */
-static void add_pci_feature(struct device *dev, unsigned bit)
-{
-        dev->features |= (1ULL << bit);
-}
-
-/* For devices with no config. */
-static void no_device_config(struct device *dev)
-{
-        dev->mmio_addr = get_mmio_region(dev->mmio_size);
-
-        dev->config.bar[0] = dev->mmio_addr;
-        /* Bottom 4 bits must be zero */
-        assert(~(dev->config.bar[0] & 0xF));
-}
-
-/* This puts the device config into BAR0 */
-static void set_device_config(struct device *dev, const void *conf, size_t len)
-{
-        /* Set up BAR 0 */
-        dev->mmio_size += len;
-        dev->mmio = realloc(dev->mmio, dev->mmio_size);
-        memcpy(dev->mmio + 1, conf, len);
-
-        /*
-         * 4.1.4.6:
-         *
-         *  The device MUST present at least one VIRTIO_PCI_CAP_DEVICE_CFG
-         *  capability for any device type which has a device-specific
-         *  configuration.
-         */
-        /* Hook up device cfg */
-        dev->config.cfg_access.cap.cap_next
-                = offsetof(struct pci_config, device);
-
-        /*
-         * 4.1.4.6.1:
-         *
-         *  The offset for the device-specific configuration MUST be 4-byte
-         *  aligned.
-         */
-        assert(dev->config.cfg_access.cap.cap_next % 4 == 0);
-
-        /* Fix up device cfg field length. */
-        dev->config.device.length = len;
-
-        /* The rest is the same as the no-config case */
-        no_device_config(dev);
-}
-
-static void init_cap(struct virtio_pci_cap *cap, size_t caplen, int type,
-                     size_t bar_offset, size_t bar_bytes, u8 next)
-{
-        cap->cap_vndr = PCI_CAP_ID_VNDR;
-        cap->cap_next = next;
-        cap->cap_len = caplen;
-        cap->cfg_type = type;
-        cap->bar = 0;
-        memset(cap->padding, 0, sizeof(cap->padding));
-        cap->offset = bar_offset;
-        cap->length = bar_bytes;
-}
-
-/*
- * This sets up the pci_config structure, as defined in the virtio 1.0
- * standard (and PCI standard).
- */
-static void init_pci_config(struct pci_config *pci, u16 type,
-                            u8 class, u8 subclass)
-{
-        size_t bar_offset, bar_len;
-
-        /*
-         * 4.1.4.4.1:
-         *
-         *  The device MUST either present notify_off_multiplier as an even
-         *  power of 2, or present notify_off_multiplier as 0.
-         *
-         * 2.1.2:
-         *
-         *   The device MUST initialize device status to 0 upon reset. 
-         */
-        memset(pci, 0, sizeof(*pci));
-
-        /* 4.1.2.1: Devices MUST have the PCI Vendor ID 0x1AF4 */
-        pci->vendor_id = 0x1AF4;
-        /* 4.1.2.1: ... PCI Device ID calculated by adding 0x1040 ... */
-        pci->device_id = 0x1040 + type;
-
-        /*
-         * PCI have specific codes for different types of devices.
-         * Linux doesn't care, but it's a good clue for people looking
-         * at the device.
-         */
-        pci->class = class;
-        pci->subclass = subclass;
-
-        /*
-         * 4.1.2.1:
-         *
-         *  Non-transitional devices SHOULD have a PCI Revision ID of 1 or
-         *  higher
-         */
-        pci->revid = 1;
-
-        /*
-         * 4.1.2.1:
-         *
-         *  Non-transitional devices SHOULD have a PCI Subsystem Device ID of
-         *  0x40 or higher.
-         */
-        pci->subsystem_device_id = 0x40;
-
-        /* We use our dummy interrupt controller, and irq_line is the irq */
-        pci->irq_line = devices.next_irq++;
-        pci->irq_pin = 0;
-
-        /* Support for extended capabilities. */
-        pci->status = (1 << 4);
-
-        /* Link them in. */
-        /*
-         * 4.1.4.3.1:
-         *
-         *  The device MUST present at least one common configuration
-         *  capability.
-         */
-        pci->capabilities = offsetof(struct pci_config, common);
-
-        /* 4.1.4.3.1 ... offset MUST be 4-byte aligned. */
-        assert(pci->capabilities % 4 == 0);
-
-        bar_offset = offsetof(struct virtio_pci_mmio, cfg);
-        bar_len = sizeof(((struct virtio_pci_mmio *)0)->cfg);
-        init_cap(&pci->common, sizeof(pci->common), VIRTIO_PCI_CAP_COMMON_CFG,
-                 bar_offset, bar_len,
-                 offsetof(struct pci_config, notify));
-
-        /*
-         * 4.1.4.4.1:
-         *
-         *  The device MUST present at least one notification capability.
-         */
-        bar_offset += bar_len;
-        bar_len = sizeof(((struct virtio_pci_mmio *)0)->notify);
-
-        /*
-         * 4.1.4.4.1:
-         *
-         *  The cap.offset MUST be 2-byte aligned.
-         */
-        assert(pci->common.cap_next % 2 == 0);
-
-        /* FIXME: Use a non-zero notify_off, for per-queue notification? */
-        /*
-         * 4.1.4.4.1:
-         *
-         *  The value cap.length presented by the device MUST be at least 2 and
-         *  MUST be large enough to support queue notification offsets for all
-         *  supported queues in all possible configurations.
-         */
-        assert(bar_len >= 2);
-
-        init_cap(&pci->notify.cap, sizeof(pci->notify),
-                 VIRTIO_PCI_CAP_NOTIFY_CFG,
-                 bar_offset, bar_len,
-                 offsetof(struct pci_config, isr));
-
-        bar_offset += bar_len;
-        bar_len = sizeof(((struct virtio_pci_mmio *)0)->isr);
-        /*
-         * 4.1.4.5.1:
-         *
-         *  The device MUST present at least one VIRTIO_PCI_CAP_ISR_CFG
-         *  capability.
-         */
-        init_cap(&pci->isr, sizeof(pci->isr),
-                 VIRTIO_PCI_CAP_ISR_CFG,
-                 bar_offset, bar_len,
-                 offsetof(struct pci_config, cfg_access));
-
-        /*
-         * 4.1.4.7.1:
-         *
-         * The device MUST present at least one VIRTIO_PCI_CAP_PCI_CFG
-         * capability.
-         */
-        /* This doesn't have any presence in the BAR */
-        init_cap(&pci->cfg_access.cap, sizeof(pci->cfg_access),
-                 VIRTIO_PCI_CAP_PCI_CFG,
-                 0, 0, 0);
-
-        bar_offset += bar_len + sizeof(((struct virtio_pci_mmio *)0)->padding);
-        assert(bar_offset == sizeof(struct virtio_pci_mmio));
-
-        /*
-         * This gets sewn in and length set in set_device_config().
-         * Some devices don't have a device configuration interface, so
-         * we never expose this if we don't call set_device_config().
-         */
-        init_cap(&pci->device, sizeof(pci->device), VIRTIO_PCI_CAP_DEVICE_CFG,
-                 bar_offset, 0, 0);
-}
-
-/*
- * This routine does all the creation and setup of a new device, but we don't
- * actually place the MMIO region until we know the size (if any) of the
- * device-specific config.  And we don't actually start the service threads
- * until later.
- *
- * See what I mean about userspace being boring?
- */
-static struct device *new_pci_device(const char *name, u16 type,
-                                     u8 class, u8 subclass)
-{
-        struct device *dev = malloc(sizeof(*dev));
-
-        /* Now we populate the fields one at a time. */
-        dev->name = name;
-        dev->vq = NULL;
-        dev->running = false;
-        dev->wrote_features_ok = false;
-        dev->mmio_size = sizeof(struct virtio_pci_mmio);
-        dev->mmio = calloc(1, dev->mmio_size);
-        dev->features = (u64)1 << VIRTIO_F_VERSION_1;
-        dev->features_accepted = 0;
-
-        if (devices.device_num + 1 >= MAX_PCI_DEVICES)
-                errx(1, "Can only handle 31 PCI devices");
-
-        init_pci_config(&dev->config, type, class, subclass);
-        assert(!devices.pci[devices.device_num+1]);
-        devices.pci[++devices.device_num] = dev;
-
-        return dev;
-}
-
-/*
- * Our first setup routine is the console.  It's a fairly simple device, but
- * UNIX tty handling makes it uglier than it could be.
- */
-static void setup_console(void)
-{
-        struct device *dev;
-        struct virtio_console_config conf;
-
-        /* If we can save the initial standard input settings... */
-        if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
-                struct termios term = orig_term;
-                /*
-                 * Then we turn off echo, line buffering and ^C etc: We want a
-                 * raw input stream to the Guest.
-                 */
-                term.c_lflag &= ~(ISIG|ICANON|ECHO);
-                tcsetattr(STDIN_FILENO, TCSANOW, &term);
-        }
-
-        dev = new_pci_device("console", VIRTIO_ID_CONSOLE, 0x07, 0x00);
-
-        /* We store the console state in dev->priv, and initialize it. */
-        dev->priv = malloc(sizeof(struct console_abort));
-        ((struct console_abort *)dev->priv)->count = 0;
-
-        /*
-         * The console needs two virtqueues: the input then the output.  When
-         * they put something the input queue, we make sure we're listening to
-         * stdin.  When they put something in the output queue, we write it to
-         * stdout.
-         */
-        add_pci_virtqueue(dev, console_input, "input");
-        add_pci_virtqueue(dev, console_output, "output");
-
-        /* We need a configuration area for the emerg_wr early writes. */
-        add_pci_feature(dev, VIRTIO_CONSOLE_F_EMERG_WRITE);
-        set_device_config(dev, &conf, sizeof(conf));
-
-        verbose("device %u: console\n", devices.device_num);
-}
-/*:*/
-
-/*M:010
- * Inter-guest networking is an interesting area.  Simplest is to have a
- * --sharenet=<name> option which opens or creates a named pipe.  This can be
- * used to send packets to another guest in a 1:1 manner.
- *
- * More sophisticated is to use one of the tools developed for project like UML
- * to do networking.
- *
- * Faster is to do virtio bonding in kernel.  Doing this 1:1 would be
- * completely generic ("here's my vring, attach to your vring") and would work
- * for any traffic.  Of course, namespace and permissions issues need to be
- * dealt with.  A more sophisticated "multi-channel" virtio_net.c could hide
- * multiple inter-guest channels behind one interface, although it would
- * require some manner of hotplugging new virtio channels.
- *
- * Finally, we could use a virtio network switch in the kernel, ie. vhost.
-:*/
-
-static u32 str2ip(const char *ipaddr)
-{
-        unsigned int b[4];
-
-        if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
-                errx(1, "Failed to parse IP address '%s'", ipaddr);
-        return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
-}
-
-static void str2mac(const char *macaddr, unsigned char mac[6])
-{
-        unsigned int m[6];
-        if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x",
-                   &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6)
-                errx(1, "Failed to parse mac address '%s'", macaddr);
-        mac[0] = m[0];
-        mac[1] = m[1];
-        mac[2] = m[2];
-        mac[3] = m[3];
-        mac[4] = m[4];
-        mac[5] = m[5];
-}
-
-/*
- * This code is "adapted" from libbridge: it attaches the Host end of the
- * network device to the bridge device specified by the command line.
- *
- * This is yet another James Morris contribution (I'm an IP-level guy, so I
- * dislike bridging), and I just try not to break it.
- */
-static void add_to_bridge(int fd, const char *if_name, const char *br_name)
-{
-        int ifidx;
-        struct ifreq ifr;
-
-        if (!*br_name)
-                errx(1, "must specify bridge name");
-
-        ifidx = if_nametoindex(if_name);
-        if (!ifidx)
-                errx(1, "interface %s does not exist!", if_name);
-
-        strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
-        ifr.ifr_name[IFNAMSIZ-1] = '\0';
-        ifr.ifr_ifindex = ifidx;
-        if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
-                err(1, "can't add %s to bridge %s", if_name, br_name);
-}
-
-/*
- * This sets up the Host end of the network device with an IP address, brings
- * it up so packets will flow, the copies the MAC address into the hwaddr
- * pointer.
- */
-static void configure_device(int fd, const char *tapif, u32 ipaddr)
-{
-        struct ifreq ifr;
-        struct sockaddr_in sin;
-
-        memset(&ifr, 0, sizeof(ifr));
-        strcpy(ifr.ifr_name, tapif);
-
-        /* Don't read these incantations.  Just cut & paste them like I did! */
-        sin.sin_family = AF_INET;
-        sin.sin_addr.s_addr = htonl(ipaddr);
-        memcpy(&ifr.ifr_addr, &sin, sizeof(sin));
-        if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
-                err(1, "Setting %s interface address", tapif);
-        ifr.ifr_flags = IFF_UP;
-        if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
-                err(1, "Bringing interface %s up", tapif);
-}
-
-static int get_tun_device(char tapif[IFNAMSIZ])
-{
-        struct ifreq ifr;
-        int vnet_hdr_sz;
-        int netfd;
-
-        /* Start with this zeroed.  Messy but sure. */
-        memset(&ifr, 0, sizeof(ifr));
-
-        /*
-         * We open the /dev/net/tun device and tell it we want a tap device.  A
-         * tap device is like a tun device, only somehow different.  To tell
-         * the truth, I completely blundered my way through this code, but it
-         * works now!
-         */
-        netfd = open_or_die("/dev/net/tun", O_RDWR);
-        ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
-        strcpy(ifr.ifr_name, "tap%d");
-        if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
-                err(1, "configuring /dev/net/tun");
-
-        if (ioctl(netfd, TUNSETOFFLOAD,
-                  TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
-                err(1, "Could not set features for tun device");
-
-        /*
-         * We don't need checksums calculated for packets coming in this
-         * device: trust us!
-         */
-        ioctl(netfd, TUNSETNOCSUM, 1);
-
-        /*
-         * In virtio before 1.0 (aka legacy virtio), we added a 16-bit
-         * field at the end of the network header iff
-         * VIRTIO_NET_F_MRG_RXBUF was negotiated.  For virtio 1.0,
-         * that became the norm, but we need to tell the tun device
-         * about our expanded header (which is called
-         * virtio_net_hdr_mrg_rxbuf in the legacy system).
-         */
-        vnet_hdr_sz = sizeof(struct virtio_net_hdr_v1);
-        if (ioctl(netfd, TUNSETVNETHDRSZ, &vnet_hdr_sz) != 0)
-                err(1, "Setting tun header size to %u", vnet_hdr_sz);
-
-        memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
-        return netfd;
-}
-
-/*L:195
- * Our network is a Host<->Guest network.  This can either use bridging or
- * routing, but the principle is the same: it uses the "tun" device to inject
- * packets into the Host as if they came in from a normal network card.  We
- * just shunt packets between the Guest and the tun device.
- */
-static void setup_tun_net(char *arg)
-{
-        struct device *dev;
-        struct net_info *net_info = malloc(sizeof(*net_info));
-        int ipfd;
-        u32 ip = INADDR_ANY;
-        bool bridging = false;
-        char tapif[IFNAMSIZ], *p;
-        struct virtio_net_config conf;
-
-        net_info->tunfd = get_tun_device(tapif);
-
-        /* First we create a new network device. */
-        dev = new_pci_device("net", VIRTIO_ID_NET, 0x02, 0x00);
-        dev->priv = net_info;
-
-        /* Network devices need a recv and a send queue, just like console. */
-        add_pci_virtqueue(dev, net_input, "rx");
-        add_pci_virtqueue(dev, net_output, "tx");
-
-        /*
-         * We need a socket to perform the magic network ioctls to bring up the
-         * tap interface, connect to the bridge etc.  Any socket will do!
-         */
-        ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
-        if (ipfd < 0)
-                err(1, "opening IP socket");
-
-        /* If the command line was --tunnet=bridge:<name> do bridging. */
-        if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
-                arg += strlen(BRIDGE_PFX);
-                bridging = true;
-        }
-
-        /* A mac address may follow the bridge name or IP address */
-        p = strchr(arg, ':');
-        if (p) {
-                str2mac(p+1, conf.mac);
-                add_pci_feature(dev, VIRTIO_NET_F_MAC);
-                *p = '\0';
-        }
-
-        /* arg is now either an IP address or a bridge name */
-        if (bridging)
-                add_to_bridge(ipfd, tapif, arg);
-        else
-                ip = str2ip(arg);
-
-        /* Set up the tun device. */
-        configure_device(ipfd, tapif, ip);
-
-        /* Expect Guest to handle everything except UFO */
-        add_pci_feature(dev, VIRTIO_NET_F_CSUM);
-        add_pci_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
-        add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
-        add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
-        add_pci_feature(dev, VIRTIO_NET_F_GUEST_ECN);
-        add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO4);
-        add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO6);
-        add_pci_feature(dev, VIRTIO_NET_F_HOST_ECN);
-        /* We handle indirect ring entries */
-        add_pci_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
-        set_device_config(dev, &conf, sizeof(conf));
-
-        /* We don't need the socket any more; setup is done. */
-        close(ipfd);
-
-        if (bridging)
-                verbose("device %u: tun %s attached to bridge: %s\n",
-                        devices.device_num, tapif, arg);
-        else
-                verbose("device %u: tun %s: %s\n",
-                        devices.device_num, tapif, arg);
-}
-/*:*/
-
-/* This hangs off device->priv. */
-struct vblk_info {
-        /* The size of the file. */
-        off64_t len;
-
-        /* The file descriptor for the file. */
-        int fd;
-
-};
-
-/*L:210
- * The Disk
- *
- * The disk only has one virtqueue, so it only has one thread.  It is really
- * simple: the Guest asks for a block number and we read or write that position
- * in the file.
- *
- * Before we serviced each virtqueue in a separate thread, that was unacceptably
- * slow: the Guest waits until the read is finished before running anything
- * else, even if it could have been doing useful work.
- *
- * We could have used async I/O, except it's reputed to suck so hard that
- * characters actually go missing from your code when you try to use it.
- */
-static void blk_request(struct virtqueue *vq)
-{
-        struct vblk_info *vblk = vq->dev->priv;
-        unsigned int head, out_num, in_num, wlen;
-        int ret, i;
-        u8 *in;
-        struct virtio_blk_outhdr out;
-        struct iovec iov[vq->vring.num];
-        off64_t off;
-
-        /*
-         * Get the next request, where we normally wait.  It triggers the
-         * interrupt to acknowledge previously serviced requests (if any).
-         */
-        head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
-
-        /* Copy the output header from the front of the iov (adjusts iov) */
-        iov_consume(vq->dev, iov, out_num, &out, sizeof(out));
-
-        /* Find and trim end of iov input array, for our status byte. */
-        in = NULL;
-        for (i = out_num + in_num - 1; i >= out_num; i--) {
-                if (iov[i].iov_len > 0) {
-                        in = iov[i].iov_base + iov[i].iov_len - 1;
-                        iov[i].iov_len--;
-                        break;
-                }
-        }
-        if (!in)
-                bad_driver_vq(vq, "Bad virtblk cmd with no room for status");
-
-        /*
-         * For historical reasons, block operations are expressed in 512 byte
-         * "sectors".
-         */
-        off = out.sector * 512;
-
-        if (out.type & VIRTIO_BLK_T_OUT) {
-                /*
-                 * Write
-                 *
-                 * Move to the right location in the block file.  This can fail
-                 * if they try to write past end.
-                 */
-                if (lseek64(vblk->fd, off, SEEK_SET) != off)
-                        err(1, "Bad seek to sector %llu", out.sector);
-
-                ret = writev(vblk->fd, iov, out_num);
-                verbose("WRITE to sector %llu: %i\n", out.sector, ret);
-
-                /*
-                 * Grr... Now we know how long the descriptor they sent was, we
-                 * make sure they didn't try to write over the end of the block
-                 * file (possibly extending it).
-                 */
-                if (ret > 0 && off + ret > vblk->len) {
-                        /* Trim it back to the correct length */
-                        ftruncate64(vblk->fd, vblk->len);
-                        /* Die, bad Guest, die. */
-                        bad_driver_vq(vq, "Write past end %llu+%u", off, ret);
-                }
-
-                wlen = sizeof(*in);
-                *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
-        } else if (out.type & VIRTIO_BLK_T_FLUSH) {
-                /* Flush */
-                ret = fdatasync(vblk->fd);
-                verbose("FLUSH fdatasync: %i\n", ret);
-                wlen = sizeof(*in);
-                *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
-        } else {
-                /*
-                 * Read
-                 *
-                 * Move to the right location in the block file.  This can fail
-                 * if they try to read past end.
-                 */
-                if (lseek64(vblk->fd, off, SEEK_SET) != off)
-                        err(1, "Bad seek to sector %llu", out.sector);
-
-                ret = readv(vblk->fd, iov + out_num, in_num);
-                if (ret >= 0) {
-                        wlen = sizeof(*in) + ret;
-                        *in = VIRTIO_BLK_S_OK;
-                } else {
-                        wlen = sizeof(*in);
-                        *in = VIRTIO_BLK_S_IOERR;
-                }
-        }
-
-        /* Finished that request. */
-        add_used(vq, head, wlen);
-}
-
-/*L:198 This actually sets up a virtual block device. */
-static void setup_block_file(const char *filename)
-{
-        struct device *dev;
-        struct vblk_info *vblk;
-        struct virtio_blk_config conf;
-
-        /* Create the device. */
-        dev = new_pci_device("block", VIRTIO_ID_BLOCK, 0x01, 0x80);
-
-        /* The device has one virtqueue, where the Guest places requests. */
-        add_pci_virtqueue(dev, blk_request, "request");
-
-        /* Allocate the room for our own bookkeeping */
-        vblk = dev->priv = malloc(sizeof(*vblk));
-
-        /* First we open the file and store the length. */
-        vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
-        vblk->len = lseek64(vblk->fd, 0, SEEK_END);
-
-        /* Tell Guest how many sectors this device has. */
-        conf.capacity = cpu_to_le64(vblk->len / 512);
-
-        /*
-         * Tell Guest not to put in too many descriptors at once: two are used
-         * for the in and out elements.
-         */
-        add_pci_feature(dev, VIRTIO_BLK_F_SEG_MAX);
-        conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
-
-        set_device_config(dev, &conf, sizeof(struct virtio_blk_config));
-
-        verbose("device %u: virtblock %llu sectors\n",
-                devices.device_num, le64_to_cpu(conf.capacity));
-}
-
-/*L:211
- * Our random number generator device reads from /dev/urandom into the Guest's
- * input buffers.  The usual case is that the Guest doesn't want random numbers
- * and so has no buffers although /dev/urandom is still readable, whereas
- * console is the reverse.
- *
- * The same logic applies, however.
- */
-struct rng_info {
-        int rfd;
-};
-
-static void rng_input(struct virtqueue *vq)
-{
-        int len;
-        unsigned int head, in_num, out_num, totlen = 0;
-        struct rng_info *rng_info = vq->dev->priv;
-        struct iovec iov[vq->vring.num];
-
-        /* First we need a buffer from the Guests's virtqueue. */
-        head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
-        if (out_num)
-                bad_driver_vq(vq, "Output buffers in rng?");
-
-        /*
-         * Just like the console write, we loop to cover the whole iovec.
-         * In this case, short reads actually happen quite a bit.
-         */
-        while (!iov_empty(iov, in_num)) {
-                len = readv(rng_info->rfd, iov, in_num);
-                if (len <= 0)
-                        err(1, "Read from /dev/urandom gave %i", len);
-                iov_consume(vq->dev, iov, in_num, NULL, len);
-                totlen += len;
-        }
-
-        /* Tell the Guest about the new input. */
-        add_used(vq, head, totlen);
-}
-
-/*L:199
- * This creates a "hardware" random number device for the Guest.
- */
-static void setup_rng(void)
-{
-        struct device *dev;
-        struct rng_info *rng_info = malloc(sizeof(*rng_info));
-
-        /* Our device's private info simply contains the /dev/urandom fd. */
-        rng_info->rfd = open_or_die("/dev/urandom", O_RDONLY);
-
-        /* Create the new device. */
-        dev = new_pci_device("rng", VIRTIO_ID_RNG, 0xff, 0);
-        dev->priv = rng_info;
-
-        /* The device has one virtqueue, where the Guest places inbufs. */
-        add_pci_virtqueue(dev, rng_input, "input");
-
-        /* We don't have any configuration space */
-        no_device_config(dev);
-
-        verbose("device %u: rng\n", devices.device_num);
-}
-/* That's the end of device setup. */
-
-/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */
-static void __attribute__((noreturn)) restart_guest(void)
-{
-        unsigned int i;
-
-        /*
-         * Since we don't track all open fds, we simply close everything beyond
-         * stderr.
-         */
-        for (i = 3; i < FD_SETSIZE; i++)
-                close(i);
-
-        /* Reset all the devices (kills all threads). */
-        cleanup_devices();
-
-        execv(main_args[0], main_args);
-        err(1, "Could not exec %s", main_args[0]);
-}
-
-/*L:220
- * Finally we reach the core of the Launcher which runs the Guest, serves
- * its input and output, and finally, lays it to rest.
- */
-static void __attribute__((noreturn)) run_guest(void)
-{
-        for (;;) {
-                struct lguest_pending notify;
-                int readval;
-
-                /* We read from the /dev/lguest device to run the Guest. */
-                readval = pread(lguest_fd, &notify, sizeof(notify), cpu_id);
-                if (readval == sizeof(notify)) {
-                        if (notify.trap == 13) {
-                                verbose("Emulating instruction at %#x\n",
-                                        getreg(eip));
-                                emulate_insn(notify.insn);
-                        } else if (notify.trap == 14) {
-                                verbose("Emulating MMIO at %#x\n",
-                                        getreg(eip));
-                                emulate_mmio(notify.addr, notify.insn);
-                        } else
-                                errx(1, "Unknown trap %i addr %#08x\n",
-                                     notify.trap, notify.addr);
-                /* ENOENT means the Guest died.  Reading tells us why. */
-                } else if (errno == ENOENT) {
-                        char reason[1024] = { 0 };
-                        pread(lguest_fd, reason, sizeof(reason)-1, cpu_id);
-                        errx(1, "%s", reason);
-                /* ERESTART means that we need to reboot the guest */
-                } else if (errno == ERESTART) {
-                        restart_guest();
-                /* Anything else means a bug or incompatible change. */
-                } else
-                        err(1, "Running guest failed");
-        }
-}
-/*L:240
- * This is the end of the Launcher.  The good news: we are over halfway
- * through!  The bad news: the most fiendish part of the code still lies ahead
- * of us.
- *
- * Are you ready?  Take a deep breath and join me in the core of the Host, in
- * "make Host".
-:*/
-
-static struct option opts[] = {
-        { "verbose", 0, NULL, 'v' },
-        { "tunnet", 1, NULL, 't' },
-        { "block", 1, NULL, 'b' },
-        { "rng", 0, NULL, 'r' },
-        { "initrd", 1, NULL, 'i' },
-        { "username", 1, NULL, 'u' },
-        { "chroot", 1, NULL, 'c' },
-        { NULL },
-};
-static void usage(void)
-{
-        errx(1, "Usage: lguest [--verbose] "
-             "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\n"
-             "|--block=<filename>|--initrd=<filename>]...\n"
-             "<mem-in-mb> vmlinux [args...]");
-}
-
-/*L:105 The main routine is where the real work begins: */
-int main(int argc, char *argv[])
-{
-        /* Memory, code startpoint and size of the (optional) initrd. */
-        unsigned long mem = 0, start, initrd_size = 0;
-        /* Two temporaries. */
-        int i, c;
-        /* The boot information for the Guest. */
-        struct boot_params *boot;
-        /* If they specify an initrd file to load. */
-        const char *initrd_name = NULL;
-
-        /* Password structure for initgroups/setres[gu]id */
-        struct passwd *user_details = NULL;
-
-        /* Directory to chroot to */
-        char *chroot_path = NULL;
-
-        /* Save the args: we "reboot" by execing ourselves again. */
-        main_args = argv;
-
-        /*
-         * First we initialize the device list.  We remember next interrupt
-         * number to use for devices (1: remember that 0 is used by the timer).
-         */
-        devices.next_irq = 1;
-
-        /* We're CPU 0.  In fact, that's the only CPU possible right now. */
-        cpu_id = 0;
-
-        /*
-         * We need to know how much memory so we can set up the device
-         * descriptor and memory pages for the devices as we parse the command
-         * line.  So we quickly look through the arguments to find the amount
-         * of memory now.
-         */
-        for (i = 1; i < argc; i++) {
-                if (argv[i][0] != '-') {
-                        mem = atoi(argv[i]) * 1024 * 1024;
-                        /*
-                         * We start by mapping anonymous pages over all of
-                         * guest-physical memory range.  This fills it with 0,
-                         * and ensures that the Guest won't be killed when it
-                         * tries to access it.
-                         */
-                        guest_base = map_zeroed_pages(mem / getpagesize()
-                                                      + DEVICE_PAGES);
-                        guest_limit = mem;
-                        guest_max = guest_mmio = mem + DEVICE_PAGES*getpagesize();
-                        break;
-                }
-        }
-
-        /* If we exit via err(), this kills all the threads, restores tty. */
-        atexit(cleanup_devices);
-
-        /* We always have a console device, and it's always device 1. */
-        setup_console();
-
-        /* The options are fairly straight-forward */
-        while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) {
-                switch (c) {
-                case 'v':
-                        verbose = true;
-                        break;
-                case 't':
-                        setup_tun_net(optarg);
-                        break;
-                case 'b':
-                        setup_block_file(optarg);
-                        break;
-                case 'r':
-                        setup_rng();
-                        break;
-                case 'i':
-                        initrd_name = optarg;
-                        break;
-                case 'u':
-                        user_details = getpwnam(optarg);
-                        if (!user_details)
-                                err(1, "getpwnam failed, incorrect username?");
-                        break;
-                case 'c':
-                        chroot_path = optarg;
-                        break;
-                default:
-                        warnx("Unknown argument %s", argv[optind]);
-                        usage();
-                }
-        }
-        /*
-         * After the other arguments we expect memory and kernel image name,
-         * followed by command line arguments for the kernel.
-         */
-        if (optind + 2 > argc)
-                usage();
-
-        verbose("Guest base is at %p\n", guest_base);
-
-        /* Initialize the (fake) PCI host bridge device. */
-        init_pci_host_bridge();
-
-        /* Now we load the kernel */
-        start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));
-
-        /* Boot information is stashed at physical address 0 */
-        boot = from_guest_phys(0);
-
-        /* Map the initrd image if requested (at top of physical memory) */
-        if (initrd_name) {
-                initrd_size = load_initrd(initrd_name, mem);
-                /*
-                 * These are the location in the Linux boot header where the
-                 * start and size of the initrd are expected to be found.
-                 */
-                boot->hdr.ramdisk_image = mem - initrd_size;
-                boot->hdr.ramdisk_size = initrd_size;
-                /* The bootloader type 0xFF means "unknown"; that's OK. */
-                boot->hdr.type_of_loader = 0xFF;
-        }
-
-        /*
-         * The Linux boot header contains an "E820" memory map: ours is a
-         * simple, single region.
-         */
-        boot->e820_entries = 1;
-        boot->e820_table[0] = ((struct e820_entry) { 0, mem, E820_TYPE_RAM });
-        /*
-         * The boot header contains a command line pointer: we put the command
-         * line after the boot header.
-         */
-        boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1);
-        /* We use a simple helper to copy the arguments separated by spaces. */
-        concat((char *)(boot + 1), argv+optind+2);
-
-        /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */
-        boot->hdr.kernel_alignment = 0x1000000;
-
-        /* Boot protocol version: 2.07 supports the fields for lguest. */
-        boot->hdr.version = 0x207;
-
-        /* X86_SUBARCH_LGUEST tells the Guest it's an lguest. */
-        boot->hdr.hardware_subarch = X86_SUBARCH_LGUEST;
-
-        /* Tell the entry path not to try to reload segment registers. */
-        boot->hdr.loadflags |= KEEP_SEGMENTS;
-
-        /* We don't support tboot: */
-        boot->tboot_addr = 0;
-
-        /* Ensure this is 0 to prevent APM from loading: */
-        boot->apm_bios_info.version = 0;
-
-        /* We tell the kernel to initialize the Guest. */
-        tell_kernel(start);
-
-        /* Ensure that we terminate if a device-servicing child dies. */
-        signal(SIGCHLD, kill_launcher);
-
-        /* If requested, chroot to a directory */
-        if (chroot_path) {
-                if (chroot(chroot_path) != 0)
-                        err(1, "chroot(\"%s\") failed", chroot_path);
-
-                if (chdir("/") != 0)
-                        err(1, "chdir(\"/\") failed");
-
-                verbose("chroot done\n");
-        }
-
-        /* If requested, drop privileges */
-        if (user_details) {
-                uid_t u;
-                gid_t g;
-
-                u = user_details->pw_uid;
-                g = user_details->pw_gid;
-
-                if (initgroups(user_details->pw_name, g) != 0)
-                        err(1, "initgroups failed");
-
-                if (setresgid(g, g, g) != 0)
-                        err(1, "setresgid failed");
-
-                if (setresuid(u, u, u) != 0)
-                        err(1, "setresuid failed");
-
-                verbose("Dropping privileges completed\n");
-        }
-
-        /* Finally, run the Guest.  This doesn't return. */
-        run_guest();
-}
-/*:*/
-
-/*M:999
- * Mastery is done: you now know everything I do.
- *
- * But surely you have seen code, features and bugs in your wanderings which
- * you now yearn to attack?  That is the real game, and I look forward to you
- * patching and forking lguest into the Your-Name-Here-visor.
- *
- * Farewell, and good coding!
- * Rusty Russell.
- */
diff --git a/tools/lguest/lguest.txt b/tools/lguest/lguest.txt
deleted file mode 100644
index 06e1f4649511..000000000000
--- a/tools/lguest/lguest.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-      __
- (___()'`;  Rusty's Remarkably Unreliable Guide to Lguest
- /,    /`      - or, A Young Coder's Illustrated Hypervisor
- \\"--\\    http://lguest.ozlabs.org
-
-Lguest is designed to be a minimal 32-bit x86 hypervisor for the Linux kernel,
-for Linux developers and users to experiment with virtualization with the
-minimum of complexity.  Nonetheless, it should have sufficient features to
-make it useful for specific tasks, and, of course, you are encouraged to fork
-and enhance it (see drivers/lguest/README).
-
-Features:
-
-- Kernel module which runs in a normal kernel.
-- Simple I/O model for communication.
-- Simple program to create new guests.
-- Logo contains cute puppies: http://lguest.ozlabs.org
-
-Developer features:
-
-- Fun to hack on.
-- No ABI: being tied to a specific kernel anyway, you can change anything.
-- Many opportunities for improvement or feature implementation.
-
-Running Lguest:
-
-- The easiest way to run lguest is to use same kernel as guest and host.
-  You can configure them differently, but usually it's easiest not to.
-
-  You will need to configure your kernel with the following options:
-
-  "Processor type and features":
-     "Paravirtualized guest support" = Y
-        "Lguest guest support" = Y
-     "High Memory Support" = off/4GB
-     "Alignment value to which kernel should be aligned" = 0x100000
-        (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and
-         CONFIG_PHYSICAL_ALIGN=0x100000)
-
-  "Device Drivers":
-     "Block devices"
-        "Virtio block driver" = M/Y
-     "Network device support"
-        "Universal TUN/TAP device driver support" = M/Y
-        "Virtio network driver" = M/Y
-           (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m)
-
-  "Virtualization"
-     "Linux hypervisor example code" = M/Y
-        (CONFIG_LGUEST=m)
-
-- A tool called "lguest" is available in this directory: type "make"
-  to build it.  If you didn't build your kernel in-tree, use "make
-  O=<builddir>".
-
-- Create or find a root disk image.  There are several useful ones
-  around, such as the xm-test tiny root image at
-          http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img
-
-  For more serious work, I usually use a distribution ISO image and
-  install it under qemu, then make multiple copies:
-
-          dd if=/dev/zero of=rootfile bs=1M count=2048
-          qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d
-
-  Make sure that you install a getty on /dev/hvc0 if you want to log in on the
-  console!
-
-- "modprobe lg" if you built it as a module.
-
-- Run an lguest as root:
-
-      tools/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \
-        --block=rootfile root=/dev/vda
-
-   Explanation:
-    64: the amount of memory to use, in MB.
-
-    vmlinux: the kernel image found in the top of your build directory.  You
-       can also use a standard bzImage.
-
-    --tunnet=192.168.19.1: configures a "tap" device for networking with this
-       IP address.
-
-    --block=rootfile: a file or block device which becomes /dev/vda
-       inside the guest.
-
-    root=/dev/vda: this (and anything else on the command line) are
-       kernel boot parameters.
-
-- Configuring networking.  I usually have the host masquerade, using
-  "iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE" and "echo 1 >
-  /proc/sys/net/ipv4/ip_forward".  In this example, I would configure
-  eth0 inside the guest at 192.168.19.2.
-
-  Another method is to bridge the tap device to an external interface
-  using --tunnet=bridge:<bridgename>, and perhaps run dhcp on the guest
-  to obtain an IP address.  The bridge needs to be configured first:
-  this option simply adds the tap interface to it.
-
-  A simple example on my system:
-
-    ifconfig eth0 0.0.0.0
-    brctl addbr lg0
-    ifconfig lg0 up
-    brctl addif lg0 eth0
-    dhclient lg0
-
-  Then use --tunnet=bridge:lg0 when launching the guest.
-
-  See:
-  
-    http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
-    
-  for general information on how to get bridging to work.
-
-- Random number generation. Using the --rng option will provide a
-  /dev/hwrng in the guest that will read from the host's /dev/random.
-  Use this option in conjunction with rng-tools (see ../hw_random.txt)
-  to provide entropy to the guest kernel's /dev/random.
-
-There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest
-
-Good luck!
-Rusty Russell rusty@rustcorp.com.au.
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index eb6e0b36bfc1..a13e9c7f1fc5 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 include ../../scripts/Makefile.include
 include ../../scripts/utilities.mak             # QUIET_CLEAN
 
@@ -8,22 +9,28 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-LD = $(CROSS_COMPILE)ld
+CC ?= $(CROSS_COMPILE)gcc
+AR ?= $(CROSS_COMPILE)ar
+LD ?= $(CROSS_COMPILE)ld
 
 MAKEFLAGS += --no-print-directory
 
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC
 
-ifeq ($(CC), clang)
+ifeq ($(DEBUG),0)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
 endif
+endif
+
+ifeq ($(DEBUG),0)
+  CFLAGS += -D_FORTIFY_SOURCE
+endif
 
 # Treat warnings as errors unless directed not to
 ifneq ($(WERROR),0)
diff --git a/tools/lib/api/cpu.c b/tools/lib/api/cpu.c
index 8c6489356e3a..4af6d4b7aa07 100644
--- a/tools/lib/api/cpu.c
+++ b/tools/lib/api/cpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 
 #include "cpu.h"
diff --git a/tools/lib/api/cpu.h b/tools/lib/api/cpu.h
index 81e9d3955961..90a102fb20de 100644
--- a/tools/lib/api/cpu.h
+++ b/tools/lib/api/cpu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __API_CPU__
 #define __API_CPU__
 
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
index 188f7880eafe..80c783497d25 100644
--- a/tools/lib/api/debug-internal.h
+++ b/tools/lib/api/debug-internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __API_DEBUG_INTERNAL_H__
 #define __API_DEBUG_INTERNAL_H__
 
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
index 5fa5cf500a1f..69b1ba3d1ee3 100644
--- a/tools/lib/api/debug.c
+++ b/tools/lib/api/debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdarg.h>
 #include "debug.h"
diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h
index a0872f68fc56..3684dd6e0c02 100644
--- a/tools/lib/api/debug.h
+++ b/tools/lib/api/debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __API_DEBUG_H__
 #define __API_DEBUG_H__
 
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
index 71287dddc05f..b39557d1a88f 100644
--- a/tools/lib/api/fd/array.h
+++ b/tools/lib/api/fd/array.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __API_FD_ARRAY__
 #define __API_FD_ARRAY__
 
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index a7ecf8f469f4..b24afc0e6e81 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <ctype.h>
 #include <errno.h>
 #include <limits.h>
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 45605348461e..dda49deefb52 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __API_FS__
 #define __API_FS__
 
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 3e606b9c443e..7b7fd0b18551 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifndef _GNU_SOURCE
 # define _GNU_SOURCE
 #endif
diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h
index 3f233ac70b6f..0066f06cc381 100644
--- a/tools/lib/api/fs/tracing_path.h
+++ b/tools/lib/api/fs/tracing_path.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __API_FS_TRACING_PATH_H
 #define __API_FS_TRACING_PATH_H
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 1f5300e56b44..4555304dc18e 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Most of this file is copied from tools/lib/traceevent/Makefile
 
 BPF_VERSION = 0
@@ -154,12 +155,12 @@ all: fixdep $(VERSION_FILES) all_cmd
 all_cmd: $(CMD_TARGETS)
 
 $(BPF_IN): force elfdep bpfdep
-        @(test -f ../../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
+        @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
         (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
-        echo "Warning: tools/include/uapi/linux/bpf.h differs from kernel" >&2 )) || true
-        @(test -f ../../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
+        echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
+        @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
         (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
-        echo "Warning: tools/include/uapi/linux/bpf_common.h differs from kernel" >&2 )) || true
+        echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
         $(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)
@@ -189,6 +190,10 @@ install_lib: all_cmd
         $(call QUIET_INSTALL, $(LIB_FILE)) \
                 $(call do_install,$(LIB_FILE),$(libdir_SQ))
 
+install_headers:
+        $(call QUIET_INSTALL, headers) \
+                $(call do_install,bpf.h,$(prefix)/include/bpf,644)
+
 install: install_lib
 
 ### Cleaning rules
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 412a7c82995a..5128677e4117 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -39,11 +39,15 @@
 #  define __NR_bpf 280
 # elif defined(__sparc__)
 #  define __NR_bpf 349
+# elif defined(__s390__)
+#  define __NR_bpf 351
 # else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif
 #endif
 
+#define min(x, y) ((x) < (y) ? (x) : (y))
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
         return (__u64) (unsigned long) ptr;
@@ -55,9 +59,11 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
         return syscall(__NR_bpf, cmd, attr, size);
 }
 
-int bpf_create_map(enum bpf_map_type map_type, int key_size,
-                   int value_size, int max_entries, __u32 map_flags)
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+                        int key_size, int value_size, int max_entries,
+                        __u32 map_flags, int node)
 {
+        __u32 name_len = name ? strlen(name) : 0;
         union bpf_attr attr;
 
         memset(&attr, '\0', sizeof(attr));
@@ -67,13 +73,36 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
         attr.value_size = value_size;
         attr.max_entries = max_entries;
         attr.map_flags = map_flags;
+        memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+
+        if (node >= 0) {
+                attr.map_flags |= BPF_F_NUMA_NODE;
+                attr.numa_node = node;
+        }
 
         return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
-                          int inner_map_fd, int max_entries, __u32 map_flags)
+int bpf_create_map(enum bpf_map_type map_type, int key_size,
+                   int value_size, int max_entries, __u32 map_flags)
 {
+        return bpf_create_map_node(map_type, NULL, key_size, value_size,
+                                   max_entries, map_flags, -1);
+}
+
+int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+                        int key_size, int value_size, int max_entries,
+                        __u32 map_flags)
+{
+        return bpf_create_map_node(map_type, name, key_size, value_size,
+                                   max_entries, map_flags, -1);
+}
+
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
+                               int key_size, int inner_map_fd, int max_entries,
+                               __u32 map_flags, int node)
+{
+        __u32 name_len = name ? strlen(name) : 0;
         union bpf_attr attr;
 
         memset(&attr, '\0', sizeof(attr));
@@ -84,16 +113,34 @@ int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
         attr.inner_map_fd = inner_map_fd;
         attr.max_entries = max_entries;
         attr.map_flags = map_flags;
+        memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+
+        if (node >= 0) {
+                attr.map_flags |= BPF_F_NUMA_NODE;
+                attr.numa_node = node;
+        }
 
         return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
-int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-                     size_t insns_cnt, const char *license,
-                     __u32 kern_version, char *log_buf, size_t log_buf_sz)
+int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
+                          int key_size, int inner_map_fd, int max_entries,
+                          __u32 map_flags)
+{
+        return bpf_create_map_in_map_node(map_type, name, key_size,
+                                          inner_map_fd, max_entries, map_flags,
+                                          -1);
+}
+
+int bpf_load_program_name(enum bpf_prog_type type, const char *name,
+                          const struct bpf_insn *insns,
+                          size_t insns_cnt, const char *license,
+                          __u32 kern_version, char *log_buf,
+                          size_t log_buf_sz)
 {
         int fd;
         union bpf_attr attr;
+        __u32 name_len = name ? strlen(name) : 0;
 
         bzero(&attr, sizeof(attr));
         attr.prog_type = type;
@@ -104,6 +151,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
         attr.log_size = 0;
         attr.log_level = 0;
         attr.kern_version = kern_version;
+        memcpy(attr.prog_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
 
         fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
         if (fd >= 0 || !log_buf || !log_buf_sz)
@@ -117,6 +165,15 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
         return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
 
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+                     size_t insns_cnt, const char *license,
+                     __u32 kern_version, char *log_buf,
+                     size_t log_buf_sz)
+{
+        return bpf_load_program_name(type, NULL, insns, insns_cnt, license,
+                                     kern_version, log_buf, log_buf_sz);
+}
+
 int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
                        size_t insns_cnt, int strict_alignment,
                        const char *license, __u32 kern_version,
@@ -234,6 +291,38 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
         return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+        union bpf_attr attr;
+
+        bzero(&attr, sizeof(attr));
+        attr.target_fd   = target_fd;
+        attr.attach_bpf_fd = prog_fd;
+        attr.attach_type = type;
+
+        return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+                   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
+{
+        union bpf_attr attr;
+        int ret;
+
+        bzero(&attr, sizeof(attr));
+        attr.query.target_fd    = target_fd;
+        attr.query.attach_type  = type;
+        attr.query.query_flags  = query_flags;
+        attr.query.prog_cnt     = *prog_cnt;
+        attr.query.prog_ids     = ptr_to_u64(prog_ids);
+
+        ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+        if (attach_flags)
+                *attach_flags = attr.query.attach_flags;
+        *prog_cnt = attr.query.prog_cnt;
+        return ret;
+}
+
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
                       void *data_out, __u32 *size_out, __u32 *retval,
                       __u32 *duration)
@@ -314,7 +403,6 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
         int err;
 
         bzero(&attr, sizeof(attr));
-        bzero(info, *info_len);
         attr.info.bpf_fd = prog_fd;
         attr.info.info_len = *info_len;
         attr.info.info = ptr_to_u64(info);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 418c86e69bcb..6534889e2b2f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,13 +24,28 @@
 #include <linux/bpf.h>
 #include <stddef.h>
 
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+                        int key_size, int value_size, int max_entries,
+                        __u32 map_flags, int node);
+int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+                        int key_size, int value_size, int max_entries,
+                        __u32 map_flags);
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
                    int max_entries, __u32 map_flags);
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
-                          int inner_map_fd, int max_entries, __u32 map_flags);
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
+                               int key_size, int inner_map_fd, int max_entries,
+                               __u32 map_flags, int node);
+int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
+                          int key_size, int inner_map_fd, int max_entries,
+                          __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
+int bpf_load_program_name(enum bpf_prog_type type, const char *name,
+                          const struct bpf_insn *insns,
+                          size_t insns_cnt, const char *license,
+                          __u32 kern_version, char *log_buf,
+                          size_t log_buf_sz);
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
                      size_t insns_cnt, const char *license,
                      __u32 kern_version, char *log_buf,
@@ -51,6 +66,7 @@ int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
                     unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
                       void *data_out, __u32 *size_out, __u32 *retval,
                       __u32 *duration);
@@ -59,5 +75,6 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 int bpf_prog_get_fd_by_id(__u32 id);
 int bpf_map_get_fd_by_id(__u32 id);
 int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+                   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1a2c07eb7795..5aa45f89da93 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -171,6 +171,7 @@ int libbpf_strerror(int err, char *buf, size_t size)
 struct bpf_program {
         /* Index in elf obj file, for relocation use. */
         int idx;
+        char *name;
         char *section_name;
         struct bpf_insn *insns;
         size_t insns_cnt;
@@ -283,6 +284,7 @@ static void bpf_program__exit(struct bpf_program *prog)
         prog->clear_priv = NULL;
 
         bpf_program__unload(prog);
+        zfree(&prog->name);
         zfree(&prog->section_name);
         zfree(&prog->insns);
         zfree(&prog->reloc_desc);
@@ -293,26 +295,27 @@ static void bpf_program__exit(struct bpf_program *prog)
 }
 
 static int
-bpf_program__init(void *data, size_t size, char *name, int idx,
-                    struct bpf_program *prog)
+bpf_program__init(void *data, size_t size, char *section_name, int idx,
+                  struct bpf_program *prog)
 {
         if (size < sizeof(struct bpf_insn)) {
-                pr_warning("corrupted section '%s'\n", name);
+                pr_warning("corrupted section '%s'\n", section_name);
                 return -EINVAL;
         }
 
         bzero(prog, sizeof(*prog));
 
-        prog->section_name = strdup(name);
+        prog->section_name = strdup(section_name);
         if (!prog->section_name) {
-                pr_warning("failed to alloc name for prog %s\n",
-                           name);
+                pr_warning("failed to alloc name for prog under section %s\n",
+                           section_name);
                 goto errout;
         }
 
         prog->insns = malloc(size);
         if (!prog->insns) {
-                pr_warning("failed to alloc insns for %s\n", name);
+                pr_warning("failed to alloc insns for prog under section %s\n",
+                           section_name);
                 goto errout;
         }
         prog->insns_cnt = size / sizeof(struct bpf_insn);
@@ -331,12 +334,12 @@ errout:
 
 static int
 bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
-                        char *name, int idx)
+                        char *section_name, int idx)
 {
         struct bpf_program prog, *progs;
         int nr_progs, err;
 
-        err = bpf_program__init(data, size, name, idx, &prog);
+        err = bpf_program__init(data, size, section_name, idx, &prog);
         if (err)
                 return err;
 
@@ -350,8 +353,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
                  * is still valid, so don't need special treat for
                  * bpf_close_object().
                  */
-                pr_warning("failed to alloc a new program '%s'\n",
-                           name);
+                pr_warning("failed to alloc a new program under section '%s'\n",
+                           section_name);
                 bpf_program__exit(&prog);
                 return -ENOMEM;
         }
@@ -364,6 +367,54 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
         return 0;
 }
 
+static int
+bpf_object__init_prog_names(struct bpf_object *obj)
+{
+        Elf_Data *symbols = obj->efile.symbols;
+        struct bpf_program *prog;
+        size_t pi, si;
+
+        for (pi = 0; pi < obj->nr_programs; pi++) {
+                char *name = NULL;
+
+                prog = &obj->programs[pi];
+
+                for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
+                     si++) {
+                        GElf_Sym sym;
+
+                        if (!gelf_getsym(symbols, si, &sym))
+                                continue;
+                        if (sym.st_shndx != prog->idx)
+                                continue;
+
+                        name = elf_strptr(obj->efile.elf,
+                                          obj->efile.strtabidx,
+                                          sym.st_name);
+                        if (!name) {
+                                pr_warning("failed to get sym name string for prog %s\n",
+                                           prog->section_name);
+                                return -LIBBPF_ERRNO__LIBELF;
+                        }
+                }
+
+                if (!name) {
+                        pr_warning("failed to find sym for prog %s\n",
+                                   prog->section_name);
+                        return -EINVAL;
+                }
+
+                prog->name = strdup(name);
+                if (!prog->name) {
+                        pr_warning("failed to allocate memory for prog sym %s\n",
+                                   name);
+                        return -ENOMEM;
+                }
+        }
+
+        return 0;
+}
+
 static struct bpf_object *bpf_object__new(const char *path,
                                           void *obj_buf,
                                           size_t obj_buf_sz)
@@ -528,31 +579,6 @@ bpf_object__init_kversion(struct bpf_object *obj,
         return 0;
 }
 
-static int
-bpf_object__validate_maps(struct bpf_object *obj)
-{
-        int i;
-
-        /*
-         * If there's only 1 map, the only error case should have been
-         * catched in bpf_object__init_maps().
-         */
-        if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1))
-                return 0;
-
-        for (i = 1; i < obj->nr_maps; i++) {
-                const struct bpf_map *a = &obj->maps[i - 1];
-                const struct bpf_map *b = &obj->maps[i];
-
-                if (b->offset - a->offset < sizeof(struct bpf_map_def)) {
-                        pr_warning("corrupted map section in %s: map \"%s\" too small\n",
-                                   obj->path, a->name);
-                        return -EINVAL;
-                }
-        }
-        return 0;
-}
-
 static int compare_bpf_map(const void *_a, const void *_b)
 {
         const struct bpf_map *a = _a;
@@ -564,7 +590,7 @@ static int compare_bpf_map(const void *_a, const void *_b)
 static int
 bpf_object__init_maps(struct bpf_object *obj)
 {
-        int i, map_idx, nr_maps = 0;
+        int i, map_idx, map_def_sz, nr_maps = 0;
         Elf_Scn *scn;
         Elf_Data *data;
         Elf_Data *symbols = obj->efile.symbols;
@@ -607,6 +633,15 @@ bpf_object__init_maps(struct bpf_object *obj)
         if (!nr_maps)
                 return 0;
 
+        /* Assume equally sized map definitions */
+        map_def_sz = data->d_size / nr_maps;
+        if (!data->d_size || (data->d_size % nr_maps) != 0) {
+                pr_warning("unable to determine map definition size "
+                           "section %s, %d maps in %zd bytes\n",
+                           obj->path, nr_maps, data->d_size);
+                return -EINVAL;
+        }
+
         obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
         if (!obj->maps) {
                 pr_warning("alloc maps for object failed\n");
@@ -639,7 +674,7 @@ bpf_object__init_maps(struct bpf_object *obj)
                                       obj->efile.strtabidx,
                                       sym.st_name);
                 obj->maps[map_idx].offset = sym.st_value;
-                if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) {
+                if (sym.st_value + map_def_sz > data->d_size) {
                         pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
                                    obj->path, map_name);
                         return -EINVAL;
@@ -653,12 +688,40 @@ bpf_object__init_maps(struct bpf_object *obj)
                 pr_debug("map %d is \"%s\"\n", map_idx,
                          obj->maps[map_idx].name);
                 def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
-                obj->maps[map_idx].def = *def;
+                /*
+                 * If the definition of the map in the object file fits in
+                 * bpf_map_def, copy it.  Any extra fields in our version
+                 * of bpf_map_def will default to zero as a result of the
+                 * calloc above.
+                 */
+                if (map_def_sz <= sizeof(struct bpf_map_def)) {
+                        memcpy(&obj->maps[map_idx].def, def, map_def_sz);
+                } else {
+                        /*
+                         * Here the map structure being read is bigger than what
+                         * we expect, truncate if the excess bits are all zero.
+                         * If they are not zero, reject this map as
+                         * incompatible.
+                         */
+                        char *b;
+                        for (b = ((char *)def) + sizeof(struct bpf_map_def);
+                             b < ((char *)def) + map_def_sz; b++) {
+                                if (*b != 0) {
+                                        pr_warning("maps section in %s: \"%s\" "
+                                                   "has unrecognized, non-zero "
+                                                   "options\n",
+                                                   obj->path, map_name);
+                                        return -EINVAL;
+                                }
+                        }
+                        memcpy(&obj->maps[map_idx].def, def,
+                               sizeof(struct bpf_map_def));
+                }
                 map_idx++;
         }
 
         qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
-        return bpf_object__validate_maps(obj);
+        return 0;
 }
 
 static int bpf_object__elf_collect(struct bpf_object *obj)
@@ -766,8 +829,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                 pr_warning("Corrupted ELF file: index of strtab invalid\n");
                 return LIBBPF_ERRNO__FORMAT;
         }
-        if (obj->efile.maps_shndx >= 0)
+        if (obj->efile.maps_shndx >= 0) {
                 err = bpf_object__init_maps(obj);
+                if (err)
+                        goto out;
+        }
+        err = bpf_object__init_prog_names(obj);
 out:
         return err;
 }
@@ -870,16 +937,18 @@ bpf_object__create_maps(struct bpf_object *obj)
                 struct bpf_map_def *def = &obj->maps[i].def;
                 int *pfd = &obj->maps[i].fd;
 
-                *pfd = bpf_create_map(def->type,
-                                      def->key_size,
-                                      def->value_size,
-                                      def->max_entries,
-                                      0);
+                *pfd = bpf_create_map_name(def->type,
+                                           obj->maps[i].name,
+                                           def->key_size,
+                                           def->value_size,
+                                           def->max_entries,
+                                           def->map_flags);
                 if (*pfd < 0) {
                         size_t j;
                         int err = *pfd;
 
-                        pr_warning("failed to create map: %s\n",
+                        pr_warning("failed to create map (name: '%s'): %s\n",
+                                   obj->maps[i].name,
                                    strerror(errno));
                         for (j = 0; j < i; j++)
                                 zclose(obj->maps[j].fd);
@@ -981,7 +1050,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(enum bpf_prog_type type, struct bpf_insn *insns,
+load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns,
              int insns_cnt, char *license, u32 kern_version, int *pfd)
 {
         int ret;
@@ -994,8 +1063,8 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns,
         if (!log_buf)
                 pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
 
-        ret = bpf_load_program(type, insns, insns_cnt, license,
-                               kern_version, log_buf, BPF_LOG_BUF_SIZE);
+        ret = bpf_load_program_name(type, name, insns, insns_cnt, license,
+                                    kern_version, log_buf, BPF_LOG_BUF_SIZE);
 
         if (ret >= 0) {
                 *pfd = ret;
@@ -1020,9 +1089,9 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns,
                 if (type != BPF_PROG_TYPE_KPROBE) {
                         int fd;
 
-                        fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
-                                              insns_cnt, license, kern_version,
-                                              NULL, 0);
+                        fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name,
+                                                   insns, insns_cnt, license,
+                                                   kern_version, NULL, 0);
                         if (fd >= 0) {
                                 close(fd);
                                 ret = -LIBBPF_ERRNO__PROGTYPE;
@@ -1066,8 +1135,8 @@ bpf_program__load(struct bpf_program *prog,
                         pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
                                    prog->section_name, prog->instances.nr);
                 }
-                err = load_program(prog->type, prog->insns, prog->insns_cnt,
-                                   license, kern_version, &fd);
+                err = load_program(prog->type, prog->name, prog->insns,
+                                   prog->insns_cnt, license, kern_version, &fd);
                 if (!err)
                         prog->instances.fds[0] = fd;
                 goto out;
@@ -1095,7 +1164,8 @@ bpf_program__load(struct bpf_program *prog,
                         continue;
                 }
 
-                err = load_program(prog->type, result.new_insn_ptr,
+                err = load_program(prog->type, prog->name,
+                                   result.new_insn_ptr,
                                    result.new_insn_cnt,
                                    license, kern_version, &fd);
 
@@ -1744,3 +1814,32 @@ long libbpf_get_error(const void *ptr)
                 return PTR_ERR(ptr);
         return 0;
 }
+
+int bpf_prog_load(const char *file, enum bpf_prog_type type,
+                  struct bpf_object **pobj, int *prog_fd)
+{
+        struct bpf_program *prog;
+        struct bpf_object *obj;
+        int err;
+
+        obj = bpf_object__open(file);
+        if (IS_ERR(obj))
+                return -ENOENT;
+
+        prog = bpf_program__next(NULL, obj);
+        if (!prog) {
+                bpf_object__close(obj);
+                return -ENOENT;
+        }
+
+        bpf_program__set_type(prog, type);
+        err = bpf_object__load(obj);
+        if (err) {
+                bpf_object__close(obj);
+                return -EINVAL;
+        }
+
+        *pobj = obj;
+        *prog_fd = bpf_program__fd(prog);
+        return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 32c7252f734e..6e20003109e0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -207,6 +207,7 @@ struct bpf_map_def {
         unsigned int key_size;
         unsigned int value_size;
         unsigned int max_entries;
+        unsigned int map_flags;
 };
 
 /*
@@ -243,4 +244,6 @@ int bpf_map__pin(struct bpf_map *map, const char *path);
 
 long libbpf_get_error(const void *ptr);
 
+int bpf_prog_load(const char *file, enum bpf_prog_type type,
+                  struct bpf_object **pobj, int *prog_fd);
 #endif
diff --git a/tools/lib/hweight.c b/tools/lib/hweight.c
index 0b859b884339..a16ebf515417 100644
--- a/tools/lib/hweight.c
+++ b/tools/lib/hweight.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/bitops.h>
 #include <asm/types.h>
 
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index ed9ace59d112..9b0ca3ad1ef3 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # file format version
 FILE_VERSION = 1
 
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
index d1c89cc06f5f..5c3b58cce8a9 100644
--- a/tools/lib/lockdep/common.c
+++ b/tools/lib/lockdep/common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stddef.h>
 #include <stdbool.h>
 #include <linux/compiler.h>
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index 6e66277ec437..8862da80995a 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_COMMON_H
 #define _LIBLOCKDEP_COMMON_H
 
diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
index ee53a42818ca..a80ac39f966e 100644
--- a/tools/lib/lockdep/include/liblockdep/mutex.h
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_MUTEX_H
 #define _LIBLOCKDEP_MUTEX_H
 
diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
index 4ec03f861551..a96c3bf0fef1 100644
--- a/tools/lib/lockdep/include/liblockdep/rwlock.h
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_RWLOCK_H
 #define _LIBLOCKDEP_RWLOCK_H
 
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
index ced6d7443cea..6002fcf2f9bc 100644
--- a/tools/lib/lockdep/lockdep.c
+++ b/tools/lib/lockdep/lockdep.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/lockdep.h>
 #include <stdlib.h>
 
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 6a2d3c5d4e92..76245d16196d 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <pthread.h>
 #include <stdio.h>
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
index f9b94098fc98..2e570a188f16 100755
--- a/tools/lib/lockdep/run_tests.sh
+++ b/tools/lib/lockdep/run_tests.sh
@@ -1,4 +1,5 @@
 #! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 make &> /dev/null
 
diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c
index 18211a5f354f..63c7ce97bda3 100644
--- a/tools/lib/lockdep/tests/AA.c
+++ b/tools/lib/lockdep/tests/AA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 
 int main(void)
diff --git a/tools/lib/lockdep/tests/ABA.c b/tools/lib/lockdep/tests/ABA.c
index 0f782ff404ac..efa39b23f05d 100644
--- a/tools/lib/lockdep/tests/ABA.c
+++ b/tools/lib/lockdep/tests/ABA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 
 void main(void)
diff --git a/tools/lib/lockdep/tests/ABBA.c b/tools/lib/lockdep/tests/ABBA.c
index 07f0e29d5485..1460afd33d71 100644
--- a/tools/lib/lockdep/tests/ABBA.c
+++ b/tools/lib/lockdep/tests/ABBA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 #include "common.h"
 
diff --git a/tools/lib/lockdep/tests/ABBA_2threads.c b/tools/lib/lockdep/tests/ABBA_2threads.c
index cd807d736361..39325ef8a2ac 100644
--- a/tools/lib/lockdep/tests/ABBA_2threads.c
+++ b/tools/lib/lockdep/tests/ABBA_2threads.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <pthread.h>
 
diff --git a/tools/lib/lockdep/tests/ABBCCA.c b/tools/lib/lockdep/tests/ABBCCA.c
index 843db09ac666..a54c1b2af118 100644
--- a/tools/lib/lockdep/tests/ABBCCA.c
+++ b/tools/lib/lockdep/tests/ABBCCA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 #include "common.h"
 
diff --git a/tools/lib/lockdep/tests/ABBCCDDA.c b/tools/lib/lockdep/tests/ABBCCDDA.c
index 33620e268f85..aa5d194e8869 100644
--- a/tools/lib/lockdep/tests/ABBCCDDA.c
+++ b/tools/lib/lockdep/tests/ABBCCDDA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 #include "common.h"
 
diff --git a/tools/lib/lockdep/tests/ABCABC.c b/tools/lib/lockdep/tests/ABCABC.c
index 3fee51e3a68a..b54a08e60416 100644
--- a/tools/lib/lockdep/tests/ABCABC.c
+++ b/tools/lib/lockdep/tests/ABCABC.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 #include "common.h"
 
diff --git a/tools/lib/lockdep/tests/ABCDBCDA.c b/tools/lib/lockdep/tests/ABCDBCDA.c
index 427ba562c75b..a56742250d86 100644
--- a/tools/lib/lockdep/tests/ABCDBCDA.c
+++ b/tools/lib/lockdep/tests/ABCDBCDA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 #include "common.h"
 
diff --git a/tools/lib/lockdep/tests/ABCDBDDA.c b/tools/lib/lockdep/tests/ABCDBDDA.c
index 680c6cf3e919..238a3353f3c3 100644
--- a/tools/lib/lockdep/tests/ABCDBDDA.c
+++ b/tools/lib/lockdep/tests/ABCDBDDA.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 #include "common.h"
 
diff --git a/tools/lib/lockdep/tests/WW.c b/tools/lib/lockdep/tests/WW.c
index d44f77d71029..eee88df7fc41 100644
--- a/tools/lib/lockdep/tests/WW.c
+++ b/tools/lib/lockdep/tests/WW.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/rwlock.h>
 
 void main(void)
diff --git a/tools/lib/lockdep/tests/common.h b/tools/lib/lockdep/tests/common.h
index d89e94d47d86..3026c29ccb5c 100644
--- a/tools/lib/lockdep/tests/common.h
+++ b/tools/lib/lockdep/tests/common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIBLOCKDEP_TEST_COMMON_H
 #define _LIBLOCKDEP_TEST_COMMON_H
 
diff --git a/tools/lib/lockdep/tests/unlock_balance.c b/tools/lib/lockdep/tests/unlock_balance.c
index 0bc62de686f7..34cf32f689de 100644
--- a/tools/lib/lockdep/tests/unlock_balance.c
+++ b/tools/lib/lockdep/tests/unlock_balance.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <liblockdep/mutex.h>
 
 void main(void)
diff --git a/tools/lib/str_error_r.c b/tools/lib/str_error_r.c
index 503ae072244c..d6d65537b0d9 100644
--- a/tools/lib/str_error_r.c
+++ b/tools/lib/str_error_r.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #undef _GNU_SOURCE
 #include <string.h>
 #include <stdio.h>
diff --git a/tools/lib/string.c b/tools/lib/string.c
index 8e678af1c6ee..93b3d4b6feac 100644
--- a/tools/lib/string.c
+++ b/tools/lib/string.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/tools/lib/string.c
  *
@@ -39,27 +40,45 @@ void *memdup(const void *src, size_t len)
  * @s: input string
  * @res: result
  *
- * This routine returns 0 iff the first character is one of 'Yy1Nn0'.
- * Otherwise it will return -EINVAL.  Value pointed to by res is
- * updated upon finding a match.
+ * This routine returns 0 iff the first character is one of 'Yy1Nn0', or
+ * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL.  Value
+ * pointed to by res is updated upon finding a match.
  */
 int strtobool(const char *s, bool *res)
 {
+        if (!s)
+                return -EINVAL;
+
         switch (s[0]) {
         case 'y':
         case 'Y':
         case '1':
                 *res = true;
-                break;
+                return 0;
         case 'n':
         case 'N':
         case '0':
                 *res = false;
-                break;
+                return 0;
+        case 'o':
+        case 'O':
+                switch (s[1]) {
+                case 'n':
+                case 'N':
+                        *res = true;
+                        return 0;
+                case 'f':
+                case 'F':
+                        *res = false;
+                        return 0;
+                default:
+                        break;
+                }
         default:
-                return -EINVAL;
+                break;
         }
-        return 0;
+
+        return -EINVAL;
 }
 
 /**
@@ -87,12 +106,3 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size)
         }
         return ret;
 }
-
-int prefixcmp(const char *str, const char *prefix)
-{
-        for (; ; str++, prefix++)
-                if (!*prefix)
-                        return 0;
-                else if (*str != *prefix)
-                        return (unsigned char)*prefix - (unsigned char)*str;
-}
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index 3d1c3b5b5150..95563b8e1ad7 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 include ../../scripts/Makefile.include
 include ../../scripts/utilities.mak             # QUIET_CLEAN
 
@@ -21,7 +22,7 @@ LIBFILE = $(OUTPUT)libsubcmd.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 
-ifeq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c
index 1ae833af1a4a..33e94fb83986 100644
--- a/tools/lib/subcmd/exec-cmd.c
+++ b/tools/lib/subcmd/exec-cmd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/string.h>
 #include <sys/types.h>
diff --git a/tools/lib/subcmd/exec-cmd.h b/tools/lib/subcmd/exec-cmd.h
index 5d08bda31d90..aba591b8d254 100644
--- a/tools/lib/subcmd/exec-cmd.h
+++ b/tools/lib/subcmd/exec-cmd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_EXEC_CMD_H
 #define __SUBCMD_EXEC_CMD_H
 
diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c
index ba970a73d053..2859f107abc8 100644
--- a/tools/lib/subcmd/help.c
+++ b/tools/lib/subcmd/help.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -171,7 +172,7 @@ static void list_commands_in_dir(struct cmdnames *cmds,
         while ((de = readdir(dir)) != NULL) {
                 int entlen;
 
-                if (prefixcmp(de->d_name, prefix))
+                if (!strstarts(de->d_name, prefix))
                         continue;
 
                 astrcat(&buf, de->d_name);
diff --git a/tools/lib/subcmd/help.h b/tools/lib/subcmd/help.h
index 9bd4223dc722..355c066c8d49 100644
--- a/tools/lib/subcmd/help.h
+++ b/tools/lib/subcmd/help.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_HELP_H
 #define __SUBCMD_HELP_H
 
diff --git a/tools/lib/subcmd/pager.c b/tools/lib/subcmd/pager.c
index 6518bea926d6..5ba754d17952 100644
--- a/tools/lib/subcmd/pager.c
+++ b/tools/lib/subcmd/pager.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/select.h>
 #include <stdlib.h>
 #include <stdio.h>
diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h
index 623f5542d05d..f1a53cf29880 100644
--- a/tools/lib/subcmd/pager.h
+++ b/tools/lib/subcmd/pager.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_PAGER_H
 #define __SUBCMD_PAGER_H
 
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 359bfa77f39c..f6a1babcbac4 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -368,7 +369,7 @@ retry:
                         return 0;
                 }
                 if (!rest) {
-                        if (!prefixcmp(options->long_name, "no-")) {
+                        if (strstarts(options->long_name, "no-")) {
                                 /*
                                  * The long name itself starts with "no-", so
                                  * accept the option without "no-" so that users
@@ -381,7 +382,7 @@ retry:
                                         goto match;
                                 }
                                 /* Abbreviated case */
-                                if (!prefixcmp(options->long_name + 3, arg)) {
+                                if (strstarts(options->long_name + 3, arg)) {
                                         flags |= OPT_UNSET;
                                         goto is_abbreviated;
                                 }
@@ -406,7 +407,7 @@ is_abbreviated:
                                 continue;
                         }
                         /* negated and abbreviated very much? */
-                        if (!prefixcmp("no-", arg)) {
+                        if (strstarts("no-", arg)) {
                                 flags |= OPT_UNSET;
                                 goto is_abbreviated;
                         }
@@ -416,7 +417,7 @@ is_abbreviated:
                         flags |= OPT_UNSET;
                         rest = skip_prefix(arg + 3, options->long_name);
                         /* abbreviated and negated? */
-                        if (!rest && !prefixcmp(options->long_name, arg + 3))
+                        if (!rest && strstarts(options->long_name, arg + 3))
                                 goto is_abbreviated;
                         if (!rest)
                                 continue;
@@ -456,7 +457,7 @@ static void check_typos(const char *arg, const struct option *options)
         if (strlen(arg) < 3)
                 return;
 
-        if (!prefixcmp(arg, "no-")) {
+        if (strstarts(arg, "no-")) {
                 fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
                 exit(129);
         }
@@ -464,7 +465,7 @@ static void check_typos(const char *arg, const struct option *options)
         for (; options->type != OPTION_END; options++) {
                 if (!options->long_name)
                         continue;
-                if (!prefixcmp(options->long_name, arg)) {
+                if (strstarts(options->long_name, arg)) {
                         fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
                         exit(129);
                 }
@@ -933,10 +934,10 @@ opt:
                 if (opts->long_name == NULL)
                         continue;
 
-                if (!prefixcmp(opts->long_name, optstr))
+                if (strstarts(opts->long_name, optstr))
                         print_option_help(opts, 0);
-                if (!prefixcmp("no-", optstr) &&
-                    !prefixcmp(opts->long_name, optstr + 3))
+                if (strstarts("no-", optstr) &&
+                    strstarts(opts->long_name, optstr + 3))
                         print_option_help(opts, 0);
         }
 
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index f054ca1b899d..92fdbe1519f6 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_PARSE_OPTIONS_H
 #define __SUBCMD_PARSE_OPTIONS_H
 
diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index 911f83942723..5cdac2162532 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/stat.h>
diff --git a/tools/lib/subcmd/run-command.h b/tools/lib/subcmd/run-command.h
index fe2befea1e73..17d969c6add3 100644
--- a/tools/lib/subcmd/run-command.h
+++ b/tools/lib/subcmd/run-command.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_RUN_COMMAND_H
 #define __SUBCMD_RUN_COMMAND_H
 
diff --git a/tools/lib/subcmd/sigchain.c b/tools/lib/subcmd/sigchain.c
index 3537c348a18e..f0fe3dbef7f7 100644
--- a/tools/lib/subcmd/sigchain.c
+++ b/tools/lib/subcmd/sigchain.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <signal.h>
 #include "subcmd-util.h"
 #include "sigchain.h"
diff --git a/tools/lib/subcmd/sigchain.h b/tools/lib/subcmd/sigchain.h
index 0c919f2874ca..1ec663af43ea 100644
--- a/tools/lib/subcmd/sigchain.h
+++ b/tools/lib/subcmd/sigchain.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_SIGCHAIN_H
 #define __SUBCMD_SIGCHAIN_H
 
diff --git a/tools/lib/subcmd/subcmd-config.c b/tools/lib/subcmd/subcmd-config.c
index d017c728bd1b..84a7cf6c7878 100644
--- a/tools/lib/subcmd/subcmd-config.c
+++ b/tools/lib/subcmd/subcmd-config.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "subcmd-config.h"
 
 #define UNDEFINED "SUBCMD_HAS_NOT_BEEN_INITIALIZED"
diff --git a/tools/lib/subcmd/subcmd-config.h b/tools/lib/subcmd/subcmd-config.h
index cc8514030b5c..9024dc17d100 100644
--- a/tools/lib/subcmd/subcmd-config.h
+++ b/tools/lib/subcmd/subcmd-config.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SUBCMD_CONFIG_H
 #define __PERF_SUBCMD_CONFIG_H
 
diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h
index 8fa5f036eff0..794a375dad36 100644
--- a/tools/lib/subcmd/subcmd-util.h
+++ b/tools/lib/subcmd/subcmd-util.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __SUBCMD_UTIL_H
 #define __SUBCMD_UTIL_H
 
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index d270ac00613d..914cb8e3d40b 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <ctype.h>
 #include "symbol/kallsyms.h"
 #include <stdio.h>
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index 4071316a766e..bc40101d72c1 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TOOLS_KALLSYMS_H_
 #define __TOOLS_KALLSYMS_H_ 1
 
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 9b8555ea3459..46cd5f871ad7 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # trace-cmd version
 EP_VERSION = 1
 EP_PATCHLEVEL = 1
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 7c214ceb9386..315df0a70265 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -436,13 +436,13 @@ create_arg_exp(enum filter_exp_type etype)
                 return NULL;
 
         arg->type = FILTER_ARG_EXP;
-        arg->op.type = etype;
+        arg->exp.type = etype;
 
         return arg;
 }
 
 static struct filter_arg *
-create_arg_cmp(enum filter_exp_type etype)
+create_arg_cmp(enum filter_cmp_type ctype)
 {
         struct filter_arg *arg;
 
@@ -452,7 +452,7 @@ create_arg_cmp(enum filter_exp_type etype)
 
         /* Use NUM and change if necessary */
         arg->type = FILTER_ARG_NUM;
-        arg->op.type = etype;
+        arg->num.type = ctype;
 
         return arg;
 }
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index ec57d0c1fbc2..8f8586912da7 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <string.h>
 #include <inttypes.h>
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 3727de48c8d5..5e750af2b461 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <string.h>
 #include <inttypes.h>
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index 3a413eaada68..690173bfa13e 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/lib/vsprintf.c b/tools/lib/vsprintf.c
index 45f9a06daa56..e08ee147eab4 100644
--- a/tools/lib/vsprintf.c
+++ b/tools/lib/vsprintf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <linux/kernel.h>
 #include <stdio.h>
diff --git a/tools/nfsd/inject_fault.sh b/tools/nfsd/inject_fault.sh
index 06a399ac8b2f..10ceee64a09a 100755
--- a/tools/nfsd/inject_fault.sh
+++ b/tools/nfsd/inject_fault.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com>
 #
diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore
index d3102c865a95..914cff12899b 100644
--- a/tools/objtool/.gitignore
+++ b/tools/objtool/.gitignore
@@ -1,3 +1,3 @@
-arch/x86/insn/inat-tables.c
+arch/x86/lib/inat-tables.c
 objtool
 fixdep
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 6f2e1987c4d9..749becdf5b90 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -1,6 +1,9 @@
 objtool-y += arch/$(SRCARCH)/
 objtool-y += builtin-check.o
+objtool-y += builtin-orc.o
 objtool-y += check.o
+objtool-y += orc_gen.o
+objtool-y += orc_dump.o
 objtool-y += elf.o
 objtool-y += special.o
 objtool-y += objtool.o
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index 17c1195f11f4..3995735a878f 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -11,9 +11,6 @@ analyzes every .o file and ensures the validity of its stack metadata.
 It enforces a set of rules on asm code and C inline assembly code so
 that stack traces can be reliable.
 
-Currently it only checks frame pointer usage, but there are plans to add
-CFI validation for C files and CFI generation for asm files.
-
 For each function, it recursively follows all possible code paths and
 validates the correct frame pointer state at each instruction.
 
@@ -23,6 +20,10 @@ alternative execution paths to a given instruction (or set of
 instructions).  Similarly, it knows how to follow switch statements, for
 which gcc sometimes uses jump tables.
 
+(Objtool also has an 'orc generate' subcommand which generates debuginfo
+for the ORC unwinder.  See Documentation/x86/orc-unwinder.txt in the
+kernel tree for more details.)
+
 
 Why do we need stack metadata validation?
 -----------------------------------------
@@ -93,37 +94,14 @@ a) More reliable stack traces for frame pointer enabled kernels
        or at the very end of the function after the stack frame has been
        destroyed.  This is an inherent limitation of frame pointers.
 
-b) 100% reliable stack traces for DWARF enabled kernels
-
-   (NOTE: This is not yet implemented)
-
-   As an alternative to frame pointers, DWARF Call Frame Information
-   (CFI) metadata can be used to walk the stack.  Unlike frame pointers,
-   CFI metadata is out of band.  So it doesn't affect runtime
-   performance and it can be reliable even when interrupts or exceptions
-   are involved.
-
-   For C code, gcc automatically generates DWARF CFI metadata.  But for
-   asm code, generating CFI is a tedious manual approach which requires
-   manually placed .cfi assembler macros to be scattered throughout the
-   code.  It's clumsy and very easy to get wrong, and it makes the real
-   code harder to read.
-
-   Stacktool will improve this situation in several ways.  For code
-   which already has CFI annotations, it will validate them.  For code
-   which doesn't have CFI annotations, it will generate them.  So an
-   architecture can opt to strip out all the manual .cfi annotations
-   from their asm code and have objtool generate them instead.
+b) ORC (Oops Rewind Capability) unwind table generation
 
-   We might also add a runtime stack validation debug option where we
-   periodically walk the stack from schedule() and/or an NMI to ensure
-   that the stack metadata is sane and that we reach the bottom of the
-   stack.
+   An alternative to frame pointers and DWARF, ORC unwind data can be
+   used to walk the stack.  Unlike frame pointers, ORC data is out of
+   band.  So it doesn't affect runtime performance and it can be
+   reliable even when interrupts or exceptions are involved.
 
-   So the benefit of objtool here will be that external tooling should
-   always show perfect stack traces.  And the same will be true for
-   kernel warning/oops traces if the architecture has a runtime DWARF
-   unwinder.
+   For more details, see Documentation/x86/orc-unwinder.txt.
 
 c) Higher live patching compatibility rate
 
@@ -211,15 +189,15 @@ they mean, and suggestions for how to fix them.
    function, add proper frame pointer logic using the FRAME_BEGIN and
    FRAME_END macros.  Otherwise, if it's not a callable function, remove
    its ELF function annotation by changing ENDPROC to END, and instead
-   use the manual CFI hint macros in asm/undwarf.h.
+   use the manual unwind hint macros in asm/unwind_hints.h.
 
    If it's a GCC-compiled .c file, the error may be because the function
    uses an inline asm() statement which has a "call" instruction.  An
    asm() statement with a call instruction must declare the use of the
-   stack pointer in its output operand.  For example, on x86_64:
+   stack pointer in its output operand.  On x86_64, this means adding
+   the ASM_CALL_CONSTRAINT as an output constraint:
 
-     register void *__sp asm("rsp");
-     asm volatile("call func" : "+r" (__sp));
+     asm volatile("call func" : ASM_CALL_CONSTRAINT);
 
    Otherwise the stack frame may not get created before the call.
 
@@ -231,8 +209,8 @@ they mean, and suggestions for how to fix them.
    If the error is for an asm file, and the instruction is inside (or
    reachable from) a callable function, the function should be annotated
    with the ENTRY/ENDPROC macros (ENDPROC is the important one).
-   Otherwise, the code should probably be annotated with the CFI hint
-   macros in asm/undwarf.h so objtool and the unwinder can know the
+   Otherwise, the code should probably be annotated with the unwind hint
+   macros in asm/unwind_hints.h so objtool and the unwinder can know the
    stack state associated with the code.
 
    If you're 100% sure the code won't affect stack traces, or if you're
@@ -258,7 +236,7 @@ they mean, and suggestions for how to fix them.
    instructions aren't allowed in a callable function, and are most
    likely part of the kernel entry code.  They should usually not have
    the callable function annotation (ENDPROC) and should always be
-   annotated with the CFI hint macros in asm/undwarf.h.
+   annotated with the unwind hint macros in asm/unwind_hints.h.
 
 
 6. file.o: warning: objtool: func()+0x26: sibling call from callable instruction with modified stack frame
@@ -272,7 +250,7 @@ they mean, and suggestions for how to fix them.
 
    If the instruction is not actually in a callable function (e.g.
    kernel entry code), change ENDPROC to END and annotate manually with
-   the CFI hint macros in asm/undwarf.h.
+   the unwind hint macros in asm/unwind_hints.h.
 
 
 7. file: warning: objtool: func()+0x5c: stack state mismatch
@@ -288,8 +266,8 @@ they mean, and suggestions for how to fix them.
 
    Another possibility is that the code has some asm or inline asm which
    does some unusual things to the stack or the frame pointer.  In such
-   cases it's probably appropriate to use the CFI hint macros in
-   asm/undwarf.h.
+   cases it's probably appropriate to use the unwind hint macros in
+   asm/unwind_hints.h.
 
 
 8. file.o: warning: objtool: funcA() falls through to next function funcB()
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 0e2765e243c0..0f94af3ccaaa 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 include ../scripts/Makefile.include
 include ../scripts/Makefile.arch
 
@@ -24,8 +25,11 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi
-CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -fomit-frame-pointer -O2 -g $(INCLUDES)
+INCLUDES := -I$(srctree)/tools/include \
+            -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
+            -I$(srctree)/tools/objtool/arch/$(ARCH)/include
+WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
+CFLAGS   += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD)
 
 # Allow old libelf to be used:
@@ -39,19 +43,8 @@ include $(srctree)/tools/build/Makefile.include
 $(OBJTOOL_IN): fixdep FORCE
         @$(MAKE) $(build)=objtool
 
-# Busybox's diff doesn't have -I, avoid warning in that case
-#
 $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
-        @(diff -I 2>&1 | grep -q 'option requires an argument' && \
-        test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
-        diff -I'^#include' arch/x86/insn/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
-        diff -I'^#include' arch/x86/insn/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
-        diff arch/x86/insn/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
-        diff arch/x86/insn/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
-        diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
-        diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
-        diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
-        || echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
+        @./sync-check.sh
         $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
 
@@ -61,7 +54,7 @@ $(LIBSUBCMD): fixdep FORCE
 clean:
         $(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
         $(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-        $(Q)$(RM) $(OUTPUT)arch/x86/insn/inat-tables.c $(OUTPUT)fixdep
+        $(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep
 
 FORCE:
 
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index 21aeca874edb..b0d7dc3d71b5 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -31,8 +31,9 @@
 #define INSN_RETURN             6
 #define INSN_CONTEXT_SWITCH     7
 #define INSN_STACK              8
-#define INSN_NOP                9
-#define INSN_OTHER              10
+#define INSN_BUG                9
+#define INSN_NOP                10
+#define INSN_OTHER              11
 #define INSN_LAST               INSN_OTHER
 
 enum op_dest_type {
diff --git a/tools/objtool/arch/x86/Build b/tools/objtool/arch/x86/Build
index debbdb0b5c43..b998412c017d 100644
--- a/tools/objtool/arch/x86/Build
+++ b/tools/objtool/arch/x86/Build
@@ -1,12 +1,12 @@
 objtool-y += decode.o
 
-inat_tables_script = arch/x86/insn/gen-insn-attr-x86.awk
-inat_tables_maps = arch/x86/insn/x86-opcode-map.txt
+inat_tables_script = arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = arch/x86/lib/x86-opcode-map.txt
 
-$(OUTPUT)arch/x86/insn/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+$(OUTPUT)arch/x86/lib/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
         $(call rule_mkdir)
         $(Q)$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@
 
-$(OUTPUT)arch/x86/decode.o: $(OUTPUT)arch/x86/insn/inat-tables.c
+$(OUTPUT)arch/x86/decode.o: $(OUTPUT)arch/x86/lib/inat-tables.c
 
-CFLAGS_decode.o += -I$(OUTPUT)arch/x86/insn
+CFLAGS_decode.o += -I$(OUTPUT)arch/x86/lib
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index a36c2eba64e7..8acfc47af70e 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -19,9 +19,9 @@
 #include <stdlib.h>
 
 #define unlikely(cond) (cond)
-#include "insn/insn.h"
-#include "insn/inat.c"
-#include "insn/insn.c"
+#include <asm/insn.h>
+#include "lib/inat.c"
+#include "lib/insn.c"
 
 #include "../../elf.h"
 #include "../../arch.h"
@@ -86,8 +86,8 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
         struct insn insn;
         int x86_64, sign;
         unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0,
-                      modrm = 0, modrm_mod = 0, modrm_rm = 0, modrm_reg = 0,
-                      sib = 0;
+                      rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0,
+                      modrm_reg = 0, sib = 0;
 
         x86_64 = is_x86_64(elf);
         if (x86_64 == -1)
@@ -114,6 +114,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                 rex = insn.rex_prefix.bytes[0];
                 rex_w = X86_REX_W(rex) >> 3;
                 rex_r = X86_REX_R(rex) >> 2;
+                rex_x = X86_REX_X(rex) >> 1;
                 rex_b = X86_REX_B(rex);
         }
 
@@ -207,16 +208,28 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                 break;
 
         case 0x89:
-                if (rex == 0x48 && modrm == 0xe5) {
+                if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) {
 
-                        /* mov %rsp, %rbp */
+                        /* mov %rsp, reg */
                         *type = INSN_STACK;
                         op->src.type = OP_SRC_REG;
                         op->src.reg = CFI_SP;
                         op->dest.type = OP_DEST_REG;
-                        op->dest.reg = CFI_BP;
+                        op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
+                        break;
+                }
+
+                if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) {
+
+                        /* mov reg, %rsp */
+                        *type = INSN_STACK;
+                        op->src.type = OP_SRC_REG;
+                        op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
+                        op->dest.type = OP_DEST_REG;
+                        op->dest.reg = CFI_SP;
                         break;
                 }
+
                 /* fallthrough */
         case 0x88:
                 if (!rex_b &&
@@ -269,56 +282,33 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                 break;
 
         case 0x8d:
-                if (rex == 0x48 && modrm == 0x65) {
+                if (sib == 0x24 && rex_w && !rex_b && !rex_x) {
 
-                        /* lea -disp(%rbp), %rsp */
                         *type = INSN_STACK;
-                        op->src.type = OP_SRC_ADD;
-                        op->src.reg = CFI_BP;
-                        op->src.offset = insn.displacement.value;
-                        op->dest.type = OP_DEST_REG;
-                        op->dest.reg = CFI_SP;
-                        break;
-                }
-
-                if (rex == 0x4c && modrm == 0x54 && sib == 0x24 &&
-                    insn.displacement.value == 8) {
-
-                        /*
-                         * lea 0x8(%rsp), %r10
-                         *
-                         * Here r10 is the "drap" pointer, used as a stack
-                         * pointer helper when the stack gets realigned.
-                         */
-                        *type = INSN_STACK;
-                        op->src.type = OP_SRC_ADD;
+                        if (!insn.displacement.value) {
+                                /* lea (%rsp), reg */
+                                op->src.type = OP_SRC_REG;
+                        } else {
+                                /* lea disp(%rsp), reg */
+                                op->src.type = OP_SRC_ADD;
+                                op->src.offset = insn.displacement.value;
+                        }
                         op->src.reg = CFI_SP;
-                        op->src.offset = 8;
                         op->dest.type = OP_DEST_REG;
-                        op->dest.reg = CFI_R10;
-                        break;
-                }
+                        op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
 
-                if (rex == 0x4c && modrm == 0x6c && sib == 0x24 &&
-                    insn.displacement.value == 16) {
+                } else if (rex == 0x48 && modrm == 0x65) {
 
-                        /*
-                         * lea 0x10(%rsp), %r13
-                         *
-                         * Here r13 is the "drap" pointer, used as a stack
-                         * pointer helper when the stack gets realigned.
-                         */
+                        /* lea disp(%rbp), %rsp */
                         *type = INSN_STACK;
                         op->src.type = OP_SRC_ADD;
-                        op->src.reg = CFI_SP;
-                        op->src.offset = 16;
+                        op->src.reg = CFI_BP;
+                        op->src.offset = insn.displacement.value;
                         op->dest.type = OP_DEST_REG;
-                        op->dest.reg = CFI_R13;
-                        break;
-                }
+                        op->dest.reg = CFI_SP;
 
-                if (rex == 0x49 && modrm == 0x62 &&
-                    insn.displacement.value == -8) {
+                } else if (rex == 0x49 && modrm == 0x62 &&
+                           insn.displacement.value == -8) {
 
                         /*
                          * lea -0x8(%r10), %rsp
@@ -332,11 +322,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                         op->src.offset = -8;
                         op->dest.type = OP_DEST_REG;
                         op->dest.reg = CFI_SP;
-                        break;
-                }
 
-                if (rex == 0x49 && modrm == 0x65 &&
-                    insn.displacement.value == -16) {
+                } else if (rex == 0x49 && modrm == 0x65 &&
+                           insn.displacement.value == -16) {
 
                         /*
                          * lea -0x10(%r13), %rsp
@@ -350,7 +338,6 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                         op->src.offset = -16;
                         op->dest.type = OP_DEST_REG;
                         op->dest.reg = CFI_SP;
-                        break;
                 }
 
                 break;
@@ -382,20 +369,27 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 
         case 0x0f:
 
-                if (op2 >= 0x80 && op2 <= 0x8f)
+                if (op2 >= 0x80 && op2 <= 0x8f) {
+
                         *type = INSN_JUMP_CONDITIONAL;
-                else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 ||
-                         op2 == 0x35)
+
+                } else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 ||
+                           op2 == 0x35) {
 
                         /* sysenter, sysret */
                         *type = INSN_CONTEXT_SWITCH;
 
-                else if (op2 == 0x0d || op2 == 0x1f)
+                } else if (op2 == 0x0b || op2 == 0xb9) {
+
+                        /* ud2 */
+                        *type = INSN_BUG;
+
+                } else if (op2 == 0x0d || op2 == 0x1f) {
 
                         /* nopl/nopw */
                         *type = INSN_NOP;
 
-                else if (op2 == 0xa0 || op2 == 0xa8) {
+                } else if (op2 == 0xa0 || op2 == 0xa8) {
 
                         /* push fs/gs */
                         *type = INSN_STACK;
diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/include/asm/inat.h
index 125ecd2a300d..1c78580e58be 100644
--- a/tools/objtool/arch/x86/insn/inat.h
+++ b/tools/objtool/arch/x86/include/asm/inat.h
@@ -20,7 +20,7 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  */
-#include "inat_types.h"
+#include <asm/inat_types.h>
 
 /*
  * Internal bits. Don't use bitmasks directly, because these bits are
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)    ((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)      (imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE     0
+#define INAT_SEG_REG_DEFAULT    1
+#define INAT_SEG_REG_CS         2
+#define INAT_SEG_REG_SS         3
+#define INAT_SEG_REG_DS         4
+#define INAT_SEG_REG_ES         5
+#define INAT_SEG_REG_FS         6
+#define INAT_SEG_REG_GS         7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
diff --git a/tools/objtool/arch/x86/insn/inat_types.h b/tools/objtool/arch/x86/include/asm/inat_types.h
index cb3c20ce39cf..cb3c20ce39cf 100644
--- a/tools/objtool/arch/x86/insn/inat_types.h
+++ b/tools/objtool/arch/x86/include/asm/inat_types.h
diff --git a/tools/objtool/arch/x86/insn/insn.h b/tools/objtool/arch/x86/include/asm/insn.h
index e23578c7b1be..b3e32b010ab1 100644
--- a/tools/objtool/arch/x86/insn/insn.h
+++ b/tools/objtool/arch/x86/include/asm/insn.h
@@ -21,7 +21,7 @@
  */
 
 /* insn_attr_t is defined in inat.h */
-#include "inat.h"
+#include <asm/inat.h>
 
 struct insn_field {
         union {
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
new file mode 100644
index 000000000000..9c9dc579bd7d
--- /dev/null
+++ b/tools/objtool/arch/x86/include/asm/orc_types.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ORC_TYPES_H
+#define _ORC_TYPES_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+/*
+ * The ORC_REG_* registers are base registers which are used to find other
+ * registers on the stack.
+ *
+ * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the
+ * address of the previous frame: the caller's SP before it called the current
+ * function.
+ *
+ * ORC_REG_UNDEFINED means the corresponding register's value didn't change in
+ * the current frame.
+ *
+ * The most commonly used base registers are SP and BP -- which the previous SP
+ * is usually based on -- and PREV_SP and UNDEFINED -- which the previous BP is
+ * usually based on.
+ *
+ * The rest of the base registers are needed for special cases like entry code
+ * and GCC realigned stacks.
+ */
+#define ORC_REG_UNDEFINED               0
+#define ORC_REG_PREV_SP                 1
+#define ORC_REG_DX                      2
+#define ORC_REG_DI                      3
+#define ORC_REG_BP                      4
+#define ORC_REG_SP                      5
+#define ORC_REG_R10                     6
+#define ORC_REG_R13                     7
+#define ORC_REG_BP_INDIRECT             8
+#define ORC_REG_SP_INDIRECT             9
+#define ORC_REG_MAX                     15
+
+/*
+ * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
+ * caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
+ * to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
+ * points to the iret return frame.
+ *
+ * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
+ * aren't used in struct orc_entry due to size and complexity constraints.
+ * Objtool converts them to real types when it converts the hints to orc
+ * entries.
+ */
+#define ORC_TYPE_CALL                   0
+#define ORC_TYPE_REGS                   1
+#define ORC_TYPE_REGS_IRET              2
+#define UNWIND_HINT_TYPE_SAVE           3
+#define UNWIND_HINT_TYPE_RESTORE        4
+
+#ifndef __ASSEMBLY__
+/*
+ * This struct is more or less a vastly simplified version of the DWARF Call
+ * Frame Information standard.  It contains only the necessary parts of DWARF
+ * CFI, simplified for ease of access by the in-kernel unwinder.  It tells the
+ * unwinder how to find the previous SP and BP (and sometimes entry regs) on
+ * the stack for a given code address.  Each instance of the struct corresponds
+ * to one or more code locations.
+ */
+struct orc_entry {
+        s16             sp_offset;
+        s16             bp_offset;
+        unsigned        sp_reg:4;
+        unsigned        bp_reg:4;
+        unsigned        type:2;
+} __packed;
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack for the ORC unwinder.
+ *
+ * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
+ */
+struct unwind_hint {
+        u32             ip;
+        s16             sp_offset;
+        u8              sp_reg;
+        u8              type;
+};
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ORC_TYPES_H */
diff --git a/tools/objtool/arch/x86/insn/inat.c b/tools/objtool/arch/x86/lib/inat.c
index e4bf28e6f4c7..c1f01a8e9f65 100644
--- a/tools/objtool/arch/x86/insn/inat.c
+++ b/tools/objtool/arch/x86/lib/inat.c
@@ -18,7 +18,7 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  */
-#include "insn.h"
+#include <asm/insn.h>
 
 /* Attribute tables are generated from opcode map */
 #include "inat-tables.c"
diff --git a/tools/objtool/arch/x86/insn/insn.c b/tools/objtool/arch/x86/lib/insn.c
index ca983e2bea8b..1088eb8f3a5f 100644
--- a/tools/objtool/arch/x86/insn/insn.c
+++ b/tools/objtool/arch/x86/lib/insn.c
@@ -23,8 +23,8 @@
 #else
 #include <string.h>
 #endif
-#include "inat.h"
-#include "insn.h"
+#include <asm/inat.h>
+#include <asm/insn.h>
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)       \
diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
index 12e377184ee4..12e377184ee4 100644
--- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt
+++ b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
diff --git a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
index a3d2c62fd805..b02a36b2c14f 100644
--- a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
+++ b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
@@ -1,4 +1,5 @@
 #!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
 # gen-insn-attr-x86.awk: Instruction attribute table generator
 # Written by Masami Hiramatsu <mhiramat@redhat.com>
 #
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 365c34ecab26..57254f5b2779 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -29,7 +29,7 @@
 #include "builtin.h"
 #include "check.h"
 
-bool nofp;
+bool no_fp, no_unreachable;
 
 static const char * const check_usage[] = {
         "objtool check [<options>] file.o",
@@ -37,7 +37,8 @@ static const char * const check_usage[] = {
 };
 
 const struct option check_options[] = {
-        OPT_BOOLEAN('f', "no-fp", &nofp, "Skip frame pointer validation"),
+        OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"),
+        OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
         OPT_END(),
 };
 
@@ -52,5 +53,5 @@ int cmd_check(int argc, const char **argv)
 
         objname = argv[0];
 
-        return check(objname, nofp);
+        return check(objname, no_fp, no_unreachable, false);
 }
diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c
new file mode 100644
index 000000000000..4c6b5c9ef073
--- /dev/null
+++ b/tools/objtool/builtin-orc.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * objtool orc:
+ *
+ * This command analyzes a .o file and adds .orc_unwind and .orc_unwind_ip
+ * sections to it, which is used by the in-kernel ORC unwinder.
+ *
+ * This command is a superset of "objtool check".
+ */
+
+#include <string.h>
+#include <subcmd/parse-options.h>
+#include "builtin.h"
+#include "check.h"
+
+
+static const char *orc_usage[] = {
+        "objtool orc generate [<options>] file.o",
+        "objtool orc dump file.o",
+        NULL,
+};
+
+extern const struct option check_options[];
+extern bool no_fp, no_unreachable;
+
+int cmd_orc(int argc, const char **argv)
+{
+        const char *objname;
+
+        argc--; argv++;
+        if (!strncmp(argv[0], "gen", 3)) {
+                argc = parse_options(argc, argv, check_options, orc_usage, 0);
+                if (argc != 1)
+                        usage_with_options(orc_usage, check_options);
+
+                objname = argv[0];
+
+                return check(objname, no_fp, no_unreachable, true);
+
+        }
+
+        if (!strcmp(argv[0], "dump")) {
+                if (argc != 2)
+                        usage_with_options(orc_usage, check_options);
+
+                objname = argv[1];
+
+                return orc_dump(objname);
+        }
+
+        usage_with_options(orc_usage, check_options);
+
+        return 0;
+}
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index 34d2ba78a616..dd526067fed5 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -18,5 +18,6 @@
 #define _BUILTIN_H
 
 extern int cmd_check(int argc, const char **argv);
+extern int cmd_orc(int argc, const char **argv);
 
 #endif /* _BUILTIN_H */
diff --git a/tools/objtool/cfi.h b/tools/objtool/cfi.h
index 443ab2c69992..2fe883c665c7 100644
--- a/tools/objtool/cfi.h
+++ b/tools/objtool/cfi.h
@@ -40,7 +40,7 @@
 #define CFI_R14                 14
 #define CFI_R15                 15
 #define CFI_RA                  16
-#define CFI_NUM_REGS    17
+#define CFI_NUM_REGS            17
 
 struct cfi_reg {
         int base;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 2c6d74880403..9b341584eb1b 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -33,11 +33,11 @@ struct alternative {
 };
 
 const char *objname;
-static bool nofp;
+static bool no_fp;
 struct cfi_state initial_func_cfi;
 
-static struct instruction *find_insn(struct objtool_file *file,
-                                     struct section *sec, unsigned long offset)
+struct instruction *find_insn(struct objtool_file *file,
+                              struct section *sec, unsigned long offset)
 {
         struct instruction *insn;
 
@@ -59,19 +59,6 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
         return next;
 }
 
-static bool gcov_enabled(struct objtool_file *file)
-{
-        struct section *sec;
-        struct symbol *sym;
-
-        for_each_sec(file, sec)
-                list_for_each_entry(sym, &sec->symbol_list, list)
-                        if (!strncmp(sym->name, "__gcov_.", 8))
-                                return true;
-
-        return false;
-}
-
 #define func_for_each_insn(file, func, insn)                            \
         for (insn = find_insn(file, func->sec, func->offset);           \
              insn && &insn->list != &file->insn_list &&                 \
@@ -100,7 +87,6 @@ static bool gcov_enabled(struct objtool_file *file)
 static bool ignore_func(struct objtool_file *file, struct symbol *func)
 {
         struct rela *rela;
-        struct instruction *insn;
 
         /* check for STACK_FRAME_NON_STANDARD */
         if (file->whitelist && file->whitelist->rela)
@@ -113,11 +99,6 @@ static bool ignore_func(struct objtool_file *file, struct symbol *func)
                                 return true;
                 }
 
-        /* check if it has a context switching instruction */
-        func_for_each_insn(file, func, insn)
-                if (insn->type == INSN_CONTEXT_SWITCH)
-                        return true;
-
         return false;
 }
 
@@ -237,9 +218,12 @@ static void clear_insn_state(struct insn_state *state)
 
         memset(state, 0, sizeof(*state));
         state->cfa.base = CFI_UNDEFINED;
-        for (i = 0; i < CFI_NUM_REGS; i++)
+        for (i = 0; i < CFI_NUM_REGS; i++) {
                 state->regs[i].base = CFI_UNDEFINED;
+                state->vals[i].base = CFI_UNDEFINED;
+        }
         state->drap_reg = CFI_UNDEFINED;
+        state->drap_offset = -1;
 }
 
 /*
@@ -259,6 +243,11 @@ static int decode_instructions(struct objtool_file *file)
                 if (!(sec->sh.sh_flags & SHF_EXECINSTR))
                         continue;
 
+                if (strcmp(sec->name, ".altinstr_replacement") &&
+                    strcmp(sec->name, ".altinstr_aux") &&
+                    strncmp(sec->name, ".discard.", 9))
+                        sec->text = true;
+
                 for (offset = 0; offset < sec->len; offset += insn->len) {
                         insn = malloc(sizeof(*insn));
                         if (!insn) {
@@ -278,12 +267,13 @@ static int decode_instructions(struct objtool_file *file)
                                                       &insn->immediate,
                                                       &insn->stack_op);
                         if (ret)
-                                return ret;
+                                goto err;
 
                         if (!insn->type || insn->type > INSN_LAST) {
                                 WARN_FUNC("invalid instruction type %d",
                                           insn->sec, insn->offset, insn->type);
-                                return -1;
+                                ret = -1;
+                                goto err;
                         }
 
                         hash_add(file->insn_hash, &insn->hash, insn->offset);
@@ -307,10 +297,14 @@ static int decode_instructions(struct objtool_file *file)
         }
 
         return 0;
+
+err:
+        free(insn);
+        return ret;
 }
 
 /*
- * Find all uses of the unreachable() macro, which are code path dead ends.
+ * Mark "ud2" instructions and manually annotated dead ends.
  */
 static int add_dead_ends(struct objtool_file *file)
 {
@@ -319,9 +313,20 @@ static int add_dead_ends(struct objtool_file *file)
         struct instruction *insn;
         bool found;
 
+        /*
+         * By default, "ud2" is a dead end unless otherwise annotated, because
+         * GCC 7 inserts it for certain divide-by-zero cases.
+         */
+        for_each_insn(file, insn)
+                if (insn->type == INSN_BUG)
+                        insn->dead_end = true;
+
+        /*
+         * Check for manually annotated dead ends.
+         */
         sec = find_section_by_name(file->elf, ".rela.discard.unreachable");
         if (!sec)
-                return 0;
+                goto reachable;
 
         list_for_each_entry(rela, &sec->rela_list, list) {
                 if (rela->sym->type != STT_SECTION) {
@@ -354,6 +359,48 @@ static int add_dead_ends(struct objtool_file *file)
                 insn->dead_end = true;
         }
 
+reachable:
+        /*
+         * These manually annotated reachable checks are needed for GCC 4.4,
+         * where the Linux unreachable() macro isn't supported.  In that case
+         * GCC doesn't know the "ud2" is fatal, so it generates code as if it's
+         * not a dead end.
+         */
+        sec = find_section_by_name(file->elf, ".rela.discard.reachable");
+        if (!sec)
+                return 0;
+
+        list_for_each_entry(rela, &sec->rela_list, list) {
+                if (rela->sym->type != STT_SECTION) {
+                        WARN("unexpected relocation symbol type in %s", sec->name);
+                        return -1;
+                }
+                insn = find_insn(file, rela->sym->sec, rela->addend);
+                if (insn)
+                        insn = list_prev_entry(insn, list);
+                else if (rela->addend == rela->sym->sec->len) {
+                        found = false;
+                        list_for_each_entry_reverse(insn, &file->insn_list, list) {
+                                if (insn->sec == rela->sym->sec) {
+                                        found = true;
+                                        break;
+                                }
+                        }
+
+                        if (!found) {
+                                WARN("can't find reachable insn at %s+0x%x",
+                                     rela->sym->sec->name, rela->addend);
+                                return -1;
+                        }
+                } else {
+                        WARN("can't find reachable insn at %s+0x%x",
+                             rela->sym->sec->name, rela->addend);
+                        return -1;
+                }
+
+                insn->dead_end = false;
+        }
+
         return 0;
 }
 
@@ -874,6 +921,99 @@ static int add_switch_table_alts(struct objtool_file *file)
         return 0;
 }
 
+static int read_unwind_hints(struct objtool_file *file)
+{
+        struct section *sec, *relasec;
+        struct rela *rela;
+        struct unwind_hint *hint;
+        struct instruction *insn;
+        struct cfi_reg *cfa;
+        int i;
+
+        sec = find_section_by_name(file->elf, ".discard.unwind_hints");
+        if (!sec)
+                return 0;
+
+        relasec = sec->rela;
+        if (!relasec) {
+                WARN("missing .rela.discard.unwind_hints section");
+                return -1;
+        }
+
+        if (sec->len % sizeof(struct unwind_hint)) {
+                WARN("struct unwind_hint size mismatch");
+                return -1;
+        }
+
+        file->hints = true;
+
+        for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) {
+                hint = (struct unwind_hint *)sec->data->d_buf + i;
+
+                rela = find_rela_by_dest(sec, i * sizeof(*hint));
+                if (!rela) {
+                        WARN("can't find rela for unwind_hints[%d]", i);
+                        return -1;
+                }
+
+                insn = find_insn(file, rela->sym->sec, rela->addend);
+                if (!insn) {
+                        WARN("can't find insn for unwind_hints[%d]", i);
+                        return -1;
+                }
+
+                cfa = &insn->state.cfa;
+
+                if (hint->type == UNWIND_HINT_TYPE_SAVE) {
+                        insn->save = true;
+                        continue;
+
+                } else if (hint->type == UNWIND_HINT_TYPE_RESTORE) {
+                        insn->restore = true;
+                        insn->hint = true;
+                        continue;
+                }
+
+                insn->hint = true;
+
+                switch (hint->sp_reg) {
+                case ORC_REG_UNDEFINED:
+                        cfa->base = CFI_UNDEFINED;
+                        break;
+                case ORC_REG_SP:
+                        cfa->base = CFI_SP;
+                        break;
+                case ORC_REG_BP:
+                        cfa->base = CFI_BP;
+                        break;
+                case ORC_REG_SP_INDIRECT:
+                        cfa->base = CFI_SP_INDIRECT;
+                        break;
+                case ORC_REG_R10:
+                        cfa->base = CFI_R10;
+                        break;
+                case ORC_REG_R13:
+                        cfa->base = CFI_R13;
+                        break;
+                case ORC_REG_DI:
+                        cfa->base = CFI_DI;
+                        break;
+                case ORC_REG_DX:
+                        cfa->base = CFI_DX;
+                        break;
+                default:
+                        WARN_FUNC("unsupported unwind_hint sp base reg %d",
+                                  insn->sec, insn->offset, hint->sp_reg);
+                        return -1;
+                }
+
+                cfa->offset = hint->sp_offset;
+                insn->state.type = hint->type;
+        }
+
+        return 0;
+}
+
 static int decode_sections(struct objtool_file *file)
 {
         int ret;
@@ -904,6 +1044,10 @@ static int decode_sections(struct objtool_file *file)
         if (ret)
                 return ret;
 
+        ret = read_unwind_hints(file);
+        if (ret)
+                return ret;
+
         return 0;
 }
 
@@ -947,11 +1091,34 @@ static bool has_valid_stack_frame(struct insn_state *state)
         return false;
 }
 
+static int update_insn_state_regs(struct instruction *insn, struct insn_state *state)
+{
+        struct cfi_reg *cfa = &state->cfa;
+        struct stack_op *op = &insn->stack_op;
+
+        if (cfa->base != CFI_SP)
+                return 0;
+
+        /* push */
+        if (op->dest.type == OP_DEST_PUSH)
+                cfa->offset += 8;
+
+        /* pop */
+        if (op->src.type == OP_SRC_POP)
+                cfa->offset -= 8;
+
+        /* add immediate to sp */
+        if (op->dest.type == OP_DEST_REG && op->src.type == OP_SRC_ADD &&
+            op->dest.reg == CFI_SP && op->src.reg == CFI_SP)
+                cfa->offset -= op->src.offset;
+
+        return 0;
+}
+
 static void save_reg(struct insn_state *state, unsigned char reg, int base,
                      int offset)
 {
-        if ((arch_callee_saved_reg(reg) ||
-            (state->drap && reg == state->drap_reg)) &&
+        if (arch_callee_saved_reg(reg) &&
             state->regs[reg].base == CFI_UNDEFINED) {
                 state->regs[reg].base = base;
                 state->regs[reg].offset = offset;
@@ -1032,30 +1199,71 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                 return 0;
         }
 
+        if (state->type == ORC_TYPE_REGS || state->type == ORC_TYPE_REGS_IRET)
+                return update_insn_state_regs(insn, state);
+
         switch (op->dest.type) {
 
         case OP_DEST_REG:
                 switch (op->src.type) {
 
                 case OP_SRC_REG:
-                        if (cfa->base == op->src.reg && cfa->base == CFI_SP &&
-                            op->dest.reg == CFI_BP && regs[CFI_BP].base == CFI_CFA &&
+                        if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP &&
+                            cfa->base == CFI_SP &&
+                            regs[CFI_BP].base == CFI_CFA &&
                             regs[CFI_BP].offset == -cfa->offset) {
 
                                 /* mov %rsp, %rbp */
                                 cfa->base = op->dest.reg;
                                 state->bp_scratch = false;
-                        } else if (state->drap) {
+                        }
+
+                        else if (op->src.reg == CFI_SP &&
+                                 op->dest.reg == CFI_BP && state->drap) {
 
                                 /* drap: mov %rsp, %rbp */
                                 regs[CFI_BP].base = CFI_BP;
                                 regs[CFI_BP].offset = -state->stack_size;
                                 state->bp_scratch = false;
-                        } else if (!nofp) {
+                        }
 
-                                WARN_FUNC("unknown stack-related register move",
-                                          insn->sec, insn->offset);
-                                return -1;
+                        else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
+
+                                /*
+                                 * mov %rsp, %reg
+                                 *
+                                 * This is needed for the rare case where GCC
+                                 * does:
+                                 *
+                                 *   mov    %rsp, %rax
+                                 *   ...
+                                 *   mov    %rax, %rsp
+                                 */
+                                state->vals[op->dest.reg].base = CFI_CFA;
+                                state->vals[op->dest.reg].offset = -state->stack_size;
+                        }
+
+                        else if (op->dest.reg == cfa->base) {
+
+                                /* mov %reg, %rsp */
+                                if (cfa->base == CFI_SP &&
+                                    state->vals[op->src.reg].base == CFI_CFA) {
+
+                                        /*
+                                         * This is needed for the rare case
+                                         * where GCC does something dumb like:
+                                         *
+                                         *   lea    0x8(%rsp), %rcx
+                                         *   ...
+                                         *   mov    %rcx, %rsp
+                                         */
+                                        cfa->offset = -state->vals[op->src.reg].offset;
+                                        state->stack_size = cfa->offset;
+
+                                } else {
+                                        cfa->base = CFI_UNDEFINED;
+                                        cfa->offset = 0;
+                                }
                         }
 
                         break;
@@ -1077,11 +1285,25 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                                 break;
                         }
 
-                        if (op->dest.reg != CFI_BP && op->src.reg == CFI_SP &&
-                            cfa->base == CFI_SP) {
+                        if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
 
                                 /* drap: lea disp(%rsp), %drap */
                                 state->drap_reg = op->dest.reg;
+
+                                /*
+                                 * lea disp(%rsp), %reg
+                                 *
+                                 * This is needed for the rare case where GCC
+                                 * does something dumb like:
+                                 *
+                                 *   lea    0x8(%rsp), %rcx
+                                 *   ...
+                                 *   mov    %rcx, %rsp
+                                 */
+                                state->vals[op->dest.reg].base = CFI_CFA;
+                                state->vals[op->dest.reg].offset = \
+                                        -state->stack_size + op->src.offset;
+
                                 break;
                         }
 
@@ -1118,7 +1340,6 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                                 cfa->base = state->drap_reg;
                                 cfa->offset = state->stack_size = 0;
                                 state->drap = true;
-
                         }
 
                         /*
@@ -1136,17 +1357,19 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                                 cfa->base = CFI_SP;
                         }
 
-                        if (regs[op->dest.reg].offset == -state->stack_size) {
+                        if (state->drap && cfa->base == CFI_BP_INDIRECT &&
+                            op->dest.type == OP_DEST_REG &&
+                            op->dest.reg == state->drap_reg &&
+                            state->drap_offset == -state->stack_size) {
 
-                                if (state->drap && cfa->base == CFI_BP_INDIRECT &&
-                                    op->dest.type == OP_DEST_REG &&
-                                    op->dest.reg == state->drap_reg) {
+                                /* drap: pop %drap */
+                                cfa->base = state->drap_reg;
+                                cfa->offset = 0;
+                                state->drap_offset = -1;
 
-                                        /* drap: pop %drap */
-                                        cfa->base = state->drap_reg;
-                                        cfa->offset = 0;
-                                }
+                        } else if (regs[op->dest.reg].offset == -state->stack_size) {
 
+                                /* pop %reg */
                                 restore_reg(state, op->dest.reg);
                         }
 
@@ -1158,14 +1381,18 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 
                 case OP_SRC_REG_INDIRECT:
                         if (state->drap && op->src.reg == CFI_BP &&
+                            op->src.offset == state->drap_offset) {
+
+                                /* drap: mov disp(%rbp), %drap */
+                                cfa->base = state->drap_reg;
+                                cfa->offset = 0;
+                                state->drap_offset = -1;
+                        }
+
+                        if (state->drap && op->src.reg == CFI_BP &&
                             op->src.offset == regs[op->dest.reg].offset) {
 
                                 /* drap: mov disp(%rbp), %reg */
-                                if (op->dest.reg == state->drap_reg) {
-                                        cfa->base = state->drap_reg;
-                                        cfa->offset = 0;
-                                }
-
                                 restore_reg(state, op->dest.reg);
 
                         } else if (op->src.reg == cfa->base &&
@@ -1201,8 +1428,8 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                                 cfa->base = CFI_BP_INDIRECT;
                                 cfa->offset = -state->stack_size;
 
-                                /* save drap so we know when to undefine it */
-                                save_reg(state, op->src.reg, CFI_CFA, -state->stack_size);
+                                /* save drap so we know when to restore it */
+                                state->drap_offset = -state->stack_size;
 
                         } else if (op->src.reg == CFI_BP && cfa->base == state->drap_reg) {
 
@@ -1222,7 +1449,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                 }
 
                 /* detect when asm code uses rbp as a scratch register */
-                if (!nofp && insn->func && op->src.reg == CFI_BP &&
+                if (!no_fp && insn->func && op->src.reg == CFI_BP &&
                     cfa->base != CFI_BP)
                         state->bp_scratch = true;
                 break;
@@ -1236,8 +1463,8 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
                                 cfa->base = CFI_BP_INDIRECT;
                                 cfa->offset = op->dest.offset;
 
-                                /* save drap so we know when to undefine it */
-                                save_reg(state, op->src.reg, CFI_CFA, op->dest.offset);
+                                /* save drap offset so we know when to restore it */
+                                state->drap_offset = op->dest.offset;
                         }
 
                         else if (regs[op->src.reg].base == CFI_UNDEFINED) {
@@ -1323,12 +1550,17 @@ static bool insn_state_match(struct instruction *insn, struct insn_state *state)
                         break;
                 }
 
+        } else if (state1->type != state2->type) {
+                WARN_FUNC("stack state mismatch: type1=%d type2=%d",
+                          insn->sec, insn->offset, state1->type, state2->type);
+
         } else if (state1->drap != state2->drap ||
-                 (state1->drap && state1->drap_reg != state2->drap_reg)) {
-                WARN_FUNC("stack state mismatch: drap1=%d(%d) drap2=%d(%d)",
+                 (state1->drap && state1->drap_reg != state2->drap_reg) ||
+                 (state1->drap && state1->drap_offset != state2->drap_offset)) {
+                WARN_FUNC("stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)",
                           insn->sec, insn->offset,
-                          state1->drap, state1->drap_reg,
-                          state2->drap, state2->drap_reg);
+                          state1->drap, state1->drap_reg, state1->drap_offset,
+                          state2->drap, state2->drap_reg, state2->drap_offset);
 
         } else
                 return true;
@@ -1346,7 +1578,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                            struct insn_state state)
 {
         struct alternative *alt;
-        struct instruction *insn;
+        struct instruction *insn, *next_insn;
         struct section *sec;
         struct symbol *func = NULL;
         int ret;
@@ -1357,34 +1589,77 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
         if (insn->alt_group && list_empty(&insn->alts)) {
                 WARN_FUNC("don't know how to handle branch to middle of alternative instruction group",
                           sec, insn->offset);
-                return -1;
+                return 1;
         }
 
         while (1) {
-                if (file->c_file && insn->func) {
-                        if (func && func != insn->func) {
-                                WARN("%s() falls through to next function %s()",
-                                     func->name, insn->func->name);
-                                return 1;
-                        }
+                next_insn = next_insn_same_sec(file, insn);
+
+
+                if (file->c_file && func && insn->func && func != insn->func) {
+                        WARN("%s() falls through to next function %s()",
+                             func->name, insn->func->name);
+                        return 1;
                 }
 
-                func = insn->func;
+                if (insn->func)
+                        func = insn->func;
 
                 if (func && insn->ignore) {
                         WARN_FUNC("BUG: why am I validating an ignored function?",
                                   sec, insn->offset);
-                        return -1;
+                        return 1;
                 }
 
                 if (insn->visited) {
-                        if (!!insn_state_match(insn, &state))
+                        if (!insn->hint && !insn_state_match(insn, &state))
                                 return 1;
 
                         return 0;
                 }
 
-                insn->state = state;
+                if (insn->hint) {
+                        if (insn->restore) {
+                                struct instruction *save_insn, *i;
+
+                                i = insn;
+                                save_insn = NULL;
+                                func_for_each_insn_continue_reverse(file, func, i) {
+                                        if (i->save) {
+                                                save_insn = i;
+                                                break;
+                                        }
+                                }
+
+                                if (!save_insn) {
+                                        WARN_FUNC("no corresponding CFI save for CFI restore",
+                                                  sec, insn->offset);
+                                        return 1;
+                                }
+
+                                if (!save_insn->visited) {
+                                        /*
+                                         * Oops, no state to copy yet.
+                                         * Hopefully we can reach this
+                                         * instruction from another branch
+                                         * after the save insn has been
+                                         * visited.
+                                         */
+                                        if (insn == first)
+                                                return 0;
+
+                                        WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo",
+                                                  sec, insn->offset);
+                                        return 1;
+                                }
+
+                                insn->state = save_insn->state;
+                        }
+
+                        state = insn->state;
+
+                } else
+                        insn->state = state;
 
                 insn->visited = true;
 
@@ -1423,7 +1698,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
                         /* fallthrough */
                 case INSN_CALL_DYNAMIC:
-                        if (!nofp && func && !has_valid_stack_frame(&state)) {
+                        if (!no_fp && func && !has_valid_stack_frame(&state)) {
                                 WARN_FUNC("call without frame pointer save/setup",
                                           sec, insn->offset);
                                 return 1;
@@ -1461,9 +1736,17 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
                         return 0;
 
+                case INSN_CONTEXT_SWITCH:
+                        if (func && (!next_insn || !next_insn->hint)) {
+                                WARN_FUNC("unsupported instruction in callable function",
+                                          sec, insn->offset);
+                                return 1;
+                        }
+                        return 0;
+
                 case INSN_STACK:
                         if (update_insn_state(insn, &state))
-                                return -1;
+                                return 1;
 
                         break;
 
@@ -1474,16 +1757,40 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                 if (insn->dead_end)
                         return 0;
 
-                insn = next_insn_same_sec(file, insn);
-                if (!insn) {
+                if (!next_insn) {
+                        if (state.cfa.base == CFI_UNDEFINED)
+                                return 0;
                         WARN("%s: unexpected end of section", sec->name);
                         return 1;
                 }
+
+                insn = next_insn;
         }
 
         return 0;
 }
 
+static int validate_unwind_hints(struct objtool_file *file)
+{
+        struct instruction *insn;
+        int ret, warnings = 0;
+        struct insn_state state;
+
+        if (!file->hints)
+                return 0;
+
+        clear_insn_state(&state);
+
+        for_each_insn(file, insn) {
+                if (insn->hint && !insn->visited) {
+                        ret = validate_branch(file, insn, state);
+                        warnings += ret;
+                }
+        }
+
+        return warnings;
+}
+
 static bool is_kasan_insn(struct instruction *insn)
 {
         return (insn->type == INSN_CALL &&
@@ -1507,8 +1814,13 @@ static bool ignore_unreachable_insn(struct instruction *insn)
         /*
          * Ignore any unused exceptions.  This can happen when a whitelisted
          * function has an exception table entry.
+         *
+         * Also ignore alternative replacement instructions.  This can happen
+         * when a whitelisted function uses one of the ALTERNATIVE macros.
          */
-        if (!strcmp(insn->sec->name, ".fixup"))
+        if (!strcmp(insn->sec->name, ".fixup") ||
+            !strcmp(insn->sec->name, ".altinstr_replacement") ||
+            !strcmp(insn->sec->name, ".altinstr_aux"))
                 return true;
 
         /*
@@ -1580,15 +1892,6 @@ static int validate_reachable_instructions(struct objtool_file *file)
                 if (insn->visited || ignore_unreachable_insn(insn))
                         continue;
 
-                /*
-                 * gcov produces a lot of unreachable instructions.  If we get
-                 * an unreachable warning and the file has gcov enabled, just
-                 * ignore it, and all other such warnings for the file.  Do
-                 * this here because this is an expensive function.
-                 */
-                if (gcov_enabled(file))
-                        return 0;
-
                 WARN_FUNC("unreachable instruction", insn->sec, insn->offset);
                 return 1;
         }
@@ -1613,15 +1916,15 @@ static void cleanup(struct objtool_file *file)
         elf_close(file->elf);
 }
 
-int check(const char *_objname, bool _nofp)
+int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc)
 {
         struct objtool_file file;
         int ret, warnings = 0;
 
         objname = _objname;
-        nofp = _nofp;
+        no_fp = _no_fp;
 
-        file.elf = elf_open(objname);
+        file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY);
         if (!file.elf)
                 return 1;
 
@@ -1629,8 +1932,9 @@ int check(const char *_objname, bool _nofp)
         hash_init(file.insn_hash);
         file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
         file.rodata = find_section_by_name(file.elf, ".rodata");
-        file.ignore_unreachables = false;
         file.c_file = find_section_by_name(file.elf, ".comment");
+        file.ignore_unreachables = no_unreachable;
+        file.hints = false;
 
         arch_initial_func_cfi_state(&initial_func_cfi);
 
@@ -1647,6 +1951,11 @@ int check(const char *_objname, bool _nofp)
                 goto out;
         warnings += ret;
 
+        ret = validate_unwind_hints(&file);
+        if (ret < 0)
+                goto out;
+        warnings += ret;
+
         if (!warnings) {
                 ret = validate_reachable_instructions(&file);
                 if (ret < 0)
@@ -1654,6 +1963,20 @@ int check(const char *_objname, bool _nofp)
                 warnings += ret;
         }
 
+        if (orc) {
+                ret = create_orc(&file);
+                if (ret < 0)
+                        goto out;
+
+                ret = create_orc_sections(&file);
+                if (ret < 0)
+                        goto out;
+
+                ret = elf_write(file.elf);
+                if (ret < 0)
+                        goto out;
+        }
+
 out:
         cleanup(&file);
 
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index da85f5b00ec6..47d9ea70a83d 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -22,15 +22,18 @@
 #include "elf.h"
 #include "cfi.h"
 #include "arch.h"
+#include "orc.h"
 #include <linux/hashtable.h>
 
 struct insn_state {
         struct cfi_reg cfa;
         struct cfi_reg regs[CFI_NUM_REGS];
         int stack_size;
+        unsigned char type;
         bool bp_scratch;
         bool drap;
-        int drap_reg;
+        int drap_reg, drap_offset;
+        struct cfi_reg vals[CFI_NUM_REGS];
 };
 
 struct instruction {
@@ -41,13 +44,14 @@ struct instruction {
         unsigned int len;
         unsigned char type;
         unsigned long immediate;
-        bool alt_group, visited, dead_end, ignore;
+        bool alt_group, visited, dead_end, ignore, hint, save, restore;
         struct symbol *call_dest;
         struct instruction *jump_dest;
         struct list_head alts;
         struct symbol *func;
         struct stack_op stack_op;
         struct insn_state state;
+        struct orc_entry orc;
 };
 
 struct objtool_file {
@@ -55,12 +59,22 @@ struct objtool_file {
         struct list_head insn_list;
         DECLARE_HASHTABLE(insn_hash, 16);
         struct section *rodata, *whitelist;
-        bool ignore_unreachables, c_file;
+        bool ignore_unreachables, c_file, hints;
 };
 
-int check(const char *objname, bool nofp);
+int check(const char *objname, bool no_fp, bool no_unreachable, bool orc);
+
+struct instruction *find_insn(struct objtool_file *file,
+                              struct section *sec, unsigned long offset);
 
 #define for_each_insn(file, insn)                                       \
         list_for_each_entry(insn, &file->insn_list, list)
 
+#define sec_for_each_insn(file, sec, insn)                              \
+        for (insn = find_insn(file, sec, 0);                            \
+             insn && &insn->list != &file->insn_list &&                 \
+                        insn->sec == sec;                               \
+             insn = list_next_entry(insn, list))
+
+
 #endif /* _CHECK_H */
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 1a7e8aa2af58..24460155c82c 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -30,16 +30,6 @@
 #include "elf.h"
 #include "warn.h"
 
-/*
- * Fallback for systems without this "read, mmaping if possible" cmd.
- */
-#ifndef ELF_C_READ_MMAP
-#define ELF_C_READ_MMAP ELF_C_READ
-#endif
-
-#define WARN_ELF(format, ...)                                   \
-        WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1))
-
 struct section *find_section_by_name(struct elf *elf, const char *name)
 {
         struct section *sec;
@@ -185,19 +175,20 @@ static int read_sections(struct elf *elf)
                         return -1;
                 }
 
-                sec->data = elf_getdata(s, NULL);
-                if (!sec->data) {
-                        WARN_ELF("elf_getdata");
-                        return -1;
-                }
-
-                if (sec->data->d_off != 0 ||
-                    sec->data->d_size != sec->sh.sh_size) {
-                        WARN("unexpected data attributes for %s", sec->name);
-                        return -1;
+                if (sec->sh.sh_size != 0) {
+                        sec->data = elf_getdata(s, NULL);
+                        if (!sec->data) {
+                                WARN_ELF("elf_getdata");
+                                return -1;
+                        }
+                        if (sec->data->d_off != 0 ||
+                            sec->data->d_size != sec->sh.sh_size) {
+                                WARN("unexpected data attributes for %s",
+                                     sec->name);
+                                return -1;
+                        }
                 }
-
-                sec->len = sec->data->d_size;
+                sec->len = sec->sh.sh_size;
         }
 
         /* sanity check, one more call to elf_nextscn() should return NULL */
@@ -349,9 +340,10 @@ static int read_relas(struct elf *elf)
         return 0;
 }
 
-struct elf *elf_open(const char *name)
+struct elf *elf_open(const char *name, int flags)
 {
         struct elf *elf;
+        Elf_Cmd cmd;
 
         elf_version(EV_CURRENT);
 
@@ -364,13 +356,20 @@ struct elf *elf_open(const char *name)
 
         INIT_LIST_HEAD(&elf->sections);
 
-        elf->fd = open(name, O_RDONLY);
+        elf->fd = open(name, flags);
         if (elf->fd == -1) {
                 perror("open");
                 goto err;
         }
 
-        elf->elf = elf_begin(elf->fd, ELF_C_READ_MMAP, NULL);
+        if ((flags & O_ACCMODE) == O_RDONLY)
+                cmd = ELF_C_READ_MMAP;
+        else if ((flags & O_ACCMODE) == O_RDWR)
+                cmd = ELF_C_RDWR;
+        else /* O_WRONLY */
+                cmd = ELF_C_WRITE;
+
+        elf->elf = elf_begin(elf->fd, cmd, NULL);
         if (!elf->elf) {
                 WARN_ELF("elf_begin");
                 goto err;
@@ -397,6 +396,200 @@ err:
         return NULL;
 }
 
+struct section *elf_create_section(struct elf *elf, const char *name,
+                                   size_t entsize, int nr)
+{
+        struct section *sec, *shstrtab;
+        size_t size = entsize * nr;
+        struct Elf_Scn *s;
+        Elf_Data *data;
+
+        sec = malloc(sizeof(*sec));
+        if (!sec) {
+                perror("malloc");
+                return NULL;
+        }
+        memset(sec, 0, sizeof(*sec));
+
+        INIT_LIST_HEAD(&sec->symbol_list);
+        INIT_LIST_HEAD(&sec->rela_list);
+        hash_init(sec->rela_hash);
+        hash_init(sec->symbol_hash);
+
+        list_add_tail(&sec->list, &elf->sections);
+
+        s = elf_newscn(elf->elf);
+        if (!s) {
+                WARN_ELF("elf_newscn");
+                return NULL;
+        }
+
+        sec->name = strdup(name);
+        if (!sec->name) {
+                perror("strdup");
+                return NULL;
+        }
+
+        sec->idx = elf_ndxscn(s);
+        sec->len = size;
+        sec->changed = true;
+
+        sec->data = elf_newdata(s);
+        if (!sec->data) {
+                WARN_ELF("elf_newdata");
+                return NULL;
+        }
+
+        sec->data->d_size = size;
+        sec->data->d_align = 1;
+
+        if (size) {
+                sec->data->d_buf = malloc(size);
+                if (!sec->data->d_buf) {
+                        perror("malloc");
+                        return NULL;
+                }
+                memset(sec->data->d_buf, 0, size);
+        }
+
+        if (!gelf_getshdr(s, &sec->sh)) {
+                WARN_ELF("gelf_getshdr");
+                return NULL;
+        }
+
+        sec->sh.sh_size = size;
+        sec->sh.sh_entsize = entsize;
+        sec->sh.sh_type = SHT_PROGBITS;
+        sec->sh.sh_addralign = 1;
+        sec->sh.sh_flags = SHF_ALLOC;
+
+
+        /* Add section name to .shstrtab */
+        shstrtab = find_section_by_name(elf, ".shstrtab");
+        if (!shstrtab) {
+                WARN("can't find .shstrtab section");
+                return NULL;
+        }
+
+        s = elf_getscn(elf->elf, shstrtab->idx);
+        if (!s) {
+                WARN_ELF("elf_getscn");
+                return NULL;
+        }
+
+        data = elf_newdata(s);
+        if (!data) {
+                WARN_ELF("elf_newdata");
+                return NULL;
+        }
+
+        data->d_buf = sec->name;
+        data->d_size = strlen(name) + 1;
+        data->d_align = 1;
+
+        sec->sh.sh_name = shstrtab->len;
+
+        shstrtab->len += strlen(name) + 1;
+        shstrtab->changed = true;
+
+        return sec;
+}
+
+struct section *elf_create_rela_section(struct elf *elf, struct section *base)
+{
+        char *relaname;
+        struct section *sec;
+
+        relaname = malloc(strlen(base->name) + strlen(".rela") + 1);
+        if (!relaname) {
+                perror("malloc");
+                return NULL;
+        }
+        strcpy(relaname, ".rela");
+        strcat(relaname, base->name);
+
+        sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0);
+        free(relaname);
+        if (!sec)
+                return NULL;
+
+        base->rela = sec;
+        sec->base = base;
+
+        sec->sh.sh_type = SHT_RELA;
+        sec->sh.sh_addralign = 8;
+        sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx;
+        sec->sh.sh_info = base->idx;
+        sec->sh.sh_flags = SHF_INFO_LINK;
+
+        return sec;
+}
+
+int elf_rebuild_rela_section(struct section *sec)
+{
+        struct rela *rela;
+        int nr, idx = 0, size;
+        GElf_Rela *relas;
+
+        nr = 0;
+        list_for_each_entry(rela, &sec->rela_list, list)
+                nr++;
+
+        size = nr * sizeof(*relas);
+        relas = malloc(size);
+        if (!relas) {
+                perror("malloc");
+                return -1;
+        }
+
+        sec->data->d_buf = relas;
+        sec->data->d_size = size;
+
+        sec->sh.sh_size = size;
+
+        idx = 0;
+        list_for_each_entry(rela, &sec->rela_list, list) {
+                relas[idx].r_offset = rela->offset;
+                relas[idx].r_addend = rela->addend;
+                relas[idx].r_info = GELF_R_INFO(rela->sym->idx, rela->type);
+                idx++;
+        }
+
+        return 0;
+}
+
+int elf_write(struct elf *elf)
+{
+        struct section *sec;
+        Elf_Scn *s;
+
+        /* Update section headers for changed sections: */
+        list_for_each_entry(sec, &elf->sections, list) {
+                if (sec->changed) {
+                        s = elf_getscn(elf->elf, sec->idx);
+                        if (!s) {
+                                WARN_ELF("elf_getscn");
+                                return -1;
+                        }
+                        if (!gelf_update_shdr(s, &sec->sh)) {
+                                WARN_ELF("gelf_update_shdr");
+                                return -1;
+                        }
+                }
+        }
+
+        /* Make sure the new section header entries get updated properly. */
+        elf_flagelf(elf->elf, ELF_C_SET, ELF_F_DIRTY);
+
+        /* Write all changes to the file. */
+        if (elf_update(elf->elf, ELF_C_WRITE) < 0) {
+                WARN_ELF("elf_update");
+                return -1;
+        }
+
+        return 0;
+}
+
 void elf_close(struct elf *elf)
 {
         struct section *sec, *tmpsec;
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index 343968b778cb..d86e2ff14466 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -28,6 +28,13 @@
 # define elf_getshdrstrndx elf_getshstrndx
 #endif
 
+/*
+ * Fallback for systems without this "read, mmaping if possible" cmd.
+ */
+#ifndef ELF_C_READ_MMAP
+#define ELF_C_READ_MMAP ELF_C_READ
+#endif
+
 struct section {
         struct list_head list;
         GElf_Shdr sh;
@@ -41,6 +48,7 @@ struct section {
         char *name;
         int idx;
         unsigned int len;
+        bool changed, text;
 };
 
 struct symbol {
@@ -75,7 +83,7 @@ struct elf {
 };
 
 
-struct elf *elf_open(const char *name);
+struct elf *elf_open(const char *name, int flags);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
 struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
@@ -83,6 +91,11 @@ struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
                                      unsigned int len);
 struct symbol *find_containing_func(struct section *sec, unsigned long offset);
+struct section *elf_create_section(struct elf *elf, const char *name, size_t
+                                   entsize, int nr);
+struct section *elf_create_rela_section(struct elf *elf, struct section *base);
+int elf_rebuild_rela_section(struct section *sec);
+int elf_write(struct elf *elf);
 void elf_close(struct elf *elf);
 
 #define for_each_sec(file, sec)                                         \
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index ecc5b1b5d15d..07f329919828 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -42,10 +42,11 @@ struct cmd_struct {
 };
 
 static const char objtool_usage_string[] =
-        "objtool [OPTIONS] COMMAND [ARGS]";
+        "objtool COMMAND [ARGS]";
 
 static struct cmd_struct objtool_cmds[] = {
         {"check",       cmd_check,      "Perform stack metadata validation on an object file" },
+        {"orc",         cmd_orc,        "Generate in-place ORC unwind tables for an object file" },
 };
 
 bool help;
@@ -69,7 +70,7 @@ static void cmd_usage(void)
 
         printf("\n");
 
-        exit(1);
+        exit(129);
 }
 
 static void handle_options(int *argc, const char ***argv)
@@ -85,9 +86,7 @@ static void handle_options(int *argc, const char ***argv)
                         break;
                 } else {
                         fprintf(stderr, "Unknown option: %s\n", cmd);
-                        fprintf(stderr, "\n Usage: %s\n",
-                                objtool_usage_string);
-                        exit(1);
+                        cmd_usage();
                 }
 
                 (*argv)++;
diff --git a/tools/objtool/orc.h b/tools/objtool/orc.h
new file mode 100644
index 000000000000..b0e92a6d0903
--- /dev/null
+++ b/tools/objtool/orc.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ORC_H
+#define _ORC_H
+
+#include <asm/orc_types.h>
+
+struct objtool_file;
+
+int create_orc(struct objtool_file *file);
+int create_orc_sections(struct objtool_file *file);
+
+int orc_dump(const char *objname);
+
+#endif /* _ORC_H */
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
new file mode 100644
index 000000000000..36c5bf6a2675
--- /dev/null
+++ b/tools/objtool/orc_dump.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <unistd.h>
+#include "orc.h"
+#include "warn.h"
+
+static const char *reg_name(unsigned int reg)
+{
+        switch (reg) {
+        case ORC_REG_PREV_SP:
+                return "prevsp";
+        case ORC_REG_DX:
+                return "dx";
+        case ORC_REG_DI:
+                return "di";
+        case ORC_REG_BP:
+                return "bp";
+        case ORC_REG_SP:
+                return "sp";
+        case ORC_REG_R10:
+                return "r10";
+        case ORC_REG_R13:
+                return "r13";
+        case ORC_REG_BP_INDIRECT:
+                return "bp(ind)";
+        case ORC_REG_SP_INDIRECT:
+                return "sp(ind)";
+        default:
+                return "?";
+        }
+}
+
+static const char *orc_type_name(unsigned int type)
+{
+        switch (type) {
+        case ORC_TYPE_CALL:
+                return "call";
+        case ORC_TYPE_REGS:
+                return "regs";
+        case ORC_TYPE_REGS_IRET:
+                return "iret";
+        default:
+                return "?";
+        }
+}
+
+static void print_reg(unsigned int reg, int offset)
+{
+        if (reg == ORC_REG_BP_INDIRECT)
+                printf("(bp%+d)", offset);
+        else if (reg == ORC_REG_SP_INDIRECT)
+                printf("(sp%+d)", offset);
+        else if (reg == ORC_REG_UNDEFINED)
+                printf("(und)");
+        else
+                printf("%s%+d", reg_name(reg), offset);
+}
+
+int orc_dump(const char *_objname)
+{
+        int fd, nr_entries, i, *orc_ip = NULL, orc_size = 0;
+        struct orc_entry *orc = NULL;
+        char *name;
+        unsigned long nr_sections, orc_ip_addr = 0;
+        size_t shstrtab_idx;
+        Elf *elf;
+        Elf_Scn *scn;
+        GElf_Shdr sh;
+        GElf_Rela rela;
+        GElf_Sym sym;
+        Elf_Data *data, *symtab = NULL, *rela_orc_ip = NULL;
+
+
+        objname = _objname;
+
+        elf_version(EV_CURRENT);
+
+        fd = open(objname, O_RDONLY);
+        if (fd == -1) {
+                perror("open");
+                return -1;
+        }
+
+        elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+        if (!elf) {
+                WARN_ELF("elf_begin");
+                return -1;
+        }
+
+        if (elf_getshdrnum(elf, &nr_sections)) {
+                WARN_ELF("elf_getshdrnum");
+                return -1;
+        }
+
+        if (elf_getshdrstrndx(elf, &shstrtab_idx)) {
+                WARN_ELF("elf_getshdrstrndx");
+                return -1;
+        }
+
+        for (i = 0; i < nr_sections; i++) {
+                scn = elf_getscn(elf, i);
+                if (!scn) {
+                        WARN_ELF("elf_getscn");
+                        return -1;
+                }
+
+                if (!gelf_getshdr(scn, &sh)) {
+                        WARN_ELF("gelf_getshdr");
+                        return -1;
+                }
+
+                name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
+                if (!name) {
+                        WARN_ELF("elf_strptr");
+                        return -1;
+                }
+
+                data = elf_getdata(scn, NULL);
+                if (!data) {
+                        WARN_ELF("elf_getdata");
+                        return -1;
+                }
+
+                if (!strcmp(name, ".symtab")) {
+                        symtab = data;
+                } else if (!strcmp(name, ".orc_unwind")) {
+                        orc = data->d_buf;
+                        orc_size = sh.sh_size;
+                } else if (!strcmp(name, ".orc_unwind_ip")) {
+                        orc_ip = data->d_buf;
+                        orc_ip_addr = sh.sh_addr;
+                } else if (!strcmp(name, ".rela.orc_unwind_ip")) {
+                        rela_orc_ip = data;
+                }
+        }
+
+        if (!symtab || !orc || !orc_ip)
+                return 0;
+
+        if (orc_size % sizeof(*orc) != 0) {
+                WARN("bad .orc_unwind section size");
+                return -1;
+        }
+
+        nr_entries = orc_size / sizeof(*orc);
+        for (i = 0; i < nr_entries; i++) {
+                if (rela_orc_ip) {
+                        if (!gelf_getrela(rela_orc_ip, i, &rela)) {
+                                WARN_ELF("gelf_getrela");
+                                return -1;
+                        }
+
+                        if (!gelf_getsym(symtab, GELF_R_SYM(rela.r_info), &sym)) {
+                                WARN_ELF("gelf_getsym");
+                                return -1;
+                        }
+
+                        scn = elf_getscn(elf, sym.st_shndx);
+                        if (!scn) {
+                                WARN_ELF("elf_getscn");
+                                return -1;
+                        }
+
+                        if (!gelf_getshdr(scn, &sh)) {
+                                WARN_ELF("gelf_getshdr");
+                                return -1;
+                        }
+
+                        name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
+                        if (!name || !*name) {
+                                WARN_ELF("elf_strptr");
+                                return -1;
+                        }
+
+                        printf("%s+%lx:", name, rela.r_addend);
+
+                } else {
+                        printf("%lx:", orc_ip_addr + (i * sizeof(int)) + orc_ip[i]);
+                }
+
+
+                printf(" sp:");
+
+                print_reg(orc[i].sp_reg, orc[i].sp_offset);
+
+                printf(" bp:");
+
+                print_reg(orc[i].bp_reg, orc[i].bp_offset);
+
+                printf(" type:%s\n", orc_type_name(orc[i].type));
+        }
+
+        elf_end(elf);
+        close(fd);
+
+        return 0;
+}
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
new file mode 100644
index 000000000000..e5ca31429c9b
--- /dev/null
+++ b/tools/objtool/orc_gen.c
@@ -0,0 +1,214 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "orc.h"
+#include "check.h"
+#include "warn.h"
+
+int create_orc(struct objtool_file *file)
+{
+        struct instruction *insn;
+
+        for_each_insn(file, insn) {
+                struct orc_entry *orc = &insn->orc;
+                struct cfi_reg *cfa = &insn->state.cfa;
+                struct cfi_reg *bp = &insn->state.regs[CFI_BP];
+
+                if (cfa->base == CFI_UNDEFINED) {
+                        orc->sp_reg = ORC_REG_UNDEFINED;
+                        continue;
+                }
+
+                switch (cfa->base) {
+                case CFI_SP:
+                        orc->sp_reg = ORC_REG_SP;
+                        break;
+                case CFI_SP_INDIRECT:
+                        orc->sp_reg = ORC_REG_SP_INDIRECT;
+                        break;
+                case CFI_BP:
+                        orc->sp_reg = ORC_REG_BP;
+                        break;
+                case CFI_BP_INDIRECT:
+                        orc->sp_reg = ORC_REG_BP_INDIRECT;
+                        break;
+                case CFI_R10:
+                        orc->sp_reg = ORC_REG_R10;
+                        break;
+                case CFI_R13:
+                        orc->sp_reg = ORC_REG_R13;
+                        break;
+                case CFI_DI:
+                        orc->sp_reg = ORC_REG_DI;
+                        break;
+                case CFI_DX:
+                        orc->sp_reg = ORC_REG_DX;
+                        break;
+                default:
+                        WARN_FUNC("unknown CFA base reg %d",
+                                  insn->sec, insn->offset, cfa->base);
+                        return -1;
+                }
+
+                switch(bp->base) {
+                case CFI_UNDEFINED:
+                        orc->bp_reg = ORC_REG_UNDEFINED;
+                        break;
+                case CFI_CFA:
+                        orc->bp_reg = ORC_REG_PREV_SP;
+                        break;
+                case CFI_BP:
+                        orc->bp_reg = ORC_REG_BP;
+                        break;
+                default:
+                        WARN_FUNC("unknown BP base reg %d",
+                                  insn->sec, insn->offset, bp->base);
+                        return -1;
+                }
+
+                orc->sp_offset = cfa->offset;
+                orc->bp_offset = bp->offset;
+                orc->type = insn->state.type;
+        }
+
+        return 0;
+}
+
+static int create_orc_entry(struct section *u_sec, struct section *ip_relasec,
+                                unsigned int idx, struct section *insn_sec,
+                                unsigned long insn_off, struct orc_entry *o)
+{
+        struct orc_entry *orc;
+        struct rela *rela;
+
+        /* populate ORC data */
+        orc = (struct orc_entry *)u_sec->data->d_buf + idx;
+        memcpy(orc, o, sizeof(*orc));
+
+        /* populate rela for ip */
+        rela = malloc(sizeof(*rela));
+        if (!rela) {
+                perror("malloc");
+                return -1;
+        }
+        memset(rela, 0, sizeof(*rela));
+
+        rela->sym = insn_sec->sym;
+        rela->addend = insn_off;
+        rela->type = R_X86_64_PC32;
+        rela->offset = idx * sizeof(int);
+
+        list_add_tail(&rela->list, &ip_relasec->rela_list);
+        hash_add(ip_relasec->rela_hash, &rela->hash, rela->offset);
+
+        return 0;
+}
+
+int create_orc_sections(struct objtool_file *file)
+{
+        struct instruction *insn, *prev_insn;
+        struct section *sec, *u_sec, *ip_relasec;
+        unsigned int idx;
+
+        struct orc_entry empty = {
+                .sp_reg = ORC_REG_UNDEFINED,
+                .bp_reg  = ORC_REG_UNDEFINED,
+                .type    = ORC_TYPE_CALL,
+        };
+
+        sec = find_section_by_name(file->elf, ".orc_unwind");
+        if (sec) {
+                WARN("file already has .orc_unwind section, skipping");
+                return -1;
+        }
+
+        /* count the number of needed orcs */
+        idx = 0;
+        for_each_sec(file, sec) {
+                if (!sec->text)
+                        continue;
+
+                prev_insn = NULL;
+                sec_for_each_insn(file, sec, insn) {
+                        if (!prev_insn ||
+                            memcmp(&insn->orc, &prev_insn->orc,
+                                   sizeof(struct orc_entry))) {
+                                idx++;
+                        }
+                        prev_insn = insn;
+                }
+
+                /* section terminator */
+                if (prev_insn)
+                        idx++;
+        }
+        if (!idx)
+                return -1;
+
+
+        /* create .orc_unwind_ip and .rela.orc_unwind_ip sections */
+        sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx);
+
+        ip_relasec = elf_create_rela_section(file->elf, sec);
+        if (!ip_relasec)
+                return -1;
+
+        /* create .orc_unwind section */
+        u_sec = elf_create_section(file->elf, ".orc_unwind",
+                                   sizeof(struct orc_entry), idx);
+
+        /* populate sections */
+        idx = 0;
+        for_each_sec(file, sec) {
+                if (!sec->text)
+                        continue;
+
+                prev_insn = NULL;
+                sec_for_each_insn(file, sec, insn) {
+                        if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc,
+                                                 sizeof(struct orc_entry))) {
+
+                                if (create_orc_entry(u_sec, ip_relasec, idx,
+                                                     insn->sec, insn->offset,
+                                                     &insn->orc))
+                                        return -1;
+
+                                idx++;
+                        }
+                        prev_insn = insn;
+                }
+
+                /* section terminator */
+                if (prev_insn) {
+                        if (create_orc_entry(u_sec, ip_relasec, idx,
+                                             prev_insn->sec,
+                                             prev_insn->offset + prev_insn->len,
+                                             &empty))
+                                return -1;
+
+                        idx++;
+                }
+        }
+
+        if (elf_rebuild_rela_section(ip_relasec))
+                return -1;
+
+        return 0;
+}
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
new file mode 100755
index 000000000000..1470e74e9d66
--- /dev/null
+++ b/tools/objtool/sync-check.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+FILES='
+arch/x86/lib/insn.c
+arch/x86/lib/inat.c
+arch/x86/lib/x86-opcode-map.txt
+arch/x86/tools/gen-insn-attr-x86.awk
+arch/x86/include/asm/insn.h
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/inat_types.h
+arch/x86/include/asm/orc_types.h
+'
+
+check()
+{
+        local file=$1
+
+        diff $file ../../$file > /dev/null ||
+                echo "Warning: synced file at 'tools/objtool/$file' differs from latest kernel version at '$file'"
+}
+
+if [ ! -d ../../kernel ] || [ ! -d ../../tools ] || [ ! -d ../objtool ]; then
+        exit 0
+fi
+
+for i in $FILES; do
+  check $i
+done
diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index ad54a58d7dda..9074b477bff0 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -173,6 +173,7 @@ usage:
                         "\t-D <dev>             PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n"
                         "\t-b <bar num>         BAR test (bar number between 0..5)\n"
                         "\t-m <msi num>         MSI test (msi number between 1..32)\n"
+                        "\t-l                   Legacy IRQ test\n"
                         "\t-r                   Read buffer test\n"
                         "\t-w                   Write buffer test\n"
                         "\t-c                   Copy buffer test\n"
diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh
index 5442bbea4c22..77e8c85ef744 100644
--- a/tools/pci/pcitest.sh
+++ b/tools/pci/pcitest.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 echo "BAR tests"
 echo
diff --git a/tools/pcmcia/Makefile b/tools/pcmcia/Makefile
index 81a7498c5cd9..eae24df1dbf5 100644
--- a/tools/pcmcia/Makefile
+++ b/tools/pcmcia/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC := $(CROSS_COMPILE)gcc
 CFLAGS := -I../../usr/include
 
diff --git a/tools/perf/Build b/tools/perf/Build
index bd8eeb60533c..b48ca40fccf9 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -50,6 +50,6 @@ libperf-y += util/
 libperf-y += arch/
 libperf-y += ui/
 libperf-y += scripts/
-libperf-y += trace/beauty/
+libperf-$(CONFIG_AUDIT) += trace/beauty/
 
 gtk-y += ui/gtk/
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 098cfb9ca8f0..db11478e30b4 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -192,7 +192,7 @@ do-install-man: man
 #               $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir); \
 #               $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
 
-install-man: check-man-tools man
+install-man: check-man-tools man do-install-man
 
 ifdef missing_tools
   DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed)
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4b6cdbf8f935..76971d2e4164 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -104,9 +104,9 @@ system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
 in transaction, respectively.
 
 While it is possible to create scripts to analyze the data, an alternative
-approach is available to export the data to a postgresql database.  Refer to
-script export-to-postgresql.py for more details, and to script
-call-graph-from-postgresql.py for an example of using the database.
+approach is available to export the data to a sqlite or postgresql database.
+Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
+and to script call-graph-from-sql.py for an example of using the database.
 
 There is also script intel-pt-events.py which provides an example of how to
 unpack the raw data for power events and PTWRITE.
@@ -873,7 +873,7 @@ amended to take the number of elements as a parameter.
 
         $ cat ~/.perfconfig
         [intel-pt]
-                mispred-all
+                mispred-all = on
 
         $ perf record -e intel_pt//u ./sort 3000
         Bubble sorting array of 3000 elements
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index a89273d8e744..c635eab6af54 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -43,6 +43,10 @@ OPTIONS
 --quiet::
         Do not show any message.  (Suppress -v)
 
+-n::
+--show-nr-samples::
+        Show the number of samples for each symbol
+
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
@@ -88,6 +92,8 @@ OPTIONS
 --asm-raw::
         Show raw instruction encoding of assembly instructions.
 
+--show-total-period:: Show a column with the sum of periods.
+
 --source::
         Interleave source code with assembly code. Enabled by default,
         disable with --no-source.
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 058064db39d2..84681007f80f 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -61,6 +61,11 @@ OPTIONS
 --verbose::
         Be more verbose.
 
+--target-ns=PID:
+        Obtain mount namespace information from the target pid.  This is
+        used when creating a uprobe for a process that resides in a
+        different mount namespace from the perf(1) utility.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index f709de54707b..e2a897ae3596 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,8 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
+'perf list' [--no-desc] [--long-desc]
+            [hw|sw|cache|tracepoint|pmu|sdt|metric|metricgroup|event_glob]
 
 DESCRIPTION
 -----------
@@ -47,6 +48,8 @@ counted. The following modifiers exist:
  P - use maximum detected precise level
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
+ W - group is weak and will fallback to non-group if not schedulable,
+     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
@@ -201,7 +204,7 @@ For example Intel Core CPUs typically have four generic performance counters
 for the core, plus three fixed counters for instructions, cycles and
 ref-cycles. Some special events have restrictions on which counter they
 can schedule, and may not support multiple instances in a single group.
-When too many events are specified in the group none of them will not
+When too many events are specified in the group some of them will not
 be measured.
 
 Globally pinned events can limit the number of counters available for
@@ -246,6 +249,10 @@ To limit the list use:
 
 . 'sdt' to list all Statically Defined Tracepoint events.
 
+. 'metric' to list metrics
+
+. 'metricgroup' to list metricgroups with metrics.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 73496320fca3..4be08a1e3f8d 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -59,6 +59,10 @@ OPTIONS
 --ldload::
         Specify desired latency for loads event.
 
+-p::
+--phys-data::
+        Record/Report sample physical addresses
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 165c2b1d4317..d7e4869905f1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -130,6 +130,11 @@ OPTIONS
 --max-probes=NUM::
         Set the maximum number of probe points for an event. Default is 128.
 
+--target-ns=PID:
+        Obtain mount namespace information from the target pid.  This is
+        used when creating a uprobe for a process that resides in a
+        different mount namespace from the perf(1) utility.
+
 -x::
 --exec=PATH::
         Specify path to the executable or shared library file for user
@@ -264,6 +269,15 @@ Add probes at malloc() function on libc
 
  ./perf probe -x /lib/libc.so.6 malloc or ./perf probe /lib/libc.so.6 malloc
 
+Add a uprobe to a target process running in a different mount namespace
+
+ ./perf probe --target-ns <target pid> -x /lib64/libc.so.6 malloc
+
+Add a USDT probe to a target process running in a different mount namespace
+
+ ./perf probe --target-ns <target pid> -x /usr/lib/jvm/java-1.8.0-openjdk-1.8.0.121-0.b13.el7_3.x86_64/jre/lib/amd64/server/libjvm.so %sdt_hotspot:thread__sleep__end
+
+
 SEE ALSO
 --------
 linkperf:perf-trace[1], linkperf:perf-record[1], linkperf:perf-buildid-cache[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b0e9e921d534..5a626ef666c2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -8,8 +8,8 @@ perf-record - Run a command and record its profile into perf.data
 SYNOPSIS
 --------
 [verse]
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+'perf record' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf record' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
@@ -249,7 +249,10 @@ OPTIONS
 
 -d::
 --data::
-        Record the sample addresses.
+        Record the sample virtual addresses.
+
+--phys-data::
+        Record the sample physical addresses.
 
 -T::
 --timestamp::
@@ -332,6 +335,7 @@ following filters are defined:
         - no_tx: only when the target is not in a hardware transaction
         - abort_tx: only when the target is a hardware transaction abort
         - cond: conditional branches
+        - save_type: save branch type during sampling in case binary is not available later
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
@@ -373,6 +377,8 @@ symbolic names, e.g. on x86, ax, si. To list the available registers use
 --intr-regs=\?. To name registers, pass a comma separated list such as
 --intr-regs=ax,bx. The list of register is architecture dependent.
 
+--user-regs::
+Capture user registers at sample time. Same arguments as -I.
 
 --running-time::
 Record running and enabled time for read events (:S)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9fa84617181e..ddde2b54af57 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -137,6 +137,7 @@ OPTIONS
         - mem: type of memory access for the data at the time of the sample
         - snoop: type of snoop (if any) for the data at the time of the sample
         - dcacheline: the cacheline the data address is on at the time of the sample
+        - phys_daddr: physical address of data being executed on at the time of sample
 
         And the default sort keys are changed to local_weight, mem, sym, dso,
         symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
@@ -433,7 +434,8 @@ include::itrace.txt[]
 
 --inline::
         If a callgraph address belongs to an inlined function, the inline stack
-        will be printed. Each entry is function name or file/line.
+        will be printed. Each entry is function name or file/line. Enabled by
+        default, disable with --no-inline.
 
 include::callchain-overhead-calculation.txt[]
 
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index a092a2499e8f..55b67338548e 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -106,6 +106,14 @@ OPTIONS for 'perf sched timehist'
 --max-stack::
         Maximum number of functions to display in backtrace, default 5.
 
+-p=::
+--pid=::
+        Only show events for given process ID (comma separated list).
+
+-t=::
+--tid=::
+        Only show events for given thread ID (comma separated list).
+
 -s::
 --summary::
     Show only a summary of scheduling by thread with min, max, and average
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5ee8796be96e..2811fcf684cb 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,8 +116,8 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
-        callindent, insn, insnlen, synth.
+        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
+        brstackoff, callindent, insn, insnlen, synth, phys_addr.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -325,9 +325,14 @@ include::itrace.txt[]
         Set the maximum number of program blocks to print with brstackasm for
         each sample.
 
+--per-event-dump::
+        Create per event files with a "perf.data.EVENT.dump" name instead of
+        printing to stdout, useful, for instance, for generating flamegraphs.
+
 --inline::
         If a callgraph address belongs to an inlined function, the inline stack
-        will be printed. Each entry has function name and file/line.
+        will be printed. Each entry has function name and file/line. Enabled by
+        default, disable with --no-inline.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 698076313606..823fce7674bb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -41,13 +41,13 @@ report::
 
         - a symbolically formed event like 'pmu/param1=0x3,param2/' where
           param1 and param2 are defined as formats for the PMU in
-          /sys/bus/event_sources/devices/<pmu>/format/*
+          /sys/bus/event_source/devices/<pmu>/format/*
 
         - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
           where M, N, K are numbers (in decimal, hex, octal format).
           Acceptable values for each of 'config', 'config1' and 'config2'
           parameters are defined by corresponding entries in
-          /sys/bus/event_sources/devices/<pmu>/format/*
+          /sys/bus/event_source/devices/<pmu>/format/*
 
 -i::
 --no-inherit::
@@ -199,6 +199,13 @@ Aggregate counts per processor socket for system-wide mode measurements.
 --per-core::
 Aggregate counts per physical processor for system-wide mode measurements.
 
+-M::
+--metrics::
+Print metrics or metricgroups specified in a comma separated list.
+For a group all metrics from the group are added.
+The events from the metrics are automatically measured.
+See perf list output for the possble metrics and metricgroups.
+
 -A::
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index e71d63843f45..4353262bc462 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -237,6 +237,13 @@ Default is to monitor all CPUS.
 --hierarchy::
         Enable hierarchy output.
 
+--force::
+        Don't do ownership validation.
+
+--num-thread-synthesize::
+        The number of threads to run when synthesizing events for existing processes.
+        By default, the number of threads equals to the number of online CPUs.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index c1e3288a2dfb..d53bea6bd571 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -37,7 +37,7 @@ OPTIONS
 --expr::
 --event::
         List of syscalls and other perf events (tracepoints, HW cache events,
-        etc) to show.
+        etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
         See 'perf list' for a complete list of events.
         Prefixing with ! shows all syscalls but the ones specified.  You may
         need to escape it.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index de8b39dda7b8..e90c59c6d815 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -398,6 +398,11 @@ struct auxtrace_error_event {
         char msg[MAX_AUXTRACE_ERROR_MSG];
 };
 
+        PERF_RECORD_HEADER_FEATURE              = 80,
+
+Describes a header feature. These are records used in pipe-mode that
+contain information that otherwise would be in perf.data file's header.
+
 Event types
 
 Define the event attributes with their IDs.
@@ -422,8 +427,9 @@ struct perf_pipe_file_header {
 };
 
 The information about attrs, data, and event_types is instead in the
-synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and
-PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode.
+synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA,
+PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE
+that are generated by perf record in pipe-mode.
 
 
 References:
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a29da46d180f..627b7cada144 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,34 +1,8 @@
 tools/perf
-tools/arch/alpha/include/asm/barrier.h
-tools/arch/arm/include/asm/barrier.h
-tools/arch/arm64/include/asm/barrier.h
-tools/arch/ia64/include/asm/barrier.h
-tools/arch/mips/include/asm/barrier.h
-tools/arch/powerpc/include/asm/barrier.h
-tools/arch/s390/include/asm/barrier.h
-tools/arch/sh/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier_32.h
-tools/arch/sparc/include/asm/barrier_64.h
-tools/arch/tile/include/asm/barrier.h
-tools/arch/x86/include/asm/barrier.h
-tools/arch/x86/include/asm/cmpxchg.h
-tools/arch/x86/include/asm/cpufeatures.h
-tools/arch/x86/include/asm/disabled-features.h
-tools/arch/x86/include/asm/required-features.h
-tools/arch/x86/include/uapi/asm/svm.h
-tools/arch/x86/include/uapi/asm/vmx.h
-tools/arch/x86/include/uapi/asm/kvm.h
-tools/arch/x86/include/uapi/asm/kvm_perf.h
-tools/arch/x86/lib/memcpy_64.S
-tools/arch/x86/lib/memset_64.S
-tools/arch/s390/include/uapi/asm/kvm_perf.h
-tools/arch/s390/include/uapi/asm/sie.h
-tools/arch/xtensa/include/asm/barrier.h
+tools/arch
 tools/scripts
 tools/build
-tools/arch/x86/include/asm/atomic.h
-tools/arch/x86/include/asm/rmwcc.h
+tools/include
 tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
@@ -42,52 +16,3 @@ tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
-tools/include/asm/alternative-asm.h
-tools/include/asm/atomic.h
-tools/include/asm/barrier.h
-tools/include/asm/bug.h
-tools/include/asm-generic/atomic-gcc.h
-tools/include/asm-generic/barrier.h
-tools/include/asm-generic/bitops/arch_hweight.h
-tools/include/asm-generic/bitops/atomic.h
-tools/include/asm-generic/bitops/const_hweight.h
-tools/include/asm-generic/bitops/__ffs.h
-tools/include/asm-generic/bitops/__ffz.h
-tools/include/asm-generic/bitops/__fls.h
-tools/include/asm-generic/bitops/find.h
-tools/include/asm-generic/bitops/fls64.h
-tools/include/asm-generic/bitops/fls.h
-tools/include/asm-generic/bitops/hweight.h
-tools/include/asm-generic/bitops.h
-tools/include/linux/atomic.h
-tools/include/linux/bitops.h
-tools/include/linux/compiler.h
-tools/include/linux/compiler-gcc.h
-tools/include/linux/coresight-pmu.h
-tools/include/linux/bug.h
-tools/include/linux/filter.h
-tools/include/linux/hash.h
-tools/include/linux/kernel.h
-tools/include/linux/list.h
-tools/include/linux/log2.h
-tools/include/uapi/asm-generic/mman-common.h
-tools/include/uapi/asm-generic/mman.h
-tools/include/uapi/linux/bpf.h
-tools/include/uapi/linux/bpf_common.h
-tools/include/uapi/linux/fcntl.h
-tools/include/uapi/linux/hw_breakpoint.h
-tools/include/uapi/linux/mman.h
-tools/include/uapi/linux/perf_event.h
-tools/include/uapi/linux/stat.h
-tools/include/linux/poison.h
-tools/include/linux/rbtree.h
-tools/include/linux/rbtree_augmented.h
-tools/include/linux/refcount.h
-tools/include/linux/string.h
-tools/include/linux/stringify.h
-tools/include/linux/types.h
-tools/include/linux/err.h
-tools/include/linux/bitmap.h
-tools/include/linux/time64.h
-tools/arch/*/include/uapi/asm/mman.h
-tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 32a64e619028..225454416ed5 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # This is a simple wrapper Makefile that calls the main Makefile.perf
 # with a -j option to do parallel builds
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index bdf0e87f9b29..ed65e82f034e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -35,7 +35,7 @@ ifeq ($(SRCARCH),x86)
   ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
-    LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
+    LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma
     $(call detected,CONFIG_X86_64)
   else
     LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
@@ -53,6 +53,10 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(ARCH),s390)
+  NO_PERF_REGS := 0
+endif
+
 ifeq ($(NO_PERF_REGS),0)
   $(call detected,CONFIG_PERF_REGS)
 endif
@@ -61,7 +65,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc s390))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -103,8 +107,12 @@ ifdef LIBDW_DIR
   LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
   LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
 endif
+DWARFLIBS := -ldw
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+  DWARFLIBS += -lelf -lebl -ldl -lz -llzma -lbz2
+endif
 FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 
 # for linking with debug library, run like:
 # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
@@ -144,7 +152,7 @@ ifndef DEBUG
 endif
 
 ifeq ($(DEBUG),0)
-ifeq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
@@ -180,7 +188,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  ifeq ($(CC), clang)
+  ifeq ($(CC_NO_CLANG), 1)
     PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   endif
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
@@ -330,6 +338,11 @@ ifeq ($(feature-sched_getcpu), 1)
   CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT
 endif
 
+ifeq ($(feature-setns), 1)
+  CFLAGS += -DHAVE_SETNS_SUPPORT
+  $(call detected,CONFIG_SETNS)
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
@@ -360,10 +373,6 @@ ifndef NO_LIBELF
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
-      DWARFLIBS := -ldw
-      ifeq ($(findstring -static,${LDFLAGS}),-static)
-        DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
-      endif
       EXTLIBS += ${DWARFLIBS}
       $(call detected,CONFIG_DWARF)
     endif # PERF_HAVE_DWARF_REGS
@@ -500,6 +509,10 @@ ifndef NO_LOCAL_LIBUNWIND
   EXTLIBS += $(LIBUNWIND_LIBS)
   LDFLAGS += $(LIBUNWIND_LIBS)
 endif
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+  # gcc -static links libgcc_eh which contans piece of libunwind
+  LIBUNWIND_LDFLAGS += -Wl,--allow-multiple-definition
+endif
 
 ifndef NO_LIBUNWIND
   CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5008f51a08a2..68cf1360a3f3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -33,6 +33,11 @@ include ../scripts/utilities.mak
 #
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
 #
+# Define EXCLUDE_EXTLIBS=-lmylib to exclude libmylib from the auto-generated
+# EXTLIBS.
+#
+# Define EXTRA_PERFLIBS to pass extra libraries to PERFLIBS.
+#
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
 #
 # Define WERROR=0 to disable treating any warnings as errors.
@@ -159,8 +164,8 @@ LN      = ln -f
 MKDIR   = mkdir
 FIND    = find
 INSTALL = install
-FLEX    = flex
-BISON   = bison
+FLEX    ?= flex
+BISON   ?= bison
 STRIP   = strip
 AWK     = awk
 
@@ -168,7 +173,7 @@ AWK     = awk
 # non-config cases
 config := 1
 
-NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
+NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -235,7 +240,7 @@ endif
 ifeq ($(FEATURES_DUMP),)
 FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
 else
-FEATURE_DUMP_EXPORT := $(FEATURES_DUMP)
+FEATURE_DUMP_EXPORT := $(realpath $(FEATURES_DUMP))
 endif
 
 export prefix bindir sharedir sysconfdir DESTDIR
@@ -274,7 +279,13 @@ LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
 LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
-LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+
+#
+# The static build has no dynsym table, so this does not work for
+# static build. Looks like linker starts to scream about that now
+# (in Fedora 26) so we need to switch it off for static build.
+DYNAMIC_LIST_LDFLAGS               = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = $(if $(findstring -static,$(LDFLAGS)),,$(DYNAMIC_LIST_LDFLAGS))
 
 LIBAPI = $(API_PATH)libapi.a
 export LIBAPI
@@ -352,7 +363,8 @@ ifdef ASCIIDOC8
   export ASCIIDOC8
 endif
 
-LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
+EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS))
+LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ifeq ($(USE_CLANG), 1)
   CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization
@@ -375,6 +387,81 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+beauty_outdir := $(OUTPUT)trace/beauty/generated
+beauty_ioctl_outdir := $(beauty_outdir)/ioctl
+drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
+drm_hdr_dir := $(srctree)/tools/include/uapi/drm
+drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
+
+$(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
+        $(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
+
+pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
+asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
+pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+
+$(pkey_alloc_access_rights_array): $(asm_generic_hdr_dir)/mman-common.h $(pkey_alloc_access_rights_tbl)
+        $(Q)$(SHELL) '$(pkey_alloc_access_rights_tbl)' $(asm_generic_hdr_dir) > $@
+
+sndrv_ctl_ioctl_array := $(beauty_ioctl_outdir)/sndrv_ctl_ioctl_array.c
+sndrv_ctl_hdr_dir := $(srctree)/tools/include/uapi/sound
+sndrv_ctl_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+
+$(sndrv_ctl_ioctl_array): $(sndrv_ctl_hdr_dir)/asound.h $(sndrv_ctl_ioctl_tbl)
+        $(Q)$(SHELL) '$(sndrv_ctl_ioctl_tbl)' $(sndrv_ctl_hdr_dir) > $@
+
+sndrv_pcm_ioctl_array := $(beauty_ioctl_outdir)/sndrv_pcm_ioctl_array.c
+sndrv_pcm_hdr_dir := $(srctree)/tools/include/uapi/sound
+sndrv_pcm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+
+$(sndrv_pcm_ioctl_array): $(sndrv_pcm_hdr_dir)/asound.h $(sndrv_pcm_ioctl_tbl)
+        $(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(sndrv_pcm_hdr_dir) > $@
+
+kcmp_type_array := $(beauty_outdir)/kcmp_type_array.c
+kcmp_hdr_dir := $(srctree)/tools/include/uapi/linux/
+kcmp_type_tbl := $(srctree)/tools/perf/trace/beauty/kcmp_type.sh
+
+$(kcmp_type_array): $(kcmp_hdr_dir)/kcmp.h $(kcmp_type_tbl)
+        $(Q)$(SHELL) '$(kcmp_type_tbl)' $(kcmp_hdr_dir) > $@
+
+kvm_ioctl_array := $(beauty_ioctl_outdir)/kvm_ioctl_array.c
+kvm_hdr_dir := $(srctree)/tools/include/uapi/linux
+kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
+
+$(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
+        $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
+
+vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
+vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
+vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+
+$(vhost_virtio_ioctl_array): $(vhost_virtio_hdr_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
+        $(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(vhost_virtio_hdr_dir) > $@
+
+perf_ioctl_array := $(beauty_ioctl_outdir)/perf_ioctl_array.c
+perf_hdr_dir := $(srctree)/tools/include/uapi/linux
+perf_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/perf_ioctl.sh
+
+$(perf_ioctl_array): $(perf_hdr_dir)/perf_event.h $(perf_ioctl_tbl)
+        $(Q)$(SHELL) '$(perf_ioctl_tbl)' $(perf_hdr_dir) > $@
+
+madvise_behavior_array := $(beauty_outdir)/madvise_behavior_array.c
+madvise_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
+madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
+
+$(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
+        $(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
+
+prctl_option_array := $(beauty_outdir)/prctl_option_array.c
+prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
+prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
+
+$(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
+        $(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@
+
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
@@ -469,7 +556,16 @@ endif
 __build-dir = $(subst $(OUTPUT),,$(dir $@))
 build-dir   = $(if $(__build-dir),$(__build-dir),.)
 
-prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders
+prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \
+        $(pkey_alloc_access_rights_array) \
+        $(sndrv_pcm_ioctl_array) \
+        $(sndrv_ctl_ioctl_array) \
+        $(kcmp_type_array) \
+        $(kvm_ioctl_array) \
+        $(vhost_virtio_ioctl_array) \
+        $(madvise_behavior_array) \
+        $(perf_ioctl_array) \
+        $(prctl_option_array)
 
 $(OUTPUT)%.o: %.c prepare FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@@ -512,7 +608,7 @@ $(LIBJVMTI_IN): FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti
 
 $(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN)
-        $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $< -lelf -lrt
+        $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $<
 endif
 
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
@@ -703,7 +799,11 @@ install-tests: all install-gtk
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
                 $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
-                $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+                $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+                $(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
+                $(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'
 
 install-bin: install-tools install-tests install-traceevent-plugins
 
@@ -726,7 +826,10 @@ config-clean:
         $(call QUIET_CLEAN, config)
         $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
+python-clean:
+        $(python-clean)
+
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean python-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
         $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
         $(Q)$(RM) $(OUTPUT).config-detected
@@ -734,9 +837,18 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
                 $(OUTPUT)util/intel-pt-decoder/inat-tables.c \
                 $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
-                $(OUTPUT)pmu-events/pmu-events.c
+                $(OUTPUT)pmu-events/pmu-events.c \
+                $(OUTPUT)$(madvise_behavior_array) \
+                $(OUTPUT)$(drm_ioctl_array) \
+                $(OUTPUT)$(pkey_alloc_access_rights_array) \
+                $(OUTPUT)$(sndrv_ctl_ioctl_array) \
+                $(OUTPUT)$(sndrv_pcm_ioctl_array) \
+                $(OUTPUT)$(kvm_ioctl_array) \
+                $(OUTPUT)$(kcmp_type_array) \
+                $(OUTPUT)$(vhost_virtio_ioctl_array) \
+                $(OUTPUT)$(perf_ioctl_array) \
+                $(OUTPUT)$(prctl_option_array)
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
-        $(python-clean)
 
 #
 # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index 1ce0872b1726..f64516d5b23e 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -23,7 +25,7 @@ static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const c
         return ops;
 }
 
-static int arm__annotate_init(struct arch *arch)
+static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         struct arm_annotate *arm;
         int err;
diff --git a/tools/perf/arch/arm/include/dwarf-regs-table.h b/tools/perf/arch/arm/include/dwarf-regs-table.h
index f298d034c37b..5a45046fab72 100644
--- a/tools/perf/arch/arm/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
index f619c9c5a4bf..ed20e0253e25 100644
--- a/tools/perf/arch/arm/include/perf_regs.h
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_REGS_H
 #define ARCH_PERF_REGS_H
 
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 62eff847f91c..8cb347760233 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "perf_regs.h"
 #include "thread.h"
diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S
index e09e983946fe..6e2495cc4517 100644
--- a/tools/perf/arch/arm/tests/regs_load.S
+++ b/tools/perf/arch/arm/tests/regs_load.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 
 #define R0 0x00
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 7ce3d1a25133..fbfc055d3f4d 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -266,6 +266,32 @@ static u64 cs_etm_get_config(struct auxtrace_record *itr)
         return config;
 }
 
+#ifndef BIT
+#define BIT(N) (1UL << (N))
+#endif
+
+static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
+{
+        u64 config = 0;
+        u64 config_opts = 0;
+
+        /*
+         * The perf event variable config bits represent both
+         * the command line options and register programming
+         * bits in ETMv3/PTM. For ETMv4 we must remap options
+         * to real bits
+         */
+        config_opts = cs_etm_get_config(itr);
+        if (config_opts & BIT(ETM_OPT_CYCACC))
+                config |= BIT(ETM4_CFG_BIT_CYCACC);
+        if (config_opts & BIT(ETM_OPT_TS))
+                config |= BIT(ETM4_CFG_BIT_TS);
+        if (config_opts & BIT(ETM_OPT_RETSTK))
+                config |= BIT(ETM4_CFG_BIT_RETSTK);
+
+        return config;
+}
+
 static size_t
 cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
                       struct perf_evlist *evlist __maybe_unused)
@@ -363,7 +389,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
                 magic = __perf_cs_etmv4_magic;
                 /* Get trace configuration register */
                 info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
-                                                cs_etm_get_config(itr);
+                                                cs_etmv4_get_config(itr);
                 /* Get traceID from the framework */
                 info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
                                                 coresight_get_trace_id(cpu);
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
index bacfa00fca39..36ba4c69c3c5 100644
--- a/tools/perf/arch/arm/util/unwind-libdw.c
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 62c397ed3d97..3a550225dfaf 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <errno.h>
 #include <libunwind.h>
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index eebe1ec9d2ee..91de4860faad 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 8f1908756cb6..6688977e4ac7 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -25,7 +27,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
         return ops;
 }
 
-static int arm64__annotate_init(struct arch *arch)
+static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         struct arm64_annotate *arm;
         int err;
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 36e375f5a211..177b2855f797 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 4e5af27e3fbf..baaa5e64a3fb 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_REGS_H
 #define ARCH_PERF_REGS_H
 
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
index cf04a4c91c59..e907f0f4c20c 100644
--- a/tools/perf/arch/arm64/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "perf_regs.h"
 #include "thread.h"
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
index 025b46e579a6..07042511dca9 100644
--- a/tools/perf/arch/arm64/tests/regs_load.S
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 
 .text
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index b415dfdbccca..002520d4036b 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 
 #ifndef REMOTE_UNWIND_LIBUNWIND
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 6b40e9f01740..8c0cfeb55f8e 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <sys/utsname.h>
 #include "common.h"
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
index 6b01c736b7d9..a1546509ad24 100644
--- a/tools/perf/arch/common.h
+++ b/tools/perf/arch/common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_COMMON_H
 #define ARCH_PERF_COMMON_H
 
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index cc3930904d68..42dab7c8f508 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index 3c4004db81b9..a3f423c27cae 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -1,3 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+
 static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name)
 {
         int i;
@@ -46,7 +49,7 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con
         return ops;
 }
 
-static int powerpc__annotate_init(struct arch *arch)
+static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         if (!arch->initialized) {
                 arch->initialized = true;
diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h
index 84d8dedef2ed..1c7be75cbc78 100644
--- a/tools/perf/arch/powerpc/include/arch-tests.h
+++ b/tools/perf/arch/powerpc/include/arch-tests.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
diff --git a/tools/perf/arch/powerpc/include/dwarf-regs-table.h b/tools/perf/arch/powerpc/include/dwarf-regs-table.h
index db4730f5585c..66dc015a733d 100644
--- a/tools/perf/arch/powerpc/include/dwarf-regs-table.h
+++ b/tools/perf/arch/powerpc/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index c12f4e804f66..00e37b106913 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_REGS_H
 #define ARCH_PERF_REGS_H
 
diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c
index e24f46241f40..8c3fbd4af817 100644
--- a/tools/perf/arch/powerpc/tests/arch-tests.c
+++ b/tools/perf/arch/powerpc/tests/arch-tests.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "tests/tests.h"
 #include "arch-tests.h"
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
index 0bac3137ccbd..30cbbd6d5be0 100644
--- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "perf_regs.h"
 #include "thread.h"
diff --git a/tools/perf/arch/powerpc/tests/regs_load.S b/tools/perf/arch/powerpc/tests/regs_load.S
index d76c9a32f327..36a20b0033f9 100644
--- a/tools/perf/arch/powerpc/tests/regs_load.S
+++ b/tools/perf/arch/powerpc/tests/regs_load.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 
 /* Offset is based on macros from arch/powerpc/include/uapi/asm/ptrace.h. */
diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h
index 0dd6b7f2d44f..54cfa0530e86 100644
--- a/tools/perf/arch/powerpc/util/book3s_hcalls.h
+++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H
 #define ARCH_PERF_BOOK3S_HV_HCALLS_H
 
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
index e68ba2da8970..853b95d1e139 100644
--- a/tools/perf/arch/powerpc/util/book3s_hv_exits.h
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_BOOK3S_HV_EXITS_H
 #define ARCH_PERF_BOOK3S_HV_EXITS_H
 
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 9aaa6f5a9347..7a4cf80c207a 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
index 249723f0e6a9..596ad6aedaac 100644
--- a/tools/perf/arch/powerpc/util/kvm-stat.c
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include "util/kvm-stat.h"
 #include "util/parse-events.h"
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index f860dc411f69..ec50939b0418 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <string.h>
 #include <regex.h>
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index bf9a2594572c..9c4e23d8c8ce 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -126,7 +126,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
         struct rb_node *tmp;
         int i = 0;
 
-        map = get_target_map(pev->target, pev->uprobes);
+        map = get_target_map(pev->target, pev->nsi, pev->uprobes);
         if (!map || map__load(map) < 0)
                 return;
 
diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c
index 3a24b3c43273..7a1f05ef2fc0 100644
--- a/tools/perf/arch/powerpc/util/unwind-libdw.c
+++ b/tools/perf/arch/powerpc/util/unwind-libdw.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 745b4b1b8b21..e0e466c650df 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -1,3 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
         struct ins_ops *ops = NULL;
@@ -19,7 +22,7 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
         return ops;
 }
 
-static int s390__annotate_init(struct arch *arch)
+static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         if (!arch->initialized) {
                 arch->initialized = true;
diff --git a/tools/perf/arch/s390/include/dwarf-regs-table.h b/tools/perf/arch/s390/include/dwarf-regs-table.h
index 9da74a933bd6..671553525f41 100644
--- a/tools/perf/arch/s390/include/dwarf-regs-table.h
+++ b/tools/perf/arch/s390/include/dwarf-regs-table.h
@@ -1,8 +1,72 @@
-#ifdef DEFINE_DWARF_REGSTR_TABLE
-/* This is included in perf/util/dwarf-regs.c */
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef S390_DWARF_REGS_TABLE_H
+#define S390_DWARF_REGS_TABLE_H
 
-static const char * const s390_regstr_tbl[] = {
+#define REG_DWARFNUM_NAME(reg, idx)     [idx] = "%" #reg
+
+/*
+ * For reference, see DWARF register mapping:
+ * http://refspecs.linuxfoundation.org/ELF/zSeries/lzsabi0_s390/x1542.html
+ */
+static const char * const s390_dwarf_regs[] = {
         "%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
         "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+        REG_DWARFNUM_NAME(f0, 16),
+        REG_DWARFNUM_NAME(f1, 20),
+        REG_DWARFNUM_NAME(f2, 17),
+        REG_DWARFNUM_NAME(f3, 21),
+        REG_DWARFNUM_NAME(f4, 18),
+        REG_DWARFNUM_NAME(f5, 22),
+        REG_DWARFNUM_NAME(f6, 19),
+        REG_DWARFNUM_NAME(f7, 23),
+        REG_DWARFNUM_NAME(f8, 24),
+        REG_DWARFNUM_NAME(f9, 28),
+        REG_DWARFNUM_NAME(f10, 25),
+        REG_DWARFNUM_NAME(f11, 29),
+        REG_DWARFNUM_NAME(f12, 26),
+        REG_DWARFNUM_NAME(f13, 30),
+        REG_DWARFNUM_NAME(f14, 27),
+        REG_DWARFNUM_NAME(f15, 31),
+        REG_DWARFNUM_NAME(c0, 32),
+        REG_DWARFNUM_NAME(c1, 33),
+        REG_DWARFNUM_NAME(c2, 34),
+        REG_DWARFNUM_NAME(c3, 35),
+        REG_DWARFNUM_NAME(c4, 36),
+        REG_DWARFNUM_NAME(c5, 37),
+        REG_DWARFNUM_NAME(c6, 38),
+        REG_DWARFNUM_NAME(c7, 39),
+        REG_DWARFNUM_NAME(c8, 40),
+        REG_DWARFNUM_NAME(c9, 41),
+        REG_DWARFNUM_NAME(c10, 42),
+        REG_DWARFNUM_NAME(c11, 43),
+        REG_DWARFNUM_NAME(c12, 44),
+        REG_DWARFNUM_NAME(c13, 45),
+        REG_DWARFNUM_NAME(c14, 46),
+        REG_DWARFNUM_NAME(c15, 47),
+        REG_DWARFNUM_NAME(a0, 48),
+        REG_DWARFNUM_NAME(a1, 49),
+        REG_DWARFNUM_NAME(a2, 50),
+        REG_DWARFNUM_NAME(a3, 51),
+        REG_DWARFNUM_NAME(a4, 52),
+        REG_DWARFNUM_NAME(a5, 53),
+        REG_DWARFNUM_NAME(a6, 54),
+        REG_DWARFNUM_NAME(a7, 55),
+        REG_DWARFNUM_NAME(a8, 56),
+        REG_DWARFNUM_NAME(a9, 57),
+        REG_DWARFNUM_NAME(a10, 58),
+        REG_DWARFNUM_NAME(a11, 59),
+        REG_DWARFNUM_NAME(a12, 60),
+        REG_DWARFNUM_NAME(a13, 61),
+        REG_DWARFNUM_NAME(a14, 62),
+        REG_DWARFNUM_NAME(a15, 63),
+        REG_DWARFNUM_NAME(pswm, 64),
+        REG_DWARFNUM_NAME(pswa, 65),
 };
-#endif
+
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+#define s390_regstr_tbl s390_dwarf_regs
+
+#endif  /* DEFINE_DWARF_REGSTR_TABLE */
+#endif  /* S390_DWARF_REGS_TABLE_H */
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
new file mode 100644
index 000000000000..d2df54a6bc5a
--- /dev/null
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -0,0 +1,95 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <../../../../arch/s390/include/uapi/asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK ((1ULL << PERF_REG_S390_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_S390_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
+
+#define PERF_REG_IP PERF_REG_S390_PC
+#define PERF_REG_SP PERF_REG_S390_R15
+
+static inline const char *perf_reg_name(int id)
+{
+        switch (id) {
+        case PERF_REG_S390_R0:
+                return "R0";
+        case PERF_REG_S390_R1:
+                return "R1";
+        case PERF_REG_S390_R2:
+                return "R2";
+        case PERF_REG_S390_R3:
+                return "R3";
+        case PERF_REG_S390_R4:
+                return "R4";
+        case PERF_REG_S390_R5:
+                return "R5";
+        case PERF_REG_S390_R6:
+                return "R6";
+        case PERF_REG_S390_R7:
+                return "R7";
+        case PERF_REG_S390_R8:
+                return "R8";
+        case PERF_REG_S390_R9:
+                return "R9";
+        case PERF_REG_S390_R10:
+                return "R10";
+        case PERF_REG_S390_R11:
+                return "R11";
+        case PERF_REG_S390_R12:
+                return "R12";
+        case PERF_REG_S390_R13:
+                return "R13";
+        case PERF_REG_S390_R14:
+                return "R14";
+        case PERF_REG_S390_R15:
+                return "R15";
+        case PERF_REG_S390_FP0:
+                return "FP0";
+        case PERF_REG_S390_FP1:
+                return "FP1";
+        case PERF_REG_S390_FP2:
+                return "FP2";
+        case PERF_REG_S390_FP3:
+                return "FP3";
+        case PERF_REG_S390_FP4:
+                return "FP4";
+        case PERF_REG_S390_FP5:
+                return "FP5";
+        case PERF_REG_S390_FP6:
+                return "FP6";
+        case PERF_REG_S390_FP7:
+                return "FP7";
+        case PERF_REG_S390_FP8:
+                return "FP8";
+        case PERF_REG_S390_FP9:
+                return "FP9";
+        case PERF_REG_S390_FP10:
+                return "FP10";
+        case PERF_REG_S390_FP11:
+                return "FP11";
+        case PERF_REG_S390_FP12:
+                return "FP12";
+        case PERF_REG_S390_FP13:
+                return "FP13";
+        case PERF_REG_S390_FP14:
+                return "FP14";
+        case PERF_REG_S390_FP15:
+                return "FP15";
+        case PERF_REG_S390_MASK:
+                return "MASK";
+        case PERF_REG_S390_PC:
+                return "PC";
+        default:
+                return NULL;
+        }
+
+        return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 5bd7b9260cc0..4a233683c684 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,5 +2,8 @@ libperf-y += header.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-y += machine.o
+
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
new file mode 100644
index 000000000000..6cb48e4cffd9
--- /dev/null
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -0,0 +1,118 @@
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../../util/evlist.h"
+#include "../../util/auxtrace.h"
+#include "../../util/evsel.h"
+
+#define PERF_EVENT_CPUM_SF              0xB0000 /* Event: Basic-sampling */
+#define PERF_EVENT_CPUM_SF_DIAG         0xBD000 /* Event: Combined-sampling */
+#define DEFAULT_AUX_PAGES               128
+#define DEFAULT_FREQ                    4000
+
+static void cpumsf_free(struct auxtrace_record *itr)
+{
+        free(itr);
+}
+
+static size_t cpumsf_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+                                    struct perf_evlist *evlist __maybe_unused)
+{
+        return 0;
+}
+
+static int
+cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused,
+                 struct perf_session *session __maybe_unused,
+                 struct auxtrace_info_event *auxtrace_info __maybe_unused,
+                 size_t priv_size __maybe_unused)
+{
+        return 0;
+}
+
+static unsigned long
+cpumsf_reference(struct auxtrace_record *itr __maybe_unused)
+{
+        return 0;
+}
+
+static int
+cpumsf_recording_options(struct auxtrace_record *ar __maybe_unused,
+                         struct perf_evlist *evlist __maybe_unused,
+                         struct record_opts *opts)
+{
+        unsigned int factor = 1;
+        unsigned int pages;
+
+        opts->full_auxtrace = true;
+
+        /*
+         * The AUX buffer size should be set properly to avoid
+         * overflow of samples if it is not set explicitly.
+         * DEFAULT_AUX_PAGES is an proper size when sampling frequency
+         * is DEFAULT_FREQ. It is expected to hold about 1/2 second
+         * of sampling data. The size used for AUX buffer will scale
+         * according to the specified frequency and DEFAULT_FREQ.
+         */
+        if (!opts->auxtrace_mmap_pages) {
+                if (opts->user_freq != UINT_MAX)
+                        factor = (opts->user_freq + DEFAULT_FREQ
+                                  - 1) / DEFAULT_FREQ;
+                pages = DEFAULT_AUX_PAGES * factor;
+                opts->auxtrace_mmap_pages = roundup_pow_of_two(pages);
+        }
+
+        return 0;
+}
+
+static int
+cpumsf_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+                              struct record_opts *opts __maybe_unused,
+                              const char *str __maybe_unused)
+{
+        return 0;
+}
+
+/*
+ * auxtrace_record__init is called when perf record
+ * check if the event really need auxtrace
+ */
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+                                              int *err)
+{
+        struct auxtrace_record *aux;
+        struct perf_evsel *pos;
+        int diagnose = 0;
+
+        if (evlist->nr_entries == 0)
+                return NULL;
+
+        evlist__for_each_entry(evlist, pos) {
+                if (pos->attr.config == PERF_EVENT_CPUM_SF_DIAG) {
+                        diagnose = 1;
+                        break;
+                }
+        }
+
+        if (!diagnose)
+                return NULL;
+
+        /* sampling in diagnose mode. alloc aux buffer */
+        aux = zalloc(sizeof(*aux));
+        if (aux == NULL) {
+                *err = -ENOMEM;
+                return NULL;
+        }
+
+        aux->parse_snapshot_options = cpumsf_parse_snapshot_options;
+        aux->recording_options = cpumsf_recording_options;
+        aux->info_priv_size = cpumsf_info_priv_size;
+        aux->info_fill = cpumsf_info_fill;
+        aux->free = cpumsf_free;
+        aux->reference = cpumsf_reference;
+
+        return aux;
+}
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index 0469df02ee62..f47576ce13ea 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Mapping of DWARF debug register numbers into register names.
  *
@@ -8,15 +9,10 @@
 
 #include <stddef.h>
 #include <dwarf-regs.h>
-
-#define NUM_GPRS 16
-
-static const char *gpr_names[NUM_GPRS] = {
-        "%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
-        "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
-};
+#include <linux/kernel.h>
+#include "dwarf-regs-table.h"
 
 const char *get_arch_regstr(unsigned int n)
 {
-        return (n >= NUM_GPRS) ? NULL : gpr_names[n];
+        return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
 }
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index b9a95a1a8e69..0b2054007314 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
new file mode 100644
index 000000000000..387c698cdd1b
--- /dev/null
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -0,0 +1,63 @@
+#include <linux/kernel.h>
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+#include "dwarf-regs-table.h"
+
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+        struct unwind_info *ui = arg;
+        struct regs_dump *user_regs = &ui->sample->user_regs;
+        Dwarf_Word dwarf_regs[ARRAY_SIZE(s390_dwarf_regs)];
+
+#define REG(r) ({                                               \
+        Dwarf_Word val = 0;                                     \
+        perf_reg_value(&val, user_regs, PERF_REG_S390_##r);     \
+        val;                                                    \
+})
+        /*
+         * For DWARF register mapping details,
+         * see also perf/arch/s390/include/dwarf-regs-table.h
+         */
+        dwarf_regs[0]  = REG(R0);
+        dwarf_regs[1]  = REG(R1);
+        dwarf_regs[2]  = REG(R2);
+        dwarf_regs[3]  = REG(R3);
+        dwarf_regs[4]  = REG(R4);
+        dwarf_regs[5]  = REG(R5);
+        dwarf_regs[6]  = REG(R6);
+        dwarf_regs[7]  = REG(R7);
+        dwarf_regs[8]  = REG(R8);
+        dwarf_regs[9]  = REG(R9);
+        dwarf_regs[10] = REG(R10);
+        dwarf_regs[11] = REG(R11);
+        dwarf_regs[12] = REG(R12);
+        dwarf_regs[13] = REG(R13);
+        dwarf_regs[14] = REG(R14);
+        dwarf_regs[15] = REG(R15);
+
+        dwarf_regs[16] = REG(FP0);
+        dwarf_regs[17] = REG(FP2);
+        dwarf_regs[18] = REG(FP4);
+        dwarf_regs[19] = REG(FP6);
+        dwarf_regs[20] = REG(FP1);
+        dwarf_regs[21] = REG(FP3);
+        dwarf_regs[22] = REG(FP5);
+        dwarf_regs[23] = REG(FP7);
+        dwarf_regs[24] = REG(FP8);
+        dwarf_regs[25] = REG(FP10);
+        dwarf_regs[26] = REG(FP12);
+        dwarf_regs[27] = REG(FP14);
+        dwarf_regs[28] = REG(FP9);
+        dwarf_regs[29] = REG(FP11);
+        dwarf_regs[30] = REG(FP13);
+        dwarf_regs[31] = REG(FP15);
+
+        dwarf_regs[64] = REG(MASK);
+        dwarf_regs[65] = REG(PC);
+
+        dwfl_thread_state_register_pc(thread, dwarf_regs[65]);
+        return dwfl_thread_state_registers(thread, 0, 32, dwarf_regs);
+}
diff --git a/tools/perf/arch/sh/include/dwarf-regs-table.h b/tools/perf/arch/sh/include/dwarf-regs-table.h
index 3a2deaf3dab4..900e69619970 100644
--- a/tools/perf/arch/sh/include/dwarf-regs-table.h
+++ b/tools/perf/arch/sh/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/arch/sparc/include/dwarf-regs-table.h b/tools/perf/arch/sparc/include/dwarf-regs-table.h
index 12c07619002c..35ede84a6b0d 100644
--- a/tools/perf/arch/sparc/include/dwarf-regs-table.h
+++ b/tools/perf/arch/sparc/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 6c9211b18ec0..d74eaa7aa927 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
@@ -20,7 +21,7 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 $(header): $(sys)/syscall_64.tbl $(systbl)
         @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
         (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
-        || echo "Warning: x86_64's syscall_64.tbl differs from kernel" >&2 )) || true
+        || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
         $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index c1625f256df3..5bd1ba8c0282 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 static struct ins x86__instructions[] = {
         { .name = "add",        .ops = &mov_ops,  },
         { .name = "addl",       .ops = &mov_ops,  },
@@ -76,3 +77,63 @@ static struct ins x86__instructions[] = {
         { .name = "xbeginq",    .ops = &jump_ops, },
         { .name = "retq",       .ops = &ret_ops,  },
 };
+
+static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
+                              const char *ins2)
+{
+        if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp"))
+                return false;
+
+        if (arch->model == 0x1e) {
+                /* Nehalem */
+                if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) ||
+                     strstr(ins1, "test")) {
+                        return true;
+                }
+        } else {
+                /* Newer platform */
+                if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) ||
+                     strstr(ins1, "test") ||
+                     strstr(ins1, "add") ||
+                     strstr(ins1, "sub") ||
+                     strstr(ins1, "and") ||
+                     strstr(ins1, "inc") ||
+                     strstr(ins1, "dec")) {
+                        return true;
+                }
+        }
+
+        return false;
+}
+
+static int x86__cpuid_parse(struct arch *arch, char *cpuid)
+{
+        unsigned int family, model, stepping;
+        int ret;
+
+        /*
+         * cpuid = "GenuineIntel,family,model,stepping"
+         */
+        ret = sscanf(cpuid, "%*[^,],%u,%u,%u", &family, &model, &stepping);
+        if (ret == 3) {
+                arch->family = family;
+                arch->model = model;
+                return 0;
+        }
+
+        return -1;
+}
+
+static int x86__annotate_init(struct arch *arch, char *cpuid)
+{
+        int err = 0;
+
+        if (arch->initialized)
+                return 0;
+
+        if (cpuid)
+                err = x86__cpuid_parse(arch, cpuid);
+
+        arch->initialized = true;
+        return err;
+}
diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
index 49a18b9ad9cf..029a72c20b19 100755
--- a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
+++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 in="$1"
 arch="$2"
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index b48de2f5813c..c1bd979b957b 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -1,11 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
+#include <linux/compiler.h>
+struct test;
+
 /* Tests */
-int test__rdpmc(int subtest);
-int test__perf_time_to_tsc(int subtest);
-int test__insn_x86(int subtest);
-int test__intel_cqm_count_nmi_context(int subtest);
+int test__rdpmc(struct test *test __maybe_unused, int subtest);
+int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
+int test__insn_x86(struct test *test __maybe_unused, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/include/dwarf-regs-table.h b/tools/perf/arch/x86/include/dwarf-regs-table.h
index 9b5e5cbb4209..b9bd5dc9d4c0 100644
--- a/tools/perf/arch/x86/include/dwarf-regs-table.h
+++ b/tools/perf/arch/x86/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 7df517acfef8..7f6d538f8a89 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ARCH_PERF_REGS_H
 #define ARCH_PERF_REGS_H
 
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index cbb7e978166b..8e2c5a38c3b9 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -5,4 +5,3 @@ libperf-y += arch-tests.o
 libperf-y += rdpmc.o
 libperf-y += perf-time-to-tsc.o
 libperf-$(CONFIG_AUXTRACE) += insn-x86.o
-libperf-y += intel-cqm.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 99d66191e56c..cc1802ff5410 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "tests/tests.h"
 #include "arch-tests.h"
@@ -24,10 +25,6 @@ struct test arch_tests[] = {
         },
 #endif
         {
-                .desc = "Intel cqm nmi context read",
-                .func = test__intel_cqm_count_nmi_context,
-        },
-        {
                 .func = NULL,
         },
 
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 7f209ce827bf..95036c7a59e8 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "perf_regs.h"
 #include "thread.h"
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
index 3cbf6fad169f..fab3c6de73fa 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generated by gen-insn-x86-dat.sh and gen-insn-x86-dat.awk
  * from insn-x86-dat-src.c for inclusion by insn-x86.c
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
index aa512fa944dd..c57f34603b9b 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generated by gen-insn-x86-dat.sh and gen-insn-x86-dat.awk
  * from insn-x86-dat-src.c for inclusion by insn-x86.c
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
index 6cdb65d25b79..891415b10984 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * This file contains instructions for testing by the test titled:
  *
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index 08d9b2bc185c..a5d24ae5810d 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 
 #include "debug.h"
@@ -171,7 +172,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64)
  * verbose (-v) option to see all the instructions and whether or not they
  * decoded successfuly.
  */
-int test__insn_x86(int subtest __maybe_unused)
+int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret = 0;
 
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index f9713a71d77e..90a4a8c58a62 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "tests/tests.h"
 #include "perf.h"
 #include "cloexec.h"
@@ -36,7 +37,7 @@ static pid_t spawn(void)
  * the last read counter value to avoid triggering a WARN_ON_ONCE() in
  * smp_call_function_many() caused by sending IPIs from NMI context.
  */
-int test__intel_cqm_count_nmi_context(int subtest __maybe_unused)
+int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_evlist *evlist = NULL;
         struct perf_evsel *evsel = NULL;
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index e3ae9cff2b67..b59678e8c1e2 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <stdio.h>
@@ -37,7 +38,7 @@
  * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
  * supported then then the test passes but " (not supported)" is printed.
  */
-int test__perf_time_to_tsc(int subtest __maybe_unused)
+int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 500cf96db979..7a11f02d6c6c 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <unistd.h>
 #include <stdlib.h>
@@ -154,7 +155,7 @@ out_close:
         return 0;
 }
 
-int test__rdpmc(int subtest __maybe_unused)
+int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int status = 0;
         int wret = 0;
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
index 60875d5c556c..bbe5a0d16e51 100644
--- a/tools/perf/arch/x86/tests/regs_load.S
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 
 #define AX       0
diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c
index 37f92aa39a5d..e2f8034b8973 100644
--- a/tools/perf/arch/x86/util/group.c
+++ b/tools/perf/arch/x86/util/group.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include "api/fs/fs.h"
 #include "util/group.h"
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index a74a48db26f5..33027c5e6f92 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 9535be57033f..db0ba8caf5a2 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -701,6 +701,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                                 perf_evsel__set_sample_bit(switch_evsel, TID);
                                 perf_evsel__set_sample_bit(switch_evsel, TIME);
                                 perf_evsel__set_sample_bit(switch_evsel, CPU);
+                                perf_evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
 
                                 opts->record_switch_events = false;
                                 ptr->have_sched_switch = 3;
@@ -752,6 +753,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                 tracking_evsel->attr.freq = 0;
                 tracking_evsel->attr.sample_period = 1;
 
+                tracking_evsel->no_aux_samples = true;
                 if (need_immediate)
                         tracking_evsel->immediate = true;
 
@@ -761,6 +763,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                         /* And the CPU for switch events */
                         perf_evsel__set_sample_bit(tracking_evsel, CPU);
                 }
+                perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
         }
 
         /*
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index bf817beca0a8..b32409a0e546 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include "../../util/kvm-stat.h"
 #include <asm/svm.h>
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index f95edebfb716..4b2caf6d48e7 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <string.h>
 #include <regex.h>
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 79fe07158d00..63a74c32ddc5 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 
 #include <linux/perf_event.h>
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 2e5567c94e09..06bae7023a51 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <errno.h>
 
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
index 38dc9bb2a7c9..fda8f4206ee4 100644
--- a/tools/perf/arch/x86/util/unwind-libdw.c
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 4f16661cbdbb..9c917f80c906 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <errno.h>
diff --git a/tools/perf/arch/xtensa/include/dwarf-regs-table.h b/tools/perf/arch/xtensa/include/dwarf-regs-table.h
index aa0444a33fe6..d7c9f1fb4444 100644
--- a/tools/perf/arch/xtensa/include/dwarf-regs-table.h
+++ b/tools/perf/arch/xtensa/include/dwarf-regs-table.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef DEFINE_DWARF_REGSTR_TABLE
 /* This is included in perf/util/dwarf-regs.c */
 
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 842ab2781cdc..6c9fcd757f31 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BENCH_H
 #define BENCH_H
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fe16b310097f..58ae6ed8f38b 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
  *
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 73a1c44ea63c..08653ae8a8c4 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2015 Davidlohr Bueso.
  */
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 41786cbea24c..1058c194608a 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
  *
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 4ab12c8e016a..b4732dad9f89 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2015 Davidlohr Bueso.
  *
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 2fa49222ef8d..8c5c0b6b5c97 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
  *
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index e44fd3239530..db4853f209c7 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Glibc independent futex library for testing kernel functionality.
  * Shamelessly stolen from Darren Hart <dvhltc@us.ibm.com>
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index fbd732b54047..0251dd348124 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * mem-memcpy.c
  *
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
index 5aad2a9408b0..5bcaec5601a8 100644
--- a/tools/perf/bench/mem-memcpy-arch.h
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
index 8c0c1a2770c8..50ae8bd58296 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 MEMCPY_FN(memcpy_orig,
         "x86-64-unrolled",
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index f700369bb0f6..b43f8d2a34ec 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 /* Various wrappers to make the kernel .S file build in user-space: */
 
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
index 0d15786d9ae3..53f45482663f 100644
--- a/tools/perf/bench/mem-memset-arch.h
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
index f02d028771d9..dac6d2b7c39b 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 MEMSET_FN(memset_orig,
         "x86-64-unrolled",
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index 58407aa24c1b..d550bd526162 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 469d65b21122..d95fdcc26f4b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * numa.c
  *
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 4f961e74535b..f9d7641ae833 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *
  * sched-messaging.c
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index a152737370c5..0591be008f2a 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *
  * sched-pipe.c
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 7a5dc7e5c577..f15731a3d438 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-annotate.c
  *
@@ -177,14 +178,11 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
          */
         process_branch_stack(sample->branch_stack, al, sample);
 
-        sample->period = 1;
-        sample->weight = 1;
-
         he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
-        ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+        ret = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr);
         hists__inc_nr_samples(hists, true);
         return ret;
 }
@@ -359,7 +357,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
         }
 
         if (total_nr_samples == 0) {
-                ui__error("The %s file has no samples!\n", session->file->path);
+                ui__error("The %s file has no samples!\n", session->data->file.path);
                 goto out;
         }
 
@@ -397,21 +395,23 @@ int cmd_annotate(int argc, const char **argv)
                         .namespaces = perf_event__process_namespaces,
                         .attr   = perf_event__process_attr,
                         .build_id = perf_event__process_build_id,
+                        .tracing_data   = perf_event__process_tracing_data,
+                        .feature        = perf_event__process_feature,
                         .ordered_events = true,
                         .ordering_requires_timestamps = true,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
-        const struct option options[] = {
+        struct option options[] = {
         OPT_STRING('i', "input", &input_name, "file",
                     "input file name"),
         OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
                    "only consider symbols in these dsos"),
         OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
                     "symbol to annotate"),
-        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+        OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
         OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
@@ -446,13 +446,20 @@ int cmd_annotate(int argc, const char **argv)
                     "Show event group information together"),
         OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
                     "Show a column with the sum of periods"),
+        OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
+                    "Show a column with the number of samples"),
         OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
                              "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
                              stdio__config_color, "always"),
         OPT_END()
         };
-        int ret = hists__init();
+        int ret;
+
+        set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE);
+        set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE);
+
 
+        ret = hists__init();
         if (ret < 0)
                 return ret;
 
@@ -468,12 +475,17 @@ int cmd_annotate(int argc, const char **argv)
                 annotate.sym_hist_filter = argv[0];
         }
 
+        if (symbol_conf.show_nr_samples && annotate.use_gtk) {
+                pr_err("--show-nr-samples is not available in --gtk mode at this time\n");
+                return ret;
+        }
+
         if (quiet)
                 perf_quiet_option();
 
-        file.path  = input_name;
+        data.file.path = input_name;
 
-        annotate.session = perf_session__new(&file, false, &annotate.tool);
+        annotate.session = perf_session__new(&data, false, &annotate.tool);
         if (annotate.session == NULL)
                 return -1;
 
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 445e62881254..17a6bcd01aa6 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-bench.c
  *
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 9eba7f1add1f..3d354ba6e9c5 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-buildid-cache.c
  *
@@ -14,6 +15,7 @@
 #include <unistd.h>
 #include "builtin.h"
 #include "perf.h"
+#include "namespaces.h"
 #include "util/cache.h"
 #include "util/debug.h"
 #include "util/header.h"
@@ -165,33 +167,41 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
         return 0;
 }
 
-static int build_id_cache__add_file(const char *filename)
+static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi)
 {
         char sbuild_id[SBUILD_ID_SIZE];
         u8 build_id[BUILD_ID_SIZE];
         int err;
+        struct nscookie nsc;
 
-        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        nsinfo__mountns_exit(&nsc);
+        if (err < 0) {
                 pr_debug("Couldn't read a build-id in %s\n", filename);
                 return -1;
         }
 
         build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-        err = build_id_cache__add_s(sbuild_id, filename,
+        err = build_id_cache__add_s(sbuild_id, filename, nsi,
                                     false, false);
         pr_debug("Adding %s %s: %s\n", sbuild_id, filename,
                  err ? "FAIL" : "Ok");
         return err;
 }
 
-static int build_id_cache__remove_file(const char *filename)
+static int build_id_cache__remove_file(const char *filename, struct nsinfo *nsi)
 {
         u8 build_id[BUILD_ID_SIZE];
         char sbuild_id[SBUILD_ID_SIZE];
+        struct nscookie nsc;
 
         int err;
 
-        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        nsinfo__mountns_exit(&nsc);
+        if (err < 0) {
                 pr_debug("Couldn't read a build-id in %s\n", filename);
                 return -1;
         }
@@ -204,13 +214,13 @@ static int build_id_cache__remove_file(const char *filename)
         return err;
 }
 
-static int build_id_cache__purge_path(const char *pathname)
+static int build_id_cache__purge_path(const char *pathname, struct nsinfo *nsi)
 {
         struct strlist *list;
         struct str_node *pos;
         int err;
 
-        err = build_id_cache__list_build_ids(pathname, &list);
+        err = build_id_cache__list_build_ids(pathname, nsi, &list);
         if (err)
                 goto out;
 
@@ -234,7 +244,7 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
         char filename[PATH_MAX];
         u8 build_id[BUILD_ID_SIZE];
 
-        if (dso__build_id_filename(dso, filename, sizeof(filename)) &&
+        if (dso__build_id_filename(dso, filename, sizeof(filename), false) &&
             filename__read_build_id(filename, build_id,
                                     sizeof(build_id)) != sizeof(build_id)) {
                 if (errno == ENOENT)
@@ -256,24 +266,30 @@ static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *f
         return 0;
 }
 
-static int build_id_cache__update_file(const char *filename)
+static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
 {
         u8 build_id[BUILD_ID_SIZE];
         char sbuild_id[SBUILD_ID_SIZE];
+        struct nscookie nsc;
 
-        int err = 0;
+        int err;
 
-        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        nsinfo__mountns_exit(&nsc);
+        if (err < 0) {
                 pr_debug("Couldn't read a build-id in %s\n", filename);
                 return -1;
         }
+        err = 0;
 
         build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
         if (build_id_cache__cached(sbuild_id))
                 err = build_id_cache__remove_s(sbuild_id);
 
         if (!err)
-                err = build_id_cache__add_s(sbuild_id, filename, false, false);
+                err = build_id_cache__add_s(sbuild_id, filename, nsi, false,
+                                            false);
 
         pr_debug("Updating %s %s: %s\n", sbuild_id, filename,
                  err ? "FAIL" : "Ok");
@@ -286,6 +302,7 @@ int cmd_buildid_cache(int argc, const char **argv)
         struct strlist *list;
         struct str_node *pos;
         int ret = 0;
+        int ns_id = -1;
         bool force = false;
         char const *add_name_list_str = NULL,
                    *remove_name_list_str = NULL,
@@ -295,10 +312,11 @@ int cmd_buildid_cache(int argc, const char **argv)
                    *kcore_filename = NULL;
         char sbuf[STRERR_BUFSIZE];
 
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
         struct perf_session *session = NULL;
+        struct nsinfo *nsi = NULL;
 
         const struct option buildid_cache_options[] = {
         OPT_STRING('a', "add", &add_name_list_str,
@@ -315,6 +333,7 @@ int cmd_buildid_cache(int argc, const char **argv)
         OPT_STRING('u', "update", &update_name_list_str, "file list",
                     "file(s) to update"),
         OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+        OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"),
         OPT_END()
         };
         const char * const buildid_cache_usage[] = {
@@ -330,11 +349,14 @@ int cmd_buildid_cache(int argc, const char **argv)
                      !missing_filename && !update_name_list_str))
                 usage_with_options(buildid_cache_usage, buildid_cache_options);
 
+        if (ns_id > 0)
+                nsi = nsinfo__new(ns_id);
+
         if (missing_filename) {
-                file.path = missing_filename;
-                file.force = force;
+                data.file.path = missing_filename;
+                data.force     = force;
 
-                session = perf_session__new(&file, false, NULL);
+                session = perf_session__new(&data, false, NULL);
                 if (session == NULL)
                         return -1;
         }
@@ -348,7 +370,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(add_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__add_file(pos->s)) {
+                                if (build_id_cache__add_file(pos->s, nsi)) {
                                         if (errno == EEXIST) {
                                                 pr_debug("%s already in the cache\n",
                                                          pos->s);
@@ -366,7 +388,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(remove_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__remove_file(pos->s)) {
+                                if (build_id_cache__remove_file(pos->s, nsi)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -384,7 +406,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(purge_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__purge_path(pos->s)) {
+                                if (build_id_cache__purge_path(pos->s, nsi)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -405,7 +427,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(update_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__update_file(pos->s)) {
+                                if (build_id_cache__update_file(pos->s, nsi)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -424,6 +446,7 @@ int cmd_buildid_cache(int argc, const char **argv)
 
 out:
         perf_session__delete(session);
+        nsinfo__zput(nsi);
 
         return ret;
 }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index fdaca16e0c74..78abbe8d9d5f 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-buildid-list.c
  *
@@ -50,10 +51,12 @@ static bool dso__skip_buildid(struct dso *dso, int with_hits)
 static int perf_session__list_build_ids(bool force, bool with_hits)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path  = input_name,
-                .mode  = PERF_DATA_MODE_READ,
-                .force = force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = force,
         };
 
         symbol__elf_init();
@@ -63,7 +66,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
         if (filename__fprintf_build_id(input_name, stdout) > 0)
                 goto out;
 
-        session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
+        session = perf_session__new(&data, false, &build_id__mark_dso_hit_ops);
         if (session == NULL)
                 return -1;
 
@@ -71,7 +74,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
          * We take all buildids when the file contains AUX area tracing data
          * because we do not decode the trace because it would take too long.
          */
-        if (!perf_data_file__is_pipe(&file) &&
+        if (!perf_data__is_pipe(&data) &&
             perf_header__has_feat(&session->header, HEADER_AUXTRACE))
                 with_hits = false;
 
@@ -79,7 +82,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
          * in pipe-mode, the only way to get the buildids is to parse
          * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
          */
-        if (with_hits || perf_data_file__is_pipe(&file))
+        if (with_hits || perf_data__is_pipe(&data))
                 perf_session__process_events(session);
 
         perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 475999e48f66..17855c4626a0 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * This is rewrite of original c2c tool introduced in here:
  *   http://lwn.net/Articles/588866/
@@ -2523,7 +2524,7 @@ static int perf_c2c__report(int argc, const char **argv)
 {
         struct perf_session *session;
         struct ui_progress prog;
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT;
@@ -2572,8 +2573,8 @@ static int perf_c2c__report(int argc, const char **argv)
         if (!input_name || !strlen(input_name))
                 input_name = "perf.data";
 
-        file.path  = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
         err = setup_display(display);
         if (err)
@@ -2591,7 +2592,7 @@ static int perf_c2c__report(int argc, const char **argv)
                 goto out;
         }
 
-        session = perf_session__new(&file, 0, &c2c.tool);
+        session = perf_session__new(&data, 0, &c2c.tool);
         if (session == NULL) {
                 pr_debug("No memory for session\n");
                 goto out;
@@ -2611,7 +2612,7 @@ static int perf_c2c__report(int argc, const char **argv)
                 goto out_session;
 
         /* No pipe support at the moment. */
-        if (perf_data_file__is_pipe(session->file)) {
+        if (perf_data__is_pipe(session->data)) {
                 pr_debug("No pipe support at the moment.\n");
                 goto out_session;
         }
@@ -2732,6 +2733,7 @@ static int perf_c2c__record(int argc, const char **argv)
                 if (!perf_mem_events[j].supported) {
                         pr_err("failed: event '%s' not supported\n",
                                perf_mem_events[j].name);
+                        free(rec_argv);
                         return -1;
                 }
 
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index ece45582a48d..514f70f95b57 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-config.c
  *
@@ -13,6 +14,7 @@
 #include "util/util.h"
 #include "util/debug.h"
 #include "util/config.h"
+#include <linux/string.h>
 
 static bool use_system_config, use_user_config;
 
@@ -33,8 +35,7 @@ static struct option config_options[] = {
         OPT_END()
 };
 
-static int set_config(struct perf_config_set *set, const char *file_name,
-                      const char *var, const char *value)
+static int set_config(struct perf_config_set *set, const char *file_name)
 {
         struct perf_config_section *section = NULL;
         struct perf_config_item *item = NULL;
@@ -48,7 +49,6 @@ static int set_config(struct perf_config_set *set, const char *file_name,
         if (!fp)
                 return -1;
 
-        perf_config_set__collect(set, file_name, var, value);
         fprintf(fp, "%s\n", first_line);
 
         /* overwrite configvariables */
@@ -58,7 +58,7 @@ static int set_config(struct perf_config_set *set, const char *file_name,
                 fprintf(fp, "[%s]\n", section->name);
 
                 perf_config_items__for_each_entry(&section->items, item) {
-                        if (!use_system_config && section->from_system_config)
+                        if (!use_system_config && item->from_system_config)
                                 continue;
                         if (item->value)
                                 fprintf(fp, "\t%s = %s\n",
@@ -79,7 +79,7 @@ static int show_spec_config(struct perf_config_set *set, const char *var)
                 return -1;
 
         perf_config_items__for_each_entry(&set->sections, section) {
-                if (prefixcmp(var, section->name) != 0)
+                if (!strstarts(var, section->name))
                         continue;
 
                 perf_config_items__for_each_entry(&section->items, item) {
@@ -160,6 +160,7 @@ int cmd_config(int argc, const char **argv)
         struct perf_config_set *set;
         char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
         const char *config_filename;
+        bool changed = false;
 
         argc = parse_options(argc, argv, config_options, config_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
@@ -230,15 +231,26 @@ int cmd_config(int argc, const char **argv)
                                         goto out_err;
                                 }
                         } else {
-                                if (set_config(set, config_filename, var, value) < 0) {
-                                        pr_err("Failed to set '%s=%s' on %s\n",
-                                               var, value, config_filename);
+                                if (perf_config_set__collect(set, config_filename,
+                                                             var, value) < 0) {
+                                        pr_err("Failed to add '%s=%s'\n",
+                                               var, value);
                                         free(arg);
                                         goto out_err;
                                 }
+                                changed = true;
                         }
                         free(arg);
                 }
+
+                if (!changed)
+                        break;
+
+                if (set_config(set, config_filename) < 0) {
+                        pr_err("Failed to set the configs on %s\n",
+                               config_filename);
+                        goto out_err;
+                }
         }
 
         ret = 0;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 0adb5f82335a..dde25d4ca56d 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include "builtin.h"
 #include "perf.h"
@@ -69,7 +70,7 @@ static int cmd_data_convert(int argc, const char **argv)
         };
 
 #ifndef HAVE_LIBBABELTRACE_SUPPORT
-        pr_err("No conversion support compiled in.\n");
+        pr_err("No conversion support compiled in. perf should be compiled with environment variables LIBBABELTRACE=1 and LIBBABELTRACE_DIR=/path/to/libbabeltrace/\n");
         return -1;
 #endif
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 0cd4cf6a344b..d660cb7b222b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-diff.c
  *
@@ -47,7 +48,7 @@ struct diff_hpp_fmt {
 
 struct data__file {
         struct perf_session     *session;
-        struct perf_data_file   file;
+        struct perf_data         data;
         int                      idx;
         struct hists            *hists;
         struct diff_hpp_fmt      fmt[PERF_HPP_DIFF__MAX_INDEX];
@@ -707,7 +708,7 @@ static void data__fprintf(void)
 
         data__for_each_file(i, d)
                 fprintf(stdout, "#  [%d] %s %s\n",
-                        d->idx, d->file.path,
+                        d->idx, d->data.file.path,
                         !d->idx ? "(Baseline)" : "");
 
         fprintf(stdout, "#\n");
@@ -776,16 +777,16 @@ static int __cmd_diff(void)
         int ret = -EINVAL, i;
 
         data__for_each_file(i, d) {
-                d->session = perf_session__new(&d->file, false, &tool);
+                d->session = perf_session__new(&d->data, false, &tool);
                 if (!d->session) {
-                        pr_err("Failed to open %s\n", d->file.path);
+                        pr_err("Failed to open %s\n", d->data.file.path);
                         ret = -1;
                         goto out_delete;
                 }
 
                 ret = perf_session__process_events(d->session);
                 if (ret) {
-                        pr_err("Failed to process %s\n", d->file.path);
+                        pr_err("Failed to process %s\n", d->data.file.path);
                         goto out_delete;
                 }
 
@@ -1286,11 +1287,11 @@ static int data_init(int argc, const char **argv)
                 return -ENOMEM;
 
         data__for_each_file(i, d) {
-                struct perf_data_file *file = &d->file;
+                struct perf_data *data = &d->data;
 
-                file->path  = use_default ? defaults[i] : argv[i];
-                file->mode  = PERF_DATA_MODE_READ,
-                file->force = force,
+                data->file.path = use_default ? defaults[i] : argv[i];
+                data->mode      = PERF_DATA_MODE_READ,
+                data->force     = force,
 
                 d->idx  = i;
         }
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 6d210e40d611..e06e822ce634 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Builtin evlist command: Show the list of event selectors present
  * in a perf.data file.
@@ -21,14 +22,16 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 {
         struct perf_session *session;
         struct perf_evsel *pos;
-        struct perf_data_file file = {
-                .path = file_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = details->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = file_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = details->force,
         };
         bool has_tracepoint = false;
 
-        session = perf_session__new(&file, 0, NULL);
+        session = perf_session__new(&data, 0, NULL);
         if (session == NULL)
                 return -1;
 
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index dd26c62c9893..25a42acabee1 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -381,7 +381,7 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb)
 {
         struct perf_ftrace *ftrace = cb;
 
-        if (prefixcmp(var, "ftrace."))
+        if (!strstarts(var, "ftrace."))
                 return 0;
 
         if (strcmp(var, "ftrace.tracer"))
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 530a7f2fa0f3..bd1fedef3d1c 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-help.c
  *
@@ -90,7 +91,7 @@ static int check_emacsclient_version(void)
          */
         finish_command(&ec_process);
 
-        if (prefixcmp(buffer.buf, "emacsclient")) {
+        if (!strstarts(buffer.buf, "emacsclient")) {
                 fprintf(stderr, "Failed to parse emacsclient version.\n");
                 goto out;
         }
@@ -283,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
                 add_man_viewer(value);
                 return 0;
         }
-        if (!prefixcmp(var, "man."))
+        if (!strstarts(var, "man."))
                 return add_man_viewer_info(var, value);
 
         return 0;
@@ -313,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
         if (!perf_cmd)
                 return "perf";
-        else if (!prefixcmp(perf_cmd, "perf"))
+        else if (!strstarts(perf_cmd, "perf"))
                 return perf_cmd;
 
         return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index ea8db38eedd1..16a28547ca86 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-inject.c
  *
@@ -35,7 +36,7 @@ struct perf_inject {
         bool                    strip;
         bool                    jit_mode;
         const char              *input_name;
-        struct perf_data_file   output;
+        struct perf_data        output;
         u64                     bytes_written;
         u64                     aux_id;
         struct list_head        samples;
@@ -52,7 +53,7 @@ static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
 {
         ssize_t size;
 
-        size = perf_data_file__write(&inject->output, buf, sz);
+        size = perf_data__write(&inject->output, buf, sz);
         if (size < 0)
                 return -errno;
 
@@ -145,7 +146,7 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
         if (!inject->output.is_pipe) {
                 off_t offset;
 
-                offset = lseek(inject->output.fd, 0, SEEK_CUR);
+                offset = lseek(inject->output.file.fd, 0, SEEK_CUR);
                 if (offset == -1)
                         return -errno;
                 ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
@@ -154,11 +155,11 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
                         return ret;
         }
 
-        if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+        if (perf_data__is_pipe(session->data) || !session->one_mmap) {
                 ret = output_bytes(inject, event, event->header.size);
                 if (ret < 0)
                         return ret;
-                ret = copy_bytes(inject, perf_data_file__fd(session->file),
+                ret = copy_bytes(inject, perf_data__fd(session->data),
                                  event->auxtrace.size);
         } else {
                 ret = output_bytes(inject, event,
@@ -637,8 +638,8 @@ static int __cmd_inject(struct perf_inject *inject)
 {
         int ret = -EINVAL;
         struct perf_session *session = inject->session;
-        struct perf_data_file *file_out = &inject->output;
-        int fd = perf_data_file__fd(file_out);
+        struct perf_data *data_out = &inject->output;
+        int fd = perf_data__fd(data_out);
         u64 output_data_offset;
 
         signal(SIGINT, sig_handler);
@@ -693,14 +694,14 @@ static int __cmd_inject(struct perf_inject *inject)
         if (!inject->itrace_synth_opts.set)
                 auxtrace_index__free(&session->auxtrace_index);
 
-        if (!file_out->is_pipe)
+        if (!data_out->is_pipe)
                 lseek(fd, output_data_offset, SEEK_SET);
 
         ret = perf_session__process_events(session);
         if (ret)
                 return ret;
 
-        if (!file_out->is_pipe) {
+        if (!data_out->is_pipe) {
                 if (inject->build_ids)
                         perf_header__set_feat(&session->header,
                                               HEADER_BUILD_ID);
@@ -770,15 +771,18 @@ int cmd_inject(int argc, const char **argv)
                         .finished_round = perf_event__repipe_oe_synth,
                         .build_id       = perf_event__repipe_op2_synth,
                         .id_index       = perf_event__repipe_op2_synth,
+                        .feature        = perf_event__repipe_op2_synth,
                 },
                 .input_name  = "-",
                 .samples = LIST_HEAD_INIT(inject.samples),
                 .output = {
-                        .path = "-",
-                        .mode = PERF_DATA_MODE_WRITE,
+                        .file      = {
+                                .path = "-",
+                        },
+                        .mode      = PERF_DATA_MODE_WRITE,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         int ret;
@@ -788,7 +792,7 @@ int cmd_inject(int argc, const char **argv)
                             "Inject build-ids into the output stream"),
                 OPT_STRING('i', "input", &inject.input_name, "file",
                            "input file name"),
-                OPT_STRING('o', "output", &inject.output.path, "file",
+                OPT_STRING('o', "output", &inject.output.file.path, "file",
                            "output file name"),
                 OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
                             "Merge sched-stat and sched-switch for getting events "
@@ -800,7 +804,7 @@ int cmd_inject(int argc, const char **argv)
                          "be more verbose (show build ids, etc)"),
                 OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
                            "kallsyms pathname"),
-                OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+                OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
                 OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
                                     NULL, "opts", "Instruction Tracing options",
                                     itrace_parse_synth_opts),
@@ -828,15 +832,15 @@ int cmd_inject(int argc, const char **argv)
                 return -1;
         }
 
-        if (perf_data_file__open(&inject.output)) {
+        if (perf_data__open(&inject.output)) {
                 perror("failed to create output file");
                 return -1;
         }
 
         inject.tool.ordered_events = inject.sched_stat;
 
-        file.path = inject.input_name;
-        inject.session = perf_session__new(&file, true, &inject.tool);
+        data.file.path = inject.input_name;
+        inject.session = perf_session__new(&data, true, &inject.tool);
         if (inject.session == NULL)
                 return -1;
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index a1497c516d85..ae11e4c3516a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
 
@@ -627,7 +628,6 @@ static const struct {
         { "GFP_HIGHUSER_MOVABLE",       "HUM" },
         { "GFP_HIGHUSER",               "HU" },
         { "GFP_USER",                   "U" },
-        { "GFP_TEMPORARY",              "TMP" },
         { "GFP_KERNEL_ACCOUNT",         "KAC" },
         { "GFP_KERNEL",                 "K" },
         { "GFP_NOFS",                   "NF" },
@@ -641,7 +641,6 @@ static const struct {
         { "__GFP_ATOMIC",               "_A" },
         { "__GFP_IO",                   "I" },
         { "__GFP_FS",                   "F" },
-        { "__GFP_COLD",                 "CO" },
         { "__GFP_NOWARN",               "NWR" },
         { "__GFP_RETRY_MAYFAIL",        "R" },
         { "__GFP_NOFAIL",               "NF" },
@@ -655,7 +654,6 @@ static const struct {
         { "__GFP_RECLAIMABLE",          "RC" },
         { "__GFP_MOVABLE",              "M" },
         { "__GFP_ACCOUNT",              "AC" },
-        { "__GFP_NOTRACK",              "NT" },
         { "__GFP_WRITE",                "WR" },
         { "__GFP_RECLAIM",              "R" },
         { "__GFP_DIRECT_RECLAIM",       "DR" },
@@ -1894,7 +1892,7 @@ int cmd_kmem(int argc, const char **argv)
 {
         const char * const default_slab_sort = "frag,hit,bytes";
         const char * const default_page_sort = "bytes,hit";
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         const struct option kmem_options[] = {
@@ -1910,7 +1908,7 @@ int cmd_kmem(int argc, const char **argv)
                      "page, order, migtype, gfp", parse_sort_opt),
         OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
         OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
-        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+        OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
         OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator",
                            parse_slab_opt),
         OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
@@ -1950,9 +1948,9 @@ int cmd_kmem(int argc, const char **argv)
                 return __cmd_record(argc, argv);
         }
 
-        file.path = input_name;
+        data.file.path = input_name;
 
-        kmem_session = session = perf_session__new(&file, false, &perf_kmem);
+        kmem_session = session = perf_session__new(&data, false, &perf_kmem);
         if (session == NULL)
                 return -1;
 
@@ -1984,7 +1982,8 @@ int cmd_kmem(int argc, const char **argv)
 
         if (perf_time__parse_str(&ptime, time_str) != 0) {
                 pr_err("Invalid time string\n");
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out_delete;
         }
 
         if (!strcmp(argv[0], "stat")) {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f309c3773522..0c36f2ac6a0e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
 
@@ -34,7 +35,6 @@
 #include <termios.h>
 #include <semaphore.h>
 #include <signal.h>
-#include <pthread.h>
 #include <math.h>
 
 static const char *get_filename_for_perf_kvm(void)
@@ -1068,10 +1068,12 @@ static int read_events(struct perf_kvm_stat *kvm)
                 .namespaces             = perf_event__process_namespaces,
                 .ordered_events         = true,
         };
-        struct perf_data_file file = {
-                .path = kvm->file_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = kvm->force,
+        struct perf_data file = {
+                .file      = {
+                        .path = kvm->file_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = kvm->force,
         };
 
         kvm->tool = eops;
@@ -1359,7 +1361,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
                 "perf kvm stat live [<options>]",
                 NULL
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_WRITE,
         };
 
@@ -1433,7 +1435,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         /*
          * perf session
          */
-        kvm->session = perf_session__new(&file, false, &kvm->tool);
+        kvm->session = perf_session__new(&data, false, &kvm->tool);
         if (kvm->session == NULL) {
                 err = -1;
                 goto out;
@@ -1442,7 +1444,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         perf_session__set_id_hdr_size(kvm->session);
         ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
         machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
-                                    kvm->evlist->threads, false, kvm->opts.proc_map_timeout);
+                                    kvm->evlist->threads, false,
+                                    kvm->opts.proc_map_timeout, 1);
         err = kvm_live_open_events(kvm);
         if (err)
                 goto out;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 4bf2cb4d25aa..ead221e49f00 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-list.c
  *
@@ -15,6 +16,7 @@
 #include "util/cache.h"
 #include "util/pmu.h"
 #include "util/debug.h"
+#include "util/metricgroup.h"
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;
@@ -79,6 +81,10 @@ int cmd_list(int argc, const char **argv)
                                                 long_desc_flag, details_flag);
                 else if (strcmp(argv[i], "sdt") == 0)
                         print_sdt_events(NULL, NULL, raw_dump);
+                else if (strcmp(argv[i], "metric") == 0)
+                        metricgroup__print(true, false, NULL, raw_dump);
+                else if (strcmp(argv[i], "metricgroup") == 0)
+                        metricgroup__print(false, true, NULL, raw_dump);
                 else if ((sep = strchr(argv[i], ':')) != NULL) {
                         int sep_idx;
 
@@ -96,6 +102,7 @@ int cmd_list(int argc, const char **argv)
                         s[sep_idx] = '\0';
                         print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
                         print_sdt_events(s, s + sep_idx + 1, raw_dump);
+                        metricgroup__print(true, true, s, raw_dump);
                         free(s);
                 } else {
                         if (asprintf(&s, "*%s*", argv[i]) < 0) {
@@ -112,6 +119,7 @@ int cmd_list(int argc, const char **argv)
                                                 details_flag);
                         print_tracepoint_events(NULL, s, raw_dump);
                         print_sdt_events(NULL, s, raw_dump);
+                        metricgroup__print(true, true, NULL, raw_dump);
                         free(s);
                 }
         }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index ff98652484a7..6e0189df2b3b 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include "builtin.h"
@@ -864,13 +865,15 @@ static int __cmd_report(bool display_info)
                 .namespaces      = perf_event__process_namespaces,
                 .ordered_events  = true,
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = force,
         };
 
-        session = perf_session__new(&file, false, &eops);
+        session = perf_session__new(&data, false, &eops);
         if (!session) {
                 pr_err("Initializing perf session failed\n");
                 return -1;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e001c0290793..506564651cda 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -23,6 +24,7 @@ struct perf_mem {
         bool                    hide_unresolved;
         bool                    dump_raw;
         bool                    force;
+        bool                    phys_addr;
         int                     operation;
         const char              *cpu_list;
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -101,6 +103,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
         rec_argv[i++] = "-d";
 
+        if (mem->phys_addr)
+                rec_argv[i++] = "--phys-data";
+
         for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
                 if (!perf_mem_events[j].record)
                         continue;
@@ -108,6 +113,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
                 if (!perf_mem_events[j].supported) {
                         pr_err("failed: event '%s' not supported\n",
                                perf_mem_events__name(j));
+                        free(rec_argv);
                         return -1;
                 }
 
@@ -161,30 +167,60 @@ dump_raw_samples(struct perf_tool *tool,
         if (al.map != NULL)
                 al.map->dso->hit = 1;
 
-        if (symbol_conf.field_sep) {
-                fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
-                      "%s0x%"PRIx64"%s%s:%s\n";
+        if (mem->phys_addr) {
+                if (symbol_conf.field_sep) {
+                        fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64
+                              "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+                } else {
+                        fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+                              "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64
+                              "%s%s:%s\n";
+                        symbol_conf.field_sep = " ";
+                }
+
+                printf(fmt,
+                        sample->pid,
+                        symbol_conf.field_sep,
+                        sample->tid,
+                        symbol_conf.field_sep,
+                        sample->ip,
+                        symbol_conf.field_sep,
+                        sample->addr,
+                        symbol_conf.field_sep,
+                        sample->phys_addr,
+                        symbol_conf.field_sep,
+                        sample->weight,
+                        symbol_conf.field_sep,
+                        sample->data_src,
+                        symbol_conf.field_sep,
+                        al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+                        al.sym ? al.sym->name : "???");
         } else {
-                fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
-                      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
-                symbol_conf.field_sep = " ";
-        }
+                if (symbol_conf.field_sep) {
+                        fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+                              "%s0x%"PRIx64"%s%s:%s\n";
+                } else {
+                        fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+                              "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+                        symbol_conf.field_sep = " ";
+                }
 
-        printf(fmt,
-                sample->pid,
-                symbol_conf.field_sep,
-                sample->tid,
-                symbol_conf.field_sep,
-                sample->ip,
-                symbol_conf.field_sep,
-                sample->addr,
-                symbol_conf.field_sep,
-                sample->weight,
-                symbol_conf.field_sep,
-                sample->data_src,
-                symbol_conf.field_sep,
-                al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
-                al.sym ? al.sym->name : "???");
+                printf(fmt,
+                        sample->pid,
+                        symbol_conf.field_sep,
+                        sample->tid,
+                        symbol_conf.field_sep,
+                        sample->ip,
+                        symbol_conf.field_sep,
+                        sample->addr,
+                        symbol_conf.field_sep,
+                        sample->weight,
+                        symbol_conf.field_sep,
+                        sample->data_src,
+                        symbol_conf.field_sep,
+                        al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+                        al.sym ? al.sym->name : "???");
+        }
 out_put:
         addr_location__put(&al);
         return 0;
@@ -201,13 +237,15 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int report_raw_events(struct perf_mem *mem)
 {
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = mem->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = mem->force,
         };
         int ret;
-        struct perf_session *session = perf_session__new(&file, false,
+        struct perf_session *session = perf_session__new(&data, false,
                                                          &mem->tool);
 
         if (session == NULL)
@@ -224,7 +262,10 @@ static int report_raw_events(struct perf_mem *mem)
         if (ret < 0)
                 goto out_delete;
 
-        printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+        if (mem->phys_addr)
+                printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+        else
+                printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
         ret = perf_session__process_events(session);
 
@@ -254,9 +295,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
          * there is no weight (cost) associated with stores, so don't print
          * the column
          */
-        if (!(mem->operation & MEM_OPERATION_LOAD))
-                rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
-                                "dso_daddr,tlb,locked";
+        if (!(mem->operation & MEM_OPERATION_LOAD)) {
+                if (mem->phys_addr)
+                        rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+                                        "dso_daddr,tlb,locked,phys_daddr";
+                else
+                        rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+                                        "dso_daddr,tlb,locked";
+        } else if (mem->phys_addr)
+                rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+                                "dso_daddr,snoop,tlb,locked,phys_daddr";
 
         for (j = 1; j < argc; j++, i++)
                 rep_argv[i] = argv[j];
@@ -373,6 +421,7 @@ int cmd_mem(int argc, const char **argv)
                    "separator for columns, no spaces will be added"
                    " between columns '.' is reserved."),
         OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+        OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
         OPT_END()
         };
         const char *const mem_subcommands[] = { "record", "report", NULL };
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index cf9f9e9c2fc0..c0065923a525 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -58,6 +58,7 @@ static struct {
         struct line_range line_range;
         char *target;
         struct strfilter *filter;
+        struct nsinfo *nsi;
 } params;
 
 /* Parse an event definition. Note that any error must die. */
@@ -80,6 +81,9 @@ static int parse_probe_event(const char *str)
                 params.target_used = true;
         }
 
+        if (params.nsi)
+                pev->nsi = nsinfo__get(params.nsi);
+
         /* Parse a perf-probe command into event */
         ret = parse_perf_probe_command(str, pev);
         pr_debug("%d arguments\n", pev->nargs);
@@ -189,7 +193,7 @@ static int opt_set_target(const struct option *opt, const char *str,
 
                 /* Expand given path to absolute path, except for modulename */
                 if (params.uprobes || strchr(str, '/')) {
-                        tmp = realpath(str, NULL);
+                        tmp = nsinfo__realpath(str, params.nsi);
                         if (!tmp) {
                                 pr_warning("Failed to get the absolute path of %s: %m\n", str);
                                 return ret;
@@ -208,6 +212,34 @@ static int opt_set_target(const struct option *opt, const char *str,
         return ret;
 }
 
+static int opt_set_target_ns(const struct option *opt __maybe_unused,
+                             const char *str, int unset __maybe_unused)
+{
+        int ret = -ENOENT;
+        pid_t ns_pid;
+        struct nsinfo *nsip;
+
+        if (str) {
+                errno = 0;
+                ns_pid = (pid_t)strtol(str, NULL, 10);
+                if (errno != 0) {
+                        ret = -errno;
+                        pr_warning("Failed to parse %s as a pid: %s\n", str,
+                                   strerror(errno));
+                        return ret;
+                }
+                nsip = nsinfo__new(ns_pid);
+                if (nsip && nsip->need_setns)
+                        params.nsi = nsinfo__get(nsip);
+                nsinfo__put(nsip);
+
+                ret = 0;
+        }
+
+        return ret;
+}
+
+
 /* Command option callbacks */
 
 #ifdef HAVE_DWARF_SUPPORT
@@ -299,6 +331,7 @@ static void cleanup_params(void)
         line_range__clear(&params.line_range);
         free(params.target);
         strfilter__delete(params.filter);
+        nsinfo__put(params.nsi);
         memset(&params, 0, sizeof(params));
 }
 
@@ -383,7 +416,7 @@ static int del_perf_probe_caches(struct strfilter *filter)
         }
 
         strlist__for_each_entry(nd, bidlist) {
-                cache = probe_cache__new(nd->s);
+                cache = probe_cache__new(nd->s, NULL);
                 if (!cache)
                         continue;
                 if (probe_cache__filter_purge(cache, filter) < 0 ||
@@ -554,6 +587,8 @@ __cmd_probe(int argc, const char **argv)
         OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
         OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
                    "Look for files with symbols relative to this directory"),
+        OPT_CALLBACK(0, "target-ns", NULL, "pid",
+                     "target pid for namespace contexts", opt_set_target_ns),
         OPT_END()
         };
         int ret;
@@ -634,15 +669,15 @@ __cmd_probe(int argc, const char **argv)
                         pr_err_with_code("  Error: Failed to show event list.", ret);
                 return ret;
         case 'F':
-                ret = show_available_funcs(params.target, params.filter,
-                                        params.uprobes);
+                ret = show_available_funcs(params.target, params.nsi,
+                                           params.filter, params.uprobes);
                 if (ret < 0)
                         pr_err_with_code("  Error: Failed to show functions.", ret);
                 return ret;
 #ifdef HAVE_DWARF_SUPPORT
         case 'L':
                 ret = show_line_range(&params.line_range, params.target,
-                                      params.uprobes);
+                                      params.nsi, params.uprobes);
                 if (ret < 0)
                         pr_err_with_code("  Error: Failed to show lines.", ret);
                 return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 17a14bcce34a..3d7f33e19df2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-record.c
  *
@@ -66,7 +67,7 @@ struct record {
         struct perf_tool        tool;
         struct record_opts      opts;
         u64                     bytes_written;
-        struct perf_data_file   file;
+        struct perf_data        data;
         struct auxtrace_record  *itr;
         struct perf_evlist      *evlist;
         struct perf_session     *session;
@@ -107,7 +108,7 @@ static bool switch_output_time(struct record *rec)
 
 static int record__write(struct record *rec, void *bf, size_t size)
 {
-        if (perf_data_file__write(rec->session->file, bf, size) < 0) {
+        if (perf_data__write(rec->session->data, bf, size) < 0) {
                 pr_err("failed to write perf data, error: %m\n");
                 return -1;
         }
@@ -129,107 +130,12 @@ static int process_synthesized_event(struct perf_tool *tool,
         return record__write(rec, event, event->header.size);
 }
 
-static int
-backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+static int record__pushfn(void *to, void *bf, size_t size)
 {
-        struct perf_event_header *pheader;
-        u64 evt_head = head;
-        int size = mask + 1;
-
-        pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
-        pheader = (struct perf_event_header *)(buf + (head & mask));
-        *start = head;
-        while (true) {
-                if (evt_head - head >= (unsigned int)size) {
-                        pr_debug("Finished reading backward ring buffer: rewind\n");
-                        if (evt_head - head > (unsigned int)size)
-                                evt_head -= pheader->size;
-                        *end = evt_head;
-                        return 0;
-                }
-
-                pheader = (struct perf_event_header *)(buf + (evt_head & mask));
-
-                if (pheader->size == 0) {
-                        pr_debug("Finished reading backward ring buffer: get start\n");
-                        *end = evt_head;
-                        return 0;
-                }
-
-                evt_head += pheader->size;
-                pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
-        }
-        WARN_ONCE(1, "Shouldn't get here\n");
-        return -1;
-}
-
-static int
-rb_find_range(void *data, int mask, u64 head, u64 old,
-              u64 *start, u64 *end, bool backward)
-{
-        if (!backward) {
-                *start = old;
-                *end = head;
-                return 0;
-        }
-
-        return backward_rb_find_range(data, mask, head, start, end);
-}
-
-static int
-record__mmap_read(struct record *rec, struct perf_mmap *md,
-                  bool overwrite, bool backward)
-{
-        u64 head = perf_mmap__read_head(md);
-        u64 old = md->prev;
-        u64 end = head, start = old;
-        unsigned char *data = md->base + page_size;
-        unsigned long size;
-        void *buf;
-        int rc = 0;
-
-        if (rb_find_range(data, md->mask, head,
-                          old, &start, &end, backward))
-                return -1;
-
-        if (start == end)
-                return 0;
+        struct record *rec = to;
 
         rec->samples++;
-
-        size = end - start;
-        if (size > (unsigned long)(md->mask) + 1) {
-                WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
-
-                md->prev = head;
-                perf_mmap__consume(md, overwrite || backward);
-                return 0;
-        }
-
-        if ((start & md->mask) + size != (end & md->mask)) {
-                buf = &data[start & md->mask];
-                size = md->mask + 1 - (start & md->mask);
-                start += size;
-
-                if (record__write(rec, buf, size) < 0) {
-                        rc = -1;
-                        goto out;
-                }
-        }
-
-        buf = &data[start & md->mask];
-        size = end - start;
-        start += size;
-
-        if (record__write(rec, buf, size) < 0) {
-                rc = -1;
-                goto out;
-        }
-
-        md->prev = head;
-        perf_mmap__consume(md, overwrite || backward);
-out:
-        return rc;
+        return record__write(rec, bf, size);
 }
 
 static volatile int done;
@@ -268,13 +174,13 @@ static int record__process_auxtrace(struct perf_tool *tool,
                                     size_t len1, void *data2, size_t len2)
 {
         struct record *rec = container_of(tool, struct record, tool);
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         size_t padding;
         u8 pad[8] = {0};
 
-        if (!perf_data_file__is_pipe(file)) {
+        if (!perf_data__is_pipe(data)) {
                 off_t file_offset;
-                int fd = perf_data_file__fd(file);
+                int fd = perf_data__fd(data);
                 int err;
 
                 file_offset = lseek(fd, 0, SEEK_CUR);
@@ -493,10 +399,10 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int process_buildids(struct record *rec)
 {
-        struct perf_data_file *file  = &rec->file;
+        struct perf_data *data = &rec->data;
         struct perf_session *session = rec->session;
 
-        if (file->size == 0)
+        if (data->size == 0)
                 return 0;
 
         /*
@@ -576,8 +482,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
                 struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
                 if (maps[i].base) {
-                        if (record__mmap_read(rec, &maps[i],
-                                              evlist->overwrite, backward) != 0) {
+                        if (perf_mmap__push(&maps[i], evlist->overwrite, backward, rec, record__pushfn) != 0) {
                                 rc = -1;
                                 goto out;
                         }
@@ -640,14 +545,14 @@ static void record__init_features(struct record *rec)
 static void
 record__finish_output(struct record *rec)
 {
-        struct perf_data_file *file = &rec->file;
-        int fd = perf_data_file__fd(file);
+        struct perf_data *data = &rec->data;
+        int fd = perf_data__fd(data);
 
-        if (file->is_pipe)
+        if (data->is_pipe)
                 return;
 
         rec->session->header.data_size += rec->bytes_written;
-        file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+        data->size = lseek(perf_data__fd(data), 0, SEEK_CUR);
 
         if (!rec->no_buildid) {
                 process_buildids(rec);
@@ -686,7 +591,7 @@ static int record__synthesize(struct record *rec, bool tail);
 static int
 record__switch_output(struct record *rec, bool at_exit)
 {
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         int fd, err;
 
         /* Same Size:      "2015122520103046"*/
@@ -704,7 +609,7 @@ record__switch_output(struct record *rec, bool at_exit)
                 return -EINVAL;
         }
 
-        fd = perf_data_file__switch(file, timestamp,
+        fd = perf_data__switch(data, timestamp,
                                     rec->session->header.data_offset,
                                     at_exit);
         if (fd >= 0 && !at_exit) {
@@ -714,7 +619,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
         if (!quiet)
                 fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
-                        file->path, timestamp);
+                        data->file.path, timestamp);
 
         /* Output tracking events */
         if (!at_exit) {
@@ -789,16 +694,23 @@ static int record__synthesize(struct record *rec, bool tail)
 {
         struct perf_session *session = rec->session;
         struct machine *machine = &session->machines.host;
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         struct record_opts *opts = &rec->opts;
         struct perf_tool *tool = &rec->tool;
-        int fd = perf_data_file__fd(file);
+        int fd = perf_data__fd(data);
         int err = 0;
 
         if (rec->opts.tail_synthesize != tail)
                 return 0;
 
-        if (file->is_pipe) {
+        if (data->is_pipe) {
+                err = perf_event__synthesize_features(
+                        tool, session, rec->evlist, process_synthesized_event);
+                if (err < 0) {
+                        pr_err("Couldn't synthesize features.\n");
+                        return err;
+                }
+
                 err = perf_event__synthesize_attrs(tool, session,
                                                    process_synthesized_event);
                 if (err < 0) {
@@ -856,7 +768,7 @@ static int record__synthesize(struct record *rec, bool tail)
 
         err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
                                             process_synthesized_event, opts->sample_address,
-                                            opts->proc_map_timeout);
+                                            opts->proc_map_timeout, 1);
 out:
         return err;
 }
@@ -870,7 +782,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         struct machine *machine;
         struct perf_tool *tool = &rec->tool;
         struct record_opts *opts = &rec->opts;
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         struct perf_session *session;
         bool disabled = false, draining = false;
         int fd;
@@ -896,20 +808,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 signal(SIGUSR2, SIG_IGN);
         }
 
-        session = perf_session__new(file, false, tool);
+        session = perf_session__new(data, false, tool);
         if (session == NULL) {
                 pr_err("Perf session creation failed.\n");
                 return -1;
         }
 
-        fd = perf_data_file__fd(file);
+        fd = perf_data__fd(data);
         rec->session = session;
 
         record__init_features(rec);
 
         if (forks) {
                 err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
-                                                    argv, file->is_pipe,
+                                                    argv, data->is_pipe,
                                                     workload_exec_failed_signal);
                 if (err < 0) {
                         pr_err("Couldn't run the workload!\n");
@@ -945,7 +857,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         if (!rec->evlist->nr_groups)
                 perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
-        if (file->is_pipe) {
+        if (data->is_pipe) {
                 err = perf_header__write_pipe(fd);
                 if (err < 0)
                         goto out_child;
@@ -1206,8 +1118,8 @@ out_child:
                         samples[0] = '\0';
 
                 fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
-                        perf_data_file__size(file) / 1024.0 / 1024.0,
-                        file->path, postfix, samples);
+                        perf_data__size(data) / 1024.0 / 1024.0,
+                        data->file.path, postfix, samples);
         }
 
 out_delete_session:
@@ -1571,7 +1483,7 @@ static struct option __record_options[] = {
         OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
                     "list of cpus to monitor"),
         OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
-        OPT_STRING('o', "output", &record.file.path, "file",
+        OPT_STRING('o', "output", &record.data.file.path, "file",
                     "output file name"),
         OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
                         &record.opts.no_inherit_set,
@@ -1597,6 +1509,8 @@ static struct option __record_options[] = {
         OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
                     "per thread counts"),
         OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+        OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
+                    "Record the sample physical addresses"),
         OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
         OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
                         &record.opts.sample_time_set,
@@ -1634,6 +1548,9 @@ static struct option __record_options[] = {
         OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
                     "sample selected machine registers on interrupt,"
                     " use -I ? to list register names", parse_regs),
+        OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
+                    "sample selected machine registers on interrupt,"
+                    " use -I ? to list register names", parse_regs),
         OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
                     "Record running/enabled time of read (:S) events"),
         OPT_CALLBACK('k', "clockid", &record.opts,
@@ -1821,7 +1738,7 @@ int cmd_record(int argc, const char **argv)
                 record.opts.tail_synthesize = true;
 
         if (rec->evlist->nr_entries == 0 &&
-            perf_evlist__add_default(rec->evlist) < 0) {
+            __perf_evlist__add_default(rec->evlist, !record.opts.no_samples) < 0) {
                 pr_err("Not enough memory for event selector list\n");
                 goto out;
         }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 79a33eb1a10d..1394cd8d96f7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-report.c
  *
@@ -38,6 +39,7 @@
 #include "util/time-utils.h"
 #include "util/auxtrace.h"
 #include "util/units.h"
+#include "util/branch.h"
 
 #include <dlfcn.h>
 #include <errno.h>
@@ -73,6 +75,7 @@ struct report {
         u64                     queue_size;
         int                     socket_filter;
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+        struct branch_type_stat brtype_stat;
 };
 
 static int report__config(const char *var, const char *value, void *cb)
@@ -113,43 +116,60 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
         struct report *rep = arg;
         struct hist_entry *he = iter->he;
         struct perf_evsel *evsel = iter->evsel;
+        struct perf_sample *sample = iter->sample;
         struct mem_info *mi;
         struct branch_info *bi;
 
         if (!ui__has_annotation())
                 return 0;
 
-        hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
+        hist__account_cycles(sample->branch_stack, al, sample,
                              rep->nonany_branch_mode);
 
         if (sort__mode == SORT_MODE__BRANCH) {
                 bi = he->branch_info;
-                err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
+                err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
                 if (err)
                         goto out;
 
-                err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
+                err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
 
         } else if (rep->mem_mode) {
                 mi = he->mem_info;
-                err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+                err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel->idx);
                 if (err)
                         goto out;
 
-                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+                err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr);
 
         } else if (symbol_conf.cumulate_callchain) {
                 if (single)
-                        err = hist_entry__inc_addr_samples(he, evsel->idx,
+                        err = hist_entry__inc_addr_samples(he, sample, evsel->idx,
                                                            al->addr);
         } else {
-                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+                err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr);
         }
 
 out:
         return err;
 }
 
+static int hist_iter__branch_callback(struct hist_entry_iter *iter,
+                                      struct addr_location *al __maybe_unused,
+                                      bool single __maybe_unused,
+                                      void *arg)
+{
+        struct hist_entry *he = iter->he;
+        struct report *rep = arg;
+        struct branch_info *bi;
+
+        bi = he->branch_info;
+        branch_type_count(&rep->brtype_stat, &bi->flags,
+                          bi->from.addr, bi->to.addr);
+
+        return 0;
+}
+
 static int process_sample_event(struct perf_tool *tool,
                                 union perf_event *event,
                                 struct perf_sample *sample,
@@ -188,6 +208,8 @@ static int process_sample_event(struct perf_tool *tool,
                  */
                 if (!sample->branch_stack)
                         goto out_put;
+
+                iter.add_entry_cb = hist_iter__branch_callback;
                 iter.ops = &hist_iter_branch;
         } else if (rep->mem_mode) {
                 iter.ops = &hist_iter_mem;
@@ -220,7 +242,7 @@ static int process_read_event(struct perf_tool *tool,
                 const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
                 int err = perf_read_values_add_value(&rep->show_threads_values,
                                            event->read.pid, event->read.tid,
-                                           event->read.id,
+                                           evsel->idx,
                                            name,
                                            event->read.value);
 
@@ -228,10 +250,6 @@ static int process_read_event(struct perf_tool *tool,
                         return err;
         }
 
-        dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-                    evsel ? perf_evsel__name(evsel) : "FAIL",
-                    event->read.value);
-
         return 0;
 }
 
@@ -240,7 +258,7 @@ static int report__setup_sample_type(struct report *rep)
 {
         struct perf_session *session = rep->session;
         u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
-        bool is_pipe = perf_data_file__is_pipe(session->file);
+        bool is_pipe = perf_data__is_pipe(session->data);
 
         if (session->itrace_synth_opts->callchain ||
             (!is_pipe &&
@@ -258,10 +276,11 @@ static int report__setup_sample_type(struct report *rep)
                                     "'perf record' without -g?\n");
                         return -EINVAL;
                 }
-                if (symbol_conf.use_callchain) {
-                        ui__error("Selected -g or --branch-history but no "
-                                  "callchain data. Did\n"
-                                  "you call 'perf record' without -g?\n");
+                if (symbol_conf.use_callchain &&
+                        !symbol_conf.show_branchflag_count) {
+                        ui__error("Selected -g or --branch-history.\n"
+                                  "But no callchain or branch data.\n"
+                                  "Did you call 'perf record' without -g or -b?\n");
                         return -1;
                 }
         } else if (!callchain_param.enabled &&
@@ -396,7 +415,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
                 hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
                 hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-                               symbol_conf.use_callchain);
+                               symbol_conf.use_callchain ||
+                               symbol_conf.show_branchflag_count);
                 fprintf(stdout, "\n\n");
         }
 
@@ -410,6 +430,9 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
                 perf_read_values_destroy(&rep->show_threads_values);
         }
 
+        if (sort__mode == SORT_MODE__BRANCH)
+                branch_type_stat_display(stdout, &rep->brtype_stat);
+
         return 0;
 }
 
@@ -546,7 +569,7 @@ static int __cmd_report(struct report *rep)
         int ret;
         struct perf_session *session = rep->session;
         struct perf_evsel *pos;
-        struct perf_data_file *file = session->file;
+        struct perf_data *data = session->data;
 
         signal(SIGINT, sig_handler);
 
@@ -615,7 +638,7 @@ static int __cmd_report(struct report *rep)
                 rep->nr_entries += evsel__hists(pos)->nr_entries;
 
         if (rep->nr_entries == 0) {
-                ui__error("The %s file has no samples!\n", file->path);
+                ui__error("The %s file has no samples!\n", data->file.path);
                 return 0;
         }
 
@@ -718,6 +741,7 @@ int cmd_report(int argc, const char **argv)
                         .id_index        = perf_event__process_id_index,
                         .auxtrace_info   = perf_event__process_auxtrace_info,
                         .auxtrace        = perf_event__process_auxtrace,
+                        .feature         = perf_event__process_feature,
                         .ordered_events  = true,
                         .ordering_requires_timestamps = true,
                 },
@@ -856,7 +880,7 @@ int cmd_report(int argc, const char **argv)
                     "Show inline function"),
         OPT_END()
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
         int ret = hists__init();
@@ -917,11 +941,11 @@ int cmd_report(int argc, const char **argv)
                         input_name = "perf.data";
         }
 
-        file.path  = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
 repeat:
-        session = perf_session__new(&file, false, &report.tool);
+        session = perf_session__new(&data, false, &report.tool);
         if (session == NULL)
                 return -1;
 
@@ -943,6 +967,8 @@ repeat:
         if (has_br_stack && branch_call_mode)
                 symbol_conf.show_branchflag_count = true;
 
+        memset(&report.brtype_stat, 0, sizeof(struct branch_type_stat));
+
         /*
          * Branch mode is a tristate:
          * -1 means default, so decide based on the file having branch data.
@@ -988,6 +1014,10 @@ repeat:
         /* Force tty output for header output and per-thread stat. */
         if (report.header || report.header_only || report.show_threads)
                 use_browser = 0;
+        if (report.header || report.header_only)
+                report.tool.show_feat_hdr = SHOW_FEAT_HEADER;
+        if (report.show_full_info)
+                report.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
 
         if (strcmp(input_name, "-") != 0)
                 setup_browser(true);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 322b4def8411..83283fedb00f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
 
@@ -1700,14 +1701,16 @@ static int perf_sched__read_events(struct perf_sched *sched)
                 { "sched:sched_migrate_task", process_sched_migrate_task_event, },
         };
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = sched->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = sched->force,
         };
         int rc = -1;
 
-        session = perf_session__new(&file, false, &sched->tool);
+        session = perf_session__new(&data, false, &sched->tool);
         if (session == NULL) {
                 pr_debug("No Memory for session\n");
                 return -1;
@@ -2902,10 +2905,12 @@ static int perf_sched__timehist(struct perf_sched *sched)
         const struct perf_evsel_str_handler migrate_handlers[] = {
                 { "sched:sched_migrate_task", timehist_migrate_task_event, },
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = sched->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = sched->force,
         };
 
         struct perf_session *session;
@@ -2930,7 +2935,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 
         symbol_conf.use_callchain = sched->show_callchain;
 
-        session = perf_session__new(&file, false, &sched->tool);
+        session = perf_session__new(&data, false, &sched->tool);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -3363,6 +3368,10 @@ int cmd_sched(int argc, const char **argv)
         OPT_STRING(0, "time", &sched.time_str, "str",
                    "Time span for analysis (start,stop)"),
         OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
+        OPT_STRING('p', "pid", &symbol_conf.pid_list_str, "pid[,pid...]",
+                   "analyze events only for given process id(s)"),
+        OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
+                   "analyze events only for given thread id(s)"),
         OPT_PARENT(sched_options)
         };
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 83cdc0a61fd6..68f36dc0344f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 
 #include "perf.h"
@@ -87,6 +88,8 @@ enum perf_output_field {
         PERF_OUTPUT_BRSTACKINSN     = 1U << 23,
         PERF_OUTPUT_BRSTACKOFF      = 1U << 24,
         PERF_OUTPUT_SYNTH           = 1U << 25,
+        PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
+        PERF_OUTPUT_UREGS           = 1U << 27,
 };
 
 struct output_option {
@@ -108,6 +111,7 @@ struct output_option {
         {.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
         {.str = "period", .field = PERF_OUTPUT_PERIOD},
         {.str = "iregs", .field = PERF_OUTPUT_IREGS},
+        {.str = "uregs", .field = PERF_OUTPUT_UREGS},
         {.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
         {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
         {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
@@ -119,6 +123,7 @@ struct output_option {
         {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
         {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
         {.str = "synth", .field = PERF_OUTPUT_SYNTH},
+        {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
 };
 
 enum {
@@ -175,7 +180,8 @@ static struct {
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
                               PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+                              PERF_OUTPUT_PHYS_ADDR,
 
                 .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
@@ -205,6 +211,51 @@ static struct {
         },
 };
 
+struct perf_evsel_script {
+       char *filename;
+       FILE *fp;
+       u64  samples;
+};
+
+static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel,
+                                                        struct perf_data *data)
+{
+        struct perf_evsel_script *es = malloc(sizeof(*es));
+
+        if (es != NULL) {
+                if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
+                        goto out_free;
+                es->fp = fopen(es->filename, "w");
+                if (es->fp == NULL)
+                        goto out_free_filename;
+                es->samples = 0;
+        }
+
+        return es;
+out_free_filename:
+        zfree(&es->filename);
+out_free:
+        free(es);
+        return NULL;
+}
+
+static void perf_evsel_script__delete(struct perf_evsel_script *es)
+{
+        zfree(&es->filename);
+        fclose(es->fp);
+        es->fp = NULL;
+        free(es);
+}
+
+static int perf_evsel_script__fprintf(struct perf_evsel_script *es, FILE *fp)
+{
+        struct stat st;
+
+        fstat(fileno(es->fp), &st);
+        return fprintf(fp, "[ perf script: Wrote %.3f MB %s (%" PRIu64 " samples) ]\n",
+                       st.st_size / 1024.0 / 1024.0, es->filename, es->samples);
+}
+
 static inline int output_type(unsigned int type)
 {
         switch (type) {
@@ -382,6 +433,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                         PERF_OUTPUT_IREGS))
                 return -EINVAL;
 
+        if (PRINT_FIELD(UREGS) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS",
+                                        PERF_OUTPUT_UREGS))
+                return -EINVAL;
+
+        if (PRINT_FIELD(PHYS_ADDR) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+                                        PERF_OUTPUT_PHYS_ADDR))
+                return -EINVAL;
+
         return 0;
 }
 
@@ -485,51 +546,76 @@ out:
         return 0;
 }
 
-static void print_sample_iregs(struct perf_sample *sample,
-                          struct perf_event_attr *attr)
+static int perf_sample__fprintf_iregs(struct perf_sample *sample,
+                                      struct perf_event_attr *attr, FILE *fp)
 {
         struct regs_dump *regs = &sample->intr_regs;
         uint64_t mask = attr->sample_regs_intr;
         unsigned i = 0, r;
+        int printed = 0;
 
         if (!regs)
-                return;
+                return 0;
+
+        for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+                u64 val = regs->regs[i++];
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+        }
+
+        return printed;
+}
+
+static int perf_sample__fprintf_uregs(struct perf_sample *sample,
+                                      struct perf_event_attr *attr, FILE *fp)
+{
+        struct regs_dump *regs = &sample->user_regs;
+        uint64_t mask = attr->sample_regs_user;
+        unsigned i = 0, r;
+        int printed = 0;
+
+        if (!regs || !regs->regs)
+                return 0;
+
+        printed += fprintf(fp, " ABI:%" PRIu64 " ", regs->abi);
 
         for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
                 u64 val = regs->regs[i++];
-                printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
         }
+
+        return printed;
 }
 
-static void print_sample_start(struct perf_sample *sample,
-                               struct thread *thread,
-                               struct perf_evsel *evsel)
+static int perf_sample__fprintf_start(struct perf_sample *sample,
+                                      struct thread *thread,
+                                      struct perf_evsel *evsel, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         unsigned long secs;
         unsigned long long nsecs;
+        int printed = 0;
 
         if (PRINT_FIELD(COMM)) {
                 if (latency_format)
-                        printf("%8.8s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%8.8s ", thread__comm_str(thread));
                 else if (PRINT_FIELD(IP) && symbol_conf.use_callchain)
-                        printf("%s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%s ", thread__comm_str(thread));
                 else
-                        printf("%16s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%16s ", thread__comm_str(thread));
         }
 
         if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
-                printf("%5d/%-5d ", sample->pid, sample->tid);
+                printed += fprintf(fp, "%5d/%-5d ", sample->pid, sample->tid);
         else if (PRINT_FIELD(PID))
-                printf("%5d ", sample->pid);
+                printed += fprintf(fp, "%5d ", sample->pid);
         else if (PRINT_FIELD(TID))
-                printf("%5d ", sample->tid);
+                printed += fprintf(fp, "%5d ", sample->tid);
 
         if (PRINT_FIELD(CPU)) {
                 if (latency_format)
-                        printf("%3d ", sample->cpu);
+                        printed += fprintf(fp, "%3d ", sample->cpu);
                 else
-                        printf("[%03d] ", sample->cpu);
+                        printed += fprintf(fp, "[%03d] ", sample->cpu);
         }
 
         if (PRINT_FIELD(TIME)) {
@@ -538,13 +624,15 @@ static void print_sample_start(struct perf_sample *sample,
                 nsecs -= secs * NSEC_PER_SEC;
 
                 if (nanosecs)
-                        printf("%5lu.%09llu: ", secs, nsecs);
+                        printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
                 else {
                         char sample_time[32];
                         timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
-                        printf("%12s: ", sample_time);
+                        printed += fprintf(fp, "%12s: ", sample_time);
                 }
         }
+
+        return printed;
 }
 
 static inline char
@@ -556,16 +644,17 @@ mispred_str(struct branch_entry *br)
         return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(struct perf_sample *sample,
-                                 struct thread *thread,
-                                 struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstack(struct perf_sample *sample,
+                                        struct thread *thread,
+                                        struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
                 from = br->entries[i].from;
@@ -578,38 +667,41 @@ static void print_sample_brstack(struct perf_sample *sample,
                         thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
                 }
 
-                printf("0x%"PRIx64, from);
+                printed += fprintf(fp, " 0x%"PRIx64, from);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
 
-                printf("/0x%"PRIx64, to);
+                printed += fprintf(fp, "/0x%"PRIx64, to);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
 
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str( br->entries + i),
                         br->entries[i].flags.in_tx? 'X' : '-',
                         br->entries[i].flags.abort? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 
-static void print_sample_brstacksym(struct perf_sample *sample,
-                                    struct thread *thread,
-                                    struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
+                                           struct thread *thread,
+                                           struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
 
@@ -626,37 +718,40 @@ static void print_sample_brstacksym(struct perf_sample *sample,
                 if (alt.map)
                         alt.sym = map__find_symbol(alt.map, alt.addr);
 
-                symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
+                printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                putchar('/');
-                symbol__fprintf_symname_offs(alt.sym, &alt, stdout);
+                printed += fprintf(fp, "%c", '/');
+                printed += symbol__fprintf_symname_offs(alt.sym, &alt, fp);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str( br->entries + i),
                         br->entries[i].flags.in_tx? 'X' : '-',
                         br->entries[i].flags.abort? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 
-static void print_sample_brstackoff(struct perf_sample *sample,
-                                    struct thread *thread,
-                                    struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
+                                           struct thread *thread,
+                                           struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
 
@@ -673,24 +768,26 @@ static void print_sample_brstackoff(struct perf_sample *sample,
                 if (alt.map && !alt.map->dso->adjust_symbols)
                         to = map__map_ip(alt.map, to);
 
-                printf("0x%"PRIx64, from);
+                printed += fprintf(fp, " 0x%"PRIx64, from);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/0x%"PRIx64, to);
+                printed += fprintf(fp, "/0x%"PRIx64, to);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str(br->entries + i),
                         br->entries[i].flags.in_tx ? 'X' : '-',
                         br->entries[i].flags.abort ? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 #define MAXBB 16384UL
 
@@ -718,27 +815,26 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
          * but the exit is not. Let the caller patch it up.
          */
         if (kernel != machine__kernel_ip(machine, end)) {
-                printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
-                                start, end);
+                pr_debug("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n", start, end);
                 return -ENXIO;
         }
 
         memset(&al, 0, sizeof(al));
         if (end - start > MAXBB - MAXINSN) {
                 if (last)
-                        printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+                        pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
                 else
-                        printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+                        pr_debug("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
                 return 0;
         }
 
         thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
         if (!al.map || !al.map->dso) {
-                printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+                pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
                 return 0;
         }
         if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
-                printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+                pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
                 return 0;
         }
 
@@ -751,36 +847,35 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
         *is64bit = al.map->dso->is_64_bit;
         if (len <= 0)
-                printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+                pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
                         start, end);
         return len;
 }
 
-static void print_jump(uint64_t ip, struct branch_entry *en,
-                       struct perf_insn *x, u8 *inbuf, int len,
-                       int insn)
+static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
+                            struct perf_insn *x, u8 *inbuf, int len,
+                            int insn, FILE *fp)
 {
-        printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
-               ip,
-               dump_insn(x, ip, inbuf, len, NULL),
-               en->flags.predicted ? " PRED" : "",
-               en->flags.mispred ? " MISPRED" : "",
-               en->flags.in_tx ? " INTX" : "",
-               en->flags.abort ? " ABORT" : "");
+        int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
+                              dump_insn(x, ip, inbuf, len, NULL),
+                              en->flags.predicted ? " PRED" : "",
+                              en->flags.mispred ? " MISPRED" : "",
+                              en->flags.in_tx ? " INTX" : "",
+                              en->flags.abort ? " ABORT" : "");
         if (en->flags.cycles) {
-                printf(" %d cycles", en->flags.cycles);
+                printed += fprintf(fp, " %d cycles", en->flags.cycles);
                 if (insn)
-                        printf(" %.2f IPC", (float)insn / en->flags.cycles);
+                        printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
         }
-        putchar('\n');
+        return printed + fprintf(fp, "\n");
 }
 
-static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
-                         uint64_t addr, struct symbol **lastsym,
-                         struct perf_event_attr *attr)
+static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
+                           u8 cpumode, int cpu, struct symbol **lastsym,
+                           struct perf_event_attr *attr, FILE *fp)
 {
         struct addr_location al;
-        int off;
+        int off, printed = 0;
 
         memset(&al, 0, sizeof(al));
 
@@ -789,7 +884,7 @@ static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
                 thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
                                       addr, &al);
         if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
-                return;
+                return 0;
 
         al.cpu = cpu;
         al.sym = NULL;
@@ -797,37 +892,39 @@ static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
                 al.sym = map__find_symbol(al.map, al.addr);
 
         if (!al.sym)
-                return;
+                return 0;
 
         if (al.addr < al.sym->end)
                 off = al.addr - al.sym->start;
         else
                 off = al.addr - al.map->start - al.sym->start;
-        printf("\t%s", al.sym->name);
+        printed += fprintf(fp, "\t%s", al.sym->name);
         if (off)
-                printf("%+d", off);
-        putchar(':');
+                printed += fprintf(fp, "%+d", off);
+        printed += fprintf(fp, ":");
         if (PRINT_FIELD(SRCLINE))
-                map__fprintf_srcline(al.map, al.addr, "\t", stdout);
-        putchar('\n');
+                printed += map__fprintf_srcline(al.map, al.addr, "\t", fp);
+        printed += fprintf(fp, "\n");
         *lastsym = al.sym;
+
+        return printed;
 }
 
-static void print_sample_brstackinsn(struct perf_sample *sample,
-                                     struct thread *thread,
-                                     struct perf_event_attr *attr,
-                                     struct machine *machine)
+static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
+                                            struct thread *thread,
+                                            struct perf_event_attr *attr,
+                                            struct machine *machine, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         u64 start, end;
-        int i, insn, len, nr, ilen;
+        int i, insn, len, nr, ilen, printed = 0;
         struct perf_insn x;
         u8 buffer[MAXBB];
         unsigned off;
         struct symbol *lastsym = NULL;
 
         if (!(br && br->nr))
-                return;
+                return 0;
         nr = br->nr;
         if (max_blocks && nr > max_blocks + 1)
                 nr = max_blocks + 1;
@@ -835,17 +932,17 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
         x.thread = thread;
         x.cpu = sample->cpu;
 
-        putchar('\n');
+        printed += fprintf(fp, "%c", '\n');
 
         /* Handle first from jump, of which we don't know the entry. */
         len = grab_bb(buffer, br->entries[nr-1].from,
                         br->entries[nr-1].from,
                         machine, thread, &x.is64bit, &x.cpumode, false);
         if (len > 0) {
-                print_ip_sym(thread, x.cpumode, x.cpu,
-                             br->entries[nr - 1].from, &lastsym, attr);
-                print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-                            &x, buffer, len, 0);
+                printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+                                           x.cpumode, x.cpu, &lastsym, attr, fp);
+                printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+                                            &x, buffer, len, 0, fp);
         }
 
         /* Print all blocks */
@@ -871,13 +968,13 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
                 for (off = 0;; off += ilen) {
                         uint64_t ip = start + off;
 
-                        print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+                        printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
                         if (ip == end) {
-                                print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+                                printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
                                 break;
                         } else {
-                                printf("\t%016" PRIx64 "\t%s\n", ip,
-                                        dump_insn(&x, ip, buffer + off, len - off, &ilen));
+                                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
+                                                   dump_insn(&x, ip, buffer + off, len - off, &ilen));
                                 if (ilen == 0)
                                         break;
                                 insn++;
@@ -890,9 +987,9 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
          * has not been executed yet.
          */
         if (br->entries[0].from == sample->ip)
-                return;
+                goto out;
         if (br->entries[0].flags.abort)
-                return;
+                goto out;
 
         /*
          * Print final block upto sample
@@ -900,58 +997,61 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
         start = br->entries[0].to;
         end = sample->ip;
         len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
-        print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+        printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
         if (len <= 0) {
                 /* Print at least last IP if basic block did not work */
                 len = grab_bb(buffer, sample->ip, sample->ip,
                               machine, thread, &x.is64bit, &x.cpumode, false);
                 if (len <= 0)
-                        return;
+                        goto out;
 
-                printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
                         dump_insn(&x, sample->ip, buffer, len, NULL));
-                return;
+                goto out;
         }
         for (off = 0; off <= end - start; off += ilen) {
-                printf("\t%016" PRIx64 "\t%s\n", start + off,
-                        dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
+                                   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
                 if (ilen == 0)
                         break;
         }
+out:
+        return printed;
 }
 
-static void print_sample_addr(struct perf_sample *sample,
-                          struct thread *thread,
-                          struct perf_event_attr *attr)
+static int perf_sample__fprintf_addr(struct perf_sample *sample,
+                                     struct thread *thread,
+                                     struct perf_event_attr *attr, FILE *fp)
 {
         struct addr_location al;
-
-        printf("%16" PRIx64, sample->addr);
+        int printed = fprintf(fp, "%16" PRIx64, sample->addr);
 
         if (!sample_addr_correlates_sym(attr))
-                return;
+                goto out;
 
         thread__resolve(thread, &al, sample);
 
         if (PRINT_FIELD(SYM)) {
-                printf(" ");
+                printed += fprintf(fp, " ");
                 if (PRINT_FIELD(SYMOFFSET))
-                        symbol__fprintf_symname_offs(al.sym, &al, stdout);
+                        printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
                 else
-                        symbol__fprintf_symname(al.sym, stdout);
+                        printed += symbol__fprintf_symname(al.sym, fp);
         }
 
         if (PRINT_FIELD(DSO)) {
-                printf(" (");
-                map__fprintf_dsoname(al.map, stdout);
-                printf(")");
+                printed += fprintf(fp, " (");
+                printed += map__fprintf_dsoname(al.map, fp);
+                printed += fprintf(fp, ")");
         }
+out:
+        return printed;
 }
 
-static void print_sample_callindent(struct perf_sample *sample,
-                                    struct perf_evsel *evsel,
-                                    struct thread *thread,
-                                    struct addr_location *al)
+static int perf_sample__fprintf_callindent(struct perf_sample *sample,
+                                           struct perf_evsel *evsel,
+                                           struct thread *thread,
+                                           struct addr_location *al, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         size_t depth = thread_stack__depth(thread);
@@ -986,12 +1086,12 @@ static void print_sample_callindent(struct perf_sample *sample,
         }
 
         if (name)
-                len = printf("%*s%s", (int)depth * 4, "", name);
+                len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
         else if (ip)
-                len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+                len = fprintf(fp, "%*s%16" PRIx64, (int)depth * 4, "", ip);
 
         if (len < 0)
-                return;
+                return len;
 
         /*
          * Try to keep the output length from changing frequently so that the
@@ -1001,39 +1101,46 @@ static void print_sample_callindent(struct perf_sample *sample,
                 spacing = round_up(len + 4, 32);
 
         if (len < spacing)
-                printf("%*s", spacing - len, "");
+                len += fprintf(fp, "%*s", spacing - len, "");
+
+        return len;
 }
 
-static void print_insn(struct perf_sample *sample,
-                       struct perf_event_attr *attr,
-                       struct thread *thread,
-                       struct machine *machine)
+static int perf_sample__fprintf_insn(struct perf_sample *sample,
+                                     struct perf_event_attr *attr,
+                                     struct thread *thread,
+                                     struct machine *machine, FILE *fp)
 {
+        int printed = 0;
+
         if (PRINT_FIELD(INSNLEN))
-                printf(" ilen: %d", sample->insn_len);
+                printed += fprintf(fp, " ilen: %d", sample->insn_len);
         if (PRINT_FIELD(INSN)) {
                 int i;
 
-                printf(" insn:");
+                printed += fprintf(fp, " insn:");
                 for (i = 0; i < sample->insn_len; i++)
-                        printf(" %02x", (unsigned char)sample->insn[i]);
+                        printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
         }
         if (PRINT_FIELD(BRSTACKINSN))
-                print_sample_brstackinsn(sample, thread, attr, machine);
+                printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
+
+        return printed;
 }
 
-static void print_sample_bts(struct perf_sample *sample,
-                             struct perf_evsel *evsel,
-                             struct thread *thread,
-                             struct addr_location *al,
-                             struct machine *machine)
+static int perf_sample__fprintf_bts(struct perf_sample *sample,
+                                    struct perf_evsel *evsel,
+                                    struct thread *thread,
+                                    struct addr_location *al,
+                                    struct machine *machine, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         unsigned int type = output_type(attr->type);
         bool print_srcline_last = false;
+        int printed = 0;
 
         if (PRINT_FIELD(CALLINDENT))
-                print_sample_callindent(sample, evsel, thread, al);
+                printed += perf_sample__fprintf_callindent(sample, evsel, thread, al, fp);
 
         /* print branch_from information */
         if (PRINT_FIELD(IP)) {
@@ -1046,31 +1153,30 @@ static void print_sample_bts(struct perf_sample *sample,
                         cursor = &callchain_cursor;
 
                 if (cursor == NULL) {
-                        putchar(' ');
+                        printed += fprintf(fp, " ");
                         if (print_opts & EVSEL__PRINT_SRCLINE) {
                                 print_srcline_last = true;
                                 print_opts &= ~EVSEL__PRINT_SRCLINE;
                         }
                 } else
-                        putchar('\n');
+                        printed += fprintf(fp, "\n");
 
-                sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout);
+                printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, fp);
         }
 
         /* print branch_to information */
         if (PRINT_FIELD(ADDR) ||
             ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
              !output[type].user_set)) {
-                printf(" => ");
-                print_sample_addr(sample, thread, attr);
+                printed += fprintf(fp, " => ");
+                printed += perf_sample__fprintf_addr(sample, thread, attr, fp);
         }
 
         if (print_srcline_last)
-                map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
-
-        print_insn(sample, attr, thread, machine);
+                printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
 
-        printf("\n");
+        printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+        return printed + fprintf(fp, "\n");
 }
 
 static struct {
@@ -1093,7 +1199,7 @@ static struct {
         {0, NULL}
 };
 
-static void print_sample_flags(u32 flags)
+static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
         const char *chars = PERF_IP_FLAG_CHARS;
         const int n = strlen(PERF_IP_FLAG_CHARS);
@@ -1120,9 +1226,9 @@ static void print_sample_flags(u32 flags)
         str[pos] = 0;
 
         if (name)
-                printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
-        else
-                printf("  %-11s ", str);
+                return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
+
+        return fprintf(fp, "  %-11s ", str);
 }
 
 struct printer_data {
@@ -1131,40 +1237,40 @@ struct printer_data {
         bool is_printable;
 };
 
-static void
-print_sample_bpf_output_printer(enum binary_printer_ops op,
-                                unsigned int val,
-                                void *extra)
+static int sample__fprintf_bpf_output(enum binary_printer_ops op,
+                                      unsigned int val,
+                                      void *extra, FILE *fp)
 {
         unsigned char ch = (unsigned char)val;
         struct printer_data *printer_data = extra;
+        int printed = 0;
 
         switch (op) {
         case BINARY_PRINT_DATA_BEGIN:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 break;
         case BINARY_PRINT_LINE_BEGIN:
-                printf("%17s", !printer_data->line_no ? "BPF output:" :
+                printed += fprintf(fp, "%17s", !printer_data->line_no ? "BPF output:" :
                                                         "           ");
                 break;
         case BINARY_PRINT_ADDR:
-                printf(" %04x:", val);
+                printed += fprintf(fp, " %04x:", val);
                 break;
         case BINARY_PRINT_NUM_DATA:
-                printf(" %02x", val);
+                printed += fprintf(fp, " %02x", val);
                 break;
         case BINARY_PRINT_NUM_PAD:
-                printf("   ");
+                printed += fprintf(fp, "   ");
                 break;
         case BINARY_PRINT_SEP:
-                printf("  ");
+                printed += fprintf(fp, "  ");
                 break;
         case BINARY_PRINT_CHAR_DATA:
                 if (printer_data->hit_nul && ch)
                         printer_data->is_printable = false;
 
                 if (!isprint(ch)) {
-                        printf("%c", '.');
+                        printed += fprintf(fp, "%c", '.');
 
                         if (!printer_data->is_printable)
                                 break;
@@ -1174,154 +1280,154 @@ print_sample_bpf_output_printer(enum binary_printer_ops op,
                         else
                                 printer_data->is_printable = false;
                 } else {
-                        printf("%c", ch);
+                        printed += fprintf(fp, "%c", ch);
                 }
                 break;
         case BINARY_PRINT_CHAR_PAD:
-                printf(" ");
+                printed += fprintf(fp, " ");
                 break;
         case BINARY_PRINT_LINE_END:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 printer_data->line_no++;
                 break;
         case BINARY_PRINT_DATA_END:
         default:
                 break;
         }
+
+        return printed;
 }
 
-static void print_sample_bpf_output(struct perf_sample *sample)
+static int perf_sample__fprintf_bpf_output(struct perf_sample *sample, FILE *fp)
 {
         unsigned int nr_bytes = sample->raw_size;
         struct printer_data printer_data = {0, false, true};
-
-        print_binary(sample->raw_data, nr_bytes, 8,
-                     print_sample_bpf_output_printer, &printer_data);
+        int printed = binary__fprintf(sample->raw_data, nr_bytes, 8,
+                                      sample__fprintf_bpf_output, &printer_data, fp);
 
         if (printer_data.is_printable && printer_data.hit_nul)
-                printf("%17s \"%s\"\n", "BPF string:",
-                       (char *)(sample->raw_data));
+                printed += fprintf(fp, "%17s \"%s\"\n", "BPF string:", (char *)(sample->raw_data));
+
+        return printed;
 }
 
-static void print_sample_spacing(int len, int spacing)
+static int perf_sample__fprintf_spacing(int len, int spacing, FILE *fp)
 {
         if (len > 0 && len < spacing)
-                printf("%*s", spacing - len, "");
+                return fprintf(fp, "%*s", spacing - len, "");
+
+        return 0;
 }
 
-static void print_sample_pt_spacing(int len)
+static int perf_sample__fprintf_pt_spacing(int len, FILE *fp)
 {
-        print_sample_spacing(len, 34);
+        return perf_sample__fprintf_spacing(len, 34, fp);
 }
 
-static void print_sample_synth_ptwrite(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_ptwrite(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" IP: %u payload: %#" PRIx64 " ",
+        len = fprintf(fp, " IP: %u payload: %#" PRIx64 " ",
                      data->ip, le64_to_cpu(data->payload));
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_mwait(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_mwait(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" hints: %#x extensions: %#x ",
-                     data->hints, data->extensions);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " hints: %#x extensions: %#x ",
+                      data->hints, data->extensions);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_pwre(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_pwre(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" hw: %u cstate: %u sub-cstate: %u ",
-                     data->hw, data->cstate, data->subcstate);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " hw: %u cstate: %u sub-cstate: %u ",
+                      data->hw, data->cstate, data->subcstate);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_exstop(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_exstop(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" IP: %u ", data->ip);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " IP: %u ", data->ip);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_pwrx(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_pwrx(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ",
+        len = fprintf(fp, " deepest cstate: %u last cstate: %u wake reason: %#x ",
                      data->deepest_cstate, data->last_cstate,
                      data->wake_reason);
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_cbr(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_cbr(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample);
         unsigned int percent, freq;
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
         freq = (le32_to_cpu(data->freq) + 500) / 1000;
-        len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq);
+        len = fprintf(fp, " cbr: %2u freq: %4u MHz ", data->cbr, freq);
         if (data->max_nonturbo) {
                 percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10;
-                len += printf("(%3u%%) ", percent);
+                len += fprintf(fp, "(%3u%%) ", percent);
         }
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth(struct perf_sample *sample,
-                               struct perf_evsel *evsel)
+static int perf_sample__fprintf_synth(struct perf_sample *sample,
+                                      struct perf_evsel *evsel, FILE *fp)
 {
         switch (evsel->attr.config) {
         case PERF_SYNTH_INTEL_PTWRITE:
-                print_sample_synth_ptwrite(sample);
-                break;
+                return perf_sample__fprintf_synth_ptwrite(sample, fp);
         case PERF_SYNTH_INTEL_MWAIT:
-                print_sample_synth_mwait(sample);
-                break;
+                return perf_sample__fprintf_synth_mwait(sample, fp);
         case PERF_SYNTH_INTEL_PWRE:
-                print_sample_synth_pwre(sample);
-                break;
+                return perf_sample__fprintf_synth_pwre(sample, fp);
         case PERF_SYNTH_INTEL_EXSTOP:
-                print_sample_synth_exstop(sample);
-                break;
+                return perf_sample__fprintf_synth_exstop(sample, fp);
         case PERF_SYNTH_INTEL_PWRX:
-                print_sample_synth_pwrx(sample);
-                break;
+                return perf_sample__fprintf_synth_pwrx(sample, fp);
         case PERF_SYNTH_INTEL_CBR:
-                print_sample_synth_cbr(sample);
-                break;
+                return perf_sample__fprintf_synth_cbr(sample, fp);
         default:
                 break;
         }
+
+        return 0;
 }
 
 struct perf_script {
@@ -1332,6 +1438,7 @@ struct perf_script {
         bool                    show_switch_events;
         bool                    show_namespace_events;
         bool                    allocated;
+        bool                    per_event_dump;
         struct cpu_map          *cpus;
         struct thread_map       *threads;
         int                     name_width;
@@ -1353,7 +1460,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
         return max;
 }
 
-static size_t data_src__printf(u64 data_src)
+static int data_src__fprintf(u64 data_src, FILE *fp)
 {
         struct mem_info mi = { .data_src.val = data_src };
         char decode[100];
@@ -1367,7 +1474,7 @@ static size_t data_src__printf(u64 data_src)
         if (maxlen < len)
                 maxlen = len;
 
-        return printf("%-*s", maxlen, out);
+        return fprintf(fp, "%-*s", maxlen, out);
 }
 
 static void process_event(struct perf_script *script,
@@ -1378,14 +1485,18 @@ static void process_event(struct perf_script *script,
         struct thread *thread = al->thread;
         struct perf_event_attr *attr = &evsel->attr;
         unsigned int type = output_type(attr->type);
+        struct perf_evsel_script *es = evsel->priv;
+        FILE *fp = es->fp;
 
         if (output[type].fields == 0)
                 return;
 
-        print_sample_start(sample, thread, evsel);
+        ++es->samples;
+
+        perf_sample__fprintf_start(sample, thread, evsel, fp);
 
         if (PRINT_FIELD(PERIOD))
-                printf("%10" PRIu64 " ", sample->period);
+                fprintf(fp, "%10" PRIu64 " ", sample->period);
 
         if (PRINT_FIELD(EVNAME)) {
                 const char *evname = perf_evsel__name(evsel);
@@ -1393,33 +1504,33 @@ static void process_event(struct perf_script *script,
                 if (!script->name_width)
                         script->name_width = perf_evlist__max_name_len(script->session->evlist);
 
-                printf("%*s: ", script->name_width,
-                       evname ? evname : "[unknown]");
+                fprintf(fp, "%*s: ", script->name_width, evname ?: "[unknown]");
         }
 
         if (print_flags)
-                print_sample_flags(sample->flags);
+                perf_sample__fprintf_flags(sample->flags, fp);
 
         if (is_bts_event(attr)) {
-                print_sample_bts(sample, evsel, thread, al, machine);
+                perf_sample__fprintf_bts(sample, evsel, thread, al, machine, fp);
                 return;
         }
 
-        if (PRINT_FIELD(TRACE))
-                event_format__print(evsel->tp_format, sample->cpu,
-                                    sample->raw_data, sample->raw_size);
+        if (PRINT_FIELD(TRACE)) {
+                event_format__fprintf(evsel->tp_format, sample->cpu,
+                                      sample->raw_data, sample->raw_size, fp);
+        }
 
         if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH))
-                print_sample_synth(sample, evsel);
+                perf_sample__fprintf_synth(sample, evsel, fp);
 
         if (PRINT_FIELD(ADDR))
-                print_sample_addr(sample, thread, attr);
+                perf_sample__fprintf_addr(sample, thread, attr, fp);
 
         if (PRINT_FIELD(DATA_SRC))
-                data_src__printf(sample->data_src);
+                data_src__fprintf(sample->data_src, fp);
 
         if (PRINT_FIELD(WEIGHT))
-                printf("%16" PRIu64, sample->weight);
+                fprintf(fp, "%16" PRIu64, sample->weight);
 
         if (PRINT_FIELD(IP)) {
                 struct callchain_cursor *cursor = NULL;
@@ -1429,24 +1540,30 @@ static void process_event(struct perf_script *script,
                                               sample, NULL, NULL, scripting_max_stack) == 0)
                         cursor = &callchain_cursor;
 
-                putchar(cursor ? '\n' : ' ');
-                sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout);
+                fputc(cursor ? '\n' : ' ', fp);
+                sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, fp);
         }
 
         if (PRINT_FIELD(IREGS))
-                print_sample_iregs(sample, attr);
+                perf_sample__fprintf_iregs(sample, attr, fp);
+
+        if (PRINT_FIELD(UREGS))
+                perf_sample__fprintf_uregs(sample, attr, fp);
 
         if (PRINT_FIELD(BRSTACK))
-                print_sample_brstack(sample, thread, attr);
+                perf_sample__fprintf_brstack(sample, thread, attr, fp);
         else if (PRINT_FIELD(BRSTACKSYM))
-                print_sample_brstacksym(sample, thread, attr);
+                perf_sample__fprintf_brstacksym(sample, thread, attr, fp);
         else if (PRINT_FIELD(BRSTACKOFF))
-                print_sample_brstackoff(sample, thread, attr);
+                perf_sample__fprintf_brstackoff(sample, thread, attr, fp);
 
         if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
-                print_sample_bpf_output(sample);
-        print_insn(sample, attr, thread, machine);
-        printf("\n");
+                perf_sample__fprintf_bpf_output(sample, fp);
+        perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+
+        if (PRINT_FIELD(PHYS_ADDR))
+                fprintf(fp, "%16" PRIx64, sample->phys_addr);
+        fprintf(fp, "\n");
 }
 
 static struct scripting_ops     *scripting_ops;
@@ -1620,7 +1737,7 @@ static int process_comm_event(struct perf_tool *tool,
                 sample->tid = event->comm.tid;
                 sample->pid = event->comm.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         ret = 0;
 out:
@@ -1655,7 +1772,7 @@ static int process_namespaces_event(struct perf_tool *tool,
                 sample->tid = event->namespaces.tid;
                 sample->pid = event->namespaces.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         ret = 0;
 out:
@@ -1688,7 +1805,7 @@ static int process_fork_event(struct perf_tool *tool,
                 sample->tid = event->fork.tid;
                 sample->pid = event->fork.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
 
@@ -1717,7 +1834,7 @@ static int process_exit_event(struct perf_tool *tool,
                 sample->tid = event->fork.tid;
                 sample->pid = event->fork.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
 
         if (perf_event__process_exit(tool, event, sample, machine) < 0)
@@ -1752,7 +1869,7 @@ static int process_mmap_event(struct perf_tool *tool,
                 sample->tid = event->mmap.tid;
                 sample->pid = event->mmap.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1783,7 +1900,7 @@ static int process_mmap2_event(struct perf_tool *tool,
                 sample->tid = event->mmap2.tid;
                 sample->pid = event->mmap2.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1809,7 +1926,7 @@ static int process_switch_event(struct perf_tool *tool,
                 return -1;
         }
 
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1820,6 +1937,65 @@ static void sig_handler(int sig __maybe_unused)
         session_done = 1;
 }
 
+static void perf_script__fclose_per_event_dump(struct perf_script *script)
+{
+        struct perf_evlist *evlist = script->session->evlist;
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (!evsel->priv)
+                        break;
+                perf_evsel_script__delete(evsel->priv);
+                evsel->priv = NULL;
+        }
+}
+
+static int perf_script__fopen_per_event_dump(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(script->session->evlist, evsel) {
+                evsel->priv = perf_evsel_script__new(evsel, script->session->data);
+                if (evsel->priv == NULL)
+                        goto out_err_fclose;
+        }
+
+        return 0;
+
+out_err_fclose:
+        perf_script__fclose_per_event_dump(script);
+        return -1;
+}
+
+static int perf_script__setup_per_event_dump(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+        static struct perf_evsel_script es_stdout;
+
+        if (script->per_event_dump)
+                return perf_script__fopen_per_event_dump(script);
+
+        es_stdout.fp = stdout;
+
+        evlist__for_each_entry(script->session->evlist, evsel)
+                evsel->priv = &es_stdout;
+
+        return 0;
+}
+
+static void perf_script__exit_per_event_dump_stats(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(script->session->evlist, evsel) {
+                struct perf_evsel_script *es = evsel->priv;
+
+                perf_evsel_script__fprintf(es, stdout);
+                perf_evsel_script__delete(es);
+                evsel->priv = NULL;
+        }
+}
+
 static int __cmd_script(struct perf_script *script)
 {
         int ret;
@@ -1841,8 +2017,16 @@ static int __cmd_script(struct perf_script *script)
         if (script->show_namespace_events)
                 script->tool.namespaces = process_namespaces_event;
 
+        if (perf_script__setup_per_event_dump(script)) {
+                pr_err("Couldn't create the per event dump files\n");
+                return -1;
+        }
+
         ret = perf_session__process_events(script->session);
 
+        if (script->per_event_dump)
+                perf_script__exit_per_event_dump_stats(script);
+
         if (debug_mode)
                 pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
 
@@ -2199,16 +2383,11 @@ static struct script_desc *script_desc__findnew(const char *name)
 
         s = script_desc__new(name);
         if (!s)
-                goto out_delete_desc;
+                return NULL;
 
         script_desc__add(s);
 
         return s;
-
-out_delete_desc:
-        script_desc__delete(s);
-
-        return NULL;
 }
 
 static const char *ends_with(const char *str, const char *suffix)
@@ -2412,14 +2591,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
         char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
         DIR *scripts_dir, *lang_dir;
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
         };
         char *temp;
         int i = 0;
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         if (!session)
                 return -1;
 
@@ -2682,6 +2863,7 @@ int cmd_script(int argc, const char **argv)
                         .attr            = process_attr,
                         .event_update   = perf_event__process_event_update,
                         .tracing_data    = perf_event__process_tracing_data,
+                        .feature         = perf_event__process_feature,
                         .build_id        = perf_event__process_build_id,
                         .id_index        = perf_event__process_id_index,
                         .auxtrace_info   = perf_event__process_auxtrace_info,
@@ -2696,7 +2878,7 @@ int cmd_script(int argc, const char **argv)
                         .ordering_requires_timestamps = true,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         const struct option options[] = {
@@ -2732,8 +2914,8 @@ int cmd_script(int argc, const char **argv)
                      "+field to add and -field to remove."
                      "Valid types: hw,sw,trace,raw,synth. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-                     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+                     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
+                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
                      parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
@@ -2764,6 +2946,8 @@ int cmd_script(int argc, const char **argv)
                     "Show context switch events (if recorded)"),
         OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
                     "Show namespace events (if recorded)"),
+        OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
+                    "Dump trace output to files named by the monitored events"),
         OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
         OPT_INTEGER(0, "max-blocks", &max_blocks,
                     "Maximum number of code blocks to dump with brstackinsn"),
@@ -2794,13 +2978,15 @@ int cmd_script(int argc, const char **argv)
                 NULL
         };
 
+        perf_set_singlethreaded();
+
         setup_scripting();
 
         argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
-        file.path = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
         if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
                 rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
@@ -2967,15 +3153,18 @@ int cmd_script(int argc, const char **argv)
         if (!script_name)
                 setup_pager();
 
-        session = perf_session__new(&file, false, &script.tool);
+        session = perf_session__new(&data, false, &script.tool);
         if (session == NULL)
                 return -1;
 
         if (header || header_only) {
+                script.tool.show_feat_hdr = SHOW_FEAT_HEADER;
                 perf_session__fprintf_info(session, stdout, show_full_info);
                 if (header_only)
                         goto out_delete;
         }
+        if (show_full_info)
+                script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
 
         if (symbol__init(&session->header.env) < 0)
                 goto out_delete;
@@ -3005,7 +3194,8 @@ int cmd_script(int argc, const char **argv)
                                          machine__resolve_kernel_addr,
                                          &session->machines.host) < 0) {
                 pr_err("%s: failed to set libtraceevent function resolver\n", __func__);
-                return -1;
+                err = -1;
+                goto out_delete;
         }
 
         if (generate_script_lang) {
@@ -3019,7 +3209,7 @@ int cmd_script(int argc, const char **argv)
                         goto out_delete;
                 }
 
-                input = open(file.path, O_RDONLY);      /* input_name */
+                input = open(data.file.path, O_RDONLY); /* input_name */
                 if (input < 0) {
                         err = -errno;
                         perror("failed to open file");
@@ -3065,7 +3255,8 @@ int cmd_script(int argc, const char **argv)
         /* needs to be parsed after looking up reference time */
         if (perf_time__parse_str(&script.ptime, script.time_str) != 0) {
                 pr_err("Invalid time string\n");
-                return -EINVAL;
+                err = -EINVAL;
+                goto out_delete;
         }
 
         err = __cmd_script(&script);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 48ac53b199fc..59af5a8419e2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
 #include "util/tool.h"
 #include "util/group.h"
 #include "util/string2.h"
+#include "util/metricgroup.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -133,6 +134,8 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist       *evsel_list;
 
+static struct rblist             metric_events;
+
 static struct target target = {
         .uid    = UINT_MAX,
 };
@@ -172,7 +175,7 @@ static int			print_free_counters_hint;
 
 struct perf_stat {
         bool                     record;
-        struct perf_data_file    file;
+        struct perf_data         data;
         struct perf_session     *session;
         u64                      bytes_written;
         struct perf_tool         tool;
@@ -192,6 +195,11 @@ static struct perf_stat_config stat_config = {
         .scale          = true,
 };
 
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+        return !strcmp(evsel->name, "duration_time");
+}
+
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
                                  struct timespec *b)
 {
@@ -213,10 +221,20 @@ static void perf_stat__reset_stats(void)
 static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
         struct perf_event_attr *attr = &evsel->attr;
+        struct perf_evsel *leader = evsel->leader;
 
-        if (stat_config.scale)
+        if (stat_config.scale) {
                 attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                     PERF_FORMAT_TOTAL_TIME_RUNNING;
+        }
+
+        /*
+         * The event is part of non trivial group, let's enable
+         * the group read (for leader) and ID retrieval for all
+         * members.
+         */
+        if (leader->nr_members > 1)
+                attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
 
         attr->inherit = !no_inherit;
 
@@ -235,7 +253,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
          * by attr->sample_type != 0, and we can't run it on
          * stat sessions.
          */
-        if (!(STAT_RECORD && perf_stat.file.is_pipe))
+        if (!(STAT_RECORD && perf_stat.data.is_pipe))
                 attr->sample_type = PERF_SAMPLE_IDENTIFIER;
 
         /*
@@ -277,7 +295,7 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
                                      struct perf_sample *sample __maybe_unused,
                                      struct machine *machine __maybe_unused)
 {
-        if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
+        if (perf_data__write(&perf_stat.data, event, event->header.size) < 0) {
                 pr_err("failed to write perf data, error: %m\n");
                 return -1;
         }
@@ -333,13 +351,21 @@ static int read_counter(struct perf_evsel *counter)
                         struct perf_counts_values *count;
 
                         count = perf_counts(counter->counts, cpu, thread);
-                        if (perf_evsel__read(counter, cpu, thread, count)) {
+
+                        /*
+                         * The leader's group read loads data into its group members
+                         * (via perf_evsel__read_counter) and sets threir count->loaded.
+                         */
+                        if (!count->loaded &&
+                            perf_evsel__read_counter(counter, cpu, thread)) {
                                 counter->counts->scaled = -1;
                                 perf_counts(counter->counts, cpu, thread)->ena = 0;
                                 perf_counts(counter->counts, cpu, thread)->run = 0;
                                 return -1;
                         }
 
+                        count->loaded = false;
+
                         if (STAT_RECORD) {
                                 if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
                                         pr_err("failed to write stat event\n");
@@ -389,6 +415,8 @@ static void process_interval(void)
                         pr_err("failed to write stat round event\n");
         }
 
+        init_stats(&walltime_nsecs_stats);
+        update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
         print_counters(&rs, 0, NULL);
 }
 
@@ -559,6 +587,37 @@ static int store_counter_ids(struct perf_evsel *counter)
         return __store_counter_ids(counter, cpus, threads);
 }
 
+static bool perf_evsel__should_store_id(struct perf_evsel *counter)
+{
+        return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
+}
+
+static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
+{
+        struct perf_evsel *c2, *leader;
+        bool is_open = true;
+
+        leader = evsel->leader;
+        pr_debug("Weak group for %s/%d failed\n",
+                        leader->name, leader->nr_members);
+
+        /*
+         * for_each_group_member doesn't work here because it doesn't
+         * include the first entry.
+         */
+        evlist__for_each_entry(evsel_list, c2) {
+                if (c2 == evsel)
+                        is_open = false;
+                if (c2->leader == leader) {
+                        if (is_open)
+                                perf_evsel__close(c2);
+                        c2->leader = c2;
+                        c2->nr_members = 0;
+                }
+        }
+        return leader;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
         int interval = stat_config.interval;
@@ -569,7 +628,7 @@ static int __run_perf_stat(int argc, const char **argv)
         size_t l;
         int status = 0;
         const bool forks = (argc > 0);
-        bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
+        bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
         struct perf_evsel_config_term *err_term;
 
         if (interval) {
@@ -595,6 +654,15 @@ static int __run_perf_stat(int argc, const char **argv)
         evlist__for_each_entry(evsel_list, counter) {
 try_again:
                 if (create_perf_stat_counter(counter) < 0) {
+
+                        /* Weak group failed. Reset the group. */
+                        if ((errno == EINVAL || errno == EBADF) &&
+                            counter->leader != counter &&
+                            counter->weak_group) {
+                                counter = perf_evsel__reset_weak_group(counter);
+                                goto try_again;
+                        }
+
                         /*
                          * PPC returns ENXIO for HW counters until 2.6.37
                          * (behavior changed with commit b0a873e).
@@ -631,7 +699,8 @@ try_again:
                 if (l > unit_width)
                         unit_width = l;
 
-                if (STAT_RECORD && store_counter_ids(counter))
+                if (perf_evsel__should_store_id(counter) &&
+                    store_counter_ids(counter))
                         return -1;
         }
 
@@ -650,10 +719,10 @@ try_again:
         }
 
         if (STAT_RECORD) {
-                int err, fd = perf_data_file__fd(&perf_stat.file);
+                int err, fd = perf_data__fd(&perf_stat.data);
 
                 if (is_pipe) {
-                        err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
+                        err = perf_header__write_pipe(perf_data__fd(&perf_stat.data));
                 } else {
                         err = perf_session__write_header(perf_stat.session, evsel_list,
                                                          fd, false);
@@ -683,7 +752,7 @@ try_again:
                                 process_interval();
                         }
                 }
-                wait(&status);
+                waitpid(child_pid, &status, 0);
 
                 if (workload_exec_errno) {
                         const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
@@ -776,7 +845,7 @@ static void print_noise(struct perf_evsel *evsel, double avg)
         if (run_count == 1)
                 return;
 
-        ps = evsel->priv;
+        ps = evsel->stats;
         print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
@@ -1175,7 +1244,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
         perf_stat__print_shadow_stats(counter, uval,
                                 first_shadow_cpu(counter, id),
-                                &out);
+                                &out, &metric_events);
         if (!csv_output && !metric_only) {
                 print_noise(counter, noise);
                 print_running(run, ena);
@@ -1198,8 +1267,7 @@ static void aggr_update_shadow(void)
                                         continue;
                                 val += perf_counts(counter->counts, cpu, 0)->val;
                         }
-                        val = val * counter->scale;
-                        perf_stat__update_shadow_stats(counter, &val,
+                        perf_stat__update_shadow_stats(counter, val,
                                                        first_shadow_cpu(counter, id));
                 }
         }
@@ -1233,7 +1301,7 @@ static bool collect_data(struct perf_evsel *counter,
         if (counter->merged_stat)
                 return false;
         cb(counter, data, true);
-        if (!no_merge)
+        if (!no_merge && counter->auto_merge_stats)
                 collect_all_aliases(counter, cb, data);
         return true;
 }
@@ -1301,6 +1369,9 @@ static void print_aggr(char *prefix)
                 ad.id = id = aggr_map->map[s];
                 first = true;
                 evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
+
                         ad.val = ad.ena = ad.run = 0;
                         ad.nr = 0;
                         if (!collect_data(counter, aggr_cb, &ad))
@@ -1360,7 +1431,7 @@ static void counter_aggr_cb(struct perf_evsel *counter, void *data,
                             bool first __maybe_unused)
 {
         struct caggr_data *cd = data;
-        struct perf_stat_evsel *ps = counter->priv;
+        struct perf_stat_evsel *ps = counter->stats;
 
         cd->avg += avg_stats(&ps->res_stats[0]);
         cd->avg_enabled += avg_stats(&ps->res_stats[1]);
@@ -1444,6 +1515,8 @@ static void print_no_aggr_metric(char *prefix)
                 if (prefix)
                         fputs(prefix, stat_config.output);
                 evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
                         if (first) {
                                 aggr_printout(counter, cpu, 0);
                                 first = false;
@@ -1498,6 +1571,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 
         /* Print metrics headers only */
         evlist__for_each_entry(evsel_list, counter) {
+                if (is_duration_time(counter))
+                        continue;
                 os.evsel = counter;
                 out.ctx = &os;
                 out.print_metric = print_metric_header;
@@ -1506,7 +1581,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
                 os.evsel = counter;
                 perf_stat__print_shadow_stats(counter, 0,
                                               0,
-                                              &out);
+                                              &out,
+                                              &metric_events);
         }
         fputc('\n', stat_config.output);
 }
@@ -1619,7 +1695,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
         char buf[64], *prefix = NULL;
 
         /* Do not print anything if we record to the pipe. */
-        if (STAT_RECORD && perf_stat.file.is_pipe)
+        if (STAT_RECORD && perf_stat.data.is_pipe)
                 return;
 
         if (interval)
@@ -1644,12 +1720,18 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
                 print_aggr(prefix);
                 break;
         case AGGR_THREAD:
-                evlist__for_each_entry(evsel_list, counter)
+                evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
                         print_aggr_thread(counter, prefix);
+                }
                 break;
         case AGGR_GLOBAL:
-                evlist__for_each_entry(evsel_list, counter)
+                evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
                         print_counter_aggr(counter, prefix);
+                }
                 if (metric_only)
                         fputc('\n', stat_config.output);
                 break;
@@ -1657,8 +1739,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
                 if (metric_only)
                         print_no_aggr_metric(prefix);
                 else {
-                        evlist__for_each_entry(evsel_list, counter)
+                        evlist__for_each_entry(evsel_list, counter) {
+                                if (is_duration_time(counter))
+                                        continue;
                                 print_counter(counter, prefix);
+                        }
                 }
                 break;
         case AGGR_UNSET:
@@ -1730,6 +1815,13 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
         return 0;
 }
 
+static int parse_metric_groups(const struct option *opt,
+                               const char *str,
+                               int unset __maybe_unused)
+{
+        return metricgroup__parse_groups(opt, str, &metric_events);
+}
+
 static const struct option stat_options[] = {
         OPT_BOOLEAN('T', "transaction", &transaction_run,
                     "hardware transaction statistics"),
@@ -1795,6 +1887,9 @@ static const struct option stat_options[] = {
                         "measure topdown level 1 statistics"),
         OPT_BOOLEAN(0, "smi-cost", &smi_cost,
                         "measure SMI cost"),
+        OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
+                     "monitor specified metrics or metric groups (separated by ,)",
+                     parse_metric_groups),
         OPT_END()
 };
 
@@ -2310,20 +2405,20 @@ static void init_features(struct perf_session *session)
 static int __cmd_record(int argc, const char **argv)
 {
         struct perf_session *session;
-        struct perf_data_file *file = &perf_stat.file;
+        struct perf_data *data = &perf_stat.data;
 
         argc = parse_options(argc, argv, stat_options, stat_record_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
         if (output_name)
-                file->path = output_name;
+                data->file.path = output_name;
 
         if (run_count != 1 || forever) {
                 pr_err("Cannot use -r option with perf stat record.\n");
                 return -1;
         }
 
-        session = perf_session__new(file, false, NULL);
+        session = perf_session__new(data, false, NULL);
         if (session == NULL) {
                 pr_err("Perf session creation failed.\n");
                 return -1;
@@ -2381,7 +2476,7 @@ int process_stat_config_event(struct perf_tool *tool,
         if (st->aggr_mode != AGGR_UNSET)
                 stat_config.aggr_mode = st->aggr_mode;
 
-        if (perf_stat.file.is_pipe)
+        if (perf_stat.data.is_pipe)
                 perf_stat_init_aggr_mode();
         else
                 perf_stat_init_aggr_mode_file(st);
@@ -2489,10 +2584,10 @@ static int __cmd_report(int argc, const char **argv)
                         input_name = "perf.data";
         }
 
-        perf_stat.file.path = input_name;
-        perf_stat.file.mode = PERF_DATA_MODE_READ;
+        perf_stat.data.file.path = input_name;
+        perf_stat.data.mode      = PERF_DATA_MODE_READ;
 
-        session = perf_session__new(&perf_stat.file, false, &perf_stat.tool);
+        session = perf_session__new(&perf_stat.data, false, &perf_stat.tool);
         if (session == NULL)
                 return -1;
 
@@ -2763,7 +2858,7 @@ int cmd_stat(int argc, const char **argv)
                  * records, but the need to suppress the kptr_restrict messages in older
                  * tools remain  -acme
                  */
-                int fd = perf_data_file__fd(&perf_stat.file);
+                int fd = perf_data__fd(&perf_stat.data);
                 int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,
                                                              process_synthesized_event,
                                                              &perf_stat.session->machines.host);
@@ -2777,7 +2872,7 @@ int cmd_stat(int argc, const char **argv)
                                 pr_err("failed to write stat round event\n");
                 }
 
-                if (!perf_stat.file.is_pipe) {
+                if (!perf_stat.data.is_pipe) {
                         perf_stat.session->header.data_size += perf_stat.bytes_written;
                         perf_session__write_header(perf_stat.session, evsel_list, fd, true);
                 }
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 4e2e61695986..813698a9b8c7 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1601,13 +1601,15 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
                 { "syscalls:sys_exit_pselect6",         process_exit_poll },
                 { "syscalls:sys_exit_select",           process_exit_poll },
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = tchart->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = tchart->force,
         };
 
-        struct perf_session *session = perf_session__new(&file, false,
+        struct perf_session *session = perf_session__new(&data, false,
                                                          &tchart->tool);
         int ret = -EINVAL;
 
@@ -1617,7 +1619,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
         symbol__init(&session->header.env);
 
         (void)perf_header__process_sections(&session->header,
-                                            perf_data_file__fd(session->file),
+                                            perf_data__fd(session->data),
                                             tchart,
                                             process_header);
 
@@ -1732,8 +1734,10 @@ static int timechart__io_record(int argc, const char **argv)
         if (rec_argv == NULL)
                 return -ENOMEM;
 
-        if (asprintf(&filter, "common_pid != %d", getpid()) < 0)
+        if (asprintf(&filter, "common_pid != %d", getpid()) < 0) {
+                free(rec_argv);
                 return -ENOMEM;
+        }
 
         p = rec_argv;
         for (i = 0; i < common_args_nr; i++)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6052376634c0..477a8699f0b5 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -134,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
                 return err;
         }
 
-        err = symbol__disassemble(sym, map, NULL, 0, NULL);
+        err = symbol__disassemble(sym, map, NULL, 0, NULL, NULL);
         if (err == 0) {
 out_assign:
                 top->sym_filter_entry = he;
@@ -183,6 +183,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip)
 
 static void perf_top__record_precise_ip(struct perf_top *top,
                                         struct hist_entry *he,
+                                        struct perf_sample *sample,
                                         int counter, u64 ip)
 {
         struct annotation *notes;
@@ -199,7 +200,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
         if (pthread_mutex_trylock(&notes->lock))
                 return;
 
-        err = hist_entry__inc_addr_samples(he, counter, ip);
+        err = hist_entry__inc_addr_samples(he, sample, counter, ip);
 
         pthread_mutex_unlock(&notes->lock);
 
@@ -586,6 +587,13 @@ static void *display_thread_tui(void *arg)
                 .refresh        = top->delay_secs,
         };
 
+        /* In order to read symbols from other namespaces perf to  needs to call
+         * setns(2).  This isn't permitted if the struct_fs has multiple users.
+         * unshare(2) the fs so that we may continue to setns into namespaces
+         * that we're observing.
+         */
+        unshare(CLONE_FS);
+
         perf_top__sort_new_samples(top);
 
         /*
@@ -627,6 +635,13 @@ static void *display_thread(void *arg)
         struct perf_top *top = arg;
         int delay_msecs, c;
 
+        /* In order to read symbols from other namespaces perf to  needs to call
+         * setns(2).  This isn't permitted if the struct_fs has multiple users.
+         * unshare(2) the fs so that we may continue to setns into namespaces
+         * that we're observing.
+         */
+        unshare(CLONE_FS);
+
         display_setup_sig();
         pthread__unblock_sigwinch();
 repeat:
@@ -671,7 +686,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,
         struct perf_evsel *evsel = iter->evsel;
 
         if (perf_hpp_list.sym && single)
-                perf_top__record_precise_ip(top, he, evsel->idx, al->addr);
+                perf_top__record_precise_ip(top, he, iter->sample, evsel->idx, al->addr);
 
         hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
                      !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY));
@@ -943,8 +958,16 @@ static int __cmd_top(struct perf_top *top)
         if (perf_session__register_idle_thread(top->session) < 0)
                 goto out_delete;
 
+        if (top->nr_threads_synthesize > 1)
+                perf_set_multithreaded();
+
         machine__synthesize_threads(&top->session->machines.host, &opts->target,
-                                    top->evlist->threads, false, opts->proc_map_timeout);
+                                    top->evlist->threads, false,
+                                    opts->proc_map_timeout,
+                                    top->nr_threads_synthesize);
+
+        if (top->nr_threads_synthesize > 1)
+                perf_set_singlethreaded();
 
         if (perf_hpp_list.socket) {
                 ret = perf_env__read_cpu_topology_map(&perf_env);
@@ -1097,6 +1120,7 @@ int cmd_top(int argc, const char **argv)
                 },
                 .max_stack           = sysctl_perf_event_max_stack,
                 .sym_pcnt_filter     = 5,
+                .nr_threads_synthesize = UINT_MAX,
         };
         struct record_opts *opts = &top.record_opts;
         struct target *target = &opts->target;
@@ -1205,6 +1229,9 @@ int cmd_top(int argc, const char **argv)
                     "Show raw trace event output (do not use print fmt or plugins)"),
         OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
                     "Show entries in a hierarchy"),
+        OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
+        OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
+                        "number of thread to run event synthesize"),
         OPT_END()
         };
         const char * const top_usage[] = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 4b2a5d298197..f2757d38c7d7 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -64,6 +64,10 @@
 # define O_CLOEXEC              02000000
 #endif
 
+#ifndef F_LINUX_SPECIFIC_BASE
+# define F_LINUX_SPECIFIC_BASE  1024
+#endif
+
 struct trace {
         struct perf_tool        tool;
         struct syscalltbl       *sctbl;
@@ -279,34 +283,21 @@ out_delete:
         ({ struct syscall_tp *fields = evsel->priv; \
            fields->name.pointer(&fields->name, sample); })
 
-struct strarray {
-        int         offset;
-        int         nr_entries;
-        const char **entries;
-};
+size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val)
+{
+        int idx = val - sa->offset;
 
-#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
-        .nr_entries = ARRAY_SIZE(array), \
-        .entries = array, \
-}
+        if (idx < 0 || idx >= sa->nr_entries)
+                return scnprintf(bf, size, intfmt, val);
 
-#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
-        .offset     = off, \
-        .nr_entries = ARRAY_SIZE(array), \
-        .entries = array, \
+        return scnprintf(bf, size, "%s", sa->entries[idx]);
 }
 
 static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
                                                 const char *intfmt,
                                                 struct syscall_arg *arg)
 {
-        struct strarray *sa = arg->parm;
-        int idx = arg->val - sa->offset;
-
-        if (idx < 0 || idx >= sa->nr_entries)
-                return scnprintf(bf, size, intfmt, arg->val);
-
-        return scnprintf(bf, size, "%s", sa->entries[idx]);
+        return strarray__scnprintf(arg->parm, bf, size, intfmt, arg->val);
 }
 
 static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
@@ -317,24 +308,35 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
 
 #define SCA_STRARRAY syscall_arg__scnprintf_strarray
 
-#if defined(__i386__) || defined(__x86_64__)
-/*
- * FIXME: Make this available to all arches as soon as the ioctl beautifier
- *        gets rewritten to support all arches.
- */
-static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
-                                                 struct syscall_arg *arg)
-{
-        return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
+struct strarrays {
+        int             nr_entries;
+        struct strarray **entries;
+};
+
+#define DEFINE_STRARRAYS(array) struct strarrays strarrays__##array = { \
+        .nr_entries = ARRAY_SIZE(array), \
+        .entries = array, \
 }
 
-#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
-#endif /* defined(__i386__) || defined(__x86_64__) */
+size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size,
+                                        struct syscall_arg *arg)
+{
+        struct strarrays *sas = arg->parm;
+        int i;
 
-static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
-                                        struct syscall_arg *arg);
+        for (i = 0; i < sas->nr_entries; ++i) {
+                struct strarray *sa = sas->entries[i];
+                int idx = arg->val - sa->offset;
 
-#define SCA_FD syscall_arg__scnprintf_fd
+                if (idx >= 0 && idx < sa->nr_entries) {
+                        if (sa->entries[idx] == NULL)
+                                break;
+                        return scnprintf(bf, size, "%s", sa->entries[idx]);
+                }
+        }
+
+        return scnprintf(bf, size, "%d", arg->val);
+}
 
 #ifndef AT_FDCWD
 #define AT_FDCWD        -100
@@ -358,21 +360,20 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 
 #define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd
 
-static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
-                                         struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg)
 {
         return scnprintf(bf, size, "%#lx", arg->val);
 }
 
-#define SCA_HEX syscall_arg__scnprintf_hex
-
-static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
-                                         struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg)
 {
         return scnprintf(bf, size, "%d", arg->val);
 }
 
-#define SCA_INT syscall_arg__scnprintf_int
+size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg)
+{
+        return scnprintf(bf, size, "%ld", arg->val);
+}
 
 static const char *bpf_cmd[] = {
         "MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
@@ -407,12 +408,27 @@ static DEFINE_STRARRAY(whences);
 
 static const char *fcntl_cmds[] = {
         "DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
-        "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64",
-        "F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
-        "F_GETOWNER_UIDS",
+        "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "GETLK64",
+        "SETLK64", "SETLKW64", "SETOWN_EX", "GETOWN_EX",
+        "GETOWNER_UIDS",
 };
 static DEFINE_STRARRAY(fcntl_cmds);
 
+static const char *fcntl_linux_specific_cmds[] = {
+        "SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC",
+        "SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS",
+        "GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT",
+};
+
+static DEFINE_STRARRAY_OFFSET(fcntl_linux_specific_cmds, F_LINUX_SPECIFIC_BASE);
+
+static struct strarray *fcntl_cmds_arrays[] = {
+        &strarray__fcntl_cmds,
+        &strarray__fcntl_linux_specific_cmds,
+};
+
+static DEFINE_STRARRAYS(fcntl_cmds_arrays);
+
 static const char *rlimit_resources[] = {
         "CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
         "MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
@@ -495,33 +511,6 @@ static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
 
 #define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
 
-#if defined(__i386__) || defined(__x86_64__)
-/*
- * FIXME: Make this available to all arches.
- */
-#define TCGETS          0x5401
-
-static const char *tioctls[] = {
-        "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
-        "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
-        "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
-        "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
-        "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
-        "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
-        "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
-        "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
-        "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
-        "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
-        "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
-        [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
-        "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
-        "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
-        "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
-};
-
-static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
-#endif /* defined(__i386__) || defined(__x86_64__) */
-
 #ifndef GRND_NONBLOCK
 #define GRND_NONBLOCK   0x0001
 #endif
@@ -552,9 +541,9 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 #define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags
 
-#define STRARRAY(arg, name, array) \
-          .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
-          .arg_parm      = { [arg] = &strarray__##array, }
+#define STRARRAY(name, array) \
+          { .scnprintf  = SCA_STRARRAY, \
+            .parm       = &strarray__##array, }
 
 #include "trace/beauty/eventfd.c"
 #include "trace/beauty/flock.c"
@@ -571,242 +560,228 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 #include "trace/beauty/socket_type.c"
 #include "trace/beauty/waitid_options.c"
 
+struct syscall_arg_fmt {
+        size_t     (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+        void       *parm;
+        const char *name;
+        bool       show_zero;
+};
+
 static struct syscall_fmt {
         const char *name;
         const char *alias;
-        size_t     (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
-        void       *arg_parm[6];
-        bool       errmsg;
+        struct syscall_arg_fmt arg[6];
+        u8         nr_args;
         bool       errpid;
         bool       timeout;
         bool       hexret;
 } syscall_fmts[] = {
-        { .name     = "access",     .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_ACCMODE,  /* mode */ }, },
-        { .name     = "arch_prctl", .errmsg = true, .alias = "prctl", },
-        { .name     = "bpf",        .errmsg = true, STRARRAY(0, cmd, bpf_cmd), },
+        { .name     = "access",
+          .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
+        { .name     = "bpf",
+          .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
         { .name     = "brk",        .hexret = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
-        { .name     = "chdir",      .errmsg = true, },
-        { .name     = "chmod",      .errmsg = true, },
-        { .name     = "chroot",     .errmsg = true, },
-        { .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
-        { .name     = "clone",      .errpid = true, },
-        { .name     = "close",      .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
-        { .name     = "connect",    .errmsg = true, },
-        { .name     = "creat",      .errmsg = true, },
-        { .name     = "dup",        .errmsg = true, },
-        { .name     = "dup2",       .errmsg = true, },
-        { .name     = "dup3",       .errmsg = true, },
-        { .name     = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
-        { .name     = "eventfd2",   .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
-        { .name     = "faccessat",  .errmsg = true, },
-        { .name     = "fadvise64",  .errmsg = true, },
-        { .name     = "fallocate",  .errmsg = true, },
-        { .name     = "fchdir",     .errmsg = true, },
-        { .name     = "fchmod",     .errmsg = true, },
-        { .name     = "fchmodat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "fchown",     .errmsg = true, },
-        { .name     = "fchownat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "fcntl",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
-          .arg_parm      = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
-        { .name     = "fdatasync",  .errmsg = true, },
-        { .name     = "flock",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, },
-        { .name     = "fsetxattr",  .errmsg = true, },
-        { .name     = "fstat",      .errmsg = true, .alias = "newfstat", },
-        { .name     = "fstatat",    .errmsg = true, .alias = "newfstatat", },
-        { .name     = "fstatfs",    .errmsg = true, },
-        { .name     = "fsync",    .errmsg = true, },
-        { .name     = "ftruncate", .errmsg = true, },
-        { .name     = "futex",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
-        { .name     = "futimesat", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "getdents",   .errmsg = true, },
-        { .name     = "getdents64", .errmsg = true, },
-        { .name     = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* brk */ }, }, },
+        { .name     = "clock_gettime",
+          .arg = { [0] = STRARRAY(clk_id, clockid), }, },
+        { .name     = "clone",      .errpid = true, .nr_args = 5,
+          .arg = { [0] = { .name = "flags",         .scnprintf = SCA_CLONE_FLAGS, },
+                   [1] = { .name = "child_stack",   .scnprintf = SCA_HEX, },
+                   [2] = { .name = "parent_tidptr", .scnprintf = SCA_HEX, },
+                   [3] = { .name = "child_tidptr",  .scnprintf = SCA_HEX, },
+                   [4] = { .name = "tls",           .scnprintf = SCA_HEX, }, }, },
+        { .name     = "close",
+          .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
+        { .name     = "epoll_ctl",
+          .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
+        { .name     = "eventfd2",
+          .arg = { [1] = { .scnprintf = SCA_EFD_FLAGS, /* flags */ }, }, },
+        { .name     = "fchmodat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "fchownat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "fcntl",
+          .arg = { [1] = { .scnprintf = SCA_FCNTL_CMD, /* cmd */
+                           .parm      = &strarrays__fcntl_cmds_arrays,
+                           .show_zero = true, },
+                   [2] = { .scnprintf =  SCA_FCNTL_ARG, /* arg */ }, }, },
+        { .name     = "flock",
+          .arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, },
+        { .name     = "fstat", .alias = "newfstat", },
+        { .name     = "fstatat", .alias = "newfstatat", },
+        { .name     = "futex",
+          .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ }, }, },
+        { .name     = "futimesat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "getitimer",
+          .arg = { [0] = STRARRAY(which, itimers), }, },
         { .name     = "getpid",     .errpid = true, },
         { .name     = "getpgid",    .errpid = true, },
         { .name     = "getppid",    .errpid = true, },
-        { .name     = "getrandom",  .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
-        { .name     = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-        { .name     = "getxattr",   .errmsg = true, },
-        { .name     = "inotify_add_watch",          .errmsg = true, },
-        { .name     = "ioctl",      .errmsg = true,
-          .arg_scnprintf = {
+        { .name     = "getrandom",
+          .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, },
+        { .name     = "getrlimit",
+          .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "ioctl",
+          .arg = {
 #if defined(__i386__) || defined(__x86_64__)
 /*
  * FIXME: Make this available to all arches.
  */
-                             [1] = SCA_STRHEXARRAY, /* cmd */
-                             [2] = SCA_HEX, /* arg */ },
-          .arg_parm      = { [1] = &strarray__tioctls, /* cmd */ }, },
+                   [1] = { .scnprintf = SCA_IOCTL_CMD, /* cmd */ },
+                   [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
 #else
-                             [2] = SCA_HEX, /* arg */ }, },
+                   [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
 #endif
-        { .name     = "keyctl",     .errmsg = true, STRARRAY(0, option, keyctl_options), },
-        { .name     = "kill",       .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "lchown",    .errmsg = true, },
-        { .name     = "lgetxattr",  .errmsg = true, },
-        { .name     = "linkat",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "listxattr",  .errmsg = true, },
-        { .name     = "llistxattr", .errmsg = true, },
-        { .name     = "lremovexattr",  .errmsg = true, },
-        { .name     = "lseek",      .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
-          .arg_parm      = { [2] = &strarray__whences, /* whence */ }, },
-        { .name     = "lsetxattr",  .errmsg = true, },
-        { .name     = "lstat",      .errmsg = true, .alias = "newlstat", },
-        { .name     = "lsxattr",    .errmsg = true, },
-        { .name     = "madvise",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX,      /* start */
-                             [2] = SCA_MADV_BHV, /* behavior */ }, },
-        { .name     = "mkdir",    .errmsg = true, },
-        { .name     = "mkdirat",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "mknod",      .errmsg = true, },
-        { .name     = "mknodat",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "mlock",      .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
-        { .name     = "mlockall",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+        { .name     = "kcmp",       .nr_args = 5,
+          .arg = { [0] = { .name = "pid1",      .scnprintf = SCA_PID, },
+                   [1] = { .name = "pid2",      .scnprintf = SCA_PID, },
+                   [2] = { .name = "type",      .scnprintf = SCA_KCMP_TYPE, },
+                   [3] = { .name = "idx1",      .scnprintf = SCA_KCMP_IDX, },
+                   [4] = { .name = "idx2",      .scnprintf = SCA_KCMP_IDX, }, }, },
+        { .name     = "keyctl",
+          .arg = { [0] = STRARRAY(option, keyctl_options), }, },
+        { .name     = "kill",
+          .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "linkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "lseek",
+          .arg = { [2] = STRARRAY(whence, whences), }, },
+        { .name     = "lstat", .alias = "newlstat", },
+        { .name     = "madvise",
+          .arg = { [0] = { .scnprintf = SCA_HEX,      /* start */ },
+                   [2] = { .scnprintf = SCA_MADV_BHV, /* behavior */ }, }, },
+        { .name     = "mkdirat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "mknodat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "mlock",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
+        { .name     = "mlockall",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
         { .name     = "mmap",       .hexret = true,
 /* The standard mmap maps to old_mmap on s390x */
 #if defined(__s390x__)
         .alias = "old_mmap",
 #endif
-          .arg_scnprintf = { [0] = SCA_HEX,       /* addr */
-                             [2] = SCA_MMAP_PROT, /* prot */
-                             [3] = SCA_MMAP_FLAGS, /* flags */ }, },
-        { .name     = "mprotect",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* start */
-                             [2] = SCA_MMAP_PROT, /* prot */ }, },
-        { .name     = "mq_unlink", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FILENAME, /* u_name */ }, },
+          .arg = { [0] = { .scnprintf = SCA_HEX,        /* addr */ },
+                   [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ },
+                   [3] = { .scnprintf = SCA_MMAP_FLAGS, /* flags */ }, }, },
+        { .name     = "mprotect",
+          .arg = { [0] = { .scnprintf = SCA_HEX,        /* start */ },
+                   [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ }, }, },
+        { .name     = "mq_unlink",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* u_name */ }, }, },
         { .name     = "mremap",     .hexret = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */
-                             [3] = SCA_MREMAP_FLAGS, /* flags */
-                             [4] = SCA_HEX, /* new_addr */ }, },
-        { .name     = "munlock",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
-        { .name     = "munmap",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
-        { .name     = "name_to_handle_at", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "newfstatat", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "open",       .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
-        { .name     = "open_by_handle_at", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-                             [2] = SCA_OPEN_FLAGS, /* flags */ }, },
-        { .name     = "openat",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-                             [2] = SCA_OPEN_FLAGS, /* flags */ }, },
-        { .name     = "perf_event_open", .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_INT, /* cpu */
-                             [3] = SCA_FD,  /* group_fd */
-                             [4] = SCA_PERF_FLAGS,  /* flags */ }, },
-        { .name     = "pipe2",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
-        { .name     = "poll",       .errmsg = true, .timeout = true, },
-        { .name     = "ppoll",      .errmsg = true, .timeout = true, },
-        { .name     = "pread",      .errmsg = true, .alias = "pread64", },
-        { .name     = "preadv",     .errmsg = true, .alias = "pread", },
-        { .name     = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
-        { .name     = "pwrite",     .errmsg = true, .alias = "pwrite64", },
-        { .name     = "pwritev",    .errmsg = true, },
-        { .name     = "read",       .errmsg = true, },
-        { .name     = "readlink",   .errmsg = true, },
-        { .name     = "readlinkat", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "readv",      .errmsg = true, },
-        { .name     = "recvfrom",   .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "recvmmsg",   .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "recvmsg",    .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "removexattr", .errmsg = true, },
-        { .name     = "renameat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "rmdir",    .errmsg = true, },
-        { .name     = "rt_sigaction", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
-        { .name     = "rt_sigqueueinfo", .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "rt_tgsigqueueinfo", .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "sched_getattr",        .errmsg = true, },
-        { .name     = "sched_setattr",        .errmsg = true, },
-        { .name     = "sched_setscheduler",   .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
-        { .name     = "seccomp", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */
-                             [1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
-        { .name     = "select",     .errmsg = true, .timeout = true, },
-        { .name     = "sendmmsg",    .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "sendmsg",    .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "sendto",     .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+          .arg = { [0] = { .scnprintf = SCA_HEX,          /* addr */ },
+                   [3] = { .scnprintf = SCA_MREMAP_FLAGS, /* flags */ },
+                   [4] = { .scnprintf = SCA_HEX,          /* new_addr */ }, }, },
+        { .name     = "munlock",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
+        { .name     = "munmap",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
+        { .name     = "name_to_handle_at",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "newfstatat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "open",
+          .arg = { [1] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
+        { .name     = "open_by_handle_at",
+          .arg = { [0] = { .scnprintf = SCA_FDAT,       /* dfd */ },
+                   [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
+        { .name     = "openat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT,       /* dfd */ },
+                   [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
+        { .name     = "perf_event_open",
+          .arg = { [2] = { .scnprintf = SCA_INT,        /* cpu */ },
+                   [3] = { .scnprintf = SCA_FD,         /* group_fd */ },
+                   [4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, },
+        { .name     = "pipe2",
+          .arg = { [1] = { .scnprintf = SCA_PIPE_FLAGS, /* flags */ }, }, },
+        { .name     = "pkey_alloc",
+          .arg = { [1] = { .scnprintf = SCA_PKEY_ALLOC_ACCESS_RIGHTS,   /* access_rights */ }, }, },
+        { .name     = "pkey_free",
+          .arg = { [0] = { .scnprintf = SCA_INT,        /* key */ }, }, },
+        { .name     = "pkey_mprotect",
+          .arg = { [0] = { .scnprintf = SCA_HEX,        /* start */ },
+                   [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ },
+                   [3] = { .scnprintf = SCA_INT,        /* pkey */ }, }, },
+        { .name     = "poll", .timeout = true, },
+        { .name     = "ppoll", .timeout = true, },
+        { .name     = "prctl", .alias = "arch_prctl",
+          .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
+                   [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
+                   [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
+        { .name     = "pread", .alias = "pread64", },
+        { .name     = "preadv", .alias = "pread", },
+        { .name     = "prlimit64",
+          .arg = { [1] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "pwrite", .alias = "pwrite64", },
+        { .name     = "readlinkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "recvfrom",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "recvmmsg",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "recvmsg",
+          .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "renameat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "rt_sigaction",
+          .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "rt_sigprocmask",
+          .arg = { [0] = STRARRAY(how, sighow), }, },
+        { .name     = "rt_sigqueueinfo",
+          .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "rt_tgsigqueueinfo",
+          .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "sched_setscheduler",
+          .arg = { [1] = { .scnprintf = SCA_SCHED_POLICY, /* policy */ }, }, },
+        { .name     = "seccomp",
+          .arg = { [0] = { .scnprintf = SCA_SECCOMP_OP,    /* op */ },
+                   [1] = { .scnprintf = SCA_SECCOMP_FLAGS, /* flags */ }, }, },
+        { .name     = "select", .timeout = true, },
+        { .name     = "sendmmsg",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "sendmsg",
+          .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "sendto",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
         { .name     = "set_tid_address", .errpid = true, },
-        { .name     = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
-        { .name     = "setpgid",    .errmsg = true, },
-        { .name     = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-        { .name     = "setxattr",   .errmsg = true, },
-        { .name     = "shutdown",   .errmsg = true, },
-        { .name     = "socket",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
-                             [1] = SCA_SK_TYPE, /* type */ },
-          .arg_parm      = { [0] = &strarray__socket_families, /* family */ }, },
-        { .name     = "socketpair", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
-                             [1] = SCA_SK_TYPE, /* type */ },
-          .arg_parm      = { [0] = &strarray__socket_families, /* family */ }, },
-        { .name     = "stat",       .errmsg = true, .alias = "newstat", },
-        { .name     = "statfs",     .errmsg = true, },
-        { .name     = "statx",      .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* flags */
-                             [2] = SCA_STATX_FLAGS, /* flags */
-                             [3] = SCA_STATX_MASK, /* mask */ }, },
-        { .name     = "swapoff",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
-        { .name     = "swapon",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
-        { .name     = "symlinkat",  .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "tgkill",     .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "tkill",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "truncate",   .errmsg = true, },
-        { .name     = "uname",      .errmsg = true, .alias = "newuname", },
-        { .name     = "unlinkat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "utime",  .errmsg = true, },
-        { .name     = "utimensat",  .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
-        { .name     = "utimes",  .errmsg = true, },
-        { .name     = "vmsplice",  .errmsg = true, },
+        { .name     = "setitimer",
+          .arg = { [0] = STRARRAY(which, itimers), }, },
+        { .name     = "setrlimit",
+          .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "socket",
+          .arg = { [0] = STRARRAY(family, socket_families),
+                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+        { .name     = "socketpair",
+          .arg = { [0] = STRARRAY(family, socket_families),
+                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+        { .name     = "stat", .alias = "newstat", },
+        { .name     = "statx",
+          .arg = { [0] = { .scnprintf = SCA_FDAT,        /* fdat */ },
+                   [2] = { .scnprintf = SCA_STATX_FLAGS, /* flags */ } ,
+                   [3] = { .scnprintf = SCA_STATX_MASK,  /* mask */ }, }, },
+        { .name     = "swapoff",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
+        { .name     = "swapon",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
+        { .name     = "symlinkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "tgkill",
+          .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "tkill",
+          .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "uname", .alias = "newuname", },
+        { .name     = "unlinkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "utimensat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dirfd */ }, }, },
         { .name     = "wait4",      .errpid = true,
-          .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
+          .arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
         { .name     = "waitid",     .errpid = true,
-          .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
-        { .name     = "write",      .errmsg = true, },
-        { .name     = "writev",     .errmsg = true, },
+          .arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
 };
 
 static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -828,8 +803,7 @@ struct syscall {
         const char          *name;
         bool                is_exit;
         struct syscall_fmt  *fmt;
-        size_t              (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
-        void                **arg_parm;
+        struct syscall_arg_fmt *arg_fmt;
 };
 
 /*
@@ -859,6 +833,8 @@ static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
  * filename.ptr: The filename char pointer that will be vfs_getname'd
  * filename.entry_str_pos: Where to insert the string translated from
  *                         filename.ptr by the vfs_getname tracepoint/kprobe.
+ * ret_scnprintf: syscall args may set this to a different syscall return
+ *                formatter, for instance, fcntl may return fds, file flags, etc.
  */
 struct thread_trace {
         u64               entry_time;
@@ -867,6 +843,7 @@ struct thread_trace {
         unsigned long     pfmaj, pfmin;
         char              *entry_str;
         double            runtime_ms;
+        size_t            (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
         struct {
                 unsigned long ptr;
                 short int     entry_str_pos;
@@ -917,6 +894,15 @@ fail:
         return NULL;
 }
 
+
+void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
+                                    size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg))
+{
+        struct thread_trace *ttrace = thread__priv(arg->thread);
+
+        ttrace->ret_scnprintf = ret_scnprintf;
+}
+
 #define TRACE_PFMAJ             (1 << 0)
 #define TRACE_PFMIN             (1 << 1)
 
@@ -996,8 +982,7 @@ static const char *thread__fd_path(struct thread *thread, int fd,
         return ttrace->paths.table[fd];
 }
 
-static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
-                                        struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
 {
         int fd = arg->val;
         size_t printed = scnprintf(bf, size, "%d", fd);
@@ -1009,6 +994,23 @@ static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
         return printed;
 }
 
+size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size)
+{
+        size_t printed = scnprintf(bf, size, "%d", fd);
+        struct thread *thread = machine__find_thread(trace->host, pid, pid);
+
+        if (thread) {
+                const char *path = thread__fd_path(thread, fd, trace);
+
+                if (path)
+                        printed += scnprintf(bf + printed, size - printed, "<%s>", path);
+
+                thread__put(thread);
+        }
+
+        return printed;
+}
+
 static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
                                               struct syscall_arg *arg)
 {
@@ -1155,39 +1157,61 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 
         err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
                                             evlist->threads, trace__tool_process, false,
-                                            trace->opts.proc_map_timeout);
+                                            trace->opts.proc_map_timeout, 1);
         if (err)
                 symbol__exit();
 
         return err;
 }
 
+static void trace__symbols__exit(struct trace *trace)
+{
+        machine__exit(trace->host);
+        trace->host = NULL;
+
+        symbol__exit();
+}
+
+static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
+{
+        int idx;
+
+        if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0)
+                nr_args = sc->fmt->nr_args;
+
+        sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt));
+        if (sc->arg_fmt == NULL)
+                return -1;
+
+        for (idx = 0; idx < nr_args; ++idx) {
+                if (sc->fmt)
+                        sc->arg_fmt[idx] = sc->fmt->arg[idx];
+        }
+
+        sc->nr_args = nr_args;
+        return 0;
+}
+
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
         struct format_field *field;
         int idx = 0, len;
 
-        sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
-        if (sc->arg_scnprintf == NULL)
-                return -1;
-
-        if (sc->fmt)
-                sc->arg_parm = sc->fmt->arg_parm;
+        for (field = sc->args; field; field = field->next, ++idx) {
+                if (sc->fmt && sc->fmt->arg[idx].scnprintf)
+                        continue;
 
-        for (field = sc->args; field; field = field->next) {
-                if (sc->fmt && sc->fmt->arg_scnprintf[idx])
-                        sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
-                else if (strcmp(field->type, "const char *") == 0 &&
+                if (strcmp(field->type, "const char *") == 0 &&
                          (strcmp(field->name, "filename") == 0 ||
                           strcmp(field->name, "path") == 0 ||
                           strcmp(field->name, "pathname") == 0))
-                        sc->arg_scnprintf[idx] = SCA_FILENAME;
+                        sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
                 else if (field->flags & FIELD_IS_POINTER)
-                        sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
+                        sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex;
                 else if (strcmp(field->type, "pid_t") == 0)
-                        sc->arg_scnprintf[idx] = SCA_PID;
+                        sc->arg_fmt[idx].scnprintf = SCA_PID;
                 else if (strcmp(field->type, "umode_t") == 0)
-                        sc->arg_scnprintf[idx] = SCA_MODE_T;
+                        sc->arg_fmt[idx].scnprintf = SCA_MODE_T;
                 else if ((strcmp(field->type, "int") == 0 ||
                           strcmp(field->type, "unsigned int") == 0 ||
                           strcmp(field->type, "long") == 0) &&
@@ -1200,9 +1224,8 @@ static int syscall__set_arg_fmts(struct syscall *sc)
                          * 23 unsigned int
                          * 7 unsigned long
                          */
-                        sc->arg_scnprintf[idx] = SCA_FD;
+                        sc->arg_fmt[idx].scnprintf = SCA_FD;
                 }
-                ++idx;
         }
 
         return 0;
@@ -1247,11 +1270,13 @@ static int trace__read_syscall_info(struct trace *trace, int id)
                 sc->tp_format = trace_event__tp_format("syscalls", tp_name);
         }
 
+        if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields))
+                return -1;
+
         if (IS_ERR(sc->tp_format))
                 return -1;
 
         sc->args = sc->tp_format->format.fields;
-        sc->nr_args = sc->tp_format->format.nr_fields;
         /*
          * We need to check and discard the first variable '__syscall_nr'
          * or 'nr' that mean the syscall number. It is needless here.
@@ -1270,6 +1295,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 static int trace__validate_ev_qualifier(struct trace *trace)
 {
         int err = 0, i;
+        size_t nr_allocated;
         struct str_node *pos;
 
         trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
@@ -1283,13 +1309,18 @@ static int trace__validate_ev_qualifier(struct trace *trace)
                 goto out;
         }
 
+        nr_allocated = trace->ev_qualifier_ids.nr;
         i = 0;
 
         strlist__for_each_entry(pos, trace->ev_qualifier) {
                 const char *sc = pos->s;
-                int id = syscalltbl__id(trace->sctbl, sc);
+                int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
 
                 if (id < 0) {
+                        id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
+                        if (id >= 0)
+                                goto matches;
+
                         if (err == 0) {
                                 fputs("Error:\tInvalid syscall ", trace->output);
                                 err = -EINVAL;
@@ -1299,13 +1330,37 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
                         fputs(sc, trace->output);
                 }
-
+matches:
                 trace->ev_qualifier_ids.entries[i++] = id;
+                if (match_next == -1)
+                        continue;
+
+                while (1) {
+                        id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
+                        if (id < 0)
+                                break;
+                        if (nr_allocated == trace->ev_qualifier_ids.nr) {
+                                void *entries;
+
+                                nr_allocated += 8;
+                                entries = realloc(trace->ev_qualifier_ids.entries,
+                                                  nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
+                                if (entries == NULL) {
+                                        err = -ENOMEM;
+                                        fputs("\nError:\t Not enough memory for parsing\n", trace->output);
+                                        goto out_free;
+                                }
+                                trace->ev_qualifier_ids.entries = entries;
+                        }
+                        trace->ev_qualifier_ids.nr++;
+                        trace->ev_qualifier_ids.entries[i++] = id;
+                }
         }
 
         if (err < 0) {
                 fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
                       "\nHint:\tand: 'man syscalls'\n", trace->output);
+out_free:
                 zfree(&trace->ev_qualifier_ids.entries);
                 trace->ev_qualifier_ids.nr = 0;
         }
@@ -1321,33 +1376,68 @@ out:
  * variable to read it. Most notably this avoids extended load instructions
  * on unaligned addresses
  */
+unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx)
+{
+        unsigned long val;
+        unsigned char *p = arg->args + sizeof(unsigned long) * idx;
+
+        memcpy(&val, p, sizeof(val));
+        return val;
+}
+
+static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
+                                      struct syscall_arg *arg)
+{
+        if (sc->arg_fmt && sc->arg_fmt[arg->idx].name)
+                return scnprintf(bf, size, "%s: ", sc->arg_fmt[arg->idx].name);
+
+        return scnprintf(bf, size, "arg%d: ", arg->idx);
+}
+
+static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
+                                     struct syscall_arg *arg, unsigned long val)
+{
+        if (sc->arg_fmt && sc->arg_fmt[arg->idx].scnprintf) {
+                arg->val = val;
+                if (sc->arg_fmt[arg->idx].parm)
+                        arg->parm = sc->arg_fmt[arg->idx].parm;
+                return sc->arg_fmt[arg->idx].scnprintf(bf, size, arg);
+        }
+        return scnprintf(bf, size, "%ld", val);
+}
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                                       unsigned char *args, struct trace *trace,
                                       struct thread *thread)
 {
         size_t printed = 0;
-        unsigned char *p;
         unsigned long val;
+        u8 bit = 1;
+        struct syscall_arg arg = {
+                .args   = args,
+                .idx    = 0,
+                .mask   = 0,
+                .trace  = trace,
+                .thread = thread,
+        };
+        struct thread_trace *ttrace = thread__priv(thread);
+
+        /*
+         * Things like fcntl will set this in its 'cmd' formatter to pick the
+         * right formatter for the return value (an fd? file flags?), which is
+         * not needed for syscalls that always return a given type, say an fd.
+         */
+        ttrace->ret_scnprintf = NULL;
 
         if (sc->args != NULL) {
                 struct format_field *field;
-                u8 bit = 1;
-                struct syscall_arg arg = {
-                        .idx    = 0,
-                        .mask   = 0,
-                        .trace  = trace,
-                        .thread = thread,
-                };
 
                 for (field = sc->args; field;
                      field = field->next, ++arg.idx, bit <<= 1) {
                         if (arg.mask & bit)
                                 continue;
 
-                        /* special care for unaligned accesses */
-                        p = args + sizeof(unsigned long) * arg.idx;
-                        memcpy(&val, p, sizeof(val));
+                        val = syscall_arg__val(&arg, arg.idx);
 
                         /*
                          * Suppress this argument if its value is zero and
@@ -1355,23 +1445,16 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                          * strarray for it.
                          */
                         if (val == 0 &&
-                            !(sc->arg_scnprintf &&
-                              sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
-                              sc->arg_parm[arg.idx]))
+                            !(sc->arg_fmt &&
+                              (sc->arg_fmt[arg.idx].show_zero ||
+                               sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAY ||
+                               sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAYS) &&
+                              sc->arg_fmt[arg.idx].parm))
                                 continue;
 
                         printed += scnprintf(bf + printed, size - printed,
                                              "%s%s: ", printed ? ", " : "", field->name);
-                        if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
-                                arg.val = val;
-                                if (sc->arg_parm)
-                                        arg.parm = sc->arg_parm[arg.idx];
-                                printed += sc->arg_scnprintf[arg.idx](bf + printed,
-                                                                      size - printed, &arg);
-                        } else {
-                                printed += scnprintf(bf + printed, size - printed,
-                                                     "%ld", val);
-                        }
+                        printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
                 }
         } else if (IS_ERR(sc->tp_format)) {
                 /*
@@ -1379,16 +1462,17 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                  * may end up not having any args, like with gettid(), so only
                  * print the raw args when we didn't manage to read it.
                  */
-                int i = 0;
-
-                while (i < 6) {
-                        /* special care for unaligned accesses */
-                        p = args + sizeof(unsigned long) * i;
-                        memcpy(&val, p, sizeof(val));
-                        printed += scnprintf(bf + printed, size - printed,
-                                             "%sarg%d: %ld",
-                                             printed ? ", " : "", i, val);
-                        ++i;
+                while (arg.idx < sc->nr_args) {
+                        if (arg.mask & bit)
+                                goto next_arg;
+                        val = syscall_arg__val(&arg, arg.idx);
+                        if (printed)
+                                printed += scnprintf(bf + printed, size - printed, ", ");
+                        printed += syscall__scnprintf_name(sc, bf + printed, size - printed, &arg);
+                        printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
+next_arg:
+                        ++arg.idx;
+                        bit <<= 1;
                 }
         }
 
@@ -1635,17 +1719,31 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
         }
 
         if (sc->fmt == NULL) {
+                if (ret < 0)
+                        goto errno_print;
 signed_print:
                 fprintf(trace->output, ") = %ld", ret);
-        } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
+        } else if (ret < 0) {
+errno_print: {
                 char bf[STRERR_BUFSIZE];
                 const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
                            *e = audit_errno_to_name(-ret);
 
                 fprintf(trace->output, ") = -1 %s %s", e, emsg);
+        }
         } else if (ret == 0 && sc->fmt->timeout)
                 fprintf(trace->output, ") = 0 Timeout");
-        else if (sc->fmt->hexret)
+        else if (ttrace->ret_scnprintf) {
+                char bf[1024];
+                struct syscall_arg arg = {
+                        .val    = ret,
+                        .thread = thread,
+                        .trace  = trace,
+                };
+                ttrace->ret_scnprintf(bf, sizeof(bf), &arg);
+                ttrace->ret_scnprintf = NULL;
+                fprintf(trace->output, ") = %s", bf);
+        } else if (sc->fmt->hexret)
                 fprintf(trace->output, ") = %#lx", ret);
         else if (sc->fmt->errpid) {
                 struct thread *child = machine__find_thread(trace->host, ret, ret);
@@ -1764,16 +1862,14 @@ out_dump:
         goto out_put;
 }
 
-static void bpf_output__printer(enum binary_printer_ops op,
-                                unsigned int val, void *extra)
+static int bpf_output__printer(enum binary_printer_ops op,
+                               unsigned int val, void *extra __maybe_unused, FILE *fp)
 {
-        FILE *output = extra;
         unsigned char ch = (unsigned char)val;
 
         switch (op) {
         case BINARY_PRINT_CHAR_DATA:
-                fprintf(output, "%c", isprint(ch) ? ch : '.');
-                break;
+                return fprintf(fp, "%c", isprint(ch) ? ch : '.');
         case BINARY_PRINT_DATA_BEGIN:
         case BINARY_PRINT_LINE_BEGIN:
         case BINARY_PRINT_ADDR:
@@ -1786,13 +1882,15 @@ static void bpf_output__printer(enum binary_printer_ops op,
         default:
                 break;
         }
+
+        return 0;
 }
 
 static void bpf_output__fprintf(struct trace *trace,
                                 struct perf_sample *sample)
 {
-        print_binary(sample->raw_data, sample->raw_size, 8,
-                     bpf_output__printer, trace->output);
+        binary__fprintf(sample->raw_data, sample->raw_size, 8,
+                        bpf_output__printer, NULL, trace->output);
 }
 
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
@@ -2014,6 +2112,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
                         rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
                 else {
                         pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+                        free(rec_argv);
                         return -1;
                 }
         }
@@ -2171,6 +2270,30 @@ out_enomem:
         goto out;
 }
 
+static int trace__set_filter_loop_pids(struct trace *trace)
+{
+        unsigned int nr = 1;
+        pid_t pids[32] = {
+                getpid(),
+        };
+        struct thread *thread = machine__find_thread(trace->host, pids[0], pids[0]);
+
+        while (thread && nr < ARRAY_SIZE(pids)) {
+                struct thread *parent = machine__find_thread(trace->host, thread->ppid, thread->ppid);
+
+                if (parent == NULL)
+                        break;
+
+                if (!strcmp(thread__comm_str(parent), "sshd")) {
+                        pids[nr++] = parent->tid;
+                        break;
+                }
+                thread = parent;
+        }
+
+        return perf_evlist__set_filter_pids(trace->evlist, nr, pids);
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
         struct perf_evlist *evlist = trace->evlist;
@@ -2294,7 +2417,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         if (trace->filter_pids.nr > 0)
                 err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
         else if (thread_map__pid(evlist->threads, 0) == -1)
-                err = perf_evlist__set_filter_pid(evlist, getpid());
+                err = trace__set_filter_loop_pids(trace);
 
         if (err < 0)
                 goto out_error_mem;
@@ -2393,6 +2516,8 @@ out_disable:
         }
 
 out_delete_evlist:
+        trace__symbols__exit(trace);
+
         perf_evlist__delete(evlist);
         trace->evlist = NULL;
         trace->live = false;
@@ -2440,10 +2565,12 @@ static int trace__replay(struct trace *trace)
         const struct perf_evsel_str_handler handlers[] = {
                 { "probe:vfs_getname",       trace__vfs_getname, },
         };
-        struct perf_data_file file = {
-                .path  = input_name,
-                .mode  = PERF_DATA_MODE_READ,
-                .force = trace->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = trace->force,
         };
         struct perf_session *session;
         struct perf_evsel *evsel;
@@ -2466,7 +2593,7 @@ static int trace__replay(struct trace *trace)
         /* add tid to output */
         trace->multiple_threads = true;
 
-        session = perf_session__new(&file, false, &trace->tool);
+        session = perf_session__new(&data, false, &trace->tool);
         if (session == NULL)
                 return -1;
 
@@ -2642,20 +2769,23 @@ DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_event
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 {
-        DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
         size_t printed = trace__fprintf_threads_header(fp);
         struct rb_node *nd;
+        int i;
 
-        if (threads == NULL) {
-                fprintf(fp, "%s", "Error sorting output by nr_events!\n");
-                return 0;
-        }
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host, i);
 
-        resort_rb__for_each_entry(nd, threads)
-                printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
+                if (threads == NULL) {
+                        fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+                        return 0;
+                }
 
-        resort_rb__delete(threads);
+                resort_rb__for_each_entry(nd, threads)
+                        printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
+                resort_rb__delete(threads);
+        }
         return printed;
 }
 
@@ -2756,7 +2886,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
         struct trace *trace = (struct trace *)opt->value;
         const char *s = str;
         char *sep = NULL, *lists[2] = { NULL, NULL, };
-        int len = strlen(str), err = -1, list;
+        int len = strlen(str) + 1, err = -1, list, idx;
         char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
         char group_name[PATH_MAX];
 
@@ -2773,7 +2903,8 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
                         *sep = '\0';
 
                 list = 0;
-                if (syscalltbl__id(trace->sctbl, s) >= 0) {
+                if (syscalltbl__id(trace->sctbl, s) >= 0 ||
+                    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
                         list = 1;
                 } else {
                         path__join(group_name, sizeof(group_name), strace_groups_dir, s);
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index d25149456a2f..37019c5d675f 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
 #include <linux/compiler.h>
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index d4d19fe3d050..05745f3ce912 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BUILTIN_H
 #define BUILTIN_H
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 83fe2202382e..77406d25e521 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -1,9 +1,18 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 HEADERS='
+include/uapi/drm/drm.h
+include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/kcmp.h
+include/uapi/linux/kvm.h
 include/uapi/linux/perf_event.h
+include/uapi/linux/prctl.h
+include/uapi/linux/sched.h
 include/uapi/linux/stat.h
+include/uapi/linux/vhost.h
+include/uapi/sound/asound.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
@@ -16,6 +25,7 @@ arch/x86/include/uapi/asm/perf_regs.h
 arch/x86/include/uapi/asm/kvm.h
 arch/x86/include/uapi/asm/kvm_perf.h
 arch/x86/include/uapi/asm/svm.h
+arch/x86/include/uapi/asm/unistd.h
 arch/x86/include/uapi/asm/vmx.h
 arch/powerpc/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm.h
@@ -29,12 +39,13 @@ include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/asm-generic/bitops/fls64.h
 include/linux/coresight-pmu.h
+include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
 '
 
 check () {
   file=$1
-  opts=
+  opts="--ignore-blank-lines --ignore-space-change"
 
   shift
   while [ -n "$*" ]; do
@@ -45,17 +56,22 @@ check () {
   cmd="diff $opts ../$file ../../$file > /dev/null"
 
   test -f ../../$file &&
-  eval $cmd || echo "Warning: $file differs from kernel" >&2
+  eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
 }
 
 
+# Check if we have the kernel headers (tools/perf/../../include), else
+# we're probably on a detached tarball, so no point in trying to check
+# differences.
+test -d ../../include || exit 0
+
 # simple diff check
 for i in $HEADERS; do
   check $i -B
 done
 
 # diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check arch/x86/lib/memset_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check include/uapi/asm-generic/mman.h -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
-check include/uapi/linux/mman.h       -B -I "^#include <\(uapi/\)*asm/mman.h>"
+check arch/x86/lib/memcpy_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check arch/x86/lib/memset_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
+check include/uapi/linux/mman.h       -I "^#include <\(uapi/\)*asm/mman.h>"
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
index c53a41f48b63..fe32d8344a82 100644
--- a/tools/perf/jvmti/jvmti_agent.h
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __JVMTI_AGENT_H__
 #define __JVMTI_AGENT_H__
 
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
index 6d710904c837..c62c9fc9a525 100644
--- a/tools/perf/jvmti/libjvmti.c
+++ b/tools/perf/jvmti/libjvmti.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <stdio.h>
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index e91930620269..0cfb3e2cefef 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 # perf archive
 # Arnaldo Carvalho de Melo <acme@redhat.com>
 
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index 3ba80b2359cc..345f5d6e9ed5 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -1,4 +1,5 @@
 # perf bash and zsh completion
+# SPDX-License-Identifier: GPL-2.0
 
 # Taken from git.git's completion script.
 __my_reassemble_comp_words_by_ref()
diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c
index 764e2547c25a..8c0ca0cc428f 100644
--- a/tools/perf/perf-read-vdso.c
+++ b/tools/perf/perf-read-vdso.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <string.h>
 
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index e4b717e9eb6c..36673f98d66b 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_SYS_H
 #define _PERF_SYS_H
 
@@ -9,16 +10,6 @@
 #include <linux/perf_event.h>
 #include <asm/barrier.h>
 
-#if defined(__i386__)
-#define cpu_relax()     asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC    {"model name"}
-#endif
-
-#if defined(__x86_64__)
-#define cpu_relax()     asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC    {"model name"}
-#endif
-
 #ifdef __powerpc__
 #define CPUINFO_PROC    {"cpu"}
 #endif
@@ -43,19 +34,10 @@
 #define CPUINFO_PROC    {"cpu model"}
 #endif
 
-#ifdef __ia64__
-#define cpu_relax()     asm volatile ("hint @pause" ::: "memory")
-#define CPUINFO_PROC    {"model name"}
-#endif
-
 #ifdef __arm__
 #define CPUINFO_PROC    {"model name", "Processor"}
 #endif
 
-#ifdef __aarch64__
-#define cpu_relax()     asm volatile("yield" ::: "memory")
-#endif
-
 #ifdef __mips__
 #define CPUINFO_PROC    {"cpu model"}
 #endif
@@ -72,13 +54,8 @@
 #define CPUINFO_PROC    {"core ID"}
 #endif
 
-#ifdef __tile__
-#define cpu_relax()     asm volatile ("mfspr zero, PASS" ::: "memory")
-#define CPUINFO_PROC    {"model name"}
-#endif
-
-#ifndef cpu_relax
-#define cpu_relax() barrier()
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC    { "model name", }
 #endif
 
 static inline int
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 628a5e412cb1..62b13518bc6e 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * perf.c
  *
@@ -89,7 +90,7 @@ struct pager_config {
 static int pager_command_config(const char *var, const char *value, void *data)
 {
         struct pager_config *c = data;
-        if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd))
+        if (strstarts(var, "pager.") && !strcmp(var + 6, c->cmd))
                 c->val = perf_config_bool(var, value);
         return 0;
 }
@@ -108,9 +109,9 @@ static int check_pager_config(const char *cmd)
 static int browser_command_config(const char *var, const char *value, void *data)
 {
         struct pager_config *c = data;
-        if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd))
+        if (strstarts(var, "tui.") && !strcmp(var + 4, c->cmd))
                 c->val = perf_config_bool(var, value);
-        if (!prefixcmp(var, "gtk.") && !strcmp(var + 4, c->cmd))
+        if (strstarts(var, "gtk.") && !strcmp(var + 4, c->cmd))
                 c->val = perf_config_bool(var, value) ? 2 : 0;
         return 0;
 }
@@ -192,7 +193,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                 /*
                  * Check remaining flags.
                  */
-                if (!prefixcmp(cmd, CMD_EXEC_PATH)) {
+                if (strstarts(cmd, CMD_EXEC_PATH)) {
                         cmd += strlen(CMD_EXEC_PATH);
                         if (*cmd == '=')
                                 set_argv_exec_path(cmd + 1);
@@ -229,7 +230,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                                 *envchanged = 1;
                         (*argv)++;
                         (*argc)--;
-                } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
+                } else if (strstarts(cmd, CMD_DEBUGFS_DIR)) {
                         tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR));
                         fprintf(stderr, "dir: %s\n", tracing_path);
                         if (envchanged)
@@ -467,17 +468,23 @@ int main(int argc, const char **argv)
          *  - cannot execute it externally (since it would just do
          *    the same thing over again)
          *
-         * So we just directly call the internal command handler, and
-         * die if that one cannot handle it.
+         * So we just directly call the internal command handler. If that one
+         * fails to handle this, then maybe we just run a renamed perf binary
+         * that contains a dash in its name. To handle this scenario, we just
+         * fall through and ignore the "xxxx" part of the command string.
          */
-        if (!prefixcmp(cmd, "perf-")) {
+        if (strstarts(cmd, "perf-")) {
                 cmd += 5;
                 argv[0] = cmd;
                 handle_internal_command(argc, argv);
-                fprintf(stderr, "cannot handle %s internally", cmd);
-                goto out;
+                /*
+                 * If the command is handled, the above function does not
+                 * return undo changes and fall through in such a case.
+                 */
+                cmd -= 5;
+                argv[0] = cmd;
         }
-        if (!prefixcmp(cmd, "trace")) {
+        if (strstarts(cmd, "trace")) {
 #ifdef HAVE_LIBAUDIT_SUPPORT
                 setup_path();
                 argv[0] = "trace";
@@ -495,7 +502,7 @@ int main(int argc, const char **argv)
         commit_pager_choice();
 
         if (argc > 0) {
-                if (!prefixcmp(argv[0], "--"))
+                if (strstarts(argv[0], "--"))
                         argv[0] += 2;
         } else {
                 /* The user didn't specify a command; give them help */
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 806c216a1078..2357f4ccc9c7 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_PERF_H
 #define _PERF_PERF_H
 
@@ -7,6 +8,7 @@
 #include <linux/perf_event.h>
 
 extern bool test_attr__enabled;
+void test_attr__ready(void);
 void test_attr__init(void);
 void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
                      int fd, int group_fd, unsigned long flags);
@@ -42,6 +44,7 @@ struct record_opts {
         bool         no_samples;
         bool         raw_samples;
         bool         sample_address;
+        bool         sample_phys_addr;
         bool         sample_weight;
         bool         sample_time;
         bool         sample_time_set;
@@ -63,6 +66,7 @@ struct record_opts {
         unsigned int user_freq;
         u64          branch_stack;
         u64          sample_intr_regs;
+        u64          sample_user_regs;
         u64          default_interval;
         u64          user_interval;
         size_t       auxtrace_snapshot_size;
diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README
index 1408ade0d773..c2ee3e4417fe 100644
--- a/tools/perf/pmu-events/README
+++ b/tools/perf/pmu-events/README
@@ -85,10 +85,6 @@ users to specify events by their name:
 
 where 'pm_1plus_ppc_cmpl' is a Power8 PMU event.
 
-In case of errors when processing files in the tools/perf/pmu-events/arch
-directory, 'jevents' tries to create an empty mapping file to allow the perf
-build to succeed even if the PMU event aliases cannot be used.
-
 However some errors in processing may cause the perf build to fail.
 
 Mapfile format
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index e925baa0c30b..a0f3a11ca19f 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -13,9 +13,13 @@
 #
 
 # Power8 entries
-004b0000,1,power8.json,core
-004b0201,1,power8.json,core
-004c0000,1,power8.json,core
-004d0000,1,power8.json,core
-004d0100,1,power8.json,core
-004d0200,1,power8.json,core
+004b0000,1,power8,core
+004b0201,1,power8,core
+004c0000,1,power8,core
+004d0000,1,power8,core
+004d0100,1,power8,core
+004d0200,1,power8,core
+004c0100,1,power8,core
+004e0100,1,power9,core
+004e0200,1,power9,core
+004e1200,1,power9,core
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
new file mode 100644
index 000000000000..18f6645f2897
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
@@ -0,0 +1,137 @@
+[
+  {,
+    "EventCode": "0x300F4",
+    "EventName": "PM_THRD_CONC_RUN_INST",
+    "BriefDescription": "PPC Instructions Finished by this thread when all threads in the core had the run-latch set"
+  },
+  {,
+    "EventCode": "0x1E056",
+    "EventName": "PM_CMPLU_STALL_FLUSH_ANY_THREAD",
+    "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because any of the 4 threads in the same core suffered a flush, which blocks completion"
+  },
+  {,
+    "EventCode": "0x4D016",
+    "EventName": "PM_CMPLU_STALL_FXLONG",
+    "BriefDescription": "Completion stall due to a long latency scalar fixed point instruction (division, square root)"
+  },
+  {,
+    "EventCode": "0x2D016",
+    "EventName": "PM_CMPLU_STALL_FXU",
+    "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes"
+  },
+  {,
+    "EventCode": "0x1D15C",
+    "EventName": "PM_MRK_DTLB_MISS_1G",
+    "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used"
+  },
+  {,
+    "EventCode": "0x4D12A",
+    "EventName": "PM_MRK_DATA_FROM_RL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x1003C",
+    "EventName": "PM_CMPLU_STALL_DMISS_L2L3",
+    "BriefDescription": "Completion stall by Dcache miss which resolved in L2/L3"
+  },
+  {,
+    "EventCode": "0x4C014",
+    "EventName": "PM_CMPLU_STALL_LMQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that missed in the L1 and the LMQ was unable to accept this load miss request because it was full"
+  },
+  {,
+    "EventCode": "0x14048",
+    "EventName": "PM_INST_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4D014",
+    "EventName": "PM_CMPLU_STALL_LOAD_FINISH",
+    "BriefDescription": "Finish stall because the NTF instruction was a load instruction with all its dependencies satisfied just going through the LSU pipe to finish"
+  },
+  {,
+    "EventCode": "0x2404A",
+    "EventName": "PM_INST_FROM_RL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1404A",
+    "EventName": "PM_INST_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x401EA",
+    "EventName": "PM_THRESH_EXC_128",
+    "BriefDescription": "Threshold counter exceeded a value of 128"
+  },
+  {,
+    "EventCode": "0x400F6",
+    "EventName": "PM_BR_MPRED_CMPL",
+    "BriefDescription": "Number of Branch Mispredicts"
+  },
+  {,
+    "EventCode": "0x2F140",
+    "EventName": "PM_MRK_DPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x101E6",
+    "EventName": "PM_THRESH_EXC_4096",
+    "BriefDescription": "Threshold counter exceed a count of 4096"
+  },
+  {,
+    "EventCode": "0x3D156",
+    "EventName": "PM_MRK_DTLB_MISS_64K",
+    "BriefDescription": "Marked Data TLB Miss page size 64K"
+  },
+  {,
+    "EventCode": "0x4C15E",
+    "EventName": "PM_MRK_DTLB_MISS_16M",
+    "BriefDescription": "Marked Data TLB Miss page size 16M"
+  },
+  {,
+    "EventCode": "0x2D15E",
+    "EventName": "PM_MRK_DTLB_MISS_16G",
+    "BriefDescription": "Marked Data TLB Miss page size 16G"
+  },
+  {,
+    "EventCode": "0x3F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4C016",
+    "EventName": "PM_CMPLU_STALL_DMISS_L2L3_CONFLICT",
+    "BriefDescription": "Completion stall due to cache miss that resolves in the L2 or L3 with a conflict"
+  },
+  {,
+    "EventCode": "0x2C01A",
+    "EventName": "PM_CMPLU_STALL_LHS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that hit on an older store and it was waiting for store data"
+  },
+  {,
+    "EventCode": "0x401E4",
+    "EventName": "PM_MRK_DTLB_MISS",
+    "BriefDescription": "Marked dtlb miss"
+  },
+  {,
+    "EventCode": "0x24046",
+    "EventName": "PM_INST_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1002A",
+    "EventName": "PM_CMPLU_STALL_LARX",
+    "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied"
+  },
+  {,
+    "EventCode": "0x3006C",
+    "EventName": "PM_RUN_CYC_SMT2_MODE",
+    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode"
+  },
+  {,
+    "EventCode": "0x1C058",
+    "EventName": "PM_DTLB_MISS_16G",
+    "BriefDescription": "Data TLB Miss page size 16G"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json
new file mode 100644
index 000000000000..8a83bca26552
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json
@@ -0,0 +1,32 @@
+[
+  {,
+    "EventCode": "0x1415A",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x10058",
+    "EventName": "PM_MEM_LOC_THRESH_IFU",
+    "BriefDescription": "Local Memory above threshold for IFU speculation control"
+  },
+  {,
+    "EventCode": "0x2D028",
+    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache"
+  },
+  {,
+    "EventCode": "0x30012",
+    "EventName": "PM_FLUSH_COMPLETION",
+    "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush"
+  },
+  {,
+    "EventCode": "0x2D154",
+    "EventName": "PM_MRK_DERAT_MISS_64K",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K"
+  },
+  {,
+    "EventCode": "0x4016E",
+    "EventName": "PM_THRESH_NOT_MET",
+    "BriefDescription": "Threshold counter did not meet threshold"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
new file mode 100644
index 000000000000..c63a919eda98
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -0,0 +1,372 @@
+[
+  {,
+    "EventCode": "0x3E15C",
+    "EventName": "PM_MRK_L2_TM_ST_ABORT_SISTER",
+    "BriefDescription": "TM marked store abort for this thread"
+  },
+  {,
+    "EventCode": "0x25044",
+    "EventName": "PM_IPTEG_FROM_L31_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x101E8",
+    "EventName": "PM_THRESH_EXC_256",
+    "BriefDescription": "Threshold counter exceed a count of 256"
+  },
+  {,
+    "EventCode": "0x4504E",
+    "EventName": "PM_IPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1006A",
+    "EventName": "PM_NTC_ISSUE_HELD_DARQ_FULL",
+    "BriefDescription": "The NTC instruction is being held at dispatch because there are no slots in the DARQ for it"
+  },
+  {,
+    "EventCode": "0x4E016",
+    "EventName": "PM_CMPLU_STALL_LSAQ_ARB",
+    "BriefDescription": "Finish stall because the NTF instruction was a load or store that was held in LSAQ because an older instruction from SRQ or LRQ won arbitration to the LSU pipe when this instruction tried to launch"
+  },
+  {,
+    "EventCode": "0x1001A",
+    "EventName": "PM_LSU_SRQ_FULL_CYC",
+    "BriefDescription": "Cycles in which the Store Queue is full on all 4 slices. This is event is not per thread. All the threads will see the same count for this core resource"
+  },
+  {,
+    "EventCode": "0x1E15E",
+    "EventName": "PM_MRK_L2_TM_REQ_ABORT",
+    "BriefDescription": "TM abort"
+  },
+  {,
+    "EventCode": "0x34052",
+    "EventName": "PM_INST_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x20114",
+    "EventName": "PM_MRK_L2_RC_DISP",
+    "BriefDescription": "Marked Instruction RC dispatched in L2"
+  },
+  {,
+    "EventCode": "0x4C044",
+    "EventName": "PM_DATA_FROM_L31_ECO_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x1C044",
+    "EventName": "PM_DATA_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x44050",
+    "EventName": "PM_INST_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x30154",
+    "EventName": "PM_MRK_FAB_RSP_DCLAIM",
+    "BriefDescription": "Marked store had to do a dclaim"
+  },
+  {,
+    "EventCode": "0x30014",
+    "EventName": "PM_CMPLU_STALL_STORE_FIN_ARB",
+    "BriefDescription": "Finish stall because the NTF instruction was a store waiting for a slot in the store finish pipe. This means the instruction is ready to finish but there are instructions ahead of it, using the finish pipe"
+  },
+  {,
+    "EventCode": "0x3E054",
+    "EventName": "PM_LD_MISS_L1",
+    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
+  },
+  {,
+    "EventCode": "0x2E01A",
+    "EventName": "PM_CMPLU_STALL_LSU_FLUSH_NEXT",
+    "BriefDescription": "Completion stall of one cycle because the LSU requested to flush the next iop in the sequence. It takes 1 cycle for the ISU to process this request before the LSU instruction is allowed to complete"
+  },
+  {,
+    "EventCode": "0x2D01C",
+    "EventName": "PM_CMPLU_STALL_STCX",
+    "BriefDescription": "Finish stall because the NTF instruction was a stcx waiting for response from L2"
+  },
+  {,
+    "EventCode": "0x2C010",
+    "EventName": "PM_CMPLU_STALL_LSU",
+    "BriefDescription": "Completion stall by LSU instruction"
+  },
+  {,
+    "EventCode": "0x2C042",
+    "EventName": "PM_DATA_FROM_L3_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state due to a demand load"
+  },
+  {,
+    "EventCode": "0x4E012",
+    "EventName": "PM_CMPLU_STALL_MTFPSCR",
+    "BriefDescription": "Completion stall because the ISU is updating the register and notifying the Effective Address Table (EAT)"
+  },
+  {,
+    "EventCode": "0x100F2",
+    "EventName": "PM_1PLUS_PPC_CMPL",
+    "BriefDescription": "1 or more ppc insts finished"
+  },
+  {,
+    "EventCode": "0x3001C",
+    "EventName": "PM_LSU_REJECT_LMQ_FULL",
+    "BriefDescription": "LSU Reject due to LMQ full (up to 4 per cycles)"
+  },
+  {,
+    "EventCode": "0x15046",
+    "EventName": "PM_IPTEG_FROM_L31_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1015E",
+    "EventName": "PM_MRK_FAB_RSP_RD_T_INTV",
+    "BriefDescription": "Sampled Read got a T intervention"
+  },
+  {,
+    "EventCode": "0x101EC",
+    "EventName": "PM_THRESH_MET",
+    "BriefDescription": "threshold exceeded"
+  },
+  {,
+    "EventCode": "0x10020",
+    "EventName": "PM_PMC4_REWIND",
+    "BriefDescription": "PMC4 Rewind Event"
+  },
+  {,
+    "EventCode": "0x301EA",
+    "EventName": "PM_THRESH_EXC_1024",
+    "BriefDescription": "Threshold counter exceeded a value of 1024"
+  },
+  {,
+    "EventCode": "0x34056",
+    "EventName": "PM_CMPLU_STALL_LSU_MFSPR",
+    "BriefDescription": "Finish stall because the NTF instruction was a mfspr instruction targeting an LSU SPR and it was waiting for the register data to be returned"
+  },
+  {,
+    "EventCode": "0x44056",
+    "EventName": "PM_VECTOR_ST_CMPL",
+    "BriefDescription": "Number of vector store instructions completed"
+  },
+  {,
+    "EventCode": "0x2C124",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x4C12A",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3C056",
+    "EventName": "PM_DTLB_MISS_64K",
+    "BriefDescription": "Data TLB Miss page size 64K"
+  },
+  {,
+    "EventCode": "0x30060",
+    "EventName": "PM_TM_TRANS_RUN_INST",
+    "BriefDescription": "Run instructions completed in transactional state (gated by the run latch)"
+  },
+  {,
+    "EventCode": "0x2C014",
+    "EventName": "PM_CMPLU_STALL_STORE_FINISH",
+    "BriefDescription": "Finish stall because the NTF instruction was a store with all its dependencies met, just waiting to go through the LSU pipe to finish"
+  },
+  {,
+    "EventCode": "0x3515A",
+    "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE_CYC",
+    "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x34050",
+    "EventName": "PM_INST_SYS_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x3015E",
+    "EventName": "PM_MRK_FAB_RSP_CLAIM_RTY",
+    "BriefDescription": "Sampled store did a rwitm and got a rty"
+  },
+  {,
+    "EventCode": "0x0",
+    "EventName": "PM_SUSPENDED",
+    "BriefDescription": "Counter OFF"
+  },
+  {,
+    "EventCode": "0x10010",
+    "EventName": "PM_PMC4_OVERFLOW",
+    "BriefDescription": "Overflow from counter 4"
+  },
+  {,
+    "EventCode": "0x3E04A",
+    "EventName": "PM_DPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2F152",
+    "EventName": "PM_MRK_FAB_RSP_DCLAIM_CYC",
+    "BriefDescription": "cycles L2 RC took for a dclaim"
+  },
+  {,
+    "EventCode": "0x10004",
+    "EventName": "PM_CMPLU_STALL_LRQ_OTHER",
+    "BriefDescription": "Finish stall due to LRQ miscellaneous reasons, lost arbitration to LMQ slot, bank collisions, set prediction cleanup, set prediction multihit and others"
+  },
+  {,
+    "EventCode": "0x4F150",
+    "EventName": "PM_MRK_FAB_RSP_RWITM_CYC",
+    "BriefDescription": "cycles L2 RC took for a rwitm"
+  },
+  {,
+    "EventCode": "0x4E042",
+    "EventName": "PM_DPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1F054",
+    "EventName": "PM_TLB_HIT",
+    "BriefDescription": "Number of times the TLB had the data required by the instruction. Applies to both HPT and RPT"
+  },
+  {,
+    "EventCode": "0x2C01E",
+    "EventName": "PM_CMPLU_STALL_SYNC_PMU_INT",
+    "BriefDescription": "Cycles in which the NTC instruction is waiting for a synchronous PMU interrupt"
+  },
+  {,
+    "EventCode": "0x24050",
+    "EventName": "PM_IOPS_CMPL",
+    "BriefDescription": "Internal Operations completed"
+  },
+  {,
+    "EventCode": "0x1515C",
+    "EventName": "PM_SYNC_MRK_BR_MPRED",
+    "BriefDescription": "Marked Branch mispredict that can cause a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x300FA",
+    "EventName": "PM_INST_FROM_L3MISS",
+    "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet"
+  },
+  {,
+    "EventCode": "0x15044",
+    "EventName": "PM_IPTEG_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x15152",
+    "EventName": "PM_SYNC_MRK_BR_LINK",
+    "BriefDescription": "Marked Branch and link branch that can cause a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x1E050",
+    "EventName": "PM_CMPLU_STALL_TEND",
+    "BriefDescription": "Finish stall because the NTF instruction was a tend instruction awaiting response from L2"
+  },
+  {,
+    "EventCode": "0x1013E",
+    "EventName": "PM_MRK_LD_MISS_EXPOSED_CYC",
+    "BriefDescription": "Marked Load exposed Miss (use edge detect to count #)"
+  },
+  {,
+    "EventCode": "0x25042",
+    "EventName": "PM_IPTEG_FROM_L3_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x14054",
+    "EventName": "PM_INST_PUMP_CPRED",
+    "BriefDescription": "Pump prediction correct. Counts across all types of pumps for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x4015E",
+    "EventName": "PM_MRK_FAB_RSP_RD_RTY",
+    "BriefDescription": "Sampled L2 reads retry count"
+  },
+  {,
+    "EventCode": "0x45048",
+    "EventName": "PM_IPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x44052",
+    "EventName": "PM_INST_PUMP_MPRED",
+    "BriefDescription": "Pump misprediction. Counts across all types of pumps for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x30026",
+    "EventName": "PM_CMPLU_STALL_STORE_DATA",
+    "BriefDescription": "Finish stall because the next to finish instruction was a store waiting on data"
+  },
+  {,
+    "EventCode": "0x301E6",
+    "EventName": "PM_MRK_DERAT_MISS",
+    "BriefDescription": "Erat Miss (TLB Access) All page sizes"
+  },
+  {,
+    "EventCode": "0x24154",
+    "EventName": "PM_THRESH_ACC",
+    "BriefDescription": "This event increments every time the threshold event counter ticks. Thresholding must be enabled (via MMCRA) and the thresholding start event must occur for this counter to increment. It will stop incrementing when the thresholding stop event occurs or when thresholding is disabled, until the next time a configured thresholding start event occurs."
+  },
+  {,
+    "EventCode": "0x2015E",
+    "EventName": "PM_MRK_FAB_RSP_RWITM_RTY",
+    "BriefDescription": "Sampled store did a rwitm and got a rty"
+  },
+  {,
+    "EventCode": "0x200FA",
+    "EventName": "PM_BR_TAKEN_CMPL",
+    "BriefDescription": "New event for Branch Taken"
+  },
+  {,
+    "EventCode": "0x35044",
+    "EventName": "PM_IPTEG_FROM_L31_ECO_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x4C010",
+    "EventName": "PM_CMPLU_STALL_STORE_PIPE_ARB",
+    "BriefDescription": "Finish stall because the NTF instruction was a store waiting for the next relaunch opportunity after an internal reject. This means the instruction is ready to relaunch and tried once but lost arbitration"
+  },
+  {,
+    "EventCode": "0x4C01C",
+    "EventName": "PM_CMPLU_STALL_ST_FWD",
+    "BriefDescription": "Completion stall due to store forward"
+  },
+  {,
+    "EventCode": "0x3515C",
+    "EventName": "PM_MRK_DATA_FROM_RL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x2D14C",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x40116",
+    "EventName": "PM_MRK_LARX_FIN",
+    "BriefDescription": "Larx finished"
+  },
+  {,
+    "EventCode": "0x4C056",
+    "EventName": "PM_DTLB_MISS_16M",
+    "BriefDescription": "Data TLB Miss page size 16M"
+  },
+  {,
+    "EventCode": "0x1003A",
+    "EventName": "PM_CMPLU_STALL_LSU_FIN",
+    "BriefDescription": "Finish stall because the NTF instruction was an LSU op (other than a load or a store) with all its dependencies met and just going through the LSU pipe to finish"
+  },
+  {,
+    "EventCode": "0x3012A",
+    "EventName": "PM_MRK_L2_RC_DONE",
+    "BriefDescription": "Marked RC done"
+  },
+  {,
+    "EventCode": "0x45044",
+    "EventName": "PM_IPTEG_FROM_L31_ECO_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
new file mode 100644
index 000000000000..b9df54fb37e3
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
@@ -0,0 +1,647 @@
+[
+  {,
+    "EventCode": "0x3C052",
+    "EventName": "PM_DATA_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load"
+  },
+  {,
+    "EventCode": "0x3013E",
+    "EventName": "PM_MRK_STALL_CMPLU_CYC",
+    "BriefDescription": "Number of cycles the marked instruction is experiencing a stall while it is next to complete (NTC)"
+  },
+  {,
+    "EventCode": "0x4F056",
+    "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3MISS",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from beyond the core's L3 data cache. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x24158",
+    "EventName": "PM_MRK_INST",
+    "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens"
+  },
+  {,
+    "EventCode": "0x1E046",
+    "EventName": "PM_DPTEG_FROM_L31_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3C04A",
+    "EventName": "PM_DATA_FROM_RMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C01C",
+    "EventName": "PM_CMPLU_STALL_DMISS_REMOTE",
+    "BriefDescription": "Completion stall by Dcache miss which resolved from remote chip (cache or memory)"
+  },
+  {,
+    "EventCode": "0x44040",
+    "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with dispatch conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x2E050",
+    "EventName": "PM_DARQ0_7_9_ENTRIES",
+    "BriefDescription": "Cycles in which 7,8, or 9 DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x2D02E",
+    "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L2",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L2 data cache. This implies that a level 4 PWC access was not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x3F05E",
+    "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x2E01E",
+    "EventName": "PM_CMPLU_STALL_NTC_FLUSH",
+    "BriefDescription": "Completion stall due to ntc flush"
+  },
+  {,
+    "EventCode": "0x1F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x20130",
+    "EventName": "PM_MRK_INST_DECODED",
+    "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only"
+  },
+  {,
+    "EventCode": "0x3F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D058",
+    "EventName": "PM_VECTOR_FLOP_CMPL",
+    "BriefDescription": "Vector FP instruction completed"
+  },
+  {,
+    "EventCode": "0x14040",
+    "EventName": "PM_INST_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 without conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4404E",
+    "EventName": "PM_INST_FROM_L3MISS_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to a instruction fetch"
+  },
+  {,
+    "EventCode": "0x3003A",
+    "EventName": "PM_CMPLU_STALL_EXCEPTION",
+    "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete"
+  },
+  {,
+    "EventCode": "0x4F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3E044",
+    "EventName": "PM_DPTEG_FROM_L31_ECO_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x300F6",
+    "EventName": "PM_L1_DCACHE_RELOAD_VALID",
+    "BriefDescription": "DL1 reloaded due to Demand Load"
+  },
+  {,
+    "EventCode": "0x1415E",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS_CYC",
+    "BriefDescription": "Duration in cycles to reload from a location other than the local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x1E052",
+    "EventName": "PM_CMPLU_STALL_SLB",
+    "BriefDescription": "Finish stall because the NTF instruction was awaiting L2 response for an SLB"
+  },
+  {,
+    "EventCode": "0x4404C",
+    "EventName": "PM_INST_FROM_DMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group (Distant) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3000E",
+    "EventName": "PM_FXU_1PLUS_BUSY",
+    "BriefDescription": "At least one of the 4 FXU units is busy"
+  },
+  {,
+    "EventCode": "0x2C048",
+    "EventName": "PM_DATA_FROM_LMEM",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a demand load"
+  },
+  {,
+    "EventCode": "0x3000A",
+    "EventName": "PM_CMPLU_STALL_PM",
+    "BriefDescription": "Finish stall because the NTF instruction was issued to the Permute execution pipe and waiting to finish. Includes permute and decimal fixed point instructions (128 bit BCD arithmetic) + a few 128 bit fixpoint add/subtract instructions with carry. Not qualified by vector or multicycle"
+  },
+  {,
+    "EventCode": "0x1504E",
+    "EventName": "PM_IPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1C052",
+    "EventName": "PM_DATA_GRP_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for a demand load"
+  },
+  {,
+    "EventCode": "0x30008",
+    "EventName": "PM_DISP_STARVED",
+    "BriefDescription": "Dispatched Starved"
+  },
+  {,
+    "EventCode": "0x14042",
+    "EventName": "PM_INST_FROM_L2",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4000C",
+    "EventName": "PM_FREQ_UP",
+    "BriefDescription": "Power Management: Above Threshold A"
+  },
+  {,
+    "EventCode": "0x3C050",
+    "EventName": "PM_DATA_SYS_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for a demand load"
+  },
+  {,
+    "EventCode": "0x25040",
+    "EventName": "PM_IPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x10132",
+    "EventName": "PM_MRK_INST_ISSUED",
+    "BriefDescription": "Marked instruction issued"
+  },
+  {,
+    "EventCode": "0x1C046",
+    "EventName": "PM_DATA_FROM_L31_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C044",
+    "EventName": "PM_DATA_FROM_L31_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C04A",
+    "EventName": "PM_DATA_FROM_RL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a demand load"
+  },
+  {,
+    "EventCode": "0x24044",
+    "EventName": "PM_INST_FROM_L31_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4C050",
+    "EventName": "PM_DATA_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for a demand load"
+  },
+  {,
+    "EventCode": "0x2C052",
+    "EventName": "PM_DATA_GRP_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for a demand load"
+  },
+  {,
+    "EventCode": "0x2F148",
+    "EventName": "PM_MRK_DPTEG_FROM_LMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D01A",
+    "EventName": "PM_CMPLU_STALL_EIEIO",
+    "BriefDescription": "Finish stall because the NTF instruction is an EIEIO waiting for response from L2"
+  },
+  {,
+    "EventCode": "0x4F14E",
+    "EventName": "PM_MRK_DPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4F05A",
+    "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L3 data cache. This is the deepest level of PWC possible for a translation"
+  },
+  {,
+    "EventCode": "0x1F05A",
+    "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L2",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L2 data cache. This is the deepest level of PWC possible for a translation"
+  },
+  {,
+    "EventCode": "0x30068",
+    "EventName": "PM_L1_ICACHE_RELOADED_PREF",
+    "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)"
+  },
+  {,
+    "EventCode": "0x4C04A",
+    "EventName": "PM_DATA_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a demand load"
+  },
+  {,
+    "EventCode": "0x400FE",
+    "EventName": "PM_DATA_FROM_MEMORY",
+    "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a demand load"
+  },
+  {,
+    "EventCode": "0x3F058",
+    "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L3 data cache"
+  },
+  {,
+    "EventCode": "0x4D142",
+    "EventName": "PM_MRK_DATA_FROM_L3",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x30050",
+    "EventName": "PM_SYS_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was system pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x30028",
+    "EventName": "PM_CMPLU_STALL_SPEC_FINISH",
+    "BriefDescription": "Finish stall while waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC"
+  },
+  {,
+    "EventCode": "0x400F4",
+    "EventName": "PM_RUN_PURR",
+    "BriefDescription": "Run_PURR"
+  },
+  {,
+    "EventCode": "0x3404C",
+    "EventName": "PM_INST_FROM_DL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3D05A",
+    "EventName": "PM_NTC_ISSUE_HELD_OTHER",
+    "BriefDescription": "The NTC instruction is being held at dispatch during regular pipeline cycles, or because the VSU is busy with multi-cycle instructions, or because of a write-back collision with VSU"
+  },
+  {,
+    "EventCode": "0x2E048",
+    "EventName": "PM_DPTEG_FROM_LMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2D02A",
+    "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L2 data cache"
+  },
+  {,
+    "EventCode": "0x1F05C",
+    "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L3",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L3 data cache"
+  },
+  {,
+    "EventCode": "0x4D04A",
+    "EventName": "PM_DARQ0_0_3_ENTRIES",
+    "BriefDescription": "Cycles in which 3 or less DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x1404C",
+    "EventName": "PM_INST_FROM_LL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's L4 cache due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x200FD",
+    "EventName": "PM_L1_ICACHE_MISS",
+    "BriefDescription": "Demand iCache Miss"
+  },
+  {,
+    "EventCode": "0x34040",
+    "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_LDHITST",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with load hit store conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x20138",
+    "EventName": "PM_MRK_ST_NEST",
+    "BriefDescription": "Marked store sent to nest"
+  },
+  {,
+    "EventCode": "0x44048",
+    "EventName": "PM_INST_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x35046",
+    "EventName": "PM_IPTEG_FROM_L21_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x4C04E",
+    "EventName": "PM_DATA_FROM_L3MISS_MOD",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a demand load"
+  },
+  {,
+    "EventCode": "0x401E0",
+    "EventName": "PM_MRK_INST_CMPL",
+    "BriefDescription": "marked instruction completed"
+  },
+  {,
+    "EventCode": "0x2C128",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x34044",
+    "EventName": "PM_INST_FROM_L31_ECO_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4E018",
+    "EventName": "PM_CMPLU_STALL_NTC_DISP_FIN",
+    "BriefDescription": "Finish stall because the NTF instruction was one that must finish at dispatch."
+  },
+  {,
+    "EventCode": "0x2E05E",
+    "EventName": "PM_LMQ_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the LMQ has no pending load misses for this thread"
+  },
+  {,
+    "EventCode": "0x4C122",
+    "EventName": "PM_DARQ1_0_3_ENTRIES",
+    "BriefDescription": "Cycles in which 3 or fewer DARQ1 entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x4F058",
+    "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x14046",
+    "EventName": "PM_INST_FROM_L31_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3012C",
+    "EventName": "PM_MRK_ST_FWD",
+    "BriefDescription": "Marked st forwards"
+  },
+  {,
+    "EventCode": "0x101E0",
+    "EventName": "PM_MRK_INST_DISP",
+    "BriefDescription": "The thread has dispatched a randomly sampled marked instruction"
+  },
+  {,
+    "EventCode": "0x1D058",
+    "EventName": "PM_DARQ0_10_12_ENTRIES",
+    "BriefDescription": "Cycles in which 10 or more DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x300FE",
+    "EventName": "PM_DATA_FROM_L3MISS",
+    "BriefDescription": "Demand LD - L3 Miss (not L2 hit and not L3 hit)"
+  },
+  {,
+    "EventCode": "0x30006",
+    "EventName": "PM_CMPLU_STALL_OTHER_CMPL",
+    "BriefDescription": "Instructions the core completed while this tread was stalled"
+  },
+  {,
+    "EventCode": "0x1005C",
+    "EventName": "PM_CMPLU_STALL_DP",
+    "BriefDescription": "Finish stall because the NTF instruction was a scalar instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by NOT vector"
+  },
+  {,
+    "EventCode": "0x1E042",
+    "EventName": "PM_DPTEG_FROM_L2",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1016E",
+    "EventName": "PM_MRK_BR_CMPL",
+    "BriefDescription": "Branch Instruction completed"
+  },
+  {,
+    "EventCode": "0x2013A",
+    "EventName": "PM_MRK_BRU_FIN",
+    "BriefDescription": "bru marked instr finish"
+  },
+  {,
+    "EventCode": "0x4F05E",
+    "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from beyond the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x400FC",
+    "EventName": "PM_ITLB_MISS",
+    "BriefDescription": "ITLB Reloaded. Counts 1 per ITLB miss for HPT but multiple for radix depending on number of levels traveresed"
+  },
+  {,
+    "EventCode": "0x2D024",
+    "EventName": "PM_RADIX_PWC_L2_HIT",
+    "BriefDescription": "A radix translation attempt missed in the TLB but hit on both the first and second levels of page walk cache."
+  },
+  {,
+    "EventCode": "0x3F056",
+    "EventName": "PM_RADIX_PWC_L3_HIT",
+    "BriefDescription": "A radix translation attempt missed in the TLB but hit on the first, second, and third levels of page walk cache."
+  },
+  {,
+    "EventCode": "0x4E014",
+    "EventName": "PM_TM_TX_PASS_RUN_INST",
+    "BriefDescription": "Run instructions spent in successful transactions"
+  },
+  {,
+    "EventCode": "0x1E044",
+    "EventName": "PM_DPTEG_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D05A",
+    "EventName": "PM_NON_MATH_FLOP_CMPL",
+    "BriefDescription": "Non FLOP operation completed"
+  },
+  {,
+    "EventCode": "0x101E2",
+    "EventName": "PM_MRK_BR_TAKEN_CMPL",
+    "BriefDescription": "Marked Branch Taken completed"
+  },
+  {,
+    "EventCode": "0x3E158",
+    "EventName": "PM_MRK_STCX_FAIL",
+    "BriefDescription": "marked stcx failed"
+  },
+  {,
+    "EventCode": "0x1C048",
+    "EventName": "PM_DATA_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x1C054",
+    "EventName": "PM_DATA_PUMP_CPRED",
+    "BriefDescription": "Pump prediction correct. Counts across all types of pumps for a demand load"
+  },
+  {,
+    "EventCode": "0x4405E",
+    "EventName": "PM_DARQ_STORE_REJECT",
+    "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry but It was rejected. Divide by PM_DARQ_STORE_XMIT to get reject ratio"
+  },
+  {,
+    "EventCode": "0x1C042",
+    "EventName": "PM_DATA_FROM_L2",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a demand load"
+  },
+  {,
+    "EventCode": "0x1D14C",
+    "EventName": "PM_MRK_DATA_FROM_LL4",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a marked load"
+  },
+  {,
+    "EventCode": "0x1006C",
+    "EventName": "PM_RUN_CYC_ST_MODE",
+    "BriefDescription": "Cycles run latch is set and core is in ST mode"
+  },
+  {,
+    "EventCode": "0x3C044",
+    "EventName": "PM_DATA_FROM_L31_ECO_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x4C052",
+    "EventName": "PM_DATA_PUMP_MPRED",
+    "BriefDescription": "Pump misprediction. Counts across all types of pumps for a demand load"
+  },
+  {,
+    "EventCode": "0x20050",
+    "EventName": "PM_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope and data sourced across this scope was group pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x1F150",
+    "EventName": "PM_MRK_ST_L2DISP_TO_CMPL_CYC",
+    "BriefDescription": "cycles from L2 rc disp to l2 rc completion"
+  },
+  {,
+    "EventCode": "0x4505A",
+    "EventName": "PM_SP_FLOP_CMPL",
+    "BriefDescription": "SP instruction completed"
+  },
+  {,
+    "EventCode": "0x4000A",
+    "EventName": "PM_ISQ_36_44_ENTRIES",
+    "BriefDescription": "Cycles in which 36 or more Issue Queue entries are in use. This is a shared event, not per thread. There are 44 issue queue entries across 4 slices in the whole core"
+  },
+  {,
+    "EventCode": "0x2C12E",
+    "EventName": "PM_MRK_DATA_FROM_LL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from the local chip's L4 cache due to a marked load"
+  },
+  {,
+    "EventCode": "0x2C058",
+    "EventName": "PM_MEM_PREF",
+    "BriefDescription": "Memory prefetch for this thread. Includes L4"
+  },
+  {,
+    "EventCode": "0x40012",
+    "EventName": "PM_L1_ICACHE_RELOADED_ALL",
+    "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch"
+  },
+  {,
+    "EventCode": "0x4003C",
+    "EventName": "PM_DISP_HELD_SYNC_HOLD",
+    "BriefDescription": "Cycles in which dispatch is held because of a synchronizing instruction in the pipeline"
+  },
+  {,
+    "EventCode": "0x3003C",
+    "EventName": "PM_CMPLU_STALL_NESTED_TEND",
+    "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tend and decrement the TEXASR nested level. This is a short delay"
+  },
+  {,
+    "EventCode": "0x3D05C",
+    "EventName": "PM_DISP_HELD_HB_FULL",
+    "BriefDescription": "Dispatch held due to History Buffer full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
+  },
+  {,
+    "EventCode": "0x30052",
+    "EventName": "PM_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x2E044",
+    "EventName": "PM_DPTEG_FROM_L31_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x34048",
+    "EventName": "PM_INST_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x45042",
+    "EventName": "PM_IPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x15042",
+    "EventName": "PM_IPTEG_FROM_L2",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1C05E",
+    "EventName": "PM_MEM_LOC_THRESH_LSU_MED",
+    "BriefDescription": "Local memory above threshold for data prefetch"
+  },
+  {,
+    "EventCode": "0x40134",
+    "EventName": "PM_MRK_INST_TIMEO",
+    "BriefDescription": "marked Instruction finish timeout (instruction lost)"
+  },
+  {,
+    "EventCode": "0x1002C",
+    "EventName": "PM_L1_DCACHE_RELOADED_ALL",
+    "BriefDescription": "L1 data cache reloaded for demand. If MMCR1[16] is 1, prefetches will be included as well"
+  },
+  {,
+    "EventCode": "0x30130",
+    "EventName": "PM_MRK_INST_FIN",
+    "BriefDescription": "marked instruction finished"
+  },
+  {,
+    "EventCode": "0x1F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3504E",
+    "EventName": "PM_DARQ0_4_6_ENTRIES",
+    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x30064",
+    "EventName": "PM_DARQ_STORE_XMIT",
+    "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry. Includes rejects. Not qualified by thread, so it includes counts for the whole core"
+  },
+  {,
+    "EventCode": "0x45046",
+    "EventName": "PM_IPTEG_FROM_L21_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x2C016",
+    "EventName": "PM_CMPLU_STALL_PASTE",
+    "BriefDescription": "Finish stall because the NTF instruction was a paste waiting for response from L2"
+  },
+  {,
+    "EventCode": "0x24156",
+    "EventName": "PM_MRK_STCX_FIN",
+    "BriefDescription": "Number of marked stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed"
+  },
+  {,
+    "EventCode": "0x15150",
+    "EventName": "PM_SYNC_MRK_PROBE_NOP",
+    "BriefDescription": "Marked probeNops which can cause synchronous interrupts"
+  },
+  {,
+    "EventCode": "0x301E4",
+    "EventName": "PM_MRK_BR_MPRED_CMPL",
+    "BriefDescription": "Marked Branch Mispredicted"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
new file mode 100644
index 000000000000..9960d1c0dd44
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
@@ -0,0 +1,132 @@
+[
+  {,
+    "EventCode": "0x3006E",
+    "EventName": "PM_NEST_REF_CLK",
+    "BriefDescription": "Multiply by 4 to obtain the number of PB cycles"
+  },
+  {,
+    "EventCode": "0x20010",
+    "EventName": "PM_PMC1_OVERFLOW",
+    "BriefDescription": "Overflow from counter 1"
+  },
+  {,
+    "EventCode": "0x2005A",
+    "EventName": "PM_DARQ1_7_9_ENTRIES",
+    "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x3C048",
+    "EventName": "PM_DATA_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x10008",
+    "EventName": "PM_RUN_SPURR",
+    "BriefDescription": "Run SPURR"
+  },
+  {,
+    "EventCode": "0x200F6",
+    "EventName": "PM_LSU_DERAT_MISS",
+    "BriefDescription": "DERAT Reloaded due to a DERAT miss"
+  },
+  {,
+    "EventCode": "0x4C048",
+    "EventName": "PM_DATA_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x1D15E",
+    "EventName": "PM_MRK_RUN_CYC",
+    "BriefDescription": "Run cycles in which a marked instruction is in the pipeline"
+  },
+  {,
+    "EventCode": "0x4003E",
+    "EventName": "PM_LD_CMPL",
+    "BriefDescription": "count of Loads completed"
+  },
+  {,
+    "EventCode": "0x2D156",
+    "EventName": "PM_MRK_DTLB_MISS_4K",
+    "BriefDescription": "Marked Data TLB Miss page size 4k"
+  },
+  {,
+    "EventCode": "0x4C042",
+    "EventName": "PM_DATA_FROM_L3",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load"
+  },
+  {,
+    "EventCode": "0x4D02C",
+    "EventName": "PM_PMC1_REWIND",
+    "BriefDescription": ""
+  },
+  {,
+    "EventCode": "0x15158",
+    "EventName": "PM_SYNC_MRK_L2HIT",
+    "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x3404A",
+    "EventName": "PM_INST_FROM_RMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x301E2",
+    "EventName": "PM_MRK_ST_CMPL",
+    "BriefDescription": "Marked store completed and sent to nest"
+  },
+  {,
+    "EventCode": "0x1C050",
+    "EventName": "PM_DATA_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load"
+  },
+  {,
+    "EventCode": "0x4C040",
+    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x2E05C",
+    "EventName": "PM_LSU_REJECT_ERAT_MISS",
+    "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)"
+  },
+  {,
+    "EventCode": "0x1000A",
+    "EventName": "PM_PMC3_REWIND",
+    "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change."
+  },
+  {,
+    "EventCode": "0x3C058",
+    "EventName": "PM_LARX_FIN",
+    "BriefDescription": "Larx finished"
+  },
+  {,
+    "EventCode": "0x1C040",
+    "EventName": "PM_DATA_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C040",
+    "EventName": "PM_DATA_FROM_L2_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load"
+  },
+  {,
+    "EventCode": "0x2E05A",
+    "EventName": "PM_LRQ_REJECT",
+    "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects"
+  },
+  {,
+    "EventCode": "0x2C05C",
+    "EventName": "PM_INST_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)"
+  },
+  {,
+    "EventCode": "0x4D056",
+    "EventName": "PM_NON_FMA_FLOP_CMPL",
+    "BriefDescription": "Non FMA instruction completed"
+  },
+  {,
+    "EventCode": "0x3E050",
+    "EventName": "PM_DARQ1_4_6_ENTRIES",
+    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
new file mode 100644
index 000000000000..54cc3be00fc2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -0,0 +1,2392 @@
+[
+  {,
+    "EventCode": "0x3084",
+    "EventName": "PM_ISU1_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0xF880",
+    "EventName": "PM_SNOOP_TLBIE",
+    "BriefDescription": "TLBIE snoop"
+  },
+  {,
+    "EventCode": "0x4088",
+    "EventName": "PM_IC_DEMAND_REQ",
+    "BriefDescription": "Demand Instruction fetch request"
+  },
+  {,
+    "EventCode": "0x20A4",
+    "EventName": "PM_TM_TRESUME",
+    "BriefDescription": "TM resume instruction completed"
+  },
+  {,
+    "EventCode": "0x40008",
+    "EventName": "PM_SRQ_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the SRQ has at least one (out of four) empty slice"
+  },
+  {,
+    "EventCode": "0x20064",
+    "EventName": "PM_IERAT_RELOAD_4K",
+    "BriefDescription": "IERAT reloaded (after a miss) for 4K pages"
+  },
+  {,
+    "EventCode": "0x260B4",
+    "EventName": "PM_L3_P2_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 2 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0x20006",
+    "EventName": "PM_DISP_HELD_ISSQ_FULL",
+    "BriefDescription": "Dispatch held due to Issue q full. Includes issue queue and branch queue"
+  },
+  {,
+    "EventCode": "0x201E4",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x4E044",
+    "EventName": "PM_DPTEG_FROM_L31_ECO_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40B8",
+    "EventName": "PM_BR_MPRED_TAKEN_CR",
+    "BriefDescription": "A Conditional Branch that resolved to taken was mispredicted as not taken (due to the BHT Direction Prediction)."
+  },
+  {,
+    "EventCode": "0xF8AC",
+    "EventName": "PM_DC_DEALLOC_NO_CONF",
+    "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)"
+  },
+  {,
+    "EventCode": "0xD090",
+    "EventName": "PM_LS0_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x40BC",
+    "EventName": "PM_THRD_PRIO_0_1_CYC",
+    "BriefDescription": "Cycles thread running at priority level 0 or 1"
+  },
+  {,
+    "EventCode": "0x2084",
+    "EventName": "PM_FLUSH_HB_RESTORE_CYC",
+    "BriefDescription": "Cycles in which no new instructions can be dispatched to the ICT after a flush.  History buffer recovery"
+  },
+  {,
+    "EventCode": "0x4F054",
+    "EventName": "PM_RADIX_PWC_MISS",
+    "BriefDescription": "A radix translation attempt missed in the TLB and all levels of page walk cache."
+  },
+  {,
+    "EventCode": "0x24048",
+    "EventName": "PM_INST_FROM_LMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's Memory due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0xD8B4",
+    "EventName": "PM_LSU0_LRQ_S0_VALID_CYC",
+    "BriefDescription": "Slot 0 of LRQ valid"
+  },
+  {,
+    "EventCode": "0x2E052",
+    "EventName": "PM_TM_PASSED",
+    "BriefDescription": "Number of TM transactions that passed"
+  },
+  {,
+    "EventCode": "0xD1A0",
+    "EventName": "PM_MRK_LSU_FLUSH_LHS",
+    "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
+  },
+  {,
+    "EventCode": "0xF088",
+    "EventName": "PM_LSU0_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x360B2",
+    "EventName": "PM_L3_GRP_GUESS_WRONG_LOW",
+    "BriefDescription": "Initial scope=group (GS or NNS) but data from outside group (far or rem). Prediction too Low"
+  },
+  {,
+    "EventCode": "0x168A6",
+    "EventName": "PM_TM_CAM_OVERFLOW",
+    "BriefDescription": "L3 TM cam overflow during L2 co of SC"
+  },
+  {,
+    "EventCode": "0xE8B0",
+    "EventName": "PM_TEND_PEND_CYC",
+    "BriefDescription": "TEND latency per thread"
+  },
+  {,
+    "EventCode": "0x4884",
+    "EventName": "PM_IBUF_FULL_CYC",
+    "BriefDescription": "Cycles No room in ibuff"
+  },
+  {,
+    "EventCode": "0xD08C",
+    "EventName": "PM_LSU2_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])"
+  },
+  {,
+    "EventCode": "0x300F8",
+    "EventName": "PM_TB_BIT_TRANS",
+    "BriefDescription": "timebase event"
+  },
+  {,
+    "EventCode": "0x3C040",
+    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_LDHITST",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0xE0BC",
+    "EventName": "PM_LS0_PTE_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 0"
+  },
+  {,
+    "EventCode": "0x3884",
+    "EventName": "PM_ISU3_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0x460A6",
+    "EventName": "PM_RD_FORMING_SC",
+    "BriefDescription": "Read forming SC"
+  },
+  {,
+    "EventCode": "0x468A0",
+    "EventName": "PM_L3_PF_OFF_CHIP_MEM",
+    "BriefDescription": "L3 PF from Off chip memory"
+  },
+  {,
+    "EventCode": "0x268AA",
+    "EventName": "PM_L3_P1_LCO_DATA",
+    "BriefDescription": "LCO sent with data port 1"
+  },
+  {,
+    "EventCode": "0xE894",
+    "EventName": "PM_LSU1_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x5888",
+    "EventName": "PM_IC_INVALIDATE",
+    "BriefDescription": "Ic line invalidated"
+  },
+  {,
+    "EventCode": "0x2890",
+    "EventName": "PM_DISP_CLB_HELD_TLBIE",
+    "BriefDescription": "Dispatch Hold: Due to TLBIE"
+  },
+  {,
+    "EventCode": "0x1001C",
+    "EventName": "PM_CMPLU_STALL_THRD",
+    "BriefDescription": "Completion Stalled because the thread was blocked"
+  },
+  {,
+    "EventCode": "0x368A6",
+    "EventName": "PM_SNP_TM_HIT_T",
+    "BriefDescription": "Snp TM sthit T/Tn/Te"
+  },
+  {,
+    "EventCode": "0x3001A",
+    "EventName": "PM_DATA_TABLEWALK_CYC",
+    "BriefDescription": "Data Tablewalk Cycles.  Could be 1 or 2 active tablewalks. Includes data prefetches."
+  },
+  {,
+    "EventCode": "0xD894",
+    "EventName": "PM_LS3_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x35158",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xF0B4",
+    "EventName": "PM_DC_PREF_CONS_ALLOC",
+    "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch"
+  },
+  {,
+    "EventCode": "0xF894",
+    "EventName": "PM_LSU3_L1_CAM_CANCEL",
+    "BriefDescription": "ls3 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0x2888",
+    "EventName": "PM_FLUSH_DISP_TLBIE",
+    "BriefDescription": "Dispatch Flush: TLBIE"
+  },
+  {,
+    "EventCode": "0xD1A4",
+    "EventName": "PM_MRK_LSU_FLUSH_SAO",
+    "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush"
+  },
+  {,
+    "EventCode": "0x4E11E",
+    "EventName": "PM_MRK_DATA_FROM_DMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x5894",
+    "EventName": "PM_LWSYNC",
+    "BriefDescription": "Lwsync instruction decoded and transferred"
+  },
+  {,
+    "EventCode": "0x14156",
+    "EventName": "PM_MRK_DATA_FROM_L2_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0x468A6",
+    "EventName": "PM_RD_CLEARING_SC",
+    "BriefDescription": "Read clearing SC"
+  },
+  {,
+    "EventCode": "0x50A0",
+    "EventName": "PM_HWSYNC",
+    "BriefDescription": "Hwsync instruction decoded and transferred"
+  },
+  {,
+    "EventCode": "0x168B0",
+    "EventName": "PM_L3_P1_NODE_PUMP",
+    "BriefDescription": "L3 PF sent with nodal scope port 1, counts even retried requests"
+  },
+  {,
+    "EventCode": "0xD0BC",
+    "EventName": "PM_LSU0_1_LRQF_FULL_CYC",
+    "BriefDescription": "Counts the number of cycles the LRQF is full.  LRQF is the queue that holds loads between finish and completion.  If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ"
+  },
+  {,
+    "EventCode": "0x2D148",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x460A8",
+    "EventName": "PM_SN_HIT",
+    "BriefDescription": "Any port snooper hit L3.  Up to 4 can happen in a cycle but we only count 1"
+  },
+  {,
+    "EventCode": "0x360AA",
+    "EventName": "PM_L3_P0_CO_MEM",
+    "BriefDescription": "L3 CO to memory port 0 with or without data"
+  },
+  {,
+    "EventCode": "0xF0A4",
+    "EventName": "PM_DC_PREF_HW_ALLOC",
+    "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism"
+  },
+  {,
+    "EventCode": "0xF0BC",
+    "EventName": "PM_LS2_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0xD0AC",
+    "EventName": "PM_SRQ_SYNC_CYC",
+    "BriefDescription": "A sync is in the S2Q (edge detect to count)"
+  },
+  {,
+    "EventCode": "0x401E6",
+    "EventName": "PM_MRK_INST_FROM_L3MISS",
+    "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet"
+  },
+  {,
+    "EventCode": "0x26082",
+    "EventName": "PM_L2_IC_INV",
+    "BriefDescription": "I-cache Invalidates sent over the realod bus to the core"
+  },
+  {,
+    "EventCode": "0xC8AC",
+    "EventName": "PM_LSU_FLUSH_RELAUNCH_MISS",
+    "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent"
+  },
+  {,
+    "EventCode": "0x260A4",
+    "EventName": "PM_L3_LD_HIT",
+    "BriefDescription": "L3 Hits for demand LDs"
+  },
+  {,
+    "EventCode": "0xF0A0",
+    "EventName": "PM_DATA_STORE",
+    "BriefDescription": "All ops that drain from s2q to L2 containing data"
+  },
+  {,
+    "EventCode": "0x1D148",
+    "EventName": "PM_MRK_DATA_FROM_RMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x16088",
+    "EventName": "PM_L2_LOC_GUESS_CORRECT",
+    "BriefDescription": "L2 guess local (LNS) and guess was correct (ie data local)"
+  },
+  {,
+    "EventCode": "0x160A4",
+    "EventName": "PM_L3_HIT",
+    "BriefDescription": "L3 Hits (L2 miss hitting L3, including data/instrn/xlate)"
+  },
+  {,
+    "EventCode": "0xE09C",
+    "EventName": "PM_LSU0_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x168B4",
+    "EventName": "PM_L3_P1_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 1 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0x268AC",
+    "EventName": "PM_L3_RD_USAGE",
+    "BriefDescription": "Rotating sample of 16 RD actives"
+  },
+  {,
+    "EventCode": "0x1415C",
+    "EventName": "PM_MRK_DATA_FROM_L3_MEPF_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 without dispatch conflicts hit on Mepf state due to a marked load"
+  },
+  {,
+    "EventCode": "0xE880",
+    "EventName": "PM_L1_SW_PREF",
+    "BriefDescription": "Software L1 Prefetches, including SW Transient Prefetches"
+  },
+  {,
+    "EventCode": "0x288C",
+    "EventName": "PM_DISP_CLB_HELD_BAL",
+    "BriefDescription": "Dispatch/CLB Hold: Balance Flush"
+  },
+  {,
+    "EventCode": "0x101EA",
+    "EventName": "PM_MRK_L1_RELOAD_VALID",
+    "BriefDescription": "Marked demand reload"
+  },
+  {,
+    "EventCode": "0x1D156",
+    "EventName": "PM_MRK_LD_MISS_L1_CYC",
+    "BriefDescription": "Marked ld latency"
+  },
+  {,
+    "EventCode": "0x4C01A",
+    "EventName": "PM_CMPLU_STALL_DMISS_L3MISS",
+    "BriefDescription": "Completion stall due to cache miss resolving missed the L3"
+  },
+  {,
+    "EventCode": "0x2006C",
+    "EventName": "PM_RUN_CYC_SMT4_MODE",
+    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT4 mode"
+  },
+  {,
+    "EventCode": "0x5088",
+    "EventName": "PM_DECODE_FUSION_OP_PRESERV",
+    "BriefDescription": "Destructive op operand preservation"
+  },
+  {,
+    "EventCode": "0x1D14E",
+    "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE_CYC",
+    "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x509C",
+    "EventName": "PM_FORCED_NOP",
+    "BriefDescription": "Instruction was forced to execute as a nop because it was found to behave like a nop (have no effect) at decode time"
+  },
+  {,
+    "EventCode": "0xC098",
+    "EventName": "PM_LS2_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x20058",
+    "EventName": "PM_DARQ1_10_12_ENTRIES",
+    "BriefDescription": "Cycles in which 10 or  more DARQ1 entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x360A6",
+    "EventName": "PM_SNP_TM_HIT_M",
+    "BriefDescription": "Snp TM st hit M/Mu"
+  },
+  {,
+    "EventCode": "0x5898",
+    "EventName": "PM_LINK_STACK_INVALID_PTR",
+    "BriefDescription": "It is most often caused by certain types of flush where the pointer is not available. Can result in the data in the link stack becoming unusable."
+  },
+  {,
+    "EventCode": "0x46088",
+    "EventName": "PM_L2_CHIP_PUMP",
+    "BriefDescription": "RC requests that were local (aka chip) pump attempts"
+  },
+  {,
+    "EventCode": "0x28A0",
+    "EventName": "PM_TM_TSUSPEND",
+    "BriefDescription": "TM suspend instruction completed"
+  },
+  {,
+    "EventCode": "0x20054",
+    "EventName": "PM_L1_PREF",
+    "BriefDescription": "A data line was written to the L1 due to a hardware or software prefetch"
+  },
+  {,
+    "EventCode": "0xF888",
+    "EventName": "PM_LSU1_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x4505E",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operation Finished"
+  },
+  {,
+    "EventCode": "0x1D144",
+    "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x400FA",
+    "EventName": "PM_RUN_INST_CMPL",
+    "BriefDescription": "Run_Instructions"
+  },
+  {,
+    "EventCode": "0x15154",
+    "EventName": "PM_SYNC_MRK_L3MISS",
+    "BriefDescription": "Marked L3 misses that can throw a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0xE0B4",
+    "EventName": "PM_LS0_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x26884",
+    "EventName": "PM_DSIDE_MRU_TOUCH",
+    "BriefDescription": "D-side L2 MRU touch sent to L2"
+  },
+  {,
+    "EventCode": "0x30134",
+    "EventName": "PM_MRK_ST_CMPL_INT",
+    "BriefDescription": "marked store finished with intervention"
+  },
+  {,
+    "EventCode": "0xC0B8",
+    "EventName": "PM_LSU_FLUSH_SAO",
+    "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush"
+  },
+  {,
+    "EventCode": "0x50A8",
+    "EventName": "PM_EAT_FORCE_MISPRED",
+    "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT.  The EAT forces a mispredict in this case since there is no predicated target to validate.  This is a rare case that may occur when the EAT is full and a branch is issued"
+  },
+  {,
+    "EventCode": "0xC094",
+    "EventName": "PM_LS0_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0xF8BC",
+    "EventName": "PM_LS3_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x58B0",
+    "EventName": "PM_BTAC_GOOD_RESULT",
+    "BriefDescription": "BTAC predicts a taken branch and the BHT agrees, and the target address is correct"
+  },
+  {,
+    "EventCode": "0x1C04C",
+    "EventName": "PM_DATA_FROM_LL4",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a demand load"
+  },
+  {,
+    "EventCode": "0x3608E",
+    "EventName": "PM_TM_ST_CONF",
+    "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)"
+  },
+  {,
+    "EventCode": "0xD998",
+    "EventName": "PM_MRK_LSU_FLUSH_EMSH",
+    "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
+  },
+  {,
+    "EventCode": "0xF8A0",
+    "EventName": "PM_NON_DATA_STORE",
+    "BriefDescription": "All ops that drain from s2q to L2 and contain no data"
+  },
+  {,
+    "EventCode": "0x3F146",
+    "EventName": "PM_MRK_DPTEG_FROM_L21_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40A0",
+    "EventName": "PM_BR_UNCOND",
+    "BriefDescription": "Unconditional Branch Completed. HW branch prediction was not used for this branch. This can be an I-form branch, a B-form branch with BO-field set to branch always, or a B-form branch which was covenrted to a Resolve."
+  },
+  {,
+    "EventCode": "0x1F056",
+    "EventName": "PM_RADIX_PWC_L1_HIT",
+    "BriefDescription": "A radix translation attempt missed in the TLB and only the first level page walk cache was a hit."
+  },
+  {,
+    "EventCode": "0xF8A8",
+    "EventName": "PM_DC_PREF_FUZZY_CONF",
+    "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)"
+  },
+  {,
+    "EventCode": "0xF8A4",
+    "EventName": "PM_DC_PREF_SW_ALLOC",
+    "BriefDescription": "Prefetch stream allocated by software prefetching"
+  },
+  {,
+    "EventCode": "0xE0A0",
+    "EventName": "PM_LSU2_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x2894",
+    "EventName": "PM_TM_OUTER_TEND",
+    "BriefDescription": "Completion time outer tend"
+  },
+  {,
+    "EventCode": "0xF098",
+    "EventName": "PM_XLATE_HPT_MODE",
+    "BriefDescription": "LSU reports every cycle the thread is in HPT translation mode (as opposed to radix mode)"
+  },
+  {,
+    "EventCode": "0x2C04E",
+    "EventName": "PM_LD_MISS_L1_FIN",
+    "BriefDescription": "Number of load instructions that finished with an L1 miss. Note that even if a load spans multiple slices this event will increment only once per load op."
+  },
+  {,
+    "EventCode": "0x30162",
+    "EventName": "PM_MRK_LSU_DERAT_MISS",
+    "BriefDescription": "Marked derat reload (miss) for any page size"
+  },
+  {,
+    "EventCode": "0x160A0",
+    "EventName": "PM_L3_PF_MISS_L3",
+    "BriefDescription": "L3 PF missed in L3"
+  },
+  {,
+    "EventCode": "0x1C04A",
+    "EventName": "PM_DATA_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0xD99C",
+    "EventName": "PM_MRK_LSU_FLUSH_UE",
+    "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
+  },
+  {,
+    "EventCode": "0x268B0",
+    "EventName": "PM_L3_P1_GRP_PUMP",
+    "BriefDescription": "L3 PF sent with grp scope port 1, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x30016",
+    "EventName": "PM_CMPLU_STALL_SRQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a store that was held in LSAQ because the SRQ was full"
+  },
+  {,
+    "EventCode": "0x40B4",
+    "EventName": "PM_BR_PRED_TA",
+    "BriefDescription": "Conditional Branch Completed that had its target address predicted. Only XL-form branches set this event.  This equal the sum of CCACHE, LSTACK, and PCACHE"
+  },
+  {,
+    "EventCode": "0x40AC",
+    "EventName": "PM_BR_MPRED_CCACHE",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Count Cache Target Prediction"
+  },
+  {,
+    "EventCode": "0x3688A",
+    "EventName": "PM_L2_RTY_LD",
+    "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)"
+  },
+  {,
+    "EventCode": "0xE08C",
+    "EventName": "PM_LSU0_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0xE088",
+    "EventName": "PM_LS2_ERAT_MISS_PREF",
+    "BriefDescription": "LS0 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0xF0A8",
+    "EventName": "PM_DC_PREF_CONF",
+    "BriefDescription": "A demand load referenced a line in an active prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software. Includes forwards and backwards streams"
+  },
+  {,
+    "EventCode": "0x16888",
+    "EventName": "PM_L2_LOC_GUESS_WRONG",
+    "BriefDescription": "L2 guess local (LNS) and guess was not correct (ie data not on chip)"
+  },
+  {,
+    "EventCode": "0xE0A4",
+    "EventName": "PM_TMA_REQ_L2",
+    "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding"
+  },
+  {,
+    "EventCode": "0x5884",
+    "EventName": "PM_DECODE_LANES_NOT_AVAIL",
+    "BriefDescription": "Decode has something to transmit but dispatch lanes are not available"
+  },
+  {,
+    "EventCode": "0x3C042",
+    "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x168AA",
+    "EventName": "PM_L3_P1_LCO_NO_DATA",
+    "BriefDescription": "Dataless L3 LCO sent port 1"
+  },
+  {,
+    "EventCode": "0x3D140",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0xC89C",
+    "EventName": "PM_LS1_LAUNCH_HELD_PREF",
+    "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle"
+  },
+  {,
+    "EventCode": "0x4894",
+    "EventName": "PM_IC_RELOAD_PRIVATE",
+    "BriefDescription": "Reloading line was brought in private for a specific thread.  Most lines are brought in shared for all eight threads.  If RA does not match then invalidates and then brings it shared to other thread. In P7 line brought in private , then line was invalidat"
+  },
+  {,
+    "EventCode": "0x1688E",
+    "EventName": "PM_TM_LD_CAUSED_FAIL",
+    "BriefDescription": "Non-TM Load caused any thread to fail"
+  },
+  {,
+    "EventCode": "0x26084",
+    "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER",
+    "BriefDescription": "All I-or-D side load dispatch attempts for this thread that failed due to reason other than address collision (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x101E4",
+    "EventName": "PM_MRK_L1_ICACHE_MISS",
+    "BriefDescription": "sampled Instruction suffered an icache Miss"
+  },
+  {,
+    "EventCode": "0x20A0",
+    "EventName": "PM_TM_NESTED_TBEGIN",
+    "BriefDescription": "Completion Tm nested tbegin"
+  },
+  {,
+    "EventCode": "0x368AA",
+    "EventName": "PM_L3_P1_CO_MEM",
+    "BriefDescription": "L3 CO to memory port 1 with or without data"
+  },
+  {,
+    "EventCode": "0xC8A4",
+    "EventName": "PM_LSU3_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0xD9A4",
+    "EventName": "PM_MRK_LSU_FLUSH_LARX_STCX",
+    "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread.  A stcx is flushed because an older stcx is in the LMQ.  The flush happens when the older larx/stcx relaunches"
+  },
+  {,
+    "EventCode": "0x4D012",
+    "EventName": "PM_PMC3_SAVED",
+    "BriefDescription": "PMC3 Rewind Value saved"
+  },
+  {,
+    "EventCode": "0xE888",
+    "EventName": "PM_LS3_ERAT_MISS_PREF",
+    "BriefDescription": "LS1 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0x368B4",
+    "EventName": "PM_L3_RD0_BUSY",
+    "BriefDescription": "Lifetime, sample of RD machine 0 valid"
+  },
+  {,
+    "EventCode": "0x46080",
+    "EventName": "PM_L2_DISP_ALL_L2MISS",
+    "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0xF8B8",
+    "EventName": "PM_LS1_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x408C",
+    "EventName": "PM_L1_DEMAND_WRITE",
+    "BriefDescription": "Instruction Demand sectors written into IL1"
+  },
+  {,
+    "EventCode": "0x368A8",
+    "EventName": "PM_SN_INVL",
+    "BriefDescription": "Any port snooper detects a store to a line in the Sx state and invalidates the line.  Up to 4 can happen in a cycle but we only count 1"
+  },
+  {,
+    "EventCode": "0x160B2",
+    "EventName": "PM_L3_LOC_GUESS_CORRECT",
+    "BriefDescription": "initial scope=node/chip (LNS) and data from local node (local) (pred successful) - always PFs only"
+  },
+  {,
+    "EventCode": "0x48B4",
+    "EventName": "PM_DECODE_FUSION_CONST_GEN",
+    "BriefDescription": "32-bit constant generation"
+  },
+  {,
+    "EventCode": "0x4D146",
+    "EventName": "PM_MRK_DATA_FROM_L21_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xE080",
+    "EventName": "PM_S2Q_FULL",
+    "BriefDescription": "Cycles during which the S2Q is full"
+  },
+  {,
+    "EventCode": "0x268B4",
+    "EventName": "PM_L3_P3_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 3 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0xD8B8",
+    "EventName": "PM_LSU0_LMQ_S0_VALID",
+    "BriefDescription": "Slot 0 of LMQ valid"
+  },
+  {,
+    "EventCode": "0x2098",
+    "EventName": "PM_TM_NESTED_TEND",
+    "BriefDescription": "Completion time nested tend"
+  },
+  {,
+    "EventCode": "0x36084",
+    "EventName": "PM_L2_RCST_DISP",
+    "BriefDescription": "All D-side store dispatch attempts for this thread"
+  },
+  {,
+    "EventCode": "0x368A0",
+    "EventName": "PM_L3_PF_OFF_CHIP_CACHE",
+    "BriefDescription": "L3 PF from Off chip cache"
+  },
+  {,
+    "EventCode": "0x20056",
+    "EventName": "PM_TAKEN_BR_MPRED_CMPL",
+    "BriefDescription": "Total number of taken branches that were incorrectly predicted as not-taken. This event counts branches completed and does not include speculative instructions"
+  },
+  {,
+    "EventCode": "0x4688A",
+    "EventName": "PM_L2_SYS_PUMP",
+    "BriefDescription": "RC requests that were system pump attempts"
+  },
+  {,
+    "EventCode": "0xE090",
+    "EventName": "PM_LSU2_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0x4001C",
+    "EventName": "PM_INST_IMC_MATCH_CMPL",
+    "BriefDescription": "IMC Match Count"
+  },
+  {,
+    "EventCode": "0x40A8",
+    "EventName": "PM_BR_PRED_LSTACK",
+    "BriefDescription": "Conditional Branch Completed  that used the Link Stack for Target Prediction"
+  },
+  {,
+    "EventCode": "0x268A2",
+    "EventName": "PM_L3_CI_MISS",
+    "BriefDescription": "L3 castins miss (total count)"
+  },
+  {,
+    "EventCode": "0x289C",
+    "EventName": "PM_TM_NON_FAV_TBEGIN",
+    "BriefDescription": "Dispatch time non favored tbegin"
+  },
+  {,
+    "EventCode": "0xF08C",
+    "EventName": "PM_LSU2_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x360A0",
+    "EventName": "PM_L3_PF_ON_CHIP_CACHE",
+    "BriefDescription": "L3 PF from On chip cache"
+  },
+  {,
+    "EventCode": "0x35152",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS_CYC",
+    "BriefDescription": "Duration in cycles to reload from a location other than the local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0x160AC",
+    "EventName": "PM_L3_SN_USAGE",
+    "BriefDescription": "Rotating sample of 16 snoop valids"
+  },
+  {,
+    "EventCode": "0x16084",
+    "EventName": "PM_L2_RCLD_DISP",
+    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x1608C",
+    "EventName": "PM_RC0_BUSY",
+    "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
+  },
+  {,
+    "EventCode": "0x36082",
+    "EventName": "PM_L2_LD_DISP",
+    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)."
+  },
+  {,
+    "EventCode": "0xF8B0",
+    "EventName": "PM_L3_SW_PREF",
+    "BriefDescription": "L3 load prefetch, sourced from a software prefetch stream, was sent to the nest"
+  },
+  {,
+    "EventCode": "0xF884",
+    "EventName": "PM_TABLEWALK_CYC_PREF",
+    "BriefDescription": "tablewalk qualified for pte  prefetches"
+  },
+  {,
+    "EventCode": "0x4D144",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x16884",
+    "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR",
+    "BriefDescription": "All I-od-D side load dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ machine (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x460A0",
+    "EventName": "PM_L3_PF_ON_CHIP_MEM",
+    "BriefDescription": "L3 PF from On chip memory"
+  },
+  {,
+    "EventCode": "0xF084",
+    "EventName": "PM_PTE_PREFETCH",
+    "BriefDescription": "PTE prefetches"
+  },
+  {,
+    "EventCode": "0x2D026",
+    "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L2 data cache"
+  },
+  {,
+    "EventCode": "0x48B0",
+    "EventName": "PM_BR_MPRED_PCACHE",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to pattern cache prediction"
+  },
+  {,
+    "EventCode": "0x2C126",
+    "EventName": "PM_MRK_DATA_FROM_L2",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0xE0AC",
+    "EventName": "PM_TM_FAIL_TLBIE",
+    "BriefDescription": "Transaction failed because there was a TLBIE hit in the bloom filter"
+  },
+  {,
+    "EventCode": "0x260AA",
+    "EventName": "PM_L3_P0_LCO_DATA",
+    "BriefDescription": "LCO sent with data port 0"
+  },
+  {,
+    "EventCode": "0x4888",
+    "EventName": "PM_IC_PREF_REQ",
+    "BriefDescription": "Instruction prefetch requests"
+  },
+  {,
+    "EventCode": "0xC898",
+    "EventName": "PM_LS3_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x488C",
+    "EventName": "PM_IC_PREF_WRITE",
+    "BriefDescription": "Instruction prefetch written into IL1"
+  },
+  {,
+    "EventCode": "0xF89C",
+    "EventName": "PM_XLATE_MISS",
+    "BriefDescription": "The LSU requested a line from L2 for translation.  It may be satisfied from any source beyond L2.  Includes speculative instructions"
+  },
+  {,
+    "EventCode": "0x14158",
+    "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x35156",
+    "EventName": "PM_MRK_DATA_FROM_L31_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x268A6",
+    "EventName": "PM_TM_RST_SC",
+    "BriefDescription": "TM-snp rst RM SC"
+  },
+  {,
+    "EventCode": "0x468A4",
+    "EventName": "PM_L3_TRANS_PF",
+    "BriefDescription": "L3 Transient prefetch received from L2"
+  },
+  {,
+    "EventCode": "0x4094",
+    "EventName": "PM_IC_PREF_CANCEL_L2",
+    "BriefDescription": "L2 Squashed a demand or prefetch request"
+  },
+  {,
+    "EventCode": "0x48AC",
+    "EventName": "PM_BR_MPRED_LSTACK",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Link Stack Target Prediction"
+  },
+  {,
+    "EventCode": "0xE88C",
+    "EventName": "PM_LSU1_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0xC0B4",
+    "EventName": "PM_LSU_FLUSH_WRK_ARND",
+    "BriefDescription": "LSU workaround flush.  These flushes are setup with programmable scan only latches to perform various actions when the flush macro receives a trigger from the dbg macros. These actions include things like flushing the next op encountered for a particular thread or flushing the next op that is NTC op that is encountered on a particular slice. The kind of flush that the workaround is setup to perform is highly variable."
+  },
+  {,
+    "EventCode": "0x34054",
+    "EventName": "PM_PARTIAL_ST_FIN",
+    "BriefDescription": "Any store finished by an LSU slice"
+  },
+  {,
+    "EventCode": "0x5880",
+    "EventName": "PM_THRD_PRIO_6_7_CYC",
+    "BriefDescription": "Cycles thread running at priority level 6 or 7"
+  },
+  {,
+    "EventCode": "0x4898",
+    "EventName": "PM_IC_DEMAND_L2_BR_REDIRECT",
+    "BriefDescription": "L2 I cache demand request due to branch Mispredict ( 15 cycle path)"
+  },
+  {,
+    "EventCode": "0x4880",
+    "EventName": "PM_BANK_CONFLICT",
+    "BriefDescription": "Read blocked due to interleave conflict.  The ifar logic will detect an interleave conflict and kill the data that was read that cycle."
+  },
+  {,
+    "EventCode": "0x360B0",
+    "EventName": "PM_L3_P0_SYS_PUMP",
+    "BriefDescription": "L3 PF sent with sys scope port 0, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x3006A",
+    "EventName": "PM_IERAT_RELOAD_64K",
+    "BriefDescription": "IERAT Reloaded (Miss) for a 64k page"
+  },
+  {,
+    "EventCode": "0xD8BC",
+    "EventName": "PM_LSU2_3_LRQF_FULL_CYC",
+    "BriefDescription": "Counts the number of cycles the LRQF is full.  LRQF is the queue that holds loads between finish and completion.  If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ"
+  },
+  {,
+    "EventCode": "0x46086",
+    "EventName": "PM_L2_SN_M_RD_DONE",
+    "BriefDescription": "SNP dispatched for a read and was M (true M)"
+  },
+  {,
+    "EventCode": "0x40154",
+    "EventName": "PM_MRK_FAB_RSP_BKILL",
+    "BriefDescription": "Marked store had to do a bkill"
+  },
+  {,
+    "EventCode": "0xF094",
+    "EventName": "PM_LSU2_L1_CAM_CANCEL",
+    "BriefDescription": "ls2 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0x2D014",
+    "EventName": "PM_CMPLU_STALL_LRQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that was held in LSAQ (load-store address queue) because the LRQ (load-reorder queue) was full"
+  },
+  {,
+    "EventCode": "0x3E05E",
+    "EventName": "PM_L3_CO_MEPF",
+    "BriefDescription": "L3 castouts in Mepf state for this thread"
+  },
+  {,
+    "EventCode": "0x460A2",
+    "EventName": "PM_L3_LAT_CI_HIT",
+    "BriefDescription": "L3 Lateral Castins Hit"
+  },
+  {,
+    "EventCode": "0x3D14E",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3D15E",
+    "EventName": "PM_MULT_MRK",
+    "BriefDescription": "mult marked instr"
+  },
+  {,
+    "EventCode": "0x4084",
+    "EventName": "PM_EAT_FULL_CYC",
+    "BriefDescription": "Cycles No room in EAT"
+  },
+  {,
+    "EventCode": "0x5098",
+    "EventName": "PM_LINK_STACK_WRONG_ADD_PRED",
+    "BriefDescription": "Link stack predicts wrong address, because of link stack design limitation or software violating the coding conventions"
+  },
+  {,
+    "EventCode": "0x2C050",
+    "EventName": "PM_DATA_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for a demand load"
+  },
+  {,
+    "EventCode": "0xC0A4",
+    "EventName": "PM_LSU2_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0x58A0",
+    "EventName": "PM_LINK_STACK_CORRECT",
+    "BriefDescription": "Link stack predicts right address"
+  },
+  {,
+    "EventCode": "0x4C05A",
+    "EventName": "PM_DTLB_MISS_1G",
+    "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used"
+  },
+  {,
+    "EventCode": "0x36886",
+    "EventName": "PM_L2_SN_SX_I_DONE",
+    "BriefDescription": "SNP dispatched and went from Sx to Ix"
+  },
+  {,
+    "EventCode": "0x4E04A",
+    "EventName": "PM_DPTEG_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2C12C",
+    "EventName": "PM_MRK_DATA_FROM_DL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's L4 on a different Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x2608E",
+    "EventName": "PM_TM_LD_CONF",
+    "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)"
+  },
+  {,
+    "EventCode": "0x4080",
+    "EventName": "PM_INST_FROM_L1",
+    "BriefDescription": "Instruction fetches from L1.  L1 instruction hit"
+  },
+  {,
+    "EventCode": "0xE898",
+    "EventName": "PM_LSU3_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x260A0",
+    "EventName": "PM_L3_CO_MEM",
+    "BriefDescription": "L3 CO to memory OR of port 0 and 1 (lossy = may undercount if two cresp come in the same cyc)"
+  },
+  {,
+    "EventCode": "0x16082",
+    "EventName": "PM_L2_CASTOUT_MOD",
+    "BriefDescription": "L2 Castouts - Modified (M,Mu,Me)"
+  },
+  {,
+    "EventCode": "0xC09C",
+    "EventName": "PM_LS0_LAUNCH_HELD_PREF",
+    "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle"
+  },
+  {,
+    "EventCode": "0xC8B8",
+    "EventName": "PM_LSU_FLUSH_LARX_STCX",
+    "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread.  A stcx is flushed because an older stcx is in the LMQ.  The flush happens when the older larx/stcx relaunches"
+  },
+  {,
+    "EventCode": "0x260A6",
+    "EventName": "PM_NON_TM_RST_SC",
+    "BriefDescription": "Non-TM snp rst TM SC"
+  },
+  {,
+    "EventCode": "0x3608A",
+    "EventName": "PM_L2_RTY_ST",
+    "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)"
+  },
+  {,
+    "EventCode": "0x24040",
+    "EventName": "PM_INST_FROM_L2_MEPF",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x209C",
+    "EventName": "PM_TM_FAV_TBEGIN",
+    "BriefDescription": "Dispatch time Favored tbegin"
+  },
+  {,
+    "EventCode": "0x2D01E",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_ISSQ",
+    "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full"
+  },
+  {,
+    "EventCode": "0x50A4",
+    "EventName": "PM_FLUSH_MPRED",
+    "BriefDescription": "Branch mispredict flushes.  Includes target and address misprecition"
+  },
+  {,
+    "EventCode": "0x508C",
+    "EventName": "PM_SHL_CREATED",
+    "BriefDescription": "Store-Hit-Load Table Entry Created"
+  },
+  {,
+    "EventCode": "0x1504C",
+    "EventName": "PM_IPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x268A4",
+    "EventName": "PM_L3_LD_MISS",
+    "BriefDescription": "L3 Misses for demand LDs"
+  },
+  {,
+    "EventCode": "0x26088",
+    "EventName": "PM_L2_GRP_GUESS_CORRECT",
+    "BriefDescription": "L2 guess grp (GS or NNS) and guess was correct (data intra-group AND ^on-chip)"
+  },
+  {,
+    "EventCode": "0xD088",
+    "EventName": "PM_LSU0_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
+  },
+  {,
+    "EventCode": "0xE8B4",
+    "EventName": "PM_LS1_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x1688C",
+    "EventName": "PM_RC_USAGE",
+    "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each RC machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
+  },
+  {,
+    "EventCode": "0x3F054",
+    "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from beyond the core's L3 data cache. This is the deepest level of PWC possible for a translation. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x2608A",
+    "EventName": "PM_ISIDE_DISP_FAIL_ADDR",
+    "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a addr collision with another machine (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x50B4",
+    "EventName": "PM_TAGE_CORRECT_TAKEN_CMPL",
+    "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct.  Counted at completion for taken branches only"
+  },
+  {,
+    "EventCode": "0x2090",
+    "EventName": "PM_DISP_CLB_HELD_SB",
+    "BriefDescription": "Dispatch/CLB Hold: Scoreboard"
+  },
+  {,
+    "EventCode": "0xE0B0",
+    "EventName": "PM_TM_FAIL_NON_TX_CONFLICT",
+    "BriefDescription": "Non transactional conflict from LSU, gets reported to TEXASR"
+  },
+  {,
+    "EventCode": "0xD198",
+    "EventName": "PM_MRK_LSU_FLUSH_ATOMIC",
+    "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices.  If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed"
+  },
+  {,
+    "EventCode": "0x201E0",
+    "EventName": "PM_MRK_DATA_FROM_MEMORY",
+    "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a marked load"
+  },
+  {,
+    "EventCode": "0x368A2",
+    "EventName": "PM_L3_L2_CO_MISS",
+    "BriefDescription": "L2 CO miss"
+  },
+  {,
+    "EventCode": "0x3608C",
+    "EventName": "PM_CO0_BUSY",
+    "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)"
+  },
+  {,
+    "EventCode": "0x2C122",
+    "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x35154",
+    "EventName": "PM_MRK_DATA_FROM_L3_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x1D140",
+    "EventName": "PM_MRK_DATA_FROM_L31_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x4404A",
+    "EventName": "PM_INST_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x28AC",
+    "EventName": "PM_TM_FAIL_SELF",
+    "BriefDescription": "TM aborted because a self-induced conflict occurred in Suspended state, due to one of the following: a store to a storage location that was previously accessed transactionally; a dcbf, dcbi, or icbi specify- ing a block that was previously accessed transactionally; a dcbst specifying a block that was previously written transactionally; or a tlbie that specifies a translation that was pre- viously used transactionally"
+  },
+  {,
+    "EventCode": "0x45056",
+    "EventName": "PM_SCALAR_FLOP_CMPL",
+    "BriefDescription": "Scalar flop operation completed"
+  },
+  {,
+    "EventCode": "0x16092",
+    "EventName": "PM_L2_LD_MISS_128B",
+    "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)"
+  },
+  {,
+    "EventCode": "0x2E014",
+    "EventName": "PM_STCX_FIN",
+    "BriefDescription": "Number of stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed"
+  },
+  {,
+    "EventCode": "0xE0B8",
+    "EventName": "PM_LS2_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x2094",
+    "EventName": "PM_TM_OUTER_TBEGIN",
+    "BriefDescription": "Completion time outer tbegin"
+  },
+  {,
+    "EventCode": "0x160B4",
+    "EventName": "PM_L3_P0_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 0 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0x36892",
+    "EventName": "PM_DSIDE_OTHER_64B_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory that was for hpc_read64, (RC had to fetch other 64B of a line from MC) i.e., number of times RC had to go to memory to get 'missing' 64B"
+  },
+  {,
+    "EventCode": "0x20A8",
+    "EventName": "PM_TM_FAIL_FOOTPRINT_OVERFLOW",
+    "BriefDescription": "TM aborted because the tracking limit for transactional storage accesses was exceeded.. Asynchronous"
+  },
+  {,
+    "EventCode": "0x30018",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL",
+    "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
+  },
+  {,
+    "EventCode": "0xC894",
+    "EventName": "PM_LS1_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x360A2",
+    "EventName": "PM_L3_L2_CO_HIT",
+    "BriefDescription": "L2 CO hits"
+  },
+  {,
+    "EventCode": "0x36092",
+    "EventName": "PM_DSIDE_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory (excluding hpcread64 accesses), i.e., total memory accesses by RCs"
+  },
+  {,
+    "EventCode": "0x10138",
+    "EventName": "PM_MRK_BR_2PATH",
+    "BriefDescription": "marked branches which are not strongly biased"
+  },
+  {,
+    "EventCode": "0x2884",
+    "EventName": "PM_ISYNC",
+    "BriefDescription": "Isync completion count per thread"
+  },
+  {,
+    "EventCode": "0x16882",
+    "EventName": "PM_L2_CASTOUT_SHR",
+    "BriefDescription": "L2 Castouts - Shared (Tx,Sx)"
+  },
+  {,
+    "EventCode": "0xD884",
+    "EventName": "PM_LSU3_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0x26092",
+    "EventName": "PM_L2_LD_MISS_64B",
+    "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B(i.e., M=1)"
+  },
+  {,
+    "EventCode": "0x26080",
+    "EventName": "PM_L2_LD_MISS",
+    "BriefDescription": "All successful D-Side Load dispatches that were an L2 miss for this thread"
+  },
+  {,
+    "EventCode": "0x3D14C",
+    "EventName": "PM_MRK_DATA_FROM_DMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x100FA",
+    "EventName": "PM_ANY_THRD_RUN_CYC",
+    "BriefDescription": "Cycles in which at least one thread has the run latch set"
+  },
+  {,
+    "EventCode": "0x2C12A",
+    "EventName": "PM_MRK_DATA_FROM_RMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x25048",
+    "EventName": "PM_IPTEG_FROM_LMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xD8A8",
+    "EventName": "PM_ISLB_MISS",
+    "BriefDescription": "Instruction SLB miss - Total of all segment sizes"
+  },
+  {,
+    "EventCode": "0xD19C",
+    "EventName": "PM_MRK_LSU_FLUSH_RELAUNCH_MISS",
+    "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent"
+  },
+  {,
+    "EventCode": "0x260A2",
+    "EventName": "PM_L3_CI_HIT",
+    "BriefDescription": "L3 Castins Hit (total count)"
+  },
+  {,
+    "EventCode": "0x44054",
+    "EventName": "PM_VECTOR_LD_CMPL",
+    "BriefDescription": "Number of vector load instructions completed"
+  },
+  {,
+    "EventCode": "0x1E05C",
+    "EventName": "PM_CMPLU_STALL_NESTED_TBEGIN",
+    "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tbegin. This is a short delay, and it includes ROT"
+  },
+  {,
+    "EventCode": "0x1608E",
+    "EventName": "PM_ST_CAUSED_FAIL",
+    "BriefDescription": "Non-TM Store caused any thread to fail"
+  },
+  {,
+    "EventCode": "0x3080",
+    "EventName": "PM_ISU0_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0x1515A",
+    "EventName": "PM_SYNC_MRK_L2MISS",
+    "BriefDescription": "Marked L2 Miss that can throw a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x26892",
+    "EventName": "PM_L2_ST_MISS_64B",
+    "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B (i.e., M=1)"
+  },
+  {,
+    "EventCode": "0x2688C",
+    "EventName": "PM_CO_USAGE",
+    "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
+  },
+  {,
+    "EventCode": "0xD084",
+    "EventName": "PM_LSU2_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0x48B8",
+    "EventName": "PM_BR_MPRED_TAKEN_TA",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Target Address Prediction from the Count Cache or Link Stack.  Only XL-form branches that resolved Taken set this event."
+  },
+  {,
+    "EventCode": "0x50B0",
+    "EventName": "PM_BTAC_BAD_RESULT",
+    "BriefDescription": "BTAC thinks branch will be taken but it is either predicted not-taken by the BHT, or the target address is wrong (less common).  In both cases, a redirect will happen"
+  },
+  {,
+    "EventCode": "0xD888",
+    "EventName": "PM_LSU1_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
+  },
+  {,
+    "EventCode": "0x58B4",
+    "EventName": "PM_TAGE_CORRECT",
+    "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct.   Includes taken and not taken and is counted at execution time"
+  },
+  {,
+    "EventCode": "0x3688C",
+    "EventName": "PM_SN_USAGE",
+    "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
+  },
+  {,
+    "EventCode": "0x46084",
+    "EventName": "PM_L2_RCST_DISP_FAIL_OTHER",
+    "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to reason other than address collision"
+  },
+  {,
+    "EventCode": "0xF0AC",
+    "EventName": "PM_DC_PREF_STRIDED_CONF",
+    "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software."
+  },
+  {,
+    "EventCode": "0x45054",
+    "EventName": "PM_FMA_CMPL",
+    "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. "
+  },
+  {,
+    "EventCode": "0x5090",
+    "EventName": "PM_SHL_ST_DISABLE",
+    "BriefDescription": "Store-Hit-Load Table Read Hit with entry Disabled (entry was disabled due to the entry shown to not prevent the flush)"
+  },
+  {,
+    "EventCode": "0x201E8",
+    "EventName": "PM_THRESH_EXC_512",
+    "BriefDescription": "Threshold counter exceeded a value of 512"
+  },
+  {,
+    "EventCode": "0x5084",
+    "EventName": "PM_DECODE_FUSION_EXT_ADD",
+    "BriefDescription": "32-bit extended addition"
+  },
+  {,
+    "EventCode": "0x36080",
+    "EventName": "PM_L2_INST",
+    "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)."
+  },
+  {,
+    "EventCode": "0x3504C",
+    "EventName": "PM_IPTEG_FROM_DL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xD890",
+    "EventName": "PM_LS1_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x1688A",
+    "EventName": "PM_ISIDE_DISP",
+    "BriefDescription": "All I-side dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x468AA",
+    "EventName": "PM_L3_P1_CO_L31",
+    "BriefDescription": "L3 CO to L3.1 (LCO) port 1 with or without data"
+  },
+  {,
+    "EventCode": "0x28B0",
+    "EventName": "PM_DISP_HELD_TBEGIN",
+    "BriefDescription": "This outer tbegin transaction cannot be dispatched until the previous tend instruction completes"
+  },
+  {,
+    "EventCode": "0xE8A0",
+    "EventName": "PM_LSU3_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x2C05E",
+    "EventName": "PM_INST_GRP_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for an instruction fetch (demand only)"
+  },
+  {,
+    "EventCode": "0xC8BC",
+    "EventName": "PM_STCX_SUCCESS_CMPL",
+    "BriefDescription": "Number of stcx instructions that completed successfully"
+  },
+  {,
+    "EventCode": "0xE098",
+    "EventName": "PM_LSU2_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x44044",
+    "EventName": "PM_INST_FROM_L31_ECO_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x16886",
+    "EventName": "PM_CO_DISP_FAIL",
+    "BriefDescription": "CO dispatch failed due to all CO machines being busy"
+  },
+  {,
+    "EventCode": "0x3D146",
+    "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x16892",
+    "EventName": "PM_L2_ST_MISS_128B",
+    "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)"
+  },
+  {,
+    "EventCode": "0x26890",
+    "EventName": "PM_ISIDE_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an I-side fetch where data came from memory"
+  },
+  {,
+    "EventCode": "0xD094",
+    "EventName": "PM_LS2_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x3C05E",
+    "EventName": "PM_MEM_RWITM",
+    "BriefDescription": "Memory Read With Intent to Modify for this thread"
+  },
+  {,
+    "EventCode": "0x26882",
+    "EventName": "PM_L2_DC_INV",
+    "BriefDescription": "D-cache invalidates sent over the reload bus to the core"
+  },
+  {,
+    "EventCode": "0xC090",
+    "EventName": "PM_LSU_STCX",
+    "BriefDescription": "STCX sent to nest, i.e. total"
+  },
+  {,
+    "EventCode": "0xD080",
+    "EventName": "PM_LSU0_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0x2C120",
+    "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x36086",
+    "EventName": "PM_L2_RC_ST_DONE",
+    "BriefDescription": "RC did store to line that was Tx or Sx"
+  },
+  {,
+    "EventCode": "0xE8AC",
+    "EventName": "PM_TM_FAIL_TX_CONFLICT",
+    "BriefDescription": "Transactional conflict from LSU, gets reported to TEXASR"
+  },
+  {,
+    "EventCode": "0x48A8",
+    "EventName": "PM_DECODE_FUSION_LD_ST_DISP",
+    "BriefDescription": "32-bit displacement D-form and 16-bit displacement X-form"
+  },
+  {,
+    "EventCode": "0x3D144",
+    "EventName": "PM_MRK_DATA_FROM_L2_MEPF_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load"
+  },
+  {,
+    "EventCode": "0x44046",
+    "EventName": "PM_INST_FROM_L21_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x40B0",
+    "EventName": "PM_BR_PRED_TAKEN_CR",
+    "BriefDescription": "Conditional Branch that had its direction predicted. I-form branches do not set this event.  In addition, B-form branches which do not use the BHT do not set this event - these are branches with BO-field set to 'always taken' and branches"
+  },
+  {,
+    "EventCode": "0x15040",
+    "EventName": "PM_IPTEG_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xD9A0",
+    "EventName": "PM_MRK_LSU_FLUSH_LHL_SHL",
+    "BriefDescription": "The instruction was flushed because of a sequential load/store consistency.  If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)."
+  },
+  {,
+    "EventCode": "0x35042",
+    "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xF898",
+    "EventName": "PM_XLATE_RADIX_MODE",
+    "BriefDescription": "LSU reports every cycle the thread is in radix translation mode (as opposed to HPT mode)"
+  },
+  {,
+    "EventCode": "0x2D142",
+    "EventName": "PM_MRK_DATA_FROM_L3_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked load"
+  },
+  {,
+    "EventCode": "0x160B0",
+    "EventName": "PM_L3_P0_NODE_PUMP",
+    "BriefDescription": "L3 PF sent with nodal scope port 0, counts even retried requests"
+  },
+  {,
+    "EventCode": "0xD88C",
+    "EventName": "PM_LSU3_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
+  },
+  {,
+    "EventCode": "0x36882",
+    "EventName": "PM_L2_LD_HIT",
+    "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x168AC",
+    "EventName": "PM_L3_CI_USAGE",
+    "BriefDescription": "Rotating sample of 16 CI or CO actives"
+  },
+  {,
+    "EventCode": "0x20134",
+    "EventName": "PM_MRK_FXU_FIN",
+    "BriefDescription": "fxu marked instr finish"
+  },
+  {,
+    "EventCode": "0x4608E",
+    "EventName": "PM_TM_CAP_OVERFLOW",
+    "BriefDescription": "TM Footprint Capacity Overflow"
+  },
+  {,
+    "EventCode": "0x4F05C",
+    "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from beyond the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x40014",
+    "EventName": "PM_PROBE_NOP_DISP",
+    "BriefDescription": "ProbeNops dispatched"
+  },
+  {,
+    "EventCode": "0x58A8",
+    "EventName": "PM_DECODE_HOLD_ICT_FULL",
+    "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use.  This means the ICT is full for this thread"
+  },
+  {,
+    "EventCode": "0x10052",
+    "EventName": "PM_GRP_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x2505E",
+    "EventName": "PM_BACK_BR_CMPL",
+    "BriefDescription": "Branch instruction completed with a target address less than current instruction address"
+  },
+  {,
+    "EventCode": "0x2688A",
+    "EventName": "PM_ISIDE_DISP_FAIL_OTHER",
+    "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a reason other than addrs collision (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x2001A",
+    "EventName": "PM_NTC_ALL_FIN",
+    "BriefDescription": "Cycles after all instructions have finished to group completed"
+  },
+  {,
+    "EventCode": "0x3005A",
+    "EventName": "PM_ISQ_0_8_ENTRIES",
+    "BriefDescription": "Cycles in which 8 or less Issue Queue entries are in use. This is a shared event, not per thread"
+  },
+  {,
+    "EventCode": "0x3515E",
+    "EventName": "PM_MRK_BACK_BR_CMPL",
+    "BriefDescription": "Marked branch instruction completed with a target address less than current instruction address"
+  },
+  {,
+    "EventCode": "0xF890",
+    "EventName": "PM_LSU1_L1_CAM_CANCEL",
+    "BriefDescription": "ls1 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0xE884",
+    "EventName": "PM_LS1_ERAT_MISS_PREF",
+    "BriefDescription": "LS1 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0xE89C",
+    "EventName": "PM_LSU1_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x28A8",
+    "EventName": "PM_TM_FAIL_CONF_NON_TM",
+    "BriefDescription": "TM aborted because a conflict occurred with a non-transactional access by another processor"
+  },
+  {,
+    "EventCode": "0x16890",
+    "EventName": "PM_L1PF_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an L1PF where data came from memory"
+  },
+  {,
+    "EventCode": "0x4504C",
+    "EventName": "PM_IPTEG_FROM_DMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1002E",
+    "EventName": "PM_LMQ_MERGE",
+    "BriefDescription": "A demand miss collides with a prefetch for the same line"
+  },
+  {,
+    "EventCode": "0x160B6",
+    "EventName": "PM_L3_WI0_BUSY",
+    "BriefDescription": "Rotating sample of 8 WI valid"
+  },
+  {,
+    "EventCode": "0x368AC",
+    "EventName": "PM_L3_CO0_BUSY",
+    "BriefDescription": "Lifetime, sample of CO machine 0 valid"
+  },
+  {,
+    "EventCode": "0x2E040",
+    "EventName": "PM_DPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1D152",
+    "EventName": "PM_MRK_DATA_FROM_DL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x46880",
+    "EventName": "PM_ISIDE_MRU_TOUCH",
+    "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread"
+  },
+  {,
+    "EventCode": "0x1C05C",
+    "EventName": "PM_DTLB_MISS_2M",
+    "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used"
+  },
+  {,
+    "EventCode": "0x50B8",
+    "EventName": "PM_TAGE_OVERRIDE_WRONG",
+    "BriefDescription": "The TAGE overrode BHT direction prediction but it was incorrect.  Counted at completion for taken branches only"
+  },
+  {,
+    "EventCode": "0x160AE",
+    "EventName": "PM_L3_P0_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 0, every retry counted"
+  },
+  {,
+    "EventCode": "0x268B2",
+    "EventName": "PM_L3_LOC_GUESS_WRONG",
+    "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low"
+  },
+  {,
+    "EventCode": "0x36088",
+    "EventName": "PM_L2_SYS_GUESS_CORRECT",
+    "BriefDescription": "L2 guess system (VGS or RNS) and guess was correct (ie data beyond-group)"
+  },
+  {,
+    "EventCode": "0x589C",
+    "EventName": "PM_PTESYNC",
+    "BriefDescription": "ptesync instruction counted when the instruction is decoded and transmitted"
+  },
+  {,
+    "EventCode": "0x26086",
+    "EventName": "PM_CO_TM_SC_FOOTPRINT",
+    "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3) OR L2 TM_store hit dirty HPC line and L3 indicated SC line formed in L3 on RDR bus"
+  },
+  {,
+    "EventCode": "0x1E05A",
+    "EventName": "PM_CMPLU_STALL_ANY_SYNC",
+    "BriefDescription": "Cycles in which the NTC sync instruction (isync, lwsync or hwsync) is not allowed to complete"
+  },
+  {,
+    "EventCode": "0xF090",
+    "EventName": "PM_LSU0_L1_CAM_CANCEL",
+    "BriefDescription": "ls0 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0xC0A8",
+    "EventName": "PM_LSU_FLUSH_CI",
+    "BriefDescription": "Load was not issued to LSU as a cache inhibited (non-cacheable) load but it was later determined to be cache inhibited"
+  },
+  {,
+    "EventCode": "0x20AC",
+    "EventName": "PM_TM_FAIL_CONF_TM",
+    "BriefDescription": "TM aborted because a conflict occurred with another transaction."
+  },
+  {,
+    "EventCode": "0x588C",
+    "EventName": "PM_SHL_ST_DEP_CREATED",
+    "BriefDescription": "Store-Hit-Load Table Read Hit with entry Enabled"
+  },
+  {,
+    "EventCode": "0x360AC",
+    "EventName": "PM_L3_SN0_BUSY",
+    "BriefDescription": "Lifetime, sample of snooper machine 0 valid"
+  },
+  {,
+    "EventCode": "0x3005C",
+    "EventName": "PM_BFU_BUSY",
+    "BriefDescription": "Cycles in which all 4 Binary Floating Point units are busy. The BFU is running at capacity"
+  },
+  {,
+    "EventCode": "0x48A0",
+    "EventName": "PM_BR_PRED_PCACHE",
+    "BriefDescription": "Conditional branch completed that used pattern cache prediction"
+  },
+  {,
+    "EventCode": "0x26880",
+    "EventName": "PM_L2_ST_MISS",
+    "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread"
+  },
+  {,
+    "EventCode": "0xF8B4",
+    "EventName": "PM_DC_PREF_XCONS_ALLOC",
+    "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch"
+  },
+  {,
+    "EventCode": "0x35048",
+    "EventName": "PM_IPTEG_FROM_DL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x260A8",
+    "EventName": "PM_L3_PF_HIT_L3",
+    "BriefDescription": "L3 PF hit in L3 (abandoned)"
+  },
+  {,
+    "EventCode": "0x360B4",
+    "EventName": "PM_L3_PF0_BUSY",
+    "BriefDescription": "Lifetime, sample of PF machine 0 valid"
+  },
+  {,
+    "EventCode": "0xC0B0",
+    "EventName": "PM_LSU_FLUSH_UE",
+    "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
+  },
+  {,
+    "EventCode": "0x4013A",
+    "EventName": "PM_MRK_IC_MISS",
+    "BriefDescription": "Marked instruction experienced I cache miss"
+  },
+  {,
+    "EventCode": "0x2088",
+    "EventName": "PM_FLUSH_DISP_SB",
+    "BriefDescription": "Dispatch Flush: Scoreboard"
+  },
+  {,
+    "EventCode": "0x401E8",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0x3688E",
+    "EventName": "PM_TM_ST_CAUSED_FAIL",
+    "BriefDescription": "TM Store (fav or non-fav) caused another thread to fail"
+  },
+  {,
+    "EventCode": "0x460B2",
+    "EventName": "PM_L3_SYS_GUESS_WRONG",
+    "BriefDescription": "Initial scope=system (VGS or RNS) but data from local or near. Prediction too high"
+  },
+  {,
+    "EventCode": "0x58B8",
+    "EventName": "PM_TAGE_OVERRIDE_WRONG_SPEC",
+    "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct.   Includes taken and not taken and is counted at execution time"
+  },
+  {,
+    "EventCode": "0xE890",
+    "EventName": "PM_LSU3_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0x2898",
+    "EventName": "PM_TM_TABORT_TRECLAIM",
+    "BriefDescription": "Completion time tabortnoncd, tabortcd, treclaim"
+  },
+  {,
+    "EventCode": "0x4C054",
+    "EventName": "PM_DERAT_MISS_16G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G"
+  },
+  {,
+    "EventCode": "0x268A0",
+    "EventName": "PM_L3_CO_L31",
+    "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 (lossy = may undercount if two cresps come in the same cyc)"
+  },
+  {,
+    "EventCode": "0x5080",
+    "EventName": "PM_THRD_PRIO_4_5_CYC",
+    "BriefDescription": "Cycles thread running at priority level 4 or 5"
+  },
+  {,
+    "EventCode": "0x2505C",
+    "EventName": "PM_VSU_FIN",
+    "BriefDescription": "VSU instruction finished. Up to 4 per cycle"
+  },
+  {,
+    "EventCode": "0x40A4",
+    "EventName": "PM_BR_PRED_CCACHE",
+    "BriefDescription": "Conditional Branch Completed that used the Count Cache for Target Prediction"
+  },
+  {,
+    "EventCode": "0x2E04A",
+    "EventName": "PM_DPTEG_FROM_RL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D12E",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xC8B4",
+    "EventName": "PM_LSU_FLUSH_LHL_SHL",
+    "BriefDescription": "The instruction was flushed because of a sequential load/store consistency.  If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)."
+  },
+  {,
+    "EventCode": "0x58A4",
+    "EventName": "PM_FLUSH_LSU",
+    "BriefDescription": "LSU flushes.  Includes all lsu flushes"
+  },
+  {,
+    "EventCode": "0x1D150",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xC8A0",
+    "EventName": "PM_LSU1_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0x48BC",
+    "EventName": "PM_THRD_PRIO_2_3_CYC",
+    "BriefDescription": "Cycles thread running at priority level 2 or 3"
+  },
+  {,
+    "EventCode": "0x10134",
+    "EventName": "PM_MRK_ST_DONE_L2",
+    "BriefDescription": "marked store completed in L2 ( RC machine done)"
+  },
+  {,
+    "EventCode": "0x368B2",
+    "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH",
+    "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high"
+  },
+  {,
+    "EventCode": "0xE8BC",
+    "EventName": "PM_LS1_PTE_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 1"
+  },
+  {,
+    "EventCode": "0x1F152",
+    "EventName": "PM_MRK_FAB_RSP_BKILL_CYC",
+    "BriefDescription": "cycles L2 RC took for a bkill"
+  },
+  {,
+    "EventCode": "0x4C124",
+    "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x2F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x26888",
+    "EventName": "PM_L2_GRP_GUESS_WRONG",
+    "BriefDescription": "L2 guess grp (GS or NNS) and guess was not correct (ie data on-chip OR beyond-group)"
+  },
+  {,
+    "EventCode": "0x368AE",
+    "EventName": "PM_L3_P1_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
+  },
+  {,
+    "EventCode": "0xC0AC",
+    "EventName": "PM_LSU_FLUSH_EMSH",
+    "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
+  },
+  {,
+    "EventCode": "0x260B2",
+    "EventName": "PM_L3_SYS_GUESS_CORRECT",
+    "BriefDescription": "Initial scope=system (VGS or RNS) and data from outside group (far or rem)(pred successful)"
+  },
+  {,
+    "EventCode": "0x1D146",
+    "EventName": "PM_MRK_DATA_FROM_MEMORY_CYC",
+    "BriefDescription": "Duration in cycles to reload from a memory location including L4 from local remote or distant due to a marked load"
+  },
+  {,
+    "EventCode": "0xE094",
+    "EventName": "PM_LSU0_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x46888",
+    "EventName": "PM_L2_GROUP_PUMP",
+    "BriefDescription": "RC requests that were on group (aka nodel) pump attempts"
+  },
+  {,
+    "EventCode": "0xF0B0",
+    "EventName": "PM_L3_LD_PREF",
+    "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest"
+  },
+  {,
+    "EventCode": "0x16080",
+    "EventName": "PM_L2_LD",
+    "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)"
+  },
+  {,
+    "EventCode": "0x4505C",
+    "EventName": "PM_MATH_FLOP_CMPL",
+    "BriefDescription": "Math flop instruction completed"
+  },
+  {,
+    "EventCode": "0x368B0",
+    "EventName": "PM_L3_P1_SYS_PUMP",
+    "BriefDescription": "L3 PF sent with sys scope port 1, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x1F146",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2000C",
+    "EventName": "PM_THRD_ALL_RUN_CYC",
+    "BriefDescription": "Cycles in which all the threads have the run latch set"
+  },
+  {,
+    "EventCode": "0xC0BC",
+    "EventName": "PM_LSU_FLUSH_OTHER",
+    "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)"
+  },
+  {,
+    "EventCode": "0x5094",
+    "EventName": "PM_IC_MISS_ICBI",
+    "BriefDescription": "threaded version, IC Misses where we got EA dir hit but no sector valids were on. ICBI took line out"
+  },
+  {,
+    "EventCode": "0xC8A8",
+    "EventName": "PM_LSU_FLUSH_ATOMIC",
+    "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices.  If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed"
+  },
+  {,
+    "EventCode": "0x1E04E",
+    "EventName": "PM_DPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D05E",
+    "EventName": "PM_BR_CMPL",
+    "BriefDescription": "Any Branch instruction completed"
+  },
+  {,
+    "EventCode": "0x260B0",
+    "EventName": "PM_L3_P0_GRP_PUMP",
+    "BriefDescription": "L3 PF sent with grp scope port 0, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x30132",
+    "EventName": "PM_MRK_VSU_FIN",
+    "BriefDescription": "VSU marked instr finish"
+  },
+  {,
+    "EventCode": "0x2D120",
+    "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x1E048",
+    "EventName": "PM_DPTEG_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x16086",
+    "EventName": "PM_L2_SN_M_WR_DONE",
+    "BriefDescription": "SNP dispatched for a write and was M (true M); for DMA cacheinj this will pulse if rty/push is required (won't pulse if cacheinj is accepted)"
+  },
+  {,
+    "EventCode": "0x489C",
+    "EventName": "PM_BR_CORECT_PRED_TAKEN_CMPL",
+    "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken.  Counted at completion time"
+  },
+  {,
+    "EventCode": "0xF0B8",
+    "EventName": "PM_LS0_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x20132",
+    "EventName": "PM_MRK_DFU_FIN",
+    "BriefDescription": "Decimal Unit marked Instruction Finish"
+  },
+  {,
+    "EventCode": "0x160A6",
+    "EventName": "PM_TM_SC_CO",
+    "BriefDescription": "L3 castout TM SC line"
+  },
+  {,
+    "EventCode": "0xC8B0",
+    "EventName": "PM_LSU_FLUSH_LHS",
+    "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
+  },
+  {,
+    "EventCode": "0x3F150",
+    "EventName": "PM_MRK_ST_DRAIN_TO_L2DISP_CYC",
+    "BriefDescription": "cycles to drain st from core to L2"
+  },
+  {,
+    "EventCode": "0x168A4",
+    "EventName": "PM_L3_MISS",
+    "BriefDescription": "L3 Misses (L2 miss also missing L3, including data/instrn/xlate)"
+  },
+  {,
+    "EventCode": "0xF080",
+    "EventName": "PM_LSU_STCX_FAIL",
+    "BriefDescription": ""
+  },
+  {,
+    "EventCode": "0x30038",
+    "EventName": "PM_CMPLU_STALL_DMISS_LMEM",
+    "BriefDescription": "Completion stall due to cache miss that resolves in local memory"
+  },
+  {,
+    "EventCode": "0x28A4",
+    "EventName": "PM_MRK_TEND_FAIL",
+    "BriefDescription": "Nested or not nested tend failed for a marked tend instruction"
+  },
+  {,
+    "EventCode": "0x100FC",
+    "EventName": "PM_LD_REF_L1",
+    "BriefDescription": "All L1 D cache load references counted at finish, gated by reject"
+  },
+  {,
+    "EventCode": "0xC0A0",
+    "EventName": "PM_LSU0_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0x468A8",
+    "EventName": "PM_SN_MISS",
+    "BriefDescription": "Any port snooper L3 miss or collision.  Up to 4 can happen in a cycle but we only count 1"
+  },
+  {,
+    "EventCode": "0x36888",
+    "EventName": "PM_L2_SYS_GUESS_WRONG",
+    "BriefDescription": "L2 guess system (VGS or RNS) and guess was not correct (ie data ^beyond-group)"
+  },
+  {,
+    "EventCode": "0x2080",
+    "EventName": "PM_EE_OFF_EXT_INT",
+    "BriefDescription": "CyclesMSR[EE] is off and external interrupts are active"
+  },
+  {,
+    "EventCode": "0xE8B8",
+    "EventName": "PM_LS3_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x2688E",
+    "EventName": "PM_TM_FAV_CAUSED_FAIL",
+    "BriefDescription": "TM Load (fav) caused another thread to fail"
+  },
+  {,
+    "EventCode": "0x16090",
+    "EventName": "PM_SN0_BUSY",
+    "BriefDescription": "SN mach 0 Busy. Used by PMU to sample ave SN lifetime (mach0 used as sample point)"
+  },
+  {,
+    "EventCode": "0x360AE",
+    "EventName": "PM_L3_P0_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 0 (memory only), every retry counted"
+  },
+  {,
+    "EventCode": "0x168A8",
+    "EventName": "PM_L3_WI_USAGE",
+    "BriefDescription": "Lifetime, sample of Write Inject machine 0 valid"
+  },
+  {,
+    "EventCode": "0x468A2",
+    "EventName": "PM_L3_LAT_CI_MISS",
+    "BriefDescription": "L3 Lateral Castins Miss"
+  },
+  {,
+    "EventCode": "0x4090",
+    "EventName": "PM_IC_PREF_CANCEL_PAGE",
+    "BriefDescription": "Prefetch Canceled due to page boundary"
+  },
+  {,
+    "EventCode": "0xF09C",
+    "EventName": "PM_SLB_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when a tablewalk is pending on this thread on the SLB table"
+  },
+  {,
+    "EventCode": "0x460AA",
+    "EventName": "PM_L3_P0_CO_L31",
+    "BriefDescription": "L3 CO to L3.1 (LCO) port 0 with or without data"
+  },
+  {,
+    "EventCode": "0x2880",
+    "EventName": "PM_FLUSH_DISP",
+    "BriefDescription": "Dispatch flush"
+  },
+  {,
+    "EventCode": "0x168AE",
+    "EventName": "PM_L3_P1_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 1, every retry counted"
+  },
+  {,
+    "EventCode": "0x46082",
+    "EventName": "PM_L2_ST_DISP",
+    "BriefDescription": "All successful D-side store dispatches for this thread "
+  },
+  {,
+    "EventCode": "0x4609E",
+    "EventName": "PM_L2_INST_MISS",
+    "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
+  },
+  {,
+    "EventCode": "0xE084",
+    "EventName": "PM_LS0_ERAT_MISS_PREF",
+    "BriefDescription": "LS0 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0x409C",
+    "EventName": "PM_BR_PRED",
+    "BriefDescription": "Conditional Branch Executed in which the HW predicted the Direction or Target.  Includes taken and not taken and is counted at execution time"
+  },
+  {,
+    "EventCode": "0x2D144",
+    "EventName": "PM_MRK_DATA_FROM_L31_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x360A4",
+    "EventName": "PM_L3_CO_LCO",
+    "BriefDescription": "Total L3 COs occurred on LCO L3.1 (good cresp, may end up in mem on a retry)"
+  },
+  {,
+    "EventCode": "0x4890",
+    "EventName": "PM_IC_PREF_CANCEL_HIT",
+    "BriefDescription": "Prefetch Canceled due to icache hit"
+  },
+  {,
+    "EventCode": "0x268A8",
+    "EventName": "PM_RD_HIT_PF",
+    "BriefDescription": "RD machine hit L3 PF machine"
+  },
+  {,
+    "EventCode": "0x16880",
+    "EventName": "PM_L2_ST",
+    "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)"
+  },
+  {,
+    "EventCode": "0x4098",
+    "EventName": "PM_IC_DEMAND_L2_BHT_REDIRECT",
+    "BriefDescription": "L2 I cache demand request due to BHT redirect, branch redirect ( 2 bubbles 3 cycles)"
+  },
+  {,
+    "EventCode": "0xD0B4",
+    "EventName": "PM_LSU0_SRQ_S0_VALID_CYC",
+    "BriefDescription": "Slot 0 of SRQ valid"
+  },
+  {,
+    "EventCode": "0x160AA",
+    "EventName": "PM_L3_P0_LCO_NO_DATA",
+    "BriefDescription": "Dataless L3 LCO sent port 0"
+  },
+  {,
+    "EventCode": "0x208C",
+    "EventName": "PM_CLB_HELD",
+    "BriefDescription": "CLB (control logic block - indicates quadword fetch block) Hold: Any Reason"
+  },
+  {,
+    "EventCode": "0xF88C",
+    "EventName": "PM_LSU3_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x200F2",
+    "EventName": "PM_INST_DISP",
+    "BriefDescription": "# PPC Dispatched"
+  },
+  {,
+    "EventCode": "0x4E05E",
+    "EventName": "PM_TM_OUTER_TBEGIN_DISP",
+    "BriefDescription": "Number of outer tbegin instructions dispatched. The dispatch unit determines whether the tbegin instruction is outer or nested. This is a speculative count, which includes flushed instructions"
+  },
+  {,
+    "EventCode": "0x2D018",
+    "EventName": "PM_CMPLU_STALL_EXEC_UNIT",
+    "BriefDescription": "Completion stall due to execution units (FXU/VSU/CRU)"
+  },
+  {,
+    "EventCode": "0x20B0",
+    "EventName": "PM_LSU_FLUSH_NEXT",
+    "BriefDescription": "LSU flush next reported at flush time.  Sometimes these also come with an exception"
+  },
+  {,
+    "EventCode": "0x3880",
+    "EventName": "PM_ISU2_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0x46882",
+    "EventName": "PM_L2_ST_HIT",
+    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
+  },
+  {,
+    "EventCode": "0x360A8",
+    "EventName": "PM_L3_CO",
+    "BriefDescription": "L3 castout occurring (does not include casthrough or log writes (cinj/dmaw))"
+  },
+  {,
+    "EventCode": "0x368A4",
+    "EventName": "PM_L3_CINJ",
+    "BriefDescription": "L3 castin of cache inject"
+  },
+  {,
+    "EventCode": "0xC890",
+    "EventName": "PM_LSU_NCST",
+    "BriefDescription": "Asserts when a i=1 store op is sent to the nest. No record of issue pipe (LS0/LS1) is maintained so this is for both pipes. Probably don't need separate LS0 and LS1"
+  },
+  {,
+    "EventCode": "0xD880",
+    "EventName": "PM_LSU1_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0xD0B8",
+    "EventName": "PM_LSU_LMQ_FULL_CYC",
+    "BriefDescription": "Counts the number of cycles the LMQ is full"
+  },
+  {,
+    "EventCode": "0x168B2",
+    "EventName": "PM_L3_GRP_GUESS_CORRECT",
+    "BriefDescription": "Initial scope=group (GS or NNS) and data from same group (near) (pred successful)"
+  },
+  {,
+    "EventCode": "0x48A4",
+    "EventName": "PM_STOP_FETCH_PENDING_CYC",
+    "BriefDescription": "Fetching is stopped due to an incoming instruction that will result in a flush"
+  },
+  {,
+    "EventCode": "0x36884",
+    "EventName": "PM_L2_RCST_DISP_FAIL_ADDR",
+    "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ"
+  },
+  {,
+    "EventCode": "0x260AC",
+    "EventName": "PM_L3_PF_USAGE",
+    "BriefDescription": "Rotating sample of 32 PF actives"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
new file mode 100644
index 000000000000..bc2db636dabf
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
@@ -0,0 +1,552 @@
+[
+  {,
+    "EventCode": "0x4D04C",
+    "EventName": "PM_DFU_BUSY",
+    "BriefDescription": "Cycles in which all 4 Decimal Floating Point units are busy. The DFU is running at capacity"
+  },
+  {,
+    "EventCode": "0x100F6",
+    "EventName": "PM_IERAT_RELOAD",
+    "BriefDescription": "Number of I-ERAT reloads"
+  },
+  {,
+    "EventCode": "0x201E2",
+    "EventName": "PM_MRK_LD_MISS_L1",
+    "BriefDescription": "Marked DL1 Demand Miss counted at exec time. Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
+  },
+  {,
+    "EventCode": "0x40010",
+    "EventName": "PM_PMC3_OVERFLOW",
+    "BriefDescription": "Overflow from counter 3"
+  },
+  {,
+    "EventCode": "0x1005A",
+    "EventName": "PM_CMPLU_STALL_DFLONG",
+    "BriefDescription": "Finish stall because the NTF instruction was a multi-cycle instruction issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Qualified by multicycle"
+  },
+  {,
+    "EventCode": "0x4D140",
+    "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_DL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1E040",
+    "EventName": "PM_DPTEG_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x24052",
+    "EventName": "PM_FXU_IDLE",
+    "BriefDescription": "Cycles in which FXU0, FXU1, FXU2, and FXU3 are all idle"
+  },
+  {,
+    "EventCode": "0x1E054",
+    "EventName": "PM_CMPLU_STALL",
+    "BriefDescription": "Nothing completed and ICT not empty"
+  },
+  {,
+    "EventCode": "0x2",
+    "EventName": "PM_INST_CMPL",
+    "BriefDescription": "Number of PowerPC Instructions that completed."
+  },
+  {,
+    "EventCode": "0x3D058",
+    "EventName": "PM_VSU_DP_FSQRT_FDIV",
+    "BriefDescription": "vector versions of fdiv,fsqrt"
+  },
+  {,
+    "EventCode": "0x10006",
+    "EventName": "PM_DISP_HELD",
+    "BriefDescription": "Dispatch Held"
+  },
+  {,
+    "EventCode": "0x3D154",
+    "EventName": "PM_MRK_DERAT_MISS_16M",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M"
+  },
+  {,
+    "EventCode": "0x200F8",
+    "EventName": "PM_EXT_INT",
+    "BriefDescription": "external interrupt"
+  },
+  {,
+    "EventCode": "0x20008",
+    "EventName": "PM_ICT_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the ICT is completely empty. No itags are assigned to any thread"
+  },
+  {,
+    "EventCode": "0x4F146",
+    "EventName": "PM_MRK_DPTEG_FROM_L21_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10056",
+    "EventName": "PM_MEM_READ",
+    "BriefDescription": "Reads from Memory from this thread (includes data/inst/xlate/l1prefetch/inst prefetch). Includes L4"
+  },
+  {,
+    "EventCode": "0x3C04C",
+    "EventName": "PM_DATA_FROM_DL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a demand load"
+  },
+  {,
+    "EventCode": "0x4E046",
+    "EventName": "PM_DPTEG_FROM_L21_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2E016",
+    "EventName": "PM_NTC_ISSUE_HELD_ARB",
+    "BriefDescription": "The NTC instruction is being held at dispatch because it lost arbitration onto the issue pipe to another instruction (from the same thread or a different thread)"
+  },
+  {,
+    "EventCode": "0x15156",
+    "EventName": "PM_SYNC_MRK_FX_DIVIDE",
+    "BriefDescription": "Marked fixed point divide that can cause a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x1C056",
+    "EventName": "PM_DERAT_MISS_4K",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K"
+  },
+  {,
+    "EventCode": "0x2F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10024",
+    "EventName": "PM_PMC5_OVERFLOW",
+    "BriefDescription": "Overflow from counter 5"
+  },
+  {,
+    "EventCode": "0x2C018",
+    "EventName": "PM_CMPLU_STALL_DMISS_L21_L31",
+    "BriefDescription": "Completion stall by Dcache miss which resolved on chip ( excluding local L2/L3)"
+  },
+  {,
+    "EventCode": "0x4006A",
+    "EventName": "PM_IERAT_RELOAD_16M",
+    "BriefDescription": "IERAT Reloaded (Miss) for a 16M page"
+  },
+  {,
+    "EventCode": "0x4E010",
+    "EventName": "PM_ICT_NOSLOT_IC_L3MISS",
+    "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x4D01C",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_SYNC",
+    "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch"
+  },
+  {,
+    "EventCode": "0x2D01A",
+    "EventName": "PM_ICT_NOSLOT_IC_MISS",
+    "BriefDescription": "Ict empty for this thread due to Icache Miss"
+  },
+  {,
+    "EventCode": "0x3D152",
+    "EventName": "PM_MRK_DERAT_MISS_1G",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x4F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x30058",
+    "EventName": "PM_TLBIE_FIN",
+    "BriefDescription": "tlbie finished"
+  },
+  {,
+    "EventCode": "0x100F8",
+    "EventName": "PM_ICT_NOSLOT_CYC",
+    "BriefDescription": "Number of cycles the ICT has no itags assigned to this thread"
+  },
+  {,
+    "EventCode": "0x3E042",
+    "EventName": "PM_DPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1F140",
+    "EventName": "PM_MRK_DPTEG_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2C05A",
+    "EventName": "PM_DERAT_MISS_1G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x1F058",
+    "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L2",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L2 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x1D14A",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x10050",
+    "EventName": "PM_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x45058",
+    "EventName": "PM_IC_MISS_CMPL",
+    "BriefDescription": "Non-speculative icache miss, counted at completion"
+  },
+  {,
+    "EventCode": "0x2D150",
+    "EventName": "PM_MRK_DERAT_MISS_4K",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 4K"
+  },
+  {,
+    "EventCode": "0x34058",
+    "EventName": "PM_ICT_NOSLOT_BR_MPRED_ICMISS",
+    "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred"
+  },
+  {,
+    "EventCode": "0x10022",
+    "EventName": "PM_PMC2_SAVED",
+    "BriefDescription": "PMC2 Rewind Value saved"
+  },
+  {,
+    "EventCode": "0x2000A",
+    "EventName": "PM_HV_CYC",
+    "BriefDescription": "Cycles in which msr_hv is high. Note that this event does not take msr_pr into consideration"
+  },
+  {,
+    "EventCode": "0x1F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x300FC",
+    "EventName": "PM_DTLB_MISS",
+    "BriefDescription": "Data PTEG reload"
+  },
+  {,
+    "EventCode": "0x2D152",
+    "EventName": "PM_MRK_DERAT_MISS_2M",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x2C046",
+    "EventName": "PM_DATA_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x20052",
+    "EventName": "PM_GRP_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x3F05A",
+    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L3",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L3 data cache"
+  },
+  {,
+    "EventCode": "0x1E04A",
+    "EventName": "PM_DPTEG_FROM_RL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10064",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN",
+    "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch"
+  },
+  {,
+    "EventCode": "0x2E046",
+    "EventName": "PM_DPTEG_FROM_RL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_DMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2E042",
+    "EventName": "PM_DPTEG_FROM_L3_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2D012",
+    "EventName": "PM_CMPLU_STALL_DFU",
+    "BriefDescription": "Finish stall because the NTF instruction was issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Not qualified by multicycle"
+  },
+  {,
+    "EventCode": "0x4C04C",
+    "EventName": "PM_DATA_FROM_DMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a demand load"
+  },
+  {,
+    "EventCode": "0x30022",
+    "EventName": "PM_PMC4_SAVED",
+    "BriefDescription": "PMC4 Rewind Value saved (matched condition)"
+  },
+  {,
+    "EventCode": "0x200F4",
+    "EventName": "PM_RUN_CYC",
+    "BriefDescription": "Run_cycles"
+  },
+  {,
+    "EventCode": "0x400F2",
+    "EventName": "PM_1PLUS_PPC_DISP",
+    "BriefDescription": "Cycles at least one Instr Dispatched"
+  },
+  {,
+    "EventCode": "0x3D148",
+    "EventName": "PM_MRK_DATA_FROM_L21_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L2 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x2F146",
+    "EventName": "PM_MRK_DPTEG_FROM_RL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4E01A",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD",
+    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason"
+  },
+  {,
+    "EventCode": "0x401EC",
+    "EventName": "PM_THRESH_EXC_2048",
+    "BriefDescription": "Threshold counter exceeded a value of 2048"
+  },
+  {,
+    "EventCode": "0x35150",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3E052",
+    "EventName": "PM_ICT_NOSLOT_IC_L3",
+    "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3"
+  },
+  {,
+    "EventCode": "0x2405A",
+    "EventName": "PM_NTC_FIN",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. This event is used to account for cycles in which work is being completed in the CPI stack"
+  },
+  {,
+    "EventCode": "0x40052",
+    "EventName": "PM_PUMP_MPRED",
+    "BriefDescription": "Pump misprediction. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x30056",
+    "EventName": "PM_TM_ABORTS",
+    "BriefDescription": "Number of TM transactions aborted"
+  },
+  {,
+    "EventCode": "0x2404C",
+    "EventName": "PM_INST_FROM_MEMORY",
+    "BriefDescription": "The processor's Instruction cache was reloaded from a memory location including L4 from local remote or distant due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1C05A",
+    "EventName": "PM_DERAT_MISS_2M",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x30024",
+    "EventName": "PM_PMC6_OVERFLOW",
+    "BriefDescription": "Overflow from counter 6"
+  },
+  {,
+    "EventCode": "0x10068",
+    "EventName": "PM_BRU_FIN",
+    "BriefDescription": "Branch Instruction Finished"
+  },
+  {,
+    "EventCode": "0x30020",
+    "EventName": "PM_PMC2_REWIND",
+    "BriefDescription": "PMC2 Rewind Event (did not match condition)"
+  },
+  {,
+    "EventCode": "0x40064",
+    "EventName": "PM_DUMMY2_REMOVE_ME",
+    "BriefDescription": "Space holder for LS_PC_RELOAD_RA"
+  },
+  {,
+    "EventCode": "0x3F148",
+    "EventName": "PM_MRK_DPTEG_FROM_DL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D01E",
+    "EventName": "PM_ICT_NOSLOT_BR_MPRED",
+    "BriefDescription": "Ict empty for this thread due to branch mispred"
+  },
+  {,
+    "EventCode": "0x3405E",
+    "EventName": "PM_IFETCH_THROTTLE",
+    "BriefDescription": "Cycles in which Instruction fetch throttle was active."
+  },
+  {,
+    "EventCode": "0x1F148",
+    "EventName": "PM_MRK_DPTEG_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3E046",
+    "EventName": "PM_DPTEG_FROM_L21_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4C15C",
+    "EventName": "PM_MRK_DERAT_MISS_16G",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G"
+  },
+  {,
+    "EventCode": "0x14052",
+    "EventName": "PM_INST_GRP_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0xD0A8",
+    "EventName": "PM_DSLB_MISS",
+    "BriefDescription": "Data SLB Miss - Total of all segment sizes"
+  },
+  {,
+    "EventCode": "0x4C058",
+    "EventName": "PM_MEM_CO",
+    "BriefDescription": "Memory castouts from this thread"
+  },
+  {,
+    "EventCode": "0x40004",
+    "EventName": "PM_FXU_FIN",
+    "BriefDescription": "The fixed point unit Unit finished an instruction. Instructions that finish may not necessary complete."
+  },
+  {,
+    "EventCode": "0x2C054",
+    "EventName": "PM_DERAT_MISS_64K",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K"
+  },
+  {,
+    "EventCode": "0x10018",
+    "EventName": "PM_IC_DEMAND_CYC",
+    "BriefDescription": "Icache miss demand cycles"
+  },
+  {,
+    "EventCode": "0x3C054",
+    "EventName": "PM_DERAT_MISS_16M",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M"
+  },
+  {,
+    "EventCode": "0x2D14E",
+    "EventName": "PM_MRK_DATA_FROM_L21_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3405C",
+    "EventName": "PM_CMPLU_STALL_DPLONG",
+    "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle"
+  },
+  {,
+    "EventCode": "0x4D052",
+    "EventName": "PM_2FLOP_CMPL",
+    "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg "
+  },
+  {,
+    "EventCode": "0x1F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L2",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40062",
+    "EventName": "PM_DUMMY1_REMOVE_ME",
+    "BriefDescription": "Space holder for L2_PC_PM_MK_LDST_SCOPE_PRED_STATUS"
+  },
+  {,
+    "EventCode": "0x4C012",
+    "EventName": "PM_CMPLU_STALL_ERAT_MISS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load or store that suffered a translation miss"
+  },
+  {,
+    "EventCode": "0x4D050",
+    "EventName": "PM_VSU_NON_FLOP_CMPL",
+    "BriefDescription": "Non FLOP operation completed"
+  },
+  {,
+    "EventCode": "0x2E012",
+    "EventName": "PM_TM_TX_PASS_RUN_CYC",
+    "BriefDescription": "cycles spent in successful transactions"
+  },
+  {,
+    "EventCode": "0x4D04E",
+    "EventName": "PM_VSU_FSQRT_FDIV",
+    "BriefDescription": "four flops operation (fdiv,fsqrt) Scalar Instructions only"
+  },
+  {,
+    "EventCode": "0x4C120",
+    "EventName": "PM_MRK_DATA_FROM_L2_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load"
+  },
+  {,
+    "EventCode": "0x10062",
+    "EventName": "PM_LD_L3MISS_PEND_CYC",
+    "BriefDescription": "Cycles L3 miss was pending for this thread"
+  },
+  {,
+    "EventCode": "0x2F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x14050",
+    "EventName": "PM_INST_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x2000E",
+    "EventName": "PM_FXU_BUSY",
+    "BriefDescription": "Cycles in which all 4 FXUs are busy. The FXU is running at capacity"
+  },
+  {,
+    "EventCode": "0x20066",
+    "EventName": "PM_TLB_MISS",
+    "BriefDescription": "TLB Miss (I + D)"
+  },
+  {,
+    "EventCode": "0x10054",
+    "EventName": "PM_PUMP_CPRED",
+    "BriefDescription": "Pump prediction correct. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x4D124",
+    "EventName": "PM_MRK_DATA_FROM_L31_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x400F8",
+    "EventName": "PM_FLUSH",
+    "BriefDescription": "Flush (any type)"
+  },
+  {,
+    "EventCode": "0x30004",
+    "EventName": "PM_CMPLU_STALL_EMQ_FULL",
+    "BriefDescription": "Finish stall because the next to finish instruction suffered an ERAT miss and the EMQ was full"
+  },
+  {,
+    "EventCode": "0x1D154",
+    "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
new file mode 100644
index 000000000000..3ef8a10aac86
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
@@ -0,0 +1,122 @@
+[
+  {,
+    "EventCode": "0x20036",
+    "EventName": "PM_BR_2PATH",
+    "BriefDescription": "Branches that are not strongly biased"
+  },
+  {,
+    "EventCode": "0x40056",
+    "EventName": "PM_MEM_LOC_THRESH_LSU_HIGH",
+    "BriefDescription": "Local memory above threshold for LSU medium"
+  },
+  {,
+    "EventCode": "0x2C056",
+    "EventName": "PM_DTLB_MISS_4K",
+    "BriefDescription": "Data TLB Miss page size 4k"
+  },
+  {,
+    "EventCode": "0x40118",
+    "EventName": "PM_MRK_DCACHE_RELOAD_INTV",
+    "BriefDescription": "Combined Intervention event"
+  },
+  {,
+    "EventCode": "0x4F148",
+    "EventName": "PM_MRK_DPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x301E8",
+    "EventName": "PM_THRESH_EXC_64",
+    "BriefDescription": "Threshold counter exceeded a value of 64"
+  },
+  {,
+    "EventCode": "0x4E04E",
+    "EventName": "PM_DPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40050",
+    "EventName": "PM_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x1F14E",
+    "EventName": "PM_MRK_DPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D018",
+    "EventName": "PM_CMPLU_STALL_BRU",
+    "BriefDescription": "Completion stall due to a Branch Unit"
+  },
+  {,
+    "EventCode": "0x45052",
+    "EventName": "PM_4FLOP_CMPL",
+    "BriefDescription": "4 FLOP instruction completed"
+  },
+  {,
+    "EventCode": "0x3D142",
+    "EventName": "PM_MRK_DATA_FROM_LMEM",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a marked load"
+  },
+  {,
+    "EventCode": "0x4C01E",
+    "EventName": "PM_CMPLU_STALL_CRYPTO",
+    "BriefDescription": "Finish stall because the NTF instruction was routed to the crypto execution pipe and was waiting to finish"
+  },
+  {,
+    "EventCode": "0x3000C",
+    "EventName": "PM_FREQ_DOWN",
+    "BriefDescription": "Power Management: Below Threshold B"
+  },
+  {,
+    "EventCode": "0x4D128",
+    "EventName": "PM_MRK_DATA_FROM_LMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from the local chip's Memory due to a marked load"
+  },
+  {,
+    "EventCode": "0x4D054",
+    "EventName": "PM_8FLOP_CMPL",
+    "BriefDescription": "8 FLOP instruction completed"
+  },
+  {,
+    "EventCode": "0x10026",
+    "EventName": "PM_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when an instruction tablewalk is active"
+  },
+  {,
+    "EventCode": "0x2C012",
+    "EventName": "PM_CMPLU_STALL_DCACHE_MISS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that missed the L1 and was waiting for the data to return from the nest"
+  },
+  {,
+    "EventCode": "0x2E04C",
+    "EventName": "PM_DPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10060",
+    "EventName": "PM_TM_TRANS_RUN_CYC",
+    "BriefDescription": "run cycles in transactional state"
+  },
+  {,
+    "EventCode": "0x1E04C",
+    "EventName": "PM_DPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x45050",
+    "EventName": "PM_1FLOP_CMPL",
+    "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
new file mode 100644
index 000000000000..8c0f12024afa
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
@@ -0,0 +1,232 @@
+[
+  {,
+    "EventCode": "0x1E",
+    "EventName": "PM_CYC",
+    "BriefDescription": "Processor cycles"
+  },
+  {,
+    "EventCode": "0x30010",
+    "EventName": "PM_PMC2_OVERFLOW",
+    "BriefDescription": "Overflow from counter 2"
+  },
+  {,
+    "EventCode": "0x3C046",
+    "EventName": "PM_DATA_FROM_L21_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x4D05C",
+    "EventName": "PM_DP_QP_FLOP_CMPL",
+    "BriefDescription": "Double-Precion or Quad-Precision instruction completed"
+  },
+  {,
+    "EventCode": "0x4E04C",
+    "EventName": "PM_DPTEG_FROM_DMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x20016",
+    "EventName": "PM_ST_FIN",
+    "BriefDescription": "Store finish count. Includes speculative activity"
+  },
+  {,
+    "EventCode": "0x44042",
+    "EventName": "PM_INST_FROM_L3",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1504A",
+    "EventName": "PM_IPTEG_FROM_RL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x40132",
+    "EventName": "PM_MRK_LSU_FIN",
+    "BriefDescription": "lsu marked instr PPC finish"
+  },
+  {,
+    "EventCode": "0x3C05C",
+    "EventName": "PM_CMPLU_STALL_VFXU",
+    "BriefDescription": "Finish stall due to a vector fixed point instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes"
+  },
+  {,
+    "EventCode": "0x30066",
+    "EventName": "PM_LSU_FIN",
+    "BriefDescription": "LSU Finished a PPC instruction (up to 4 per cycle)"
+  },
+  {,
+    "EventCode": "0x2011C",
+    "EventName": "PM_MRK_NTC_CYC",
+    "BriefDescription": "Cycles during which the marked instruction is next to complete (completion is held up because the marked instruction hasn't completed yet)"
+  },
+  {,
+    "EventCode": "0x3E048",
+    "EventName": "PM_DPTEG_FROM_DL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2E018",
+    "EventName": "PM_CMPLU_STALL_VFXLONG",
+    "BriefDescription": "Completion stall due to a long latency vector fixed point instruction (division, square root)"
+  },
+  {,
+    "EventCode": "0x1C04E",
+    "EventName": "PM_DATA_FROM_L2MISS_MOD",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a demand load"
+  },
+  {,
+    "EventCode": "0x15048",
+    "EventName": "PM_IPTEG_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x34046",
+    "EventName": "PM_INST_FROM_L21_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1E058",
+    "EventName": "PM_STCX_FAIL",
+    "BriefDescription": "stcx failed"
+  },
+  {,
+    "EventCode": "0x20112",
+    "EventName": "PM_MRK_NTF_FIN",
+    "BriefDescription": "Marked next to finish instruction finished"
+  },
+  {,
+    "EventCode": "0x300F0",
+    "EventName": "PM_ST_MISS_L1",
+    "BriefDescription": "Store Missed L1"
+  },
+  {,
+    "EventCode": "0x4C046",
+    "EventName": "PM_DATA_FROM_L21_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x2504A",
+    "EventName": "PM_IPTEG_FROM_RL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x2003E",
+    "EventName": "PM_LSU_LMQ_SRQ_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the LSU is empty for all threads (lmq and srq are completely empty)"
+  },
+  {,
+    "EventCode": "0x201E6",
+    "EventName": "PM_THRESH_EXC_32",
+    "BriefDescription": "Threshold counter exceeded a value of 32"
+  },
+  {,
+    "EventCode": "0x4405C",
+    "EventName": "PM_CMPLU_STALL_VDP",
+    "BriefDescription": "Finish stall because the NTF instruction was a vector instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by vector"
+  },
+  {,
+    "EventCode": "0x4D010",
+    "EventName": "PM_PMC1_SAVED",
+    "BriefDescription": "PMC1 Rewind Value saved"
+  },
+  {,
+    "EventCode": "0x200FE",
+    "EventName": "PM_DATA_FROM_L2MISS",
+    "BriefDescription": "Demand LD - L2 Miss (not L2 hit)"
+  },
+  {,
+    "EventCode": "0x2D14A",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x10028",
+    "EventName": "PM_STALL_END_ICT_EMPTY",
+    "BriefDescription": "The number a times the core transitioned from a stall to ICT-empty for this thread"
+  },
+  {,
+    "EventCode": "0x2504C",
+    "EventName": "PM_IPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x4504A",
+    "EventName": "PM_IPTEG_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1404E",
+    "EventName": "PM_INST_FROM_L2MISS",
+    "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x34042",
+    "EventName": "PM_INST_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 with dispatch conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4E048",
+    "EventName": "PM_DPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x200F0",
+    "EventName": "PM_ST_CMPL",
+    "BriefDescription": "Stores completed from S2Q (2nd-level store queue)."
+  },
+  {,
+    "EventCode": "0x4E05C",
+    "EventName": "PM_LSU_REJECT_LHS",
+    "BriefDescription": "LSU Reject due to LHS (up to 4 per cycle)"
+  },
+  {,
+    "EventCode": "0x14044",
+    "EventName": "PM_INST_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3E04C",
+    "EventName": "PM_DPTEG_FROM_DL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1F15E",
+    "EventName": "PM_MRK_PROBE_NOP_CMPL",
+    "BriefDescription": "Marked probeNops completed"
+  },
+  {,
+    "EventCode": "0x20018",
+    "EventName": "PM_ST_FWD",
+    "BriefDescription": "Store forwards that finished"
+  },
+  {,
+    "EventCode": "0x1D142",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x24042",
+    "EventName": "PM_INST_FROM_L3_MEPF",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x25046",
+    "EventName": "PM_IPTEG_FROM_RL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x3504A",
+    "EventName": "PM_IPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x3C05A",
+    "EventName": "PM_CMPLU_STALL_VDPLONG",
+    "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle"
+  },
+  {,
+    "EventCode": "0x2E01C",
+    "EventName": "PM_CMPLU_STALL_TLBIE",
+    "BriefDescription": "Finish stall because the NTF instruction was a tlbie waiting for response from L2"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
new file mode 100644
index 000000000000..00bfdb5c5acb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
new file mode 100644
index 000000000000..49c5f123d811
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / INST_RETIRED.ANY / cycles",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
new file mode 100644
index 000000000000..5a7f1ec24200
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
new file mode 100644
index 000000000000..b4791b443a66
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
@@ -0,0 +1,1453 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts memory requests originating from the core that miss in the L2 cache.",
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache request misses"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts memory requests originating from the core that reference a cache line in the L2 cache.",
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4f",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache requests"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand and prefetch transactions that the L2 XQ rejects due to a full or near full condition which likely indicates back pressure from the intra-die interconnect (IDI) fabric. The XQ may reject transactions from the L2Q (non-cacheable requests), L2 misses and L2 write-back victims.",
+        "EventCode": "0x30",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "L2_REJECT_XQ.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests rejected by the XQ"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand and L1 prefetcher requests rejected by the L2Q due to a full or nearly full condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to insure fairness between cores, or to delay a core's dirty eviction when the address conflicts with incoming external snoops.",
+        "EventCode": "0x31",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CORE_REJECT_L2Q.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests rejected by the L2Q"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts when a modified (dirty) cache line is evicted from the data L1 cache and needs to be written back to memory.  No count will occur if the evicted line is clean, and hence does not require a writeback.",
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DL1.REPLACEMENT",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L1 Cache evictions for dirty data"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.",
+        "EventCode": "0x86",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ICache miss."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "EventCode": "0xB7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts locked memory uops retired.  This includes regular locks and bus locks. (To specifically count bus locks only, see the Offcore response event.)  A locked access is one with a lock prefix, or an exchange to memory.  See the SDM for a complete description of which memory load accesses are locks.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x21",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Locked load uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired where the data requested spans a 64 byte cache line boundary.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts store uops retired where the data requested spans a 64 byte cache line boundary.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x42",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts memory uops retired where the data requested spans a 64 byte cache line boundary.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x43",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of load uops retired.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x81",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of store uops retired.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Store uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of memory uops retired that is either a loads or a store or both.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x83",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that hit the L1 data cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that hit in the L2 cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that miss the L1 data cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that miss in the L2 cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired where the cache line containing the data was in the modified state of another core or modules cache (HITM).  More specifically, this means that when the load address was checked by other caching agents (typically another processor) in the system, one of those caching agents indicated that they had a dirty copy of the data.  Loads that obtain a HITM response incur greater latency than most is typical for a load.  In addition, since HITM indicates that some other processor had this data in its cache, it implies that the data was shared between processors, or potentially was a lock or semaphore value.  This event is useful for locating sharing, false sharing, and contended locks.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts memory load uops retired where the data is retrieved from the WCB (or fill buffer), indicating that the load found its data while that data was in the process of being brought into the L1 cache.  Typically a load will receive this indication when some other load or prefetch missed the L1 cache and was in the process of retrieving the cache line containing the data, but that process had not yet finished (and written the data back to the cache). For example, consider load X and Y, both referencing the same cache line that is not in the L1 cache.  If load X misses cache first, it obtains and WCB (or fill buffer) and begins the process of requesting the data.  When load Y requests the data, it will either hit the WCB, or the L1 cache, depending on exactly what time the request to Y occurs.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts memory load uops retired where the data is retrieved from DRAM.  Event is counted at retirement, so the speculative loads are ignored.  A memory load can hit (or miss) the L1 cache, hit (or miss) the L2 cache, hit DRAM, hit in the WCB or receive a HITM response.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000011000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000041000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200001000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000001000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000001000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000012000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000042000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200002000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000002000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000002000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000014800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000044800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200004800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000004800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000004800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000018000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000013010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000043010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200003010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000003010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000003010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000013091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000043091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x00000132b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x00000432b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x02000032b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x10000032b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x40000032b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/frontend.json b/tools/perf/pmu-events/arch/x86/goldmontplus/frontend.json
new file mode 100644
index 000000000000..a7878965ceab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/frontend.json
@@ -0,0 +1,62 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is in the ICache (hit).  The event strives to count on a cache line basis, so that multiple accesses which hit in a single cache line count as one ICACHE.HIT.  Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.HIT",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "References per ICache line that are available in the ICache (hit). This event counts differently than Intel processors based on Silvermont microarchitecture"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache)  for one or more bytes in an ICache Line and that cache line is not in the ICache (miss).  The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS.  Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.MISSES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "References per ICache line that are not available in the ICache (miss). This event counts differently than Intel processors based on Silvermont microarchitecture"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line.  The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS.  Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.\r\nThis event counts differently than Intel processors based on Silvermont microarchitecture.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.ACCESSES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "References per ICache line. This event counts differently than Intel processors based on Silvermont microarchitecture"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times the Microcode Sequencer (MS) starts a flow of uops from the MSROM. It does not count every time a uop is read from the MSROM.  The most common case that this counts is when a micro-coded instruction is encountered by the front end of the machine.  Other cases include when an instruction encounters a fault, trap, or microcode assist of any sort that initiates a flow of uops.  The event will count MS startups for uops that are speculative, and subsequently cleared by branch mispredict or a machine clear.",
+        "EventCode": "0xE7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MS_DECODED.MS_ENTRY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "MS decode starts"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times the prediction (from the predecode cache) for instruction length is incorrect.",
+        "EventCode": "0xE9",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DECODE_RESTRICTION.PREDECODE_WRONG",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Decode restrictions due to predicting wrong instruction length"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/memory.json
new file mode 100644
index 000000000000..91e0815f3ffb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/memory.json
@@ -0,0 +1,38 @@
+[
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
+        "EventCode": "0x13",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops that split a page (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts when a memory store of a uop spans a page boundary (a split) is retired.",
+        "EventCode": "0x13",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Store uops that split a page (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to memory ordering issues.  This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved - as another core is in the process of modifying the data.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machine clears due to memory ordering issue"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/other.json b/tools/perf/pmu-events/arch/x86/goldmontplus/other.json
new file mode 100644
index 000000000000..b860374418ab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/other.json
@@ -0,0 +1,98 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
+        "EventCode": "0x86",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "FETCH_STALL.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to any reason."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss.  Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
+        "EventCode": "0x86",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles the code-fetch stalls and an ITLB miss is outstanding."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend due to either a full resource  in the backend (RESOURCE_FULL) or due to the processor recovering from some event (RECOVERY).",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend.  Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable.   Note that uops must be available for consumption in order for this event to fire.  If a uop is not available (Instruction Queue is empty), this event will not count.",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows).   Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle to recover"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts hardware interrupts received by the processor.",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.RECEIVED",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "203",
+        "BriefDescription": "Hardware interrupts received"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.MASKED",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles hardware interrupts are masked"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts core cycles during which there are pending interrupts, but interrupts are masked (EFLAGS.IF = 0).",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.PENDING_AND_MASKED",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles pending interrupts are masked"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
new file mode 100644
index 000000000000..ccf1aed69197
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
@@ -0,0 +1,544 @@
+[
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 0",
+        "UMask": "0x1",
+        "PEBScounters": "32",
+        "EventName": "INST_RETIRED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "PEBScounters": "33",
+        "EventName": "CPU_CLK_UNHALTED.CORE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when core is not halted  (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 2",
+        "UMask": "0x3",
+        "PEBScounters": "34",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when core is not halted  (Fixed event)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time.  The forward might occur subsequently when the data is available.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked due to store data not ready (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.4K_ALIAS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.UTLB_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.ALL_BLOCK",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine.  This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
+        "EventCode": "0x0E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Uops issued to the back end per cycle"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Core cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.CORE_P",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when core is not halted"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Reference cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when core is not halted"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound.  When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources.  When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks.  However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all.  Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots.  These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots.  A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock.  The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_NOT_DELIVERED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Uops requested but not-delivered to the back-end per cycle"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers.  This is an architectural performance event.  This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable:  The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event.  Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts INST_RETIRED.ANY using the Reduced Skid PEBS feature that reduces the shadow in which events aren't counted allowing for a more unbiased distribution of samples across instructions retired.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "INST_RETIRED.PREC_DIST",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired - using Reduced Skid PEBS feature"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts uops which retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts uops retired that are from the complex flows issued by the micro-sequencer (MS).  Counts both the uops from a micro-coded instruction, and the uops that might be generated from a micro-coded assist.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.MS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "MS uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of floating point divide uops retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.FPDIV",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Floating point divide uops retired (Precise Event Capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of integer divide uops retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.IDIV",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Integer divide uops retired (Precise Event Capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears for any reason.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "All machine clears"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Self-Modifying Code detected"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to floating point (FP) operations needing assists.  For instance, if the result was a floating point denormal, the hardware clears the pipeline and reissues uops to produce the correct IEEE compliant denormal result.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.FP_ASSIST",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machine clears due to FP assists"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to memory disambiguation.  Memory disambiguation happens when a load which has been issued conflicts with a previous unretired store in the pipeline whose address was not known at issue time, but is later resolved to be the same as the load address.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.DISAMBIGUATION",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machine clears due to memory disambiguation"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times that the machines clears due to a page fault. Covers both I-side and D-side(Loads/Stores) page faults. A page fault occurs when either page is not present, or an access violation",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.PAGE_FAULT",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machines clear due to a page fault"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts branch instructions retired for all branch types.  This is an architectural performance event.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x7e",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired conditional branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of taken branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired taken branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts far branch instructions retired.  This includes far jump, far call and return, and Interrupt call and return.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xbf",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired far branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xeb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near return branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf7",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near return instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf9",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near indirect CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.IND_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near indirect call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near relative CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfd",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.REL_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near relative call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfe",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x7e",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xeb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf7",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted near return instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.IND_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfe",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles if either divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles a divider is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles the integer divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.IDIV",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles the integer divide unit is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles the floating point divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.FPDIV",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles the FP divide unit is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call,  Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BACLEARS.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "BACLEARs asserted for any branch type"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts BACLEARS on return instructions.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BACLEARS.RETURN",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "BACLEARs asserted for return branch"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BACLEARS.COND",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "BACLEARs asserted for conditional branch"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
new file mode 100644
index 000000000000..0b53a3b0dfb8
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
@@ -0,0 +1,218 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 4K page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 2M or 4M page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 1GB pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1GB",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 1GB page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk occurring due to a load (demand data loads or SW prefetches). Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to a demand load every cycle."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M or 4M page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1GB pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1GB",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 1GB page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk occurring due to a demand data store. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to a demand data store every cycle."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk only while traversing the Extended Page Table (EPT), and does not count during the rest of the translation.  The EPT is used for translating Guest-Physical Addresses to Physical Addresses for Virtual Machine Monitors (VMMs).  Average cycles per walk can be calculated by dividing the count by number of walks.",
+        "EventCode": "0x4F",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "EPT.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to walking the EPT every cycle"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch.  It counts when new translation are filled into the ITLB.  The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
+        "EventCode": "0x81",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB.MISS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "ITLB misses"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 4K page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 2M or 4M page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 1GB pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1GB",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 1GB page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk occurring due to an instruction fetch. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to an instruction fetch every cycle."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts STLB flushes.  The TLBs are flushed on instructions like INVLPG and MOV to CR3.",
+        "EventCode": "0xBD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "TLB_FLUSHES.STLB_ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "STLB flushes"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that caused a DTLB miss.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x11",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts store uops retired that caused a DTLB miss.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x12",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts uops retired that had a DTLB miss on load, store or either.  Note that when two distinct memory operations to the same page miss the DTLB, only one of them will be recorded as a DTLB miss.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x13",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
new file mode 100644
index 000000000000..5ab5c78fe580
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -0,0 +1,158 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
new file mode 100644
index 000000000000..5ab5c78fe580
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -0,0 +1,158 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
new file mode 100644
index 000000000000..7c2679514efb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
new file mode 100644
index 000000000000..7c2679514efb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
new file mode 100644
index 000000000000..fd7d7c438226
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -0,0 +1,140 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index d1a12e584c1b..fe1a2c47cabf 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -9,6 +9,7 @@ GenuineIntel-6-27,v4,bonnell,core
 GenuineIntel-6-36,v4,bonnell,core
 GenuineIntel-6-35,v4,bonnell,core
 GenuineIntel-6-5C,v8,goldmont,core
+GenuineIntel-6-7A,v1,goldmontplus,core
 GenuineIntel-6-3C,v24,haswell,core
 GenuineIntel-6-45,v24,haswell,core
 GenuineIntel-6-46,v24,haswell,core
@@ -34,3 +35,4 @@ GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-25,v2,westmereep-sp,core
 GenuineIntel-6-2F,v2,westmereex,core
+GenuineIntel-6-55,v1,skylakex,core
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
new file mode 100644
index 000000000000..fd7d7c438226
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -0,0 +1,140 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
new file mode 100644
index 000000000000..36c903faed0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
new file mode 100644
index 000000000000..b5bc742b6fbc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -0,0 +1,1672 @@
+[
+    {
+        "EventCode": "0x24",
+        "UMask": "0x21",
+        "BriefDescription": "Demand Data Read miss L2, no rejects",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
+        "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x22",
+        "BriefDescription": "RFO requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x24",
+        "BriefDescription": "L2 cache misses when fetching instructions",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x27",
+        "BriefDescription": "Demand requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
+        "PublicDescription": "Demand requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x38",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.PF_MISS",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x3f",
+        "BriefDescription": "All requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.MISS",
+        "PublicDescription": "All requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x41",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x42",
+        "BriefDescription": "RFO requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x44",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xd8",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.PF_HIT",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe1",
+        "BriefDescription": "Demand Data Read requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe2",
+        "BriefDescription": "RFO requests to L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe4",
+        "BriefDescription": "L2 code requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "PublicDescription": "Counts the total number of L2 code requests.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe7",
+        "BriefDescription": "Demand requests to L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "PublicDescription": "Demand requests to L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xf8",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_PF",
+        "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xff",
+        "BriefDescription": "All L2 requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "PublicDescription": "All L2 requests.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "UMask": "0x41",
+        "BriefDescription": "Core-originated cacheable demand requests missed L3",
+        "Counter": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "UMask": "0x4f",
+        "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
+        "Counter": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.PENDING",
+        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "UMask": "0x1",
+        "BriefDescription": "L1D data line replacements",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D.REPLACEMENT",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x2",
+        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle. ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x4",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x8",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x1",
+        "BriefDescription": "Demand Data Read requests sent to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x2",
+        "BriefDescription": "Cacheable and noncachaeble code read requests",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x4",
+        "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x8",
+        "BriefDescription": "Demand and prefetch data reads",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x80",
+        "BriefDescription": "Any memory transaction that reached the SQ.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB2",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
+        "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x11",
+        "BriefDescription": "Retired load instructions that miss the STLB.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x12",
+        "BriefDescription": "Retired store instructions that miss the STLB.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
+        "SampleAfterValue": "100003",
+        "L1_Hit_Indication": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x21",
+        "BriefDescription": "Retired load instructions with locked access.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x41",
+        "BriefDescription": "Retired load instructions that split across a cacheline boundary.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x42",
+        "BriefDescription": "Retired store instructions that split across a cacheline boundary.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "SampleAfterValue": "100003",
+        "L1_Hit_Indication": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x81",
+        "BriefDescription": "All retired load instructions.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x82",
+        "BriefDescription": "All retired store instructions.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.ALL_STORES",
+        "SampleAfterValue": "2000003",
+        "L1_Hit_Indication": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x1",
+        "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L1_HIT",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x2",
+        "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L2_HIT",
+        "PublicDescription": "Retired load instructions with L2 cache hits as data sources.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L3_HIT",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. ",
+        "SampleAfterValue": "50021",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x8",
+        "BriefDescription": "Retired load instructions missed L1 cache as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L1_MISS",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x10",
+        "BriefDescription": "Retired load instructions missed L2 cache as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L2_MISS",
+        "PublicDescription": "Retired load instructions missed L2 cache as data sources.",
+        "SampleAfterValue": "50021",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x20",
+        "BriefDescription": "Retired load instructions missed L3 cache as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L3_MISS",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. ",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x40",
+        "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.FB_HIT",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. ",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x1",
+        "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x2",
+        "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
+        "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
+        "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x8",
+        "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
+        "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x1",
+        "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x2",
+        "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load instructions whose data sources was remote HITM",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "Retired load instructions whose data sources was remote HITM.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x8",
+        "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache",
+        "Data_LA": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD4",
+        "UMask": "0x4",
+        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xF0",
+        "UMask": "0x40",
+        "BriefDescription": "L2 writebacks that access L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_TRANS.L2_WB",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF1",
+        "UMask": "0x1f",
+        "BriefDescription": "L2 cache lines filling L2",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_IN.ALL",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x2",
+        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped ",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x4",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.USELESS_PREF",
+        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x4",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.USELESS_HWPF",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF4",
+        "UMask": "0x10",
+        "BriefDescription": "Number of cache line split locks sent to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "SQ_MISC.SPLIT_LOCK",
+        "PublicDescription": "Counts the number of cache line split locks sent to the uncore.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that have any response type.",
+        "MSRValue": "0x0000010001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
+        "MSRValue": "0x0000010002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
+        "MSRValue": "0x3f803c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that have any response type.",
+        "MSRValue": "0x0000010004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3.",
+        "MSRValue": "0x3f803c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
+        "MSRValue": "0x0000010010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
+        "MSRValue": "0x0000010020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
+        "MSRValue": "0x0000010080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
+        "MSRValue": "0x0000010100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.",
+        "MSRValue": "0x0000010400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.",
+        "MSRValue": "0x3f803c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that have any response type.",
+        "MSRValue": "0x0000010490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that have any response type.",
+        "MSRValue": "0x0000010120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
+        "MSRValue": "0x0000010491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
+        "MSRValue": "0x0000010122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
new file mode 100644
index 000000000000..1c09a328df36
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
@@ -0,0 +1,88 @@
+[
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x1",
+        "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x2",
+        "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x4",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x8",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x10",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x20",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x40",
+        "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
+        "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x80",
+        "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
+        "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "UMask": "0x1e",
+        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ASSIST.ANY",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
new file mode 100644
index 000000000000..40abc0852cd6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
@@ -0,0 +1,482 @@
+[
+    {
+        "EventCode": "0x79",
+        "UMask": "0x4",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MITE_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MITE_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.DSB_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_DSB_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x18",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x18",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x20",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x24",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x24",
+        "BriefDescription": "Cycles MITE is delivering any Uop",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x80",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_16B.IFDATA_STALL",
+        "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "UMask": "0x1",
+        "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_64B.IFTAG_HIT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "UMask": "0x2",
+        "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_64B.IFTAG_MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_64B.IFTAG_STALL",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "CounterMask": "4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "CounterMask": "3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAB",
+        "UMask": "0x2",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
+        "Counter": "0,1,2,3",
+        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
+        "PEBS": "1",
+        "MSRValue": "0x11",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. ",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x12",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.L1I_MISS",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x13",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x14",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x15",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.STLB_MISS",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. ",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x400206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x200206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x400406",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x400806",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x401006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x402006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x404006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x408006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x410006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x420006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x100206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x300206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
new file mode 100644
index 000000000000..ca22a22c1abd
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
@@ -0,0 +1,1396 @@
+[
+    {
+        "EventCode": "0x54",
+        "UMask": "0x1",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_CONFLICT",
+        "PublicDescription": "Number of times a TSX line had a cache conflict.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_CAPACITY",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x4",
+        "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x8",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x10",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x20",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x40",
+        "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
+        "PublicDescription": "Number of times we could not allocate Lock Buffer.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x2",
+        "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC2",
+        "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x4",
+        "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC3",
+        "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x8",
+        "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC4",
+        "PublicDescription": "RTM region detected inside HLE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x10",
+        "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC5",
+        "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x10",
+        "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x6",
+        "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x10",
+        "BriefDescription": "Demand Data Read requests who miss L3 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Demand Data Read requests who miss L3 cache.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC3",
+        "UMask": "0x2",
+        "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "Errata": "SKL089",
+        "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x1",
+        "BriefDescription": "Number of times an HLE execution started.",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.START",
+        "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times an HLE execution successfully committed",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.COMMIT",
+        "PublicDescription": "Number of times HLE commit succeeded.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x4",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED",
+        "PublicDescription": "Number of times HLE abort was triggered.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x8",
+        "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_MEM",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x10",
+        "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_TIMER",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x20",
+        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.). ",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x40",
+        "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_MEMTYPE",
+        "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x80",
+        "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_EVENTS",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x1",
+        "BriefDescription": "Number of times an RTM execution started.",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.START",
+        "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times an RTM execution successfully committed",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.COMMIT",
+        "PublicDescription": "Number of times RTM commit succeeded.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x4",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED",
+        "PublicDescription": "Number of times RTM abort was triggered.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x8",
+        "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_MEM",
+        "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x10",
+        "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_TIMER",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x20",
+        "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x40",
+        "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
+        "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x80",
+        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_EVENTS",
+        "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x4",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x8",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "50021",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x10",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x20",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x40",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "2003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x80",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "1009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x100",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "503",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x200",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "101",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.",
+        "MSRValue": "0x3fbc000002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss in the L3.",
+        "MSRValue": "0x3fbc000004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.",
+        "MSRValue": "0x3fbc000400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json
new file mode 100644
index 000000000000..70243b0b0586
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json
@@ -0,0 +1,72 @@
+[
+    {
+        "EventCode": "0x28",
+        "UMask": "0x7",
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.LVL0_TURBO_LICENSE",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "UMask": "0x18",
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.LVL1_TURBO_LICENSE",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "UMask": "0x20",
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture).  This includes high current AVX 512-bit instructions.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "UMask": "0x40",
+        "BriefDescription": "Core cycles the core was throttled due to a pending power level request.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.THROTTLE",
+        "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCB",
+        "UMask": "0x1",
+        "BriefDescription": "Number of hardware interrupts received by the processor.",
+        "Counter": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.RECEIVED",
+        "PublicDescription": "Counts the number of hardware interruptions received by the processor.",
+        "SampleAfterValue": "203",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xFE",
+        "UMask": "0x2",
+        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventName": "IDI_MISC.WB_UPGRADE",
+        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xFE",
+        "UMask": "0x4",
+        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventName": "IDI_MISC.WB_DOWNGRADE",
+        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
new file mode 100644
index 000000000000..0895d1e52a4a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
@@ -0,0 +1,950 @@
+[
+    {
+        "EventCode": "0x00",
+        "UMask": "0x1",
+        "BriefDescription": "Instructions retired from execution.",
+        "Counter": "Fixed counter 1",
+        "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when the thread is not in halt state",
+        "Counter": "Fixed counter 2",
+        "EventName": "CPU_CLK_UNHALTED.THREAD",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 2"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "Fixed counter 2",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 2"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x3",
+        "BriefDescription": "Reference cycles when the core is not in halt state.",
+        "Counter": "Fixed counter 3",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 3"
+    },
+    {
+        "EventCode": "0x03",
+        "UMask": "0x2",
+        "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .",
+        "Counter": "0,1,2,3",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x03",
+        "UMask": "0x8",
+        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
+        "Counter": "0,1,2,3",
+        "EventName": "LD_BLOCKS.NO_SR",
+        "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x07",
+        "UMask": "0x1",
+        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
+        "Counter": "0,1,2,3",
+        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+        "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x1",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x1",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0E",
+        "UMask": "0x2",
+        "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0E",
+        "UMask": "0x20",
+        "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.SLOW_LEA",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x14",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "Counter": "0,1,2,3",
+        "EventName": "ARITH.DIVIDER_ACTIVE",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x4C",
+        "UMask": "0x1",
+        "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
+        "Counter": "0,1,2,3",
+        "EventName": "LOAD_HIT_PRE.SW_PF",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "Invert": "1",
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "CounterMask": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x87",
+        "UMask": "0x1",
+        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+        "Counter": "0,1,2,3",
+        "EventName": "ILD_STALL.LCP",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA2",
+        "UMask": "0x1",
+        "BriefDescription": "Resource-related stall cycles",
+        "Counter": "0,1,2,3",
+        "EventName": "RESOURCE_STALLS.ANY",
+        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA2",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
+        "Counter": "0,1,2,3",
+        "EventName": "RESOURCE_STALLS.SB",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x4",
+        "BriefDescription": "Total execution stalls.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x5",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "CounterMask": "5",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "CounterMask": "8",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0xc",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "CounterMask": "12",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "CounterMask": "16",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x14",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "CounterMask": "20",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
+        "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Number of Uops delivered by the LSD.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.UOPS",
+        "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "CounterMask": "4",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Number of uops executed on the core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE",
+        "PublicDescription": "Number of uops executed from any thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "CounterMask": "3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x10",
+        "BriefDescription": "Counts the number of x87 uops dispatched.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.X87",
+        "PublicDescription": "Counts the number of x87 uops executed.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x0",
+        "BriefDescription": "Number of instructions retired. General Counter - architectural event",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "Errata": "SKL091, SKL044",
+        "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x1",
+        "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
+        "PEBS": "2",
+        "Counter": "1",
+        "EventName": "INST_RETIRED.PREC_DIST",
+        "Errata": "SKL091, SKL044",
+        "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "1"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xC0",
+        "UMask": "0x1",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS instructions retired event.",
+        "PEBS": "2",
+        "Counter": "0,2,3",
+        "EventName": "INST_RETIRED.TOTAL_CYCLES_PS",
+        "CounterMask": "10",
+        "Errata": "SKL091, SKL044",
+        "PublicDescription": "Number of cycles using an always true condition applied to  PEBS instructions retired event. (inst_ret< 16)",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,2,3"
+    },
+    {
+        "EventCode": "0xC1",
+        "UMask": "0x3f",
+        "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
+        "Counter": "0,1,2,3",
+        "EventName": "OTHER_ASSISTS.ANY",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Retirement slots used.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "Counts the retirement slots used.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles without actually retired uops.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "CounterMask": "10",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0xC3",
+        "UMask": "0x1",
+        "BriefDescription": "Number of machine clears (nukes) of any type. ",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "CounterMask": "1",
+        "PublicDescription": "Number of machine clears (nukes) of any type.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC3",
+        "UMask": "0x4",
+        "BriefDescription": "Self-modifying code (SMC) detected.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x0",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "Errata": "SKL091",
+        "PublicDescription": "Counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x1",
+        "BriefDescription": "Conditional branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x2",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x4",
+        "BriefDescription": "All (macro) branch instructions retired. ",
+        "PEBS": "2",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x8",
+        "BriefDescription": "Return instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x10",
+        "BriefDescription": "Not taken branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x20",
+        "BriefDescription": "Taken branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x40",
+        "BriefDescription": "Far branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x0",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x1",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x2",
+        "BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+        "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x4",
+        "BriefDescription": "Mispredicted macro branch instructions retired. ",
+        "PEBS": "2",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+        "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x20",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCC",
+        "UMask": "0x20",
+        "BriefDescription": "Increments whenever there is an update to the LBR array.",
+        "Counter": "0,1,2,3",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xE6",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+        "Counter": "0,1,2,3",
+        "EventName": "BACLEARS.ANY",
+        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
new file mode 100644
index 000000000000..36c903faed0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json
new file mode 100644
index 000000000000..9c7e5f8beee2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json
@@ -0,0 +1,172 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_READ",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "DRAM Page Activate commands sent due to a write request",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M_ACT_COUNT.WR",
+        "PerPkg": "1",
+        "PublicDescription": "Counts DRAM Page Activate commands sent on this channel due to a write request to the iMC (Memory Controller).  Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS (Column Access Select) command.",
+        "UMask": "0x2",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "All DRAM CAS Commands issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.ALL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts all CAS (Column Address Select) commands issued to DRAM per memory channel.  CAS commands are issued to specify the address to read or write on DRAM, so this event increments for every read and write. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.",
+        "UMask": "0xF",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_READ",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD_REG",
+        "PerPkg": "1",
+        "PublicDescription": "Counts CAS (Column Access Select) regular read commands issued to DRAM on a per channel basis.  CAS commands are issued to specify the address to read or write on DRAM, and this event increments for every regular read.  This event only counts regular reads and does not includes underfill reads due to partial write requests.  This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write)  is enabled or not.",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "DRAM Underfill Read CAS Commands issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis.  CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads.  Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request). ",
+        "UMask": "0x2",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Read Pending Queue Allocations",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x10",
+        "EventName": "UNC_M_RPQ_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ).  This queue is used to schedule reads out to the memory controller and to track the requests.  Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC.  The requests deallocate after the read CAS command has been issued to DRAM.  This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ.    ",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Read Pending Queue Occupancy",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_M_RPQ_OCCUPANCY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries in the Read Pending Queue (RPQ) at each cycle.  This can then be used to calculate both the average occupancy of the queue (in conjunction with the number of cycles not empty) and the average latency in the queue (in conjunction with the number of allocations).  The RPQ is used to schedule reads out to the memory controller and to track the requests.  Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate from the RPQ after the CAS command has been issued to memory.",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Write Pending Queue Allocations",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x20",
+        "EventName": "UNC_M_WPQ_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of writes requests allocated into the Write Pending Queue (WPQ).  The WPQ is used to schedule writes out to the memory controller and to track the requests.  Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (Memory Controller).  The write requests deallocate after being issued to DRAM.  Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC.",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Write Pending Queue Occupancy",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x81",
+        "EventName": "UNC_M_WPQ_OCCUPANCY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle.  This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations).  The WPQ is used to schedule writes out to the memory controller and to track the requests.",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json
new file mode 100644
index 000000000000..de6e70e552e2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json
@@ -0,0 +1,1156 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_CHA_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "config1=0x40e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "config1=0x40040e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "config1=0x40041e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "config1=0x41833",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "config1=0x41a33",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x03",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from local home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from remote home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0x0C",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from local home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from remote home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UPI_DATA_BANDWIDTH_TX",
+        "PerPkg": "1",
+        "ScaleUnit": "7.11E-06Bytes",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "FCMask": "0x07",
+        "Filter": "ch_mask=0x1f",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "MetricName": "LLC_MISSES.PCIE_READ",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "FCMask": "0x07",
+        "Filter": "ch_mask=0x1f",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "MetricName": "LLC_MISSES.PCIE_WRITE",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "MetricName": "LLC_MISSES.PCIE_WRITE",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 1",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 2",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 3",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "MetricName": "LLC_MISSES.PCIE_READ",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 1",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 2",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 3",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x33",
+        "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops.  Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set.  For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them.  However, if only 1 CV bit is set the core my have modified the data.  If the transaction was an RFO, it would need to invalidate the lines.  This event can be filtered based on who triggered the initial snoop(s).",
+        "UMask": "0x42",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x33",
+        "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops.  Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set.  For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them.  However, if only 1 CV bit is set the core my have modified the data.  If the transaction was an RFO, it would need to invalidate the lines.  This event can be filtered based on who triggered the initial snoop(s).",
+        "UMask": "0x82",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x53",
+        "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP",
+        "PerPkg": "1",
+        "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x53",
+        "EventName": "UNC_CHA_DIR_LOOKUP.SNP",
+        "PerPkg": "1",
+        "PublicDescription": "Counts  transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x54",
+        "EventName": "UNC_CHA_DIR_UPDATE.HA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x54",
+        "EventName": "UNC_CHA_DIR_UPDATE.TOR",
+        "PerPkg": "1",
+        "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5F",
+        "EventName": "UNC_CHA_HITME_HIT.EX_RDS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state.  This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Normal priority reads issued to the memory controller from the CHA",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x59",
+        "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5B",
+        "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Number of times that an RFO hit in S state.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x39",
+        "EventName": "UNC_CHA_MISC.RFO_HIT_S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a  write) request hit a cacheline in the S (Shared) state.",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Local requests for exclusive ownership of a cache line  without receiving data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.",
+        "UMask": "0x10",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.",
+        "UMask": "0x20",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspCnflct* Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.",
+        "UMask": "0x40",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspI Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPI",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspIFwd Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states.  This is commonly returned with RFO (the Read for Ownership issued before a write) transactions.  The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward)  states.",
+        "UMask": "0x04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspSFwd Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy.  This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to it's home socket, and the cacheline was forwarded to the requestor socket.  This snoop response is only used in >= 4 socket systems.  It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to it's home socket to be written back to memory.",
+        "UMask": "0x20",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Rsp*WB Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home.  This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured.  This reponse will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.",
+        "UMask": "0x10",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Clockticks of the IIO Traffic Controller",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_IIO_CLOCKTICKS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU ",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by  a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU ",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by  a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is  made by IIO Part1 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x22",
+        "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x24",
+        "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Messages sent direct to core (bypassing the CHA)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x23",
+        "EventName": "UNC_M2M_DIRECT2CORE_TAKEN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Number of reads in which direct to core transaction were overridden",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x25",
+        "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x28",
+        "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Cycles when direct to Intel UPI was disabled",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x27",
+        "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Messages sent direct to the Intel UPI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x26",
+        "EventName": "UNC_M2M_DIRECT2UPI_TAKEN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x29",
+        "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)",
+        "UMask": "0x1",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data.  The data may be stored in any state in the local socket.",
+        "UMask": "0x8",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data.  The data may be stored in any state in the local socket.",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data.  The data may be stored in any state in the local socket.",
+        "UMask": "0x4",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from A to I",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to I (Invalid)",
+        "UMask": "0x20",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from A to S",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to S (Shared)",
+        "UMask": "0x40",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from/to Any state ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state",
+        "UMask": "0x1",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from I to A",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to A (SnoopAll)",
+        "UMask": "0x4",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from I to S",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to S (Shared)",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from S to A",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to A (SnoopAll)",
+        "UMask": "0x10",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from S to I",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to I (Invalid)",
+        "UMask": "0x8",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Reads to iMC issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_M2M_IMC_READS.ALL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). ",
+        "UMask": "0x4",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_M2M_IMC_READS.NORMAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).  It only counts  normal priority non-isochronous reads.",
+        "UMask": "0x1",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Writes to iMC issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x38",
+        "EventName": "UNC_M2M_IMC_WRITES.ALL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).",
+        "UMask": "0x10",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Partial Non-Isochronous writes to the iMC",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x38",
+        "EventName": "UNC_M2M_IMC_WRITES.PARTIAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller).  It only counts normal priority non-isochronous writes.",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Prefecth requests that got turn into a demand request",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x56",
+        "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address.  Explanatory Side Note: The Prefecth queue is made of CAM (Content Addressable Memory)",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Inserts into the Memory Controller Prefetch Queue",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x57",
+        "EventName": "UNC_M2M_PREFCAM_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) recieves a prefetch request and inserts it into its outstanding prefetch queue.  Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "AD Ingress (from CMS) Queue Inserts",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M2M_RxC_AD_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop).  This is generally used for reads, and ",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x29",
+        "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN",
+        "PerPkg": "1",
+        "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)",
+        "Unit": "M3UPI"
+    },
+    {
+        "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_UPI_CLOCKTICKS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI).  This clock runs at1/8th the 'GT/s' speed of the UPI link.  For example, a  9.6GT/s  link will have a fixed Frequency of 1.2 Ghz.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Data Response packets that go direct to core",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x12",
+        "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C",
+        "PerPkg": "1",
+        "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.",
+        "UMask": "0x1",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Data Response packets that go direct to Intel UPI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x12",
+        "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U",
+        "PerPkg": "1",
+        "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .",
+        "UMask": "0x2",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_UPI_L1_POWER_CYCLES",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode.  L1 is a mode that totally shuts down the UPI link.  Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x25",
+        "EventName": "UNC_UPI_RxL0P_POWER_CYCLES",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x31",
+        "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress.  This is a latency optimization, and should generally be the common case.  If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+        "UMask": "0x1",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x31",
+        "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer  (Receive Queue) and passed directly across the BGF and into the Egress.  This is a latency optimization, and should generally be the common case.  If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+        "UMask": "0x2",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs received which bypassed the Slot0 Recieve Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x31",
+        "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) whcih bypassed the slot2 RxQ buffer (Receive Queue)  and passed directly to the Egress.  This is a latency optimization, and should generally be the common case.  If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+        "UMask": "0x4",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Valid data FLITs received from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3",
+        "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts valid data FLITs  (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Null FLITs received from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3",
+        "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.",
+        "UMask": "0x27",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Protocol header and credit FLITs received from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3",
+        "EventName": "UNC_UPI_RxL_FLITS.NON_DATA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts protocol header and credit FLITs  (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.",
+        "UMask": "0x97",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x27",
+        "EventName": "UNC_UPI_TxL0P_POWER_CYCLES",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs that bypassed the TxL Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x41",
+        "EventName": "UNC_UPI_TxL_BYPASSED",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link.  However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR  mode, increasing latency to transfer out to the link.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UPI_DATA_BANDWIDTH_TX",
+        "PerPkg": "1",
+        "ScaleUnit": "7.11E-06Bytes",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Null FLITs transmitted from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.",
+        "UMask": "0x27",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Idle FLITs transmitted",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_UPI_TxL_FLITS.IDLE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs).  Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.",
+        "UMask": "0x47",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Protocol header and credit FLITs transmitted across any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_UPI_TxL_FLITS.NON_DATA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.",
+        "UMask": "0x97",
+        "Unit": "UPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
new file mode 100644
index 000000000000..70750dab7ead
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
@@ -0,0 +1,284 @@
+[
+    {
+        "EventCode": "0x08",
+        "UMask": "0x1",
+        "BriefDescription": "Load misses in all DTLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x2",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x4",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x8",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts load misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0xe",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture. ",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x20",
+        "BriefDescription": "Loads that miss the DTLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x1",
+        "BriefDescription": "Store misses in all DTLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x2",
+        "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x4",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x8",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0xe",
+        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture. ",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x20",
+        "BriefDescription": "Stores that miss the DTLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x4F",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
+        "Counter": "0,1,2,3",
+        "EventName": "EPT.WALK_PENDING",
+        "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x1",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x2",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x4",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts completed page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x8",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0xe",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x20",
+        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAE",
+        "UMask": "0x1",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBD",
+        "UMask": "0x1",
+        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
+        "Counter": "0,1,2,3",
+        "EventName": "TLB_FLUSH.DTLB_THREAD",
+        "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBD",
+        "UMask": "0x20",
+        "BriefDescription": "STLB flush attempts",
+        "Counter": "0,1,2,3",
+        "EventName": "TLB_FLUSH.STLB_ANY",
+        "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index bd0aabb2bd0f..9eb7047bafe4 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -137,6 +137,8 @@ static struct field {
         { "AnyThread",  "any=" },
         { "EdgeDetect", "edge=" },
         { "SampleAfterValue", "period=" },
+        { "FCMask",     "fc_mask=" },
+        { "PortMask",   "ch_mask=" },
         { NULL, NULL }
 };
 
@@ -290,7 +292,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
                                     char *desc, char *long_desc,
                                     char *pmu, char *unit, char *perpkg,
                                     char *metric_expr,
-                                    char *metric_name)
+                                    char *metric_name, char *metric_group)
 {
         struct perf_entry_data *pd = data;
         FILE *outfp = pd->outfp;
@@ -302,8 +304,10 @@ static int print_events_table_entry(void *data, char *name, char *event,
          */
         fprintf(outfp, "{\n");
 
-        fprintf(outfp, "\t.name = \"%s\",\n", name);
-        fprintf(outfp, "\t.event = \"%s\",\n", event);
+        if (name)
+                fprintf(outfp, "\t.name = \"%s\",\n", name);
+        if (event)
+                fprintf(outfp, "\t.event = \"%s\",\n", event);
         fprintf(outfp, "\t.desc = \"%s\",\n", desc);
         fprintf(outfp, "\t.topic = \"%s\",\n", topic);
         if (long_desc && long_desc[0])
@@ -318,6 +322,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
                 fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
         if (metric_name)
                 fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
+        if (metric_group)
+                fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
         fprintf(outfp, "},\n");
 
         return 0;
@@ -355,6 +361,9 @@ static char *real_event(const char *name, char *event)
 {
         int i;
 
+        if (!name)
+                return NULL;
+
         for (i = 0; fixed[i].name; i++)
                 if (!strcasecmp(name, fixed[i].name))
                         return (char *)fixed[i].event;
@@ -367,7 +376,7 @@ int json_events(const char *fn,
                       char *long_desc,
                       char *pmu, char *unit, char *perpkg,
                       char *metric_expr,
-                      char *metric_name),
+                      char *metric_name, char *metric_group),
           void *data)
 {
         int err = -EIO;
@@ -395,6 +404,7 @@ int json_events(const char *fn,
                 char *unit = NULL;
                 char *metric_expr = NULL;
                 char *metric_name = NULL;
+                char *metric_group = NULL;
                 unsigned long long eventcode = 0;
                 struct msrmap *msr = NULL;
                 jsmntok_t *msrval = NULL;
@@ -474,6 +484,8 @@ int json_events(const char *fn,
                                 addfield(map, &perpkg, "", "", val);
                         } else if (json_streq(map, field, "MetricName")) {
                                 addfield(map, &metric_name, "", "", val);
+                        } else if (json_streq(map, field, "MetricGroup")) {
+                                addfield(map, &metric_group, "", "", val);
                         } else if (json_streq(map, field, "MetricExpr")) {
                                 addfield(map, &metric_expr, "", "", val);
                                 for (s = metric_expr; *s; s++)
@@ -499,10 +511,11 @@ int json_events(const char *fn,
                         addfield(map, &event, ",", filter, NULL);
                 if (msr != NULL)
                         addfield(map, &event, ",", msr->pname, msrval);
-                fixname(name);
+                if (name)
+                        fixname(name);
 
                 err = func(data, name, real_event(name, event), desc, long_desc,
-                                pmu, unit, perpkg, metric_expr, metric_name);
+                           pmu, unit, perpkg, metric_expr, metric_name, metric_group);
                 free(event);
                 free(desc);
                 free(name);
@@ -514,6 +527,7 @@ int json_events(const char *fn,
                 free(unit);
                 free(metric_expr);
                 free(metric_name);
+                free(metric_group);
                 if (err)
                         break;
                 tok += j;
@@ -822,10 +836,6 @@ static int process_one_file(const char *fpath, const struct stat *sb,
  * PMU event tables (see struct pmu_events_map).
  *
  * Write out the PMU events tables and the mapping table to pmu-event.c.
- *
- * If unable to process the JSON or arch files, create an empty mapping
- * table so we can continue to build/use  perf even if we cannot use the
- * PMU event aliases.
  */
 int main(int argc, char *argv[])
 {
@@ -836,6 +846,7 @@ int main(int argc, char *argv[])
         const char *arch;
         const char *output_file;
         const char *start_dirname;
+        struct stat stbuf;
 
         prog = basename(argv[0]);
         if (argc < 4) {
@@ -857,11 +868,17 @@ int main(int argc, char *argv[])
                 return 2;
         }
 
+        sprintf(ldirname, "%s/%s", start_dirname, arch);
+
+        /* If architecture does not have any event lists, bail out */
+        if (stat(ldirname, &stbuf) < 0) {
+                pr_info("%s: Arch %s has no PMU event lists\n", prog, arch);
+                goto empty_map;
+        }
+
         /* Include pmu-events.h first */
         fprintf(eventsfp, "#include \"../../pmu-events/pmu-events.h\"\n");
 
-        sprintf(ldirname, "%s/%s", start_dirname, arch);
-
         /*
          * The mapfile allows multiple CPUids to point to the same JSON file,
          * so, not sure if there is a need for symlinks within the pmu-events
@@ -878,6 +895,9 @@ int main(int argc, char *argv[])
         if (rc && verbose) {
                 pr_info("%s: Error walking file tree %s\n", prog, ldirname);
                 goto empty_map;
+        } else if (rc < 0) {
+                /* Make build fail */
+                return 1;
         } else if (rc) {
                 goto empty_map;
         }
@@ -892,7 +912,8 @@ int main(int argc, char *argv[])
 
         if (process_mapfile(eventsfp, mapfile)) {
                 pr_info("%s: Error processing mapfile %s\n", prog, mapfile);
-                goto empty_map;
+                /* Make build fail */
+                return 1;
         }
 
         return 0;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index 611fac01913d..4684c673c445 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef JEVENTS_H
 #define JEVENTS_H 1
 
@@ -6,7 +7,7 @@ int json_events(const char *fn,
                                 char *long_desc,
                                 char *pmu,
                                 char *unit, char *perpkg, char *metric_expr,
-                                char *metric_name),
+                                char *metric_name, char *metric_group),
                 void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/jsmn.h b/tools/perf/pmu-events/jsmn.h
index d666b10cf25b..c7b0f6ea2a31 100644
--- a/tools/perf/pmu-events/jsmn.h
+++ b/tools/perf/pmu-events/jsmn.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __JSMN_H_
 #define __JSMN_H_
 
diff --git a/tools/perf/pmu-events/json.h b/tools/perf/pmu-events/json.h
index 278ebd32cfb6..fbcd5a0590ad 100644
--- a/tools/perf/pmu-events/json.h
+++ b/tools/perf/pmu-events/json.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef JSON_H
 #define JSON_H 1
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 569eab3688dd..92a4d15ee0b9 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PMU_EVENTS_H
 #define PMU_EVENTS_H
 
@@ -15,6 +16,7 @@ struct pmu_event {
         const char *perpkg;
         const char *metric_expr;
         const char *metric_name;
+        const char *metric_group;
 };
 
 /*
diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py
index eb4dbed57de7..eb76f6516247 100755
--- a/tools/perf/python/tracepoint.py
+++ b/tools/perf/python/tracepoint.py
@@ -1,4 +1,5 @@
 #! /usr/bin/python
+# SPDX-License-Identifier: GPL-2.0
 # -*- python -*-
 # -*- coding: utf-8 -*-
 
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL b/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL
index decdeb0f6789..e8994332d7dc 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 use 5.010000;
 use ExtUtils::MakeMaker;
 # See lib/ExtUtils/MakeMaker.pm for details of how to influence
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 9e0985794e20..81a56cd2b3c1 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -1,4 +1,5 @@
 # EventClass.py
+# SPDX-License-Identifier: GPL-2.0
 #
 # This is a library defining some events types classes, which could
 # be used by other scripts to analyzing the perf samples.
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 1d95009592eb..f6c84966e4f8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -57,6 +57,7 @@ try:
                 'ia64'  : audit.MACH_IA64,
                 'ppc'   : audit.MACH_PPC,
                 'ppc64' : audit.MACH_PPC64,
+                'ppc64le' : audit.MACH_PPC64LE,
                 's390'  : audit.MACH_S390,
                 's390x' : audit.MACH_S390X,
                 'i386'  : audit.MACH_X86,
diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-record b/tools/perf/scripts/python/bin/export-to-sqlite-record
new file mode 100644
index 000000000000..070204fd6d00
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-sqlite-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a sqlite3 database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-report b/tools/perf/scripts/python/bin/export-to-sqlite-report
new file mode 100644
index 000000000000..5ff6033e70ba
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-sqlite-report
@@ -0,0 +1,29 @@
+#!/bin/bash
+# description: export perf data to a sqlite3 database
+# args: [database name] [columns] [calls]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+        break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-sqlite-report [database name] [columns] [calls]"
+    exit
+fi
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-sqlite.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/call-graph-from-postgresql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index e78fdc2a5a9d..b494a67a1c67 100644
--- a/tools/perf/scripts/python/call-graph-from-postgresql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -1,6 +1,6 @@
 #!/usr/bin/python2
-# call-graph-from-postgresql.py: create call-graph from postgresql database
-# Copyright (c) 2014, Intel Corporation.
+# call-graph-from-sql.py: create call-graph from sql database
+# Copyright (c) 2014-2017, Intel Corporation.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms and conditions of the GNU General Public License,
@@ -11,18 +11,19 @@
 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 # more details.
 
-# To use this script you will need to have exported data using the
-# export-to-postgresql.py script.  Refer to that script for details.
+# To use this script you will need to have exported data using either the
+# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
+# scripts for details.
 #
-# Following on from the example in the export-to-postgresql.py script, a
+# Following on from the example in the export scripts, a
 # call-graph can be displayed for the pt_example database like this:
 #
-#       python tools/perf/scripts/python/call-graph-from-postgresql.py pt_example
+#       python tools/perf/scripts/python/call-graph-from-sql.py pt_example
 #
-# Note this script supports connecting to remote databases by setting hostname,
-# port, username, password, and dbname e.g.
+# Note that for PostgreSQL, this script supports connecting to remote databases
+# by setting hostname, port, username, password, and dbname e.g.
 #
-#       python tools/perf/scripts/python/call-graph-from-postgresql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
+#       python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
 #
 # The result is a GUI window with a tree representing a context-sensitive
 # call-graph.  Expanding a couple of levels of the tree and adjusting column
@@ -160,7 +161,7 @@ class TreeItem():
                                   '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
                                   '( SELECT ip FROM call_paths where id = call_path_id ) '
                                   'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
-                                  'ORDER BY call_path_id')
+                                  ' ORDER BY call_path_id')
                 if not ret:
                         raise Exception("Query failed: " + query.lastError().text())
                 last_call_path_id = 0
@@ -291,29 +292,40 @@ class MainWindow(QMainWindow):
 
 if __name__ == '__main__':
         if (len(sys.argv) < 2):
-                print >> sys.stderr, "Usage is: call-graph-from-postgresql.py <database name>"
+                print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
                 raise Exception("Too few arguments")
 
         dbname = sys.argv[1]
 
-        db = QSqlDatabase.addDatabase('QPSQL')
-
-        opts = dbname.split()
-        for opt in opts:
-                if '=' in opt:
-                        opt = opt.split('=')
-                        if opt[0] == 'hostname':
-                                db.setHostName(opt[1])
-                        elif opt[0] == 'port':
-                                db.setPort(int(opt[1]))
-                        elif opt[0] == 'username':
-                                db.setUserName(opt[1])
-                        elif opt[0] == 'password':
-                                db.setPassword(opt[1])
-                        elif opt[0] == 'dbname':
-                                dbname = opt[1]
-                else:
-                        dbname = opt
+        is_sqlite3 = False
+        try:
+                f = open(dbname)
+                if f.read(15) == "SQLite format 3":
+                        is_sqlite3 = True
+                f.close()
+        except:
+                pass
+
+        if is_sqlite3:
+                db = QSqlDatabase.addDatabase('QSQLITE')
+        else:
+                db = QSqlDatabase.addDatabase('QPSQL')
+                opts = dbname.split()
+                for opt in opts:
+                        if '=' in opt:
+                                opt = opt.split('=')
+                                if opt[0] == 'hostname':
+                                        db.setHostName(opt[1])
+                                elif opt[0] == 'port':
+                                        db.setPort(int(opt[1]))
+                                elif opt[0] == 'username':
+                                        db.setUserName(opt[1])
+                                elif opt[0] == 'password':
+                                        db.setPassword(opt[1])
+                                elif opt[0] == 'dbname':
+                                        dbname = opt[1]
+                        else:
+                                dbname = opt
 
         db.setDatabaseName(dbname)
         if not db.open():
diff --git a/tools/perf/scripts/python/event_analyzing_sample.py b/tools/perf/scripts/python/event_analyzing_sample.py
index 163c39fa12d9..4e843b9864ec 100644
--- a/tools/perf/scripts/python/event_analyzing_sample.py
+++ b/tools/perf/scripts/python/event_analyzing_sample.py
@@ -1,4 +1,5 @@
 # event_analyzing_sample.py: general event handler in python
+# SPDX-License-Identifier: GPL-2.0
 #
 # Current perf report is already very powerful with the annotation integrated,
 # and this script is not trying to be as powerful as perf report, but
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 7656ff8aa066..efcaf6cac2eb 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -59,7 +59,7 @@ import datetime
 #       pt_example=# \q
 #
 # An example of using the database is provided by the script
-# call-graph-from-postgresql.py.  Refer to that script for details.
+# call-graph-from-sql.py.  Refer to that script for details.
 #
 # Tables:
 #
@@ -340,7 +340,8 @@ if branches:
                 'to_sym_offset  bigint,'
                 'to_ip          bigint,'
                 'branch_type    integer,'
-                'in_tx          boolean)')
+                'in_tx          boolean,'
+                'call_path_id   bigint)')
 else:
         do_query(query, 'CREATE TABLE samples ('
                 'id             bigint          NOT NULL,'
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
new file mode 100644
index 000000000000..f827bf77e9d2
--- /dev/null
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -0,0 +1,451 @@
+# export-to-sqlite.py: export perf data to a sqlite3 database
+# Copyright (c) 2017, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+import os
+import sys
+import struct
+import datetime
+
+# To use this script you will need to have installed package python-pyside which
+# provides LGPL-licensed Python bindings for Qt.  You will also need the package
+# libqt4-sql-sqlite for Qt sqlite3 support.
+#
+# An example of using this script with Intel PT:
+#
+#       $ perf record -e intel_pt//u ls
+#       $ perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls
+#       2017-07-31 14:26:07.326913 Creating database...
+#       2017-07-31 14:26:07.538097 Writing records...
+#       2017-07-31 14:26:09.889292 Adding indexes
+#       2017-07-31 14:26:09.958746 Done
+#
+# To browse the database, sqlite3 can be used e.g.
+#
+#       $ sqlite3 pt_example
+#       sqlite> .header on
+#       sqlite> select * from samples_view where id < 10;
+#       sqlite> .mode column
+#       sqlite> select * from samples_view where id < 10;
+#       sqlite> .tables
+#       sqlite> .schema samples_view
+#       sqlite> .quit
+#
+# An example of using the database is provided by the script
+# call-graph-from-sql.py.  Refer to that script for details.
+#
+# The database structure is practically the same as created by the script
+# export-to-postgresql.py. Refer to that script for details.  A notable
+# difference is  the 'transaction' column of the 'samples' table which is
+# renamed 'transaction_' in sqlite because 'transaction' is a reserved word.
+
+from PySide.QtSql import *
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+# These perf imports are not used at present
+#from perf_trace_context import *
+#from Core import *
+
+perf_db_export_mode = True
+perf_db_export_calls = False
+perf_db_export_callchains = False
+
+def usage():
+        print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"
+        print >> sys.stderr, "where:    columns         'all' or 'branches'"
+        print >> sys.stderr, "          calls           'calls' => create calls and call_paths table"
+        print >> sys.stderr, "          callchains      'callchains' => create call_paths table"
+        raise Exception("Too few arguments")
+
+if (len(sys.argv) < 2):
+        usage()
+
+dbname = sys.argv[1]
+
+if (len(sys.argv) >= 3):
+        columns = sys.argv[2]
+else:
+        columns = "all"
+
+if columns not in ("all", "branches"):
+        usage()
+
+branches = (columns == "branches")
+
+for i in range(3,len(sys.argv)):
+        if (sys.argv[i] == "calls"):
+                perf_db_export_calls = True
+        elif (sys.argv[i] == "callchains"):
+                perf_db_export_callchains = True
+        else:
+                usage()
+
+def do_query(q, s):
+        if (q.exec_(s)):
+                return
+        raise Exception("Query failed: " + q.lastError().text())
+
+def do_query_(q):
+        if (q.exec_()):
+                return
+        raise Exception("Query failed: " + q.lastError().text())
+
+print datetime.datetime.today(), "Creating database..."
+
+db_exists = False
+try:
+        f = open(dbname)
+        f.close()
+        db_exists = True
+except:
+        pass
+
+if db_exists:
+        raise Exception(dbname + " already exists")
+
+db = QSqlDatabase.addDatabase('QSQLITE')
+db.setDatabaseName(dbname)
+db.open()
+
+query = QSqlQuery(db)
+
+do_query(query, 'PRAGMA journal_mode = OFF')
+do_query(query, 'BEGIN TRANSACTION')
+
+do_query(query, 'CREATE TABLE selected_events ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'name           varchar(80))')
+do_query(query, 'CREATE TABLE machines ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'pid            integer,'
+                'root_dir       varchar(4096))')
+do_query(query, 'CREATE TABLE threads ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'machine_id     bigint,'
+                'process_id     bigint,'
+                'pid            integer,'
+                'tid            integer)')
+do_query(query, 'CREATE TABLE comms ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'comm           varchar(16))')
+do_query(query, 'CREATE TABLE comm_threads ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'comm_id        bigint,'
+                'thread_id      bigint)')
+do_query(query, 'CREATE TABLE dsos ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'machine_id     bigint,'
+                'short_name     varchar(256),'
+                'long_name      varchar(4096),'
+                'build_id       varchar(64))')
+do_query(query, 'CREATE TABLE symbols ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'dso_id         bigint,'
+                'sym_start      bigint,'
+                'sym_end        bigint,'
+                'binding        integer,'
+                'name           varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'name           varchar(80))')
+
+if branches:
+        do_query(query, 'CREATE TABLE samples ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'evsel_id       bigint,'
+                'machine_id     bigint,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'dso_id         bigint,'
+                'symbol_id      bigint,'
+                'sym_offset     bigint,'
+                'ip             bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'to_dso_id      bigint,'
+                'to_symbol_id   bigint,'
+                'to_sym_offset  bigint,'
+                'to_ip          bigint,'
+                'branch_type    integer,'
+                'in_tx          boolean,'
+                'call_path_id   bigint)')
+else:
+        do_query(query, 'CREATE TABLE samples ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'evsel_id       bigint,'
+                'machine_id     bigint,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'dso_id         bigint,'
+                'symbol_id      bigint,'
+                'sym_offset     bigint,'
+                'ip             bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'to_dso_id      bigint,'
+                'to_symbol_id   bigint,'
+                'to_sym_offset  bigint,'
+                'to_ip          bigint,'
+                'period         bigint,'
+                'weight         bigint,'
+                'transaction_   bigint,'
+                'data_src       bigint,'
+                'branch_type    integer,'
+                'in_tx          boolean,'
+                'call_path_id   bigint)')
+
+if perf_db_export_calls or perf_db_export_callchains:
+        do_query(query, 'CREATE TABLE call_paths ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'parent_id      bigint,'
+                'symbol_id      bigint,'
+                'ip             bigint)')
+if perf_db_export_calls:
+        do_query(query, 'CREATE TABLE calls ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'call_path_id   bigint,'
+                'call_time      bigint,'
+                'return_time    bigint,'
+                'branch_count   bigint,'
+                'call_id        bigint,'
+                'return_id      bigint,'
+                'parent_call_path_id    bigint,'
+                'flags          integer)')
+
+# printf was added to sqlite in version 3.8.3
+sqlite_has_printf = False
+try:
+        do_query(query, 'SELECT printf("") FROM machines')
+        sqlite_has_printf = True
+except:
+        pass
+
+def emit_to_hex(x):
+        if sqlite_has_printf:
+                return 'printf("%x", ' + x + ')'
+        else:
+                return x
+
+do_query(query, 'CREATE VIEW machines_view AS '
+        'SELECT '
+                'id,'
+                'pid,'
+                'root_dir,'
+                'CASE WHEN id=0 THEN \'unknown\' WHEN pid=-1 THEN \'host\' ELSE \'guest\' END AS host_or_guest'
+        ' FROM machines')
+
+do_query(query, 'CREATE VIEW dsos_view AS '
+        'SELECT '
+                'id,'
+                'machine_id,'
+                '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,'
+                'short_name,'
+                'long_name,'
+                'build_id'
+        ' FROM dsos')
+
+do_query(query, 'CREATE VIEW symbols_view AS '
+        'SELECT '
+                'id,'
+                'name,'
+                '(SELECT short_name FROM dsos WHERE id=dso_id) AS dso,'
+                'dso_id,'
+                'sym_start,'
+                'sym_end,'
+                'CASE WHEN binding=0 THEN \'local\' WHEN binding=1 THEN \'global\' ELSE \'weak\' END AS binding'
+        ' FROM symbols')
+
+do_query(query, 'CREATE VIEW threads_view AS '
+        'SELECT '
+                'id,'
+                'machine_id,'
+                '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,'
+                'process_id,'
+                'pid,'
+                'tid'
+        ' FROM threads')
+
+do_query(query, 'CREATE VIEW comm_threads_view AS '
+        'SELECT '
+                'comm_id,'
+                '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                'thread_id,'
+                '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                '(SELECT tid FROM threads WHERE id = thread_id) AS tid'
+        ' FROM comm_threads')
+
+if perf_db_export_calls or perf_db_export_callchains:
+        do_query(query, 'CREATE VIEW call_paths_view AS '
+                'SELECT '
+                        'c.id,'
+                        + emit_to_hex('c.ip') + ' AS ip,'
+                        'c.symbol_id,'
+                        '(SELECT name FROM symbols WHERE id = c.symbol_id) AS symbol,'
+                        '(SELECT dso_id FROM symbols WHERE id = c.symbol_id) AS dso_id,'
+                        '(SELECT dso FROM symbols_view  WHERE id = c.symbol_id) AS dso_short_name,'
+                        'c.parent_id,'
+                        + emit_to_hex('p.ip') + ' AS parent_ip,'
+                        'p.symbol_id AS parent_symbol_id,'
+                        '(SELECT name FROM symbols WHERE id = p.symbol_id) AS parent_symbol,'
+                        '(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,'
+                        '(SELECT dso FROM symbols_view  WHERE id = p.symbol_id) AS parent_dso_short_name'
+                ' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id')
+if perf_db_export_calls:
+        do_query(query, 'CREATE VIEW calls_view AS '
+                'SELECT '
+                        'calls.id,'
+                        'thread_id,'
+                        '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                        '(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+                        '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                        'call_path_id,'
+                        + emit_to_hex('ip') + ' AS ip,'
+                        'symbol_id,'
+                        '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+                        'call_time,'
+                        'return_time,'
+                        'return_time - call_time AS elapsed_time,'
+                        'branch_count,'
+                        'call_id,'
+                        'return_id,'
+                        'CASE WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' ELSE \'\' END AS flags,'
+                        'parent_call_path_id'
+                ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
+
+do_query(query, 'CREATE VIEW samples_view AS '
+        'SELECT '
+                'id,'
+                'time,'
+                'cpu,'
+                '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                '(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+                '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,'
+                + emit_to_hex('ip') + ' AS ip_hex,'
+                '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+                'sym_offset,'
+                '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,'
+                + emit_to_hex('to_ip') + ' AS to_ip_hex,'
+                '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
+                'to_sym_offset,'
+                '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+                '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+                'in_tx'
+        ' FROM samples')
+
+do_query(query, 'END TRANSACTION')
+
+evsel_query = QSqlQuery(db)
+evsel_query.prepare("INSERT INTO selected_events VALUES (?, ?)")
+machine_query = QSqlQuery(db)
+machine_query.prepare("INSERT INTO machines VALUES (?, ?, ?)")
+thread_query = QSqlQuery(db)
+thread_query.prepare("INSERT INTO threads VALUES (?, ?, ?, ?, ?)")
+comm_query = QSqlQuery(db)
+comm_query.prepare("INSERT INTO comms VALUES (?, ?)")
+comm_thread_query = QSqlQuery(db)
+comm_thread_query.prepare("INSERT INTO comm_threads VALUES (?, ?, ?)")
+dso_query = QSqlQuery(db)
+dso_query.prepare("INSERT INTO dsos VALUES (?, ?, ?, ?, ?)")
+symbol_query = QSqlQuery(db)
+symbol_query.prepare("INSERT INTO symbols VALUES (?, ?, ?, ?, ?, ?)")
+branch_type_query = QSqlQuery(db)
+branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)")
+sample_query = QSqlQuery(db)
+if branches:
+        sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+else:
+        sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+if perf_db_export_calls or perf_db_export_callchains:
+        call_path_query = QSqlQuery(db)
+        call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)")
+if perf_db_export_calls:
+        call_query = QSqlQuery(db)
+        call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+
+def trace_begin():
+        print datetime.datetime.today(), "Writing records..."
+        do_query(query, 'BEGIN TRANSACTION')
+        # id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
+        evsel_table(0, "unknown")
+        machine_table(0, 0, "unknown")
+        thread_table(0, 0, 0, -1, -1)
+        comm_table(0, "unknown")
+        dso_table(0, 0, "unknown", "unknown", "")
+        symbol_table(0, 0, 0, 0, 0, "unknown")
+        sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+        if perf_db_export_calls or perf_db_export_callchains:
+                call_path_table(0, 0, 0, 0)
+
+unhandled_count = 0
+
+def trace_end():
+        do_query(query, 'END TRANSACTION')
+
+        print datetime.datetime.today(), "Adding indexes"
+        if perf_db_export_calls:
+                do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
+
+        if (unhandled_count):
+                print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+        print datetime.datetime.today(), "Done"
+
+def trace_unhandled(event_name, context, event_fields_dict):
+        global unhandled_count
+        unhandled_count += 1
+
+def sched__sched_switch(*x):
+        pass
+
+def bind_exec(q, n, x):
+        for xx in x[0:n]:
+                q.addBindValue(str(xx))
+        do_query_(q)
+
+def evsel_table(*x):
+        bind_exec(evsel_query, 2, x)
+
+def machine_table(*x):
+        bind_exec(machine_query, 3, x)
+
+def thread_table(*x):
+        bind_exec(thread_query, 5, x)
+
+def comm_table(*x):
+        bind_exec(comm_query, 2, x)
+
+def comm_thread_table(*x):
+        bind_exec(comm_thread_query, 3, x)
+
+def dso_table(*x):
+        bind_exec(dso_query, 5, x)
+
+def symbol_table(*x):
+        bind_exec(symbol_query, 6, x)
+
+def branch_type_table(*x):
+        bind_exec(branch_type_query, 2, x)
+
+def sample_table(*x):
+        if branches:
+                bind_exec(sample_query, 18, x)
+        else:
+                bind_exec(sample_query, 22, x)
+
+def call_path_table(*x):
+        bind_exec(call_path_query, 4, x)
+
+def call_return_table(*x):
+        bind_exec(call_query, 11, x)
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
index 0b6ce8c253e8..a150164b44a3 100755
--- a/tools/perf/scripts/python/net_dropmonitor.py
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -1,4 +1,5 @@
 # Monitor the system for dropped packets and proudce a report of drop locations and counts
+# SPDX-License-Identifier: GPL-2.0
 
 import os
 import sys
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
index 4c6f09ac7d12..9b2050f778f1 100644
--- a/tools/perf/scripts/python/netdev-times.py
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -1,4 +1,5 @@
 # Display a process of packets and processed time.
+# SPDX-License-Identifier: GPL-2.0
 # It helps us to investigate networking or network device.
 #
 # options
diff --git a/tools/perf/scripts/python/stackcollapse.py b/tools/perf/scripts/python/stackcollapse.py
index 5a605f70ef32..1697b5e18c96 100755
--- a/tools/perf/scripts/python/stackcollapse.py
+++ b/tools/perf/scripts/python/stackcollapse.py
@@ -1,4 +1,5 @@
 # stackcollapse.py - format perf samples with one line per distinct call stack
+# SPDX-License-Identifier: GPL-2.0
 #
 # This script's output has two space-separated fields.  The first is a semicolon
 # separated stack including the program name (from the "comm" field) and the
diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py
index 8b60f343dd07..8410672efb8b 100644
--- a/tools/perf/scripts/python/stat-cpi.py
+++ b/tools/perf/scripts/python/stat-cpi.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# SPDX-License-Identifier: GPL-2.0
 
 data    = {}
 times   = []
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 84222bdb8689..87bf3edb037c 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -34,6 +34,7 @@ perf-y += thread-map.o
 perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
 perf-y += bpf.o
 perf-y += topology.o
+perf-y += mem.o
 perf-y += cpumap.o
 perf-y += stat.o
 perf-y += event_update.o
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 0e77b2cf61ec..0e1367f90af5 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * The struct perf_event_attr test support.
  *
@@ -36,6 +37,7 @@
 #define ENV "PERF_TEST_ATTR"
 
 static char *dir;
+static bool ready;
 
 void test_attr__init(void)
 {
@@ -67,6 +69,9 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
         FILE *file;
         char path[PATH_MAX];
 
+        if (!ready)
+                return 0;
+
         snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
                  attr->type, attr->config, fd);
 
@@ -136,7 +141,7 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 {
         int errno_saved = errno;
 
-        if (store_event(attr, pid, cpu, fd, group_fd, flags)) {
+        if ((fd != -1) && store_event(attr, pid, cpu, fd, group_fd, flags)) {
                 pr_err("test attr FAILED");
                 exit(128);
         }
@@ -144,6 +149,12 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
         errno = errno_saved;
 }
 
+void test_attr__ready(void)
+{
+        if (unlikely(test_attr__enabled) && !ready)
+                ready = true;
+}
+
 static int run_dir(const char *d, const char *perf)
 {
         char v[] = "-vvvvv";
@@ -156,10 +167,10 @@ static int run_dir(const char *d, const char *perf)
         snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
                  d, d, perf, vcnt, v);
 
-        return system(cmd);
+        return system(cmd) ? TEST_FAIL : TEST_OK;
 }
 
-int test__attr(int subtest __maybe_unused)
+int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct stat st;
         char path_perf[PATH_MAX];
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index cdf21a9d0c35..ff9b60b99f52 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -1,4 +1,5 @@
 #! /usr/bin/python
+# SPDX-License-Identifier: GPL-2.0
 
 import os
 import sys
@@ -9,6 +10,20 @@ import logging
 import shutil
 import ConfigParser
 
+def data_equal(a, b):
+    # Allow multiple values in assignment separated by '|'
+    a_list = a.split('|')
+    b_list = b.split('|')
+
+    for a_item in a_list:
+        for b_item in b_list:
+            if (a_item == b_item):
+                return True
+            elif (a_item == '*') or (b_item == '*'):
+                return True
+
+    return False
+
 class Fail(Exception):
     def __init__(self, test, msg):
         self.msg = msg
@@ -82,34 +97,25 @@ class Event(dict):
         self.add(base)
         self.add(data)
 
-    def compare_data(self, a, b):
-        # Allow multiple values in assignment separated by '|'
-        a_list = a.split('|')
-        b_list = b.split('|')
-
-        for a_item in a_list:
-            for b_item in b_list:
-                if (a_item == b_item):
-                    return True
-                elif (a_item == '*') or (b_item == '*'):
-                    return True
-
-        return False
-
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
             if not self.has_key(t) or not other.has_key(t):
                 return False
-            if not self.compare_data(self[t], other[t]):
+            if not data_equal(self[t], other[t]):
                 return False
         return True
 
+    def optional(self):
+        if self.has_key('optional') and self['optional'] == '1':
+            return True
+        return False
+
     def diff(self, other):
         for t in Event.terms:
             if not self.has_key(t) or not other.has_key(t):
                 continue
-            if not self.compare_data(self[t], other[t]):
+            if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
 
 # Test file description needs to have following sections:
@@ -218,9 +224,9 @@ class Test(object):
               self.perf, self.command, tempdir, self.args)
         ret = os.WEXITSTATUS(os.system(cmd))
 
-        log.info("  '%s' ret %d " % (cmd, ret))
+        log.info("  '%s' ret '%s', expected '%s'" % (cmd, str(ret), str(self.ret)))
 
-        if ret != int(self.ret):
+        if not data_equal(str(ret), str(self.ret)):
             raise Unsup(self)
 
     def compare(self, expect, result):
@@ -232,6 +238,7 @@ class Test(object):
         # events in result. Fail if there's not any.
         for exp_name, exp_event in expect.items():
             exp_list = []
+            res_event = {}
             log.debug("    matching [%s]" % exp_name)
             for res_name, res_event in result.items():
                 log.debug("      to [%s]" % res_name)
@@ -244,9 +251,15 @@ class Test(object):
             log.debug("    match: [%s] matches %s" % (exp_name, str(exp_list)))
 
             # we did not any matching event - fail
-            if (not exp_list):
-                exp_event.diff(res_event)
-                raise Fail(self, 'match failure');
+            if not exp_list:
+                if exp_event.optional():
+                    log.debug("    %s does not match, but is optional" % exp_name)
+                else:
+                    if not res_event:
+                        log.debug("    res_event is empty");
+                    else:
+                        exp_event.diff(res_event)
+                    raise Fail(self, 'match failure');
 
             match[exp_name] = exp_list
 
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 7e6d74946e04..37940665f736 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -7,7 +7,7 @@ cpu=*
 type=0|1
 size=112
 config=0
-sample_period=4000
+sample_period=*
 sample_type=263
 read_format=0
 disabled=1
@@ -15,7 +15,7 @@ inherit=1
 pinned=0
 exclusive=0
 exclude_user=0
-exclude_kernel=0
+exclude_kernel=0|1
 exclude_hv=0
 exclude_idle=0
 mmap=1
@@ -23,9 +23,9 @@ comm=1
 freq=1
 inherit_stat=0
 enable_on_exec=1
-task=0
+task=1
 watermark=0
-precise_ip=0
+precise_ip=0|1|2|3
 mmap_data=0
 sample_id_all=1
 exclude_host=0|1
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index f4cf148f14cb..4d0c2e42b64e 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -8,14 +8,14 @@ type=0
 size=112
 config=0
 sample_period=0
-sample_type=0
+sample_type=65536
 read_format=3
 disabled=1
 inherit=1
 pinned=0
 exclusive=0
 exclude_user=0
-exclude_kernel=0
+exclude_kernel=0|1
 exclude_hv=0
 exclude_idle=0
 mmap=0
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
index d6a7e43f61b3..cb0a3138fa54 100644
--- a/tools/perf/tests/attr/test-record-C0
+++ b/tools/perf/tests/attr/test-record-C0
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -C 0 kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 cpu=0
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic
index 55c0428370ca..85a23cf35ba1 100644
--- a/tools/perf/tests/attr/test-record-basic
+++ b/tools/perf/tests/attr/test-record-basic
@@ -1,5 +1,6 @@
 [config]
 command = record
 args    = kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any
index 1421960ed4e9..81f839e2fad0 100644
--- a/tools/perf/tests/attr/test-record-branch-any
+++ b/tools/perf/tests/attr/test-record-branch-any
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -b kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any
index 915c4df0e0c2..357421f4dfce 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any
+++ b/tools/perf/tests/attr/test-record-branch-filter-any
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j any kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call
index 8708dbd4f373..dbc55f2ab845 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any_call
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_call
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j any_call kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=16
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret
index 0d3607a6dcbe..a0824ff8e131 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any_ret
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j any_ret kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=32
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv
index f25526740cec..f34d6f120181 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-hv
+++ b/tools/perf/tests/attr/test-record-branch-filter-hv
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j hv kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call
index e862dd179128..b86a35232248 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-ind_call
+++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j ind_call kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=64
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k
index 182971e898f5..d3fbc5e1858a 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-k
+++ b/tools/perf/tests/attr/test-record-branch-filter-k
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j k kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u
index 83449ef9e687..a318f0dda173 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-u
+++ b/tools/perf/tests/attr/test-record-branch-filter-u
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j u kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count
index 2f841de56f6b..34f6cc577263 100644
--- a/tools/perf/tests/attr/test-record-count
+++ b/tools/perf/tests/attr/test-record-count
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -c 123 kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=123
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
index 716e143b5291..a9cf2233b0ce 100644
--- a/tools/perf/tests/attr/test-record-data
+++ b/tools/perf/tests/attr/test-record-data
@@ -1,10 +1,9 @@
 [config]
 command = record
 args    = -d kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
-
 # sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
 # PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC
 sample_type=33039
diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq
index 600d0f8f2583..bf4cb459f0d5 100644
--- a/tools/perf/tests/attr/test-record-freq
+++ b/tools/perf/tests/attr/test-record-freq
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -F 100 kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=100
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
index 853597a9a8f6..0b216e69760c 100644
--- a/tools/perf/tests/attr/test-record-graph-default
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -g kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf
index d6f324ea578c..da2fa73bd0a2 100644
--- a/tools/perf/tests/attr/test-record-graph-dwarf
+++ b/tools/perf/tests/attr/test-record-graph-dwarf
@@ -1,10 +1,12 @@
 [config]
 command = record
 args    = --call-graph dwarf -- kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_type=12583
+sample_type=45359
 exclude_callchain_user=1
 sample_stack_user=8192
 # TODO different for each arch, no support for that now
 sample_regs_user=*
+mmap_data=1
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
index 055e3bee7993..625d190bb798 100644
--- a/tools/perf/tests/attr/test-record-graph-fp
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = --call-graph fp kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_type=295
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index 57739cacdb2a..618ba1c17474 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = --group -e cycles,instructions kill >/dev/null 2>&1
+ret     = 1
 
 [event-1:base-record]
 fd=1
@@ -16,5 +17,6 @@ sample_type=327
 read_format=4
 mmap=0
 comm=0
+task=0
 enable_on_exec=0
 disabled=0
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 658f5d60c873..f906b793196f 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret     = 1
 
 [event-1:base-record]
 fd=1
@@ -22,7 +23,7 @@ sample_type=343
 
 # PERF_FORMAT_ID | PERF_FORMAT_GROUP
 read_format=12
-
+task=0
 mmap=0
 comm=0
 enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index c5548d054aff..48e8bd12fe46 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+ret     = 1
 
 [event-1:base-record]
 fd=1
@@ -17,5 +18,6 @@ sample_type=327
 read_format=4
 mmap=0
 comm=0
+task=0
 enable_on_exec=0
 disabled=0
diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-buffering
index f253b78cdbf2..aa3956d8fe20 100644
--- a/tools/perf/tests/attr/test-record-no-delay
+++ b/tools/perf/tests/attr/test-record-no-buffering
@@ -1,9 +1,9 @@
 [config]
 command = record
-args    = -D kill >/dev/null 2>&1
+args    = --no-buffering kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=263
 watermark=0
 wakeup_events=1
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 44edcb2edcd5..560943decb87 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -i kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_type=263
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples
index d0141b2418b5..8eb73ab639e0 100644
--- a/tools/perf/tests/attr/test-record-no-samples
+++ b/tools/perf/tests/attr/test-record-no-samples
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -n kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=0
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period
index 8abc5314fc52..69bc748f0f27 100644
--- a/tools/perf/tests/attr/test-record-period
+++ b/tools/perf/tests/attr/test-record-period
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -c 100 -P kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=100
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw
index 4a8ef25b5f49..a188a614a44c 100644
--- a/tools/perf/tests/attr/test-record-raw
+++ b/tools/perf/tests/attr/test-record-raw
@@ -1,7 +1,7 @@
 [config]
 command = record
 args    = -R kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=1415
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0
index aa835950751f..a2c76d10b2bb 100644
--- a/tools/perf/tests/attr/test-stat-C0
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -4,6 +4,7 @@ args    = -e cycles -C 0 kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-stat]
-# events are enabled by default when attached to cpu
-disabled=0
+# events are disabled by default when attached to cpu
+disabled=1
 enable_on_exec=0
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/attr/test-stat-basic
index 74e17881f2ba..69867d049fda 100644
--- a/tools/perf/tests/attr/test-stat-basic
+++ b/tools/perf/tests/attr/test-stat-basic
@@ -4,3 +4,4 @@ args    = -e cycles kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-stat]
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
index 19270f54c96e..d9e99b3f77e6 100644
--- a/tools/perf/tests/attr/test-stat-default
+++ b/tools/perf/tests/attr/test-stat-default
@@ -32,33 +32,39 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
index 51426b87153b..8b04a055d154 100644
--- a/tools/perf/tests/attr/test-stat-detailed-1
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -33,36 +33,42 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -72,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -81,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -90,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -99,3 +108,4 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
index 8de5acc31c27..4fca9f1bfbf8 100644
--- a/tools/perf/tests/attr/test-stat-detailed-2
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -33,36 +33,42 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -72,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -81,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -90,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -99,6 +108,7 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -108,6 +118,7 @@ config=65538
 fd=15
 type=3
 config=1
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -117,6 +128,7 @@ config=1
 fd=16
 type=3
 config=65537
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -126,6 +138,7 @@ config=65537
 fd=17
 type=3
 config=3
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -135,6 +148,7 @@ config=3
 fd=18
 type=3
 config=65539
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -144,6 +158,7 @@ config=65539
 fd=19
 type=3
 config=4
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -153,3 +168,4 @@ config=4
 fd=20
 type=3
 config=65540
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
index 0a1f45bf7d79..4bb58e1c82a6 100644
--- a/tools/perf/tests/attr/test-stat-detailed-3
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -33,36 +33,42 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -72,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -81,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -90,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -99,6 +108,7 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -108,6 +118,7 @@ config=65538
 fd=15
 type=3
 config=1
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -117,6 +128,7 @@ config=1
 fd=16
 type=3
 config=65537
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -126,6 +138,7 @@ config=65537
 fd=17
 type=3
 config=3
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -135,6 +148,7 @@ config=3
 fd=18
 type=3
 config=65539
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -144,6 +158,7 @@ config=65539
 fd=19
 type=3
 config=4
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -153,6 +168,7 @@ config=4
 fd=20
 type=3
 config=65540
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -162,6 +178,7 @@ config=65540
 fd=21
 type=3
 config=512
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -171,3 +188,4 @@ config=512
 fd=22
 type=3
 config=66048
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group
index fdc1596a8862..e15d6946e9b3 100644
--- a/tools/perf/tests/attr/test-stat-group
+++ b/tools/perf/tests/attr/test-stat-group
@@ -6,6 +6,7 @@ ret     = 1
 [event-1:base-stat]
 fd=1
 group_fd=-1
+read_format=3|15
 
 [event-2:base-stat]
 fd=2
@@ -13,3 +14,4 @@ group_fd=1
 config=1
 disabled=0
 enable_on_exec=0
+read_format=3|15
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1
index 2a1f86e4a904..1746751123dc 100644
--- a/tools/perf/tests/attr/test-stat-group1
+++ b/tools/perf/tests/attr/test-stat-group1
@@ -6,6 +6,7 @@ ret     = 1
 [event-1:base-stat]
 fd=1
 group_fd=-1
+read_format=3|15
 
 [event-2:base-stat]
 fd=2
@@ -13,3 +14,4 @@ group_fd=1
 config=1
 disabled=0
 enable_on_exec=0
+read_format=3|15
diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/attr/test-stat-no-inherit
index d54b2a1e3e28..924fbb9300d1 100644
--- a/tools/perf/tests/attr/test-stat-no-inherit
+++ b/tools/perf/tests/attr/test-stat-no-inherit
@@ -5,3 +5,4 @@ ret     = 1
 
 [event:base-stat]
 inherit=0
+optional=1
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 50f6d7afee58..71b9a0b613d2 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Test backward bit in event attribute, read ring buffer from end to
  * beginning
@@ -75,7 +76,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 }
 
 
-int test__backward_ring_buffer(int subtest __maybe_unused)
+int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0;
         char pid[16], sbuf[STRERR_BUFSIZE];
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 9abe6c13090f..47bedf25ba69 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/bitmap.h>
 #include "tests.h"
@@ -40,7 +41,7 @@ static int test_bitmap(const char *str)
         return ret;
 }
 
-int test__bitmap_print(int subtest __maybe_unused)
+int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         TEST_ASSERT_VAL("failed to convert map", test_bitmap("1"));
         TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5"));
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 39bbb97cd30a..335b695f4970 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Inspired by breakpoint overflow test done by
  * Vince Weaver <vincent.weaver@maine.edu> for perf_event_tests
@@ -164,7 +165,7 @@ static long long bp_count(int fd)
         return count;
 }
 
-int test__bp_signal(int subtest __maybe_unused)
+int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct sigaction sa;
         long long count1, count2, count3;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index 3b1ac6f31b15..ca962559e845 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Originally done by Vince Weaver <vincent.weaver@maine.edu> for
  * perf_event_tests (git://github.com/deater/perf_event_tests)
@@ -57,7 +58,7 @@ static long long bp_count(int fd)
 #define EXECUTIONS 10000
 #define THRESHOLD  100
 
-int test__bp_signal_overflow(int subtest __maybe_unused)
+int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_event_attr pe;
         struct sigaction sa;
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75e25ae..43f1e16486f4 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
         (void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
                          unsigned long offset, unsigned long orig)
 {
+        fmode_t f_mode = (fmode_t)_f_mode;
+
         if (err)
                 return 0;
         if (f_mode & FMODE_WRITE)
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 5876da126b58..34c22cdf4d5d 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -124,16 +124,16 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
         struct perf_evlist *evlist;
         int i, ret = TEST_FAIL, err = 0, count = 0;
 
-        struct parse_events_evlist parse_evlist;
+        struct parse_events_state parse_state;
         struct parse_events_error parse_error;
 
         bzero(&parse_error, sizeof(parse_error));
-        bzero(&parse_evlist, sizeof(parse_evlist));
-        parse_evlist.error = &parse_error;
-        INIT_LIST_HEAD(&parse_evlist.list);
+        bzero(&parse_state, sizeof(parse_state));
+        parse_state.error = &parse_error;
+        INIT_LIST_HEAD(&parse_state.list);
 
-        err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
-        if (err || list_empty(&parse_evlist.list)) {
+        err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL);
+        if (err || list_empty(&parse_state.list)) {
                 pr_debug("Failed to add events selected by BPF\n");
                 return TEST_FAIL;
         }
@@ -155,8 +155,8 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
                 goto out_delete_evlist;
         }
 
-        perf_evlist__splice_list_tail(evlist, &parse_evlist.list);
-        evlist->nr_groups = parse_evlist.nr_groups;
+        perf_evlist__splice_list_tail(evlist, &parse_state.list);
+        evlist->nr_groups = parse_state.nr_groups;
 
         perf_evlist__config(evlist, &opts, NULL);
 
@@ -321,7 +321,7 @@ static int check_env(void)
         return 0;
 }
 
-int test__bpf(int i)
+int test__bpf(struct test *test __maybe_unused, int i)
 {
         int err;
 
@@ -351,7 +351,7 @@ const char *test__bpf_subtest_get_desc(int i __maybe_unused)
         return NULL;
 }
 
-int test__bpf(int i __maybe_unused)
+int test__bpf(struct test *test __maybe_unused, int i __maybe_unused)
 {
         pr_debug("Skip BPF test because BPF support is not compiled\n");
         return TEST_SKIP;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 3ccfd58a8c3c..766573e236e4 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -1,12 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * builtin-test.c
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <fcntl.h>
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
+#include <sys/types.h>
+#include <dirent.h>
 #include <sys/wait.h>
+#include <sys/stat.h>
 #include "builtin.h"
 #include "hist.h"
 #include "intlist.h"
@@ -14,8 +19,10 @@
 #include "debug.h"
 #include "color.h"
 #include <subcmd/parse-options.h>
+#include "string2.h"
 #include "symbol.h"
 #include <linux/kernel.h>
+#include <subcmd/exec-cmd.h>
 
 static bool dont_fork;
 
@@ -43,6 +50,10 @@ static struct test generic_tests[] = {
                 .func = test__basic_mmap,
         },
         {
+                .desc = "Test data source output",
+                .func = test__mem,
+        },
+        {
                 .desc = "Parse event definition strings",
                 .func = test__parse_events,
         },
@@ -179,7 +190,7 @@ static struct test generic_tests[] = {
         },
         {
                 .desc = "Session topology",
-                .func = test_session_topology,
+                .func = test__session_topology,
         },
         {
                 .desc = "BPF filter",
@@ -325,7 +336,7 @@ static int run_test(struct test *test, int subtest)
                         }
                 }
 
-                err = test->func(subtest);
+                err = test->func(test, subtest);
                 if (!dont_fork)
                         exit(err);
         }
@@ -383,12 +394,143 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
         return err;
 }
 
+static const char *shell_test__description(char *description, size_t size,
+                                           const char *path, const char *name)
+{
+        FILE *fp;
+        char filename[PATH_MAX];
+
+        path__join(filename, sizeof(filename), path, name);
+        fp = fopen(filename, "r");
+        if (!fp)
+                return NULL;
+
+        description = fgets(description, size, fp);
+        fclose(fp);
+
+        return description ? trim(description + 1) : NULL;
+}
+
+#define for_each_shell_test(dir, ent)           \
+        while ((ent = readdir(dir)) != NULL)    \
+                if (ent->d_type == DT_REG && ent->d_name[0] != '.')
+
+static const char *shell_tests__dir(char *path, size_t size)
+{
+        const char *devel_dirs[] = { "./tools/perf/tests", "./tests", };
+        char *exec_path;
+        unsigned int i;
+
+        for (i = 0; i < ARRAY_SIZE(devel_dirs); ++i) {
+                struct stat st;
+                if (!lstat(devel_dirs[i], &st)) {
+                        scnprintf(path, size, "%s/shell", devel_dirs[i]);
+                        if (!lstat(devel_dirs[i], &st))
+                                return path;
+                }
+        }
+
+        /* Then installed path. */
+        exec_path = get_argv_exec_path();
+        scnprintf(path, size, "%s/tests/shell", exec_path);
+        free(exec_path);
+        return path;
+}
+
+static int shell_tests__max_desc_width(void)
+{
+        DIR *dir;
+        struct dirent *ent;
+        char path_dir[PATH_MAX];
+        const char *path = shell_tests__dir(path_dir, sizeof(path_dir));
+        int width = 0;
+
+        if (path == NULL)
+                return -1;
+
+        dir = opendir(path);
+        if (!dir)
+                return -1;
+
+        for_each_shell_test(dir, ent) {
+                char bf[256];
+                const char *desc = shell_test__description(bf, sizeof(bf), path, ent->d_name);
+
+                if (desc) {
+                        int len = strlen(desc);
+
+                        if (width < len)
+                                width = len;
+                }
+        }
+
+        closedir(dir);
+        return width;
+}
+
+struct shell_test {
+        const char *dir;
+        const char *file;
+};
+
+static int shell_test__run(struct test *test, int subdir __maybe_unused)
+{
+        int err;
+        char script[PATH_MAX];
+        struct shell_test *st = test->priv;
+
+        path__join(script, sizeof(script), st->dir, st->file);
+
+        err = system(script);
+        if (!err)
+                return TEST_OK;
+
+        return WEXITSTATUS(err) == 2 ? TEST_SKIP : TEST_FAIL;
+}
+
+static int run_shell_tests(int argc, const char *argv[], int i, int width)
+{
+        DIR *dir;
+        struct dirent *ent;
+        char path_dir[PATH_MAX];
+        struct shell_test st = {
+                .dir = shell_tests__dir(path_dir, sizeof(path_dir)),
+        };
+
+        if (st.dir == NULL)
+                return -1;
+
+        dir = opendir(st.dir);
+        if (!dir)
+                return -1;
+
+        for_each_shell_test(dir, ent) {
+                int curr = i++;
+                char desc[256];
+                struct test test = {
+                        .desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name),
+                        .func = shell_test__run,
+                        .priv = &st,
+                };
+
+                if (!perf_test__matches(&test, curr, argc, argv))
+                        continue;
+
+                st.file = ent->d_name;
+                pr_info("%2d: %-*s:", i, width, test.desc);
+                test_and_print(&test, false, -1);
+        }
+
+        closedir(dir);
+        return 0;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
         struct test *t;
         unsigned int j;
         int i = 0;
-        int width = 0;
+        int width = shell_tests__max_desc_width();
 
         for_each_test(j, t) {
                 int len = strlen(t->desc);
@@ -455,6 +597,37 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
                 }
         }
 
+        return run_shell_tests(argc, argv, i, width);
+}
+
+static int perf_test__list_shell(int argc, const char **argv, int i)
+{
+        DIR *dir;
+        struct dirent *ent;
+        char path_dir[PATH_MAX];
+        const char *path = shell_tests__dir(path_dir, sizeof(path_dir));
+
+        if (path == NULL)
+                return -1;
+
+        dir = opendir(path);
+        if (!dir)
+                return -1;
+
+        for_each_shell_test(dir, ent) {
+                int curr = i++;
+                char bf[256];
+                struct test t = {
+                        .desc = shell_test__description(bf, sizeof(bf), path, ent->d_name),
+                };
+
+                if (!perf_test__matches(&t, curr, argc, argv))
+                        continue;
+
+                pr_info("%2d: %s\n", i, t.desc);
+        }
+
+        closedir(dir);
         return 0;
 }
 
@@ -465,12 +638,17 @@ static int perf_test__list(int argc, const char **argv)
         int i = 0;
 
         for_each_test(j, t) {
-                if (argc > 1 && !strstr(t->desc, argv[1]))
+                int curr = i++;
+
+                if (!perf_test__matches(t, curr, argc, argv) ||
+                    (t->is_supported && !t->is_supported()))
                         continue;
 
-                pr_info("%2d: %s\n", ++i, t->desc);
+                pr_info("%2d: %s\n", i, t->desc);
         }
 
+        perf_test__list_shell(argc, argv, i);
+
         return 0;
 }
 
@@ -498,7 +676,7 @@ int cmd_test(int argc, const char **argv)
 
         argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
         if (argc >= 1 && !strcmp(argv[0], "list"))
-                return perf_test__list(argc, argv);
+                return perf_test__list(argc - 1, argv + 1);
 
         symbol_conf.priv_size = sizeof(int);
         symbol_conf.sort_by_name = true;
diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c
index c5bb2203f5a9..f45fe11dcf50 100644
--- a/tools/perf/tests/clang.c
+++ b/tools/perf/tests/clang.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "tests.h"
 #include "debug.h"
 #include "util.h"
@@ -33,12 +34,12 @@ const char *test__clang_subtest_get_desc(int i)
 }
 
 #ifndef HAVE_LIBCLANGLLVM_SUPPORT
-int test__clang(int i __maybe_unused)
+int test__clang(struct test *test __maybe_unused, int i __maybe_unused)
 {
         return TEST_SKIP;
 }
 #else
-int test__clang(int i)
+int test__clang(struct test *test __maybe_unused, int i)
 {
         if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table))
                 return TEST_FAIL;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 94b7c7b02bde..fcc8984bc329 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -237,6 +238,11 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
         thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
         if (!al.map || !al.map->dso) {
+                if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
+                        pr_debug("Hypervisor address can not be resolved - skipping\n");
+                        return 0;
+                }
+
                 pr_debug("thread__find_addr_map failed\n");
                 return -1;
         }
@@ -673,7 +679,7 @@ out_err:
         return err;
 }
 
-int test__code_reading(int subtest __maybe_unused)
+int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret;
 
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 4478773cdb97..e78b897677bd 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "tests.h"
 #include <stdio.h>
 #include "cpumap.h"
@@ -72,7 +73,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 }
 
 
-int test__cpu_map_synthesize(int subtest __maybe_unused)
+int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct cpu_map *cpus;
 
@@ -106,7 +107,7 @@ static int cpu_map_print(const char *str)
         return !strcmp(buf, str);
 }
 
-int test__cpu_map_print(int subtest __maybe_unused)
+int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1"));
         TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5"));
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 8f08df5861cb..7f6c52021e41 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <stdlib.h>
 #include <linux/kernel.h>
@@ -112,7 +113,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine)
         return fd;
 }
 
-int test__dso_data(int subtest __maybe_unused)
+int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine machine;
         struct dso *dso;
@@ -247,7 +248,7 @@ static int set_fd_limit(int n)
         return setrlimit(RLIMIT_NOFILE, &rlim);
 }
 
-int test__dso_data_cache(int subtest __maybe_unused)
+int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine machine;
         long nr_end, nr = open_files_cnt();
@@ -307,7 +308,7 @@ int test__dso_data_cache(int subtest __maybe_unused)
         return 0;
 }
 
-int test__dso_data_reopen(int subtest __maybe_unused)
+int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine machine;
         long nr_end, nr = open_files_cnt();
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 3e56d08f7995..ac40e05bcab4 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <inttypes.h>
@@ -6,7 +7,7 @@
 #include "debug.h"
 #include "machine.h"
 #include "event.h"
-#include "unwind.h"
+#include "../util/unwind.h"
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
@@ -154,7 +155,7 @@ static noinline int krava_1(struct thread *thread)
         return krava_2(thread);
 }
 
-int test__dwarf_unwind(int subtest __maybe_unused)
+int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine *machine;
         struct thread *thread;
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 634f20c631d8..1a2686f1fcf0 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <errno.h>
 #include <inttypes.h>
@@ -213,7 +214,7 @@ out_err:
  * and checks that enabled and running times
  * match.
  */
-int test__event_times(int subtest __maybe_unused)
+int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err, ret = 0;
 
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index 63ecf21750eb..f14dcd613438 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include "evlist.h"
 #include "evsel.h"
@@ -76,7 +77,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__event_update(int subtest __maybe_unused)
+int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_evlist *evlist;
         struct perf_evsel *evsel;
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index d2bea6f780f8..a104728ebf25 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "evlist.h"
 #include "evsel.h"
 #include "parse-events.h"
@@ -97,7 +98,7 @@ out_delete_evlist:
 #define perf_evsel__name_array_test(names) \
         __perf_evsel__name_array_test(names, ARRAY_SIZE(names))
 
-int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused)
+int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = 0, ret = 0;
 
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 1984b3bbfe15..699561fa512c 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/err.h>
 #include <traceevent/event-parse.h>
 #include "evsel.h"
@@ -32,7 +33,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
         return ret;
 }
 
-int test__perf_evsel__tp_sched_test(int subtest __maybe_unused)
+int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
         int ret = 0;
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 6c6a3749aaf6..01f0706995a9 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util/debug.h"
 #include "util/expr.h"
 #include "tests.h"
@@ -13,7 +14,7 @@ static int test(struct parse_ctx *ctx, const char *e, double val2)
         return 0;
 }
 
-int test__expr(int subtest __maybe_unused)
+int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
         const char *p;
         const char **other;
@@ -31,6 +32,11 @@ int test__expr(int subtest __maybe_unused)
         ret |= test(&ctx, "(BAR/2)%2", 1);
         ret |= test(&ctx, "1 - -4",  5);
         ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4",  5);
+        ret |= test(&ctx, "1-1 | 1", 1);
+        ret |= test(&ctx, "1-1 & 1", 0);
+        ret |= test(&ctx, "min(1,2) + 1", 2);
+        ret |= test(&ctx, "max(1,2) + 1", 3);
+        ret |= test(&ctx, "1+1 if 3*4 else 0", 2);
 
         if (ret)
                 return ret;
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index bc5982f42dc3..c7c81c4a5b2b 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <api/fd/array.h>
 #include <poll.h>
 #include "util/debug.h"
@@ -26,7 +27,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
         return printed + fdarray__fprintf(fda, fp);
 }
 
-int test__fdarray__filter(int subtest __maybe_unused)
+int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
         struct fdarray *fda = fdarray__new(5, 5);
@@ -104,7 +105,7 @@ out:
         return err;
 }
 
-int test__fdarray__add(int subtest __maybe_unused)
+int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct fdarray *fda = fdarray__new(2, 2);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index 00b8dc50f3db..f7c5b613d667 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include "perf.h"
 #include "util/debug.h"
diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h
index 888254e8665c..a2de0ff0ce3a 100644
--- a/tools/perf/tests/hists_common.h
+++ b/tools/perf/tests/hists_common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_TESTS__HISTS_COMMON_H__
 #define __PERF_TESTS__HISTS_COMMON_H__
 
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index d549a9f2c41b..65fe02bebbee 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "util/debug.h"
 #include "util/event.h"
@@ -687,7 +688,7 @@ out:
         return err;
 }
 
-int test__hists_cumulate(int subtest __maybe_unused)
+int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index df9c91f49af1..1c5bedab3c2c 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "util/debug.h"
 #include "util/symbol.h"
@@ -101,7 +102,7 @@ out:
         return TEST_FAIL;
 }
 
-int test__hists_filter(int subtest __maybe_unused)
+int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index a26cbb79e988..9a9d06cb0222 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "tests.h"
 #include "debug.h"
@@ -264,7 +265,7 @@ static int validate_link(struct hists *leader, struct hists *other)
         return __validate_link(leader, 0) || __validate_link(other, 1);
 }
 
-int test__hists_link(int subtest __maybe_unused)
+int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         struct hists *hists, *first_hists;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 06e5080182d3..faacb4f41460 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "util/debug.h"
 #include "util/event.h"
@@ -573,7 +574,7 @@ out:
         return err;
 }
 
-int test__hists_output(int subtest __maybe_unused)
+int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
index a5192f6a20d7..9c7b3baca4fe 100644
--- a/tools/perf/tests/is_printable_array.c
+++ b/tools/perf/tests/is_printable_array.c
@@ -1,10 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include "tests.h"
 #include "debug.h"
 #include "print_binary.h"
 
-int test__is_printable_array(int subtest __maybe_unused)
+int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
         char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 614e45a3c603..842d33637a18 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <unistd.h>
 #include <sys/prctl.h>
@@ -49,7 +50,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
  * when an event is disabled but a dummy software event is not disabled.  If the
  * test passes %0 is returned, otherwise %-1 is returned.
  */
-int test__keep_tracking(int subtest __maybe_unused)
+int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 6cd9e5107f77..8e57d46109de 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <stdlib.h>
 #include "tests.h"
@@ -50,7 +51,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect)
 #define M(path, c, e) \
         TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
 
-int test__kmod_path__parse(int subtest __maybe_unused)
+int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
         /* path                alloc_name  alloc_ext   kmod  comp   name     ext */
         T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 482b5365e68d..a039f93199e5 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <bpf/libbpf.h>
 #include <util/llvm-utils.h>
@@ -132,7 +133,7 @@ out:
         return ret;
 }
 
-int test__llvm(int subtest)
+int test__llvm(struct test *test __maybe_unused, int subtest)
 {
         int ret;
         void *obj_buf = NULL;
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index b83571758d83..f68b0d9b8ae2 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_TEST_LLVM_H
 #define PERF_TEST_LLVM_H
 
diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c
new file mode 100644
index 000000000000..21952e1e6e6d
--- /dev/null
+++ b/tools/perf/tests/mem.c
@@ -0,0 +1,56 @@
+#include "util/mem-events.h"
+#include "util/symbol.h"
+#include "linux/perf_event.h"
+#include "util/debug.h"
+#include "tests.h"
+#include <string.h>
+
+static int check(union perf_mem_data_src data_src,
+                  const char *string)
+{
+        char out[100];
+        char failure[100];
+        struct mem_info mi = { .data_src = data_src };
+
+        int n;
+
+        n = perf_mem__snp_scnprintf(out, sizeof out, &mi);
+        n += perf_mem__lvl_scnprintf(out + n, sizeof out - n, &mi);
+        snprintf(failure, sizeof failure, "unexpected %s", out);
+        TEST_ASSERT_VAL(failure, !strcmp(string, out));
+        return 0;
+}
+
+int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused)
+{
+        int ret = 0;
+        union perf_mem_data_src src;
+
+        memset(&src, 0, sizeof(src));
+
+        src.mem_lvl = PERF_MEM_LVL_HIT;
+        src.mem_lvl_num = 4;
+
+        ret |= check(src, "N/AL4 hit");
+
+        src.mem_remote = 1;
+
+        ret |= check(src, "N/ARemote L4 hit");
+
+        src.mem_lvl = PERF_MEM_LVL_MISS;
+        src.mem_lvl_num = PERF_MEM_LVLNUM_PMEM;
+        src.mem_remote = 0;
+
+        ret |= check(src, "N/APMEM miss");
+
+        src.mem_remote = 1;
+
+        ret |= check(src, "N/ARemote PMEM miss");
+
+        src.mem_snoopx = PERF_MEM_SNOOPX_FWD;
+        src.mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+
+        ret |= check(src , "FwdRemote RAM miss");
+
+        return ret;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 15c770856aac..5a8bf318f8a7 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 /* For the CLR_() macros */
@@ -22,7 +23,7 @@
  * Then it checks if the number of syscalls reported as perf events by
  * the kernel corresponds to the number of syscalls made.
  */
-int test__basic_mmap(int subtest __maybe_unused)
+int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         union perf_event *event;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 6ea4d8a5d26b..868d82b501f4 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <unistd.h>
 #include <sys/syscall.h>
@@ -131,7 +132,7 @@ static int synth_all(struct machine *machine)
 {
         return perf_event__synthesize_threads(NULL,
                                               perf_event__process,
-                                              machine, 0, 500);
+                                              machine, 0, 500, 1);
 }
 
 static int synth_process(struct machine *machine)
@@ -221,7 +222,7 @@ static int mmap_events(synth_cb synth)
  *
  * by using all thread objects.
  */
-int test__mmap_thread_lookup(int subtest __maybe_unused)
+int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         /* perf_event__synthesize_threads synthesize */
         TEST_ASSERT_VAL("failed with sythesizing all",
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 1a74dd9fd067..c531e6deb104 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 /* For the CPU_* macros */
@@ -16,7 +17,7 @@
 #include "debug.h"
 #include "stat.h"
 
-int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
+int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1, fd, cpu;
         struct cpu_map *cpus;
@@ -115,7 +116,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 
         perf_evsel__free_counts(evsel);
 out_close_fd:
-        perf_evsel__close_fd(evsel, 1, threads->nr);
+        perf_evsel__close_fd(evsel);
 out_evsel_delete:
         perf_evsel__delete(evsel);
 out_thread_map_delete:
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 9788fac91095..d9619d265314 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/err.h>
 #include "perf.h"
 #include "evlist.h"
@@ -14,7 +15,7 @@
 #define AT_FDCWD       -100
 #endif
 
-int test__syscall_openat_tp_fields(int subtest __maybe_unused)
+int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .target = {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index e44506e21ee7..00cd63f90b92 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <api/fs/tracing_path.h>
@@ -10,7 +11,7 @@
 #include "debug.h"
 #include "tests.h"
 
-int test__openat_syscall_event(int subtest __maybe_unused)
+int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1, fd;
         struct perf_evsel *evsel;
@@ -56,7 +57,7 @@ int test__openat_syscall_event(int subtest __maybe_unused)
 
         err = 0;
 out_close_fd:
-        perf_evsel__close_fd(evsel, 1, threads->nr);
+        perf_evsel__close_fd(evsel);
 out_evsel_delete:
         perf_evsel__delete(evsel);
 out_thread_map_delete:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 812a053d1941..f0679613bd18 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "parse-events.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -1810,7 +1811,7 @@ static int test_pmu_events(void)
         return ret;
 }
 
-int test__parse_events(int subtest __maybe_unused)
+int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret1, ret2 = 0;
 
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index c6207db09f12..2196d1497c0c 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <stddef.h>
@@ -68,7 +69,7 @@ struct test_attr_event {
  *
  * Return: %0 on success, %-1 if the test fails.
  */
-int test__parse_no_sample_id_all(int subtest __maybe_unused)
+int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err;
 
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index 665ecc19671c..a693bcf017ea 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <signal.h>
 #include <stdlib.h>
 
@@ -27,7 +28,7 @@ static void the_hook(void *_hook_flags)
         *p = 0;
 }
 
-int test__perf_hooks(int subtest __maybe_unused)
+int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int hook_flags = 0;
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index d37cd9588cc0..c34904d37705 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 /* For the CLR_() macros */
@@ -37,7 +38,7 @@ realloc:
         return cpu;
 }
 
-int test__PERF_RECORD(int subtest __maybe_unused)
+int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .target = {
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
index f2d9c5fe58e0..fae26b1cf08f 100755
--- a/tools/perf/tests/perf-targz-src-pkg
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Test one of the main kernel Makefile targets to generate a perf sources tarball
 # suitable for build outside the full kernel sources.
 #
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index a6d7aef30030..9abca267afa9 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "parse-events.h"
 #include "pmu.h"
 #include "util.h"
@@ -135,7 +136,7 @@ static struct list_head *test_terms_list(void)
         return &terms;
 }
 
-int test__pmu(int subtest __maybe_unused)
+int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char *format = test_format_dir_get();
         LIST_HEAD(formats);
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index fa79509da535..5d2df65ada6a 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Just test if we can load the python binding.
  */
@@ -9,7 +10,7 @@
 
 extern int verbose;
 
-int test__python_use(int subtest __maybe_unused)
+int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char *cmd;
         int ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index bac5c3885b3b..3ec6302b6498 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
@@ -141,6 +142,9 @@ static bool samples_same(const struct perf_sample *s1,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR)
+                COMP(phys_addr);
+
         return true;
 }
 
@@ -206,6 +210,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
                         .mask   = sample_regs,
                         .regs   = regs,
                 },
+                .phys_addr      = 113,
         };
         struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
         struct perf_sample sample_out;
@@ -292,7 +297,7 @@ out_free:
  * checks sample format bits separately and together.  If the test passes %0 is
  * returned, otherwise %-1 is returned.
  */
-int test__sample_parsing(int subtest __maybe_unused)
+int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
         u64 sample_type;
@@ -305,7 +310,7 @@ int test__sample_parsing(int subtest __maybe_unused)
          * were added.  Please actually update the test rather than just change
          * the condition below.
          */
-        if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
+        if (PERF_SAMPLE_MAX > PERF_SAMPLE_PHYS_ADDR << 1) {
                 pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
                 return -1;
         }
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index 06eda675ae2c..5059452d27dd 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdio.h>
 #include <sys/epoll.h>
@@ -33,7 +34,7 @@ static int build_id_cache__add_file(const char *filename)
         }
 
         build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-        err = build_id_cache__add_s(sbuild_id, filename, false, false);
+        err = build_id_cache__add_s(sbuild_id, filename, NULL, false, false);
         if (err < 0)
                 pr_debug("Failed to add build id cache of %s\n", filename);
         return err;
@@ -54,7 +55,7 @@ static char *get_self_path(void)
 static int search_cached_probe(const char *target,
                                const char *group, const char *event)
 {
-        struct probe_cache *cache = probe_cache__new(target);
+        struct probe_cache *cache = probe_cache__new(target, NULL);
         int ret = 0;
 
         if (!cache) {
@@ -71,7 +72,7 @@ static int search_cached_probe(const char *target,
         return ret;
 }
 
-int test__sdt_event(int subtests __maybe_unused)
+int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
 {
         int ret = TEST_FAIL;
         char __tempdir[] = "./test-buildid-XXXXXX";
@@ -83,6 +84,8 @@ int test__sdt_event(int subtests __maybe_unused)
         }
         /* Note that buildid_dir must be an absolute path */
         tempdir = realpath(__tempdir, NULL);
+        if (tempdir == NULL)
+                goto error_rmdir;
 
         /* At first, scan itself */
         set_buildid_dir(tempdir);
@@ -100,14 +103,14 @@ int test__sdt_event(int subtests __maybe_unused)
 
 error_rmdir:
         /* Cleanup temporary buildid dir */
-        rm_rf(tempdir);
+        rm_rf(__tempdir);
 error:
         free(tempdir);
         free(myself);
         return ret;
 }
 #else
-int test__sdt_event(int subtests __maybe_unused)
+int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
 {
         pr_debug("Skip SDT event test because SDT support is not compiled\n");
         return TEST_SKIP;
diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh
new file mode 100644
index 000000000000..6293cc660947
--- /dev/null
+++ b/tools/perf/tests/shell/lib/probe.sh
@@ -0,0 +1,6 @@
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+skip_if_no_perf_probe() {
+        perf probe 2>&1 | grep -q 'is not a perf-command' && return 2
+        return 0
+}
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
new file mode 100644
index 000000000000..30a950c9d407
--- /dev/null
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -0,0 +1,23 @@
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+perf probe -l 2>&1 | grep -q probe:vfs_getname
+had_vfs_getname=$?
+
+cleanup_probe_vfs_getname() {
+        if [ $had_vfs_getname -eq 1 ] ; then
+                perf probe -q -d probe:vfs_getname
+        fi
+}
+
+add_probe_vfs_getname() {
+        local verbose=$1
+        if [ $had_vfs_getname -eq 1 ] ; then
+                line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
+                perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string"
+        fi
+}
+
+skip_if_no_debuginfo() {
+        add_probe_vfs_getname -v 2>&1 | egrep -q "^(Failed to find the path for kernel|Debuginfo-analysis is not supported)" && return 2
+        return 1
+}
diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
new file mode 100755
index 000000000000..9b7635184dc2
--- /dev/null
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
@@ -0,0 +1,14 @@
+# Add vfs_getname probe to get syscall args filenames
+#
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
new file mode 100755
index 000000000000..ba29535b8580
--- /dev/null
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
@@ -0,0 +1,41 @@
+# Use vfs_getname probe to get syscall args filenames
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf record' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname probe in the generated
+# perf.data file, with the temp file name as the pathname argument.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+record_open_file() {
+        echo "Recording open file:"
+        perf record -o ${perfdata} -e probe:vfs_getname touch $file
+}
+
+perf_script_filenames() {
+        echo "Looking at perf.data file for vfs_getname records for the file we touched:"
+        perf script -i ${perfdata} | \
+        egrep " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname: +\([[:xdigit:]]+\) +pathname=\"${file}\""
+}
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+        exit $err
+fi
+
+record_open_file && perf_script_filenames
+err=$?
+rm -f ${perfdata}
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
new file mode 100755
index 000000000000..7a84d73324e3
--- /dev/null
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -0,0 +1,46 @@
+# probe libc's inet_pton & backtrace it with ping
+
+# Installs a probe on libc's inet_pton function, that will use uprobes,
+# then use 'perf trace' on a ping to localhost asking for just one packet
+# with the a backtrace 3 levels deep, check that it is what we expect.
+# This needs no debuginfo package, all is done using the libc ELF symtab
+# and the CFI info in the binaries.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+ld=$(realpath /lib64/ld*.so.* | uniq)
+libc=$(echo $ld | sed 's/ld/libc/g')
+
+trace_libc_inet_pton_backtrace() {
+        idx=0
+        expected[0]="PING.*bytes"
+        expected[1]="64 bytes from ::1.*"
+        expected[2]=".*ping statistics.*"
+        expected[3]=".*packets transmitted.*"
+        expected[4]="rtt min.*"
+        expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
+        expected[6]=".*inet_pton[[:space:]]\($libc\)$"
+        expected[7]="getaddrinfo[[:space:]]\($libc\)$"
+        expected[8]=".*\(.*/bin/ping.*\)$"
+
+        perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+                echo $line
+                echo "$line" | egrep -q "${expected[$idx]}"
+                if [ $? -ne 0 ] ; then
+                        printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+                        exit 1
+                fi
+                let idx+=1
+                [ $idx -eq 9 ] && break
+        done
+}
+
+skip_if_no_perf_probe && \
+perf probe -q $libc inet_pton && \
+trace_libc_inet_pton_backtrace
+err=$?
+rm -f ${file}
+perf probe -q -d probe_libc:inet_pton
+exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
new file mode 100755
index 000000000000..2e68c5f120da
--- /dev/null
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -0,0 +1,35 @@
+# Check open filename arg using perf trace + vfs_getname
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf trace' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname was used by 'perf trace',
+# that already handles "probe:vfs_getname" if present, and used in the
+# "open" syscall "filename" argument beautifier.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+trace_open_vfs_getname() {
+        perf trace -e open touch $file 2>&1 | \
+        egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+}
+
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+        exit $err
+fi
+
+trace_open_vfs_getname
+err=$?
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index 6a20ff2326bb..94250024684a 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include "event.h"
 #include "tests.h"
@@ -45,7 +46,7 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__synthesize_stat_config(int subtest __maybe_unused)
+int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_stat_config stat_config = {
                 .aggr_mode      = AGGR_CORE,
@@ -75,7 +76,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__synthesize_stat(int subtest __maybe_unused)
+int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_counts_values count;
 
@@ -101,7 +102,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__synthesize_stat_round(int subtest __maybe_unused)
+int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         TEST_ASSERT_VAL("failed to synthesize stat_config",
                 !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 828494db4a19..725a196991a8 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <unistd.h>
@@ -124,7 +125,7 @@ out_delete_evlist:
         return err;
 }
 
-int test__sw_clock_freq(int subtest __maybe_unused)
+int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret;
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 65474fd80da7..7d3f4bf9534f 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/time.h>
 #include <sys/prctl.h>
 #include <errno.h>
@@ -306,7 +307,7 @@ out_free_nodes:
  * evsel->system_wide and evsel->tracking flags (respectively) with other events
  * sometimes enabled or disabled.
  */
-int test__switch_tracking(int subtest __maybe_unused)
+int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         const char *sched_switch = "sched:sched_switch";
         struct switch_tracking switch_tracking = { .tids = NULL, };
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index cf00ebad2ef5..bc4a7344e274 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
@@ -32,7 +33,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
  * if the number of exit event reported by the kernel is 1 or not
  * in order to check the kernel returns correct number of event.
  */
-int test__task_exit(int subtest __maybe_unused)
+int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         union perf_event *event;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 577363809c9b..2862b80bc288 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef TESTS_H
 #define TESTS_H
 
@@ -28,77 +29,79 @@ enum {
 
 struct test {
         const char *desc;
-        int (*func)(int subtest);
+        int (*func)(struct test *test, int subtest);
         struct {
                 bool skip_if_fail;
                 int (*get_nr)(void);
                 const char *(*get_desc)(int subtest);
         } subtest;
         bool (*is_supported)(void);
+        void *priv;
 };
 
 /* Tests */
-int test__vmlinux_matches_kallsyms(int subtest);
-int test__openat_syscall_event(int subtest);
-int test__openat_syscall_event_on_all_cpus(int subtest);
-int test__basic_mmap(int subtest);
-int test__PERF_RECORD(int subtest);
-int test__perf_evsel__roundtrip_name_test(int subtest);
-int test__perf_evsel__tp_sched_test(int subtest);
-int test__syscall_openat_tp_fields(int subtest);
-int test__pmu(int subtest);
-int test__attr(int subtest);
-int test__dso_data(int subtest);
-int test__dso_data_cache(int subtest);
-int test__dso_data_reopen(int subtest);
-int test__parse_events(int subtest);
-int test__hists_link(int subtest);
-int test__python_use(int subtest);
-int test__bp_signal(int subtest);
-int test__bp_signal_overflow(int subtest);
-int test__task_exit(int subtest);
-int test__sw_clock_freq(int subtest);
-int test__code_reading(int subtest);
-int test__sample_parsing(int subtest);
-int test__keep_tracking(int subtest);
-int test__parse_no_sample_id_all(int subtest);
-int test__dwarf_unwind(int subtest);
-int test__expr(int subtest);
-int test__hists_filter(int subtest);
-int test__mmap_thread_lookup(int subtest);
-int test__thread_mg_share(int subtest);
-int test__hists_output(int subtest);
-int test__hists_cumulate(int subtest);
-int test__switch_tracking(int subtest);
-int test__fdarray__filter(int subtest);
-int test__fdarray__add(int subtest);
-int test__kmod_path__parse(int subtest);
-int test__thread_map(int subtest);
-int test__llvm(int subtest);
+int test__vmlinux_matches_kallsyms(struct test *test, int subtest);
+int test__openat_syscall_event(struct test *test, int subtest);
+int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest);
+int test__basic_mmap(struct test *test, int subtest);
+int test__PERF_RECORD(struct test *test, int subtest);
+int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest);
+int test__perf_evsel__tp_sched_test(struct test *test, int subtest);
+int test__syscall_openat_tp_fields(struct test *test, int subtest);
+int test__pmu(struct test *test, int subtest);
+int test__attr(struct test *test, int subtest);
+int test__dso_data(struct test *test, int subtest);
+int test__dso_data_cache(struct test *test, int subtest);
+int test__dso_data_reopen(struct test *test, int subtest);
+int test__parse_events(struct test *test, int subtest);
+int test__hists_link(struct test *test, int subtest);
+int test__python_use(struct test *test, int subtest);
+int test__bp_signal(struct test *test, int subtest);
+int test__bp_signal_overflow(struct test *test, int subtest);
+int test__task_exit(struct test *test, int subtest);
+int test__mem(struct test *test, int subtest);
+int test__sw_clock_freq(struct test *test, int subtest);
+int test__code_reading(struct test *test, int subtest);
+int test__sample_parsing(struct test *test, int subtest);
+int test__keep_tracking(struct test *test, int subtest);
+int test__parse_no_sample_id_all(struct test *test, int subtest);
+int test__dwarf_unwind(struct test *test, int subtest);
+int test__expr(struct test *test, int subtest);
+int test__hists_filter(struct test *test, int subtest);
+int test__mmap_thread_lookup(struct test *test, int subtest);
+int test__thread_mg_share(struct test *test, int subtest);
+int test__hists_output(struct test *test, int subtest);
+int test__hists_cumulate(struct test *test, int subtest);
+int test__switch_tracking(struct test *test, int subtest);
+int test__fdarray__filter(struct test *test, int subtest);
+int test__fdarray__add(struct test *test, int subtest);
+int test__kmod_path__parse(struct test *test, int subtest);
+int test__thread_map(struct test *test, int subtest);
+int test__llvm(struct test *test, int subtest);
 const char *test__llvm_subtest_get_desc(int subtest);
 int test__llvm_subtest_get_nr(void);
-int test__bpf(int subtest);
+int test__bpf(struct test *test, int subtest);
 const char *test__bpf_subtest_get_desc(int subtest);
 int test__bpf_subtest_get_nr(void);
-int test_session_topology(int subtest);
-int test__thread_map_synthesize(int subtest);
-int test__thread_map_remove(int subtest);
-int test__cpu_map_synthesize(int subtest);
-int test__synthesize_stat_config(int subtest);
-int test__synthesize_stat(int subtest);
-int test__synthesize_stat_round(int subtest);
-int test__event_update(int subtest);
-int test__event_times(int subtest);
-int test__backward_ring_buffer(int subtest);
-int test__cpu_map_print(int subtest);
-int test__sdt_event(int subtest);
-int test__is_printable_array(int subtest);
-int test__bitmap_print(int subtest);
-int test__perf_hooks(int subtest);
-int test__clang(int subtest);
+int test__session_topology(struct test *test, int subtest);
+int test__thread_map_synthesize(struct test *test, int subtest);
+int test__thread_map_remove(struct test *test, int subtest);
+int test__cpu_map_synthesize(struct test *test, int subtest);
+int test__synthesize_stat_config(struct test *test, int subtest);
+int test__synthesize_stat(struct test *test, int subtest);
+int test__synthesize_stat_round(struct test *test, int subtest);
+int test__event_update(struct test *test, int subtest);
+int test__event_times(struct test *test, int subtest);
+int test__backward_ring_buffer(struct test *test, int subtest);
+int test__cpu_map_print(struct test *test, int subtest);
+int test__sdt_event(struct test *test, int subtest);
+int test__is_printable_array(struct test *test, int subtest);
+int test__bitmap_print(struct test *test, int subtest);
+int test__perf_hooks(struct test *test, int subtest);
+int test__clang(struct test *test, int subtest);
 const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
-int test__unit_number__scnprint(int subtest);
+int test__unit_number__scnprint(struct test *test, int subtest);
 
 bool test__bp_signal_is_supported(void);
 
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index a63d6945807b..dbcb6a19b375 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <sys/types.h>
 #include <unistd.h>
@@ -9,7 +10,7 @@
 #define NAME    (const char *) "perf"
 #define NAMEUL  (unsigned long) NAME
 
-int test__thread_map(int subtest __maybe_unused)
+int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct thread_map *map;
 
@@ -76,7 +77,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__thread_map_synthesize(int subtest __maybe_unused)
+int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct thread_map *threads;
 
@@ -95,7 +96,7 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
         return 0;
 }
 
-int test__thread_map_remove(int subtest __maybe_unused)
+int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct thread_map *threads;
         char *str;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 76686dd6f5ec..b1d1bbafe7ae 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -1,10 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "tests.h"
 #include "machine.h"
 #include "thread.h"
 #include "map.h"
 #include "debug.h"
 
-int test__thread_mg_share(int subtest __maybe_unused)
+int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machines machines;
         struct machine *machine;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 803f893550d6..17cb1bb3448c 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
@@ -29,12 +30,14 @@ static int get_temp(char *path)
 static int session_write_header(char *path)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = path,
-                .mode = PERF_DATA_MODE_WRITE,
+        struct perf_data data = {
+                .file      = {
+                        .path = path,
+                },
+                .mode      = PERF_DATA_MODE_WRITE,
         };
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         TEST_ASSERT_VAL("can't get session", session);
 
         session->evlist = perf_evlist__new_default();
@@ -46,7 +49,7 @@ static int session_write_header(char *path)
         session->header.data_size += DATA_SIZE;
 
         TEST_ASSERT_VAL("failed to write header",
-                        !perf_session__write_header(session, session->evlist, file.fd, true));
+                        !perf_session__write_header(session, session->evlist, data.file.fd, true));
 
         perf_session__delete(session);
 
@@ -56,13 +59,15 @@ static int session_write_header(char *path)
 static int check_cpu_topology(char *path, struct cpu_map *map)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = path,
-                .mode = PERF_DATA_MODE_READ,
+        struct perf_data data = {
+                .file      = {
+                        .path = path,
+                },
+                .mode      = PERF_DATA_MODE_READ,
         };
         int i;
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         TEST_ASSERT_VAL("can't get session", session);
 
         for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
@@ -86,7 +91,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
         return 0;
 }
 
-int test_session_topology(int subtest __maybe_unused)
+int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char path[PATH_MAX];
         struct cpu_map *map;
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
index 44589de084b8..2bb8cb0039c1 100644
--- a/tools/perf/tests/unit_number__scnprintf.c
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
@@ -5,7 +6,7 @@
 #include "units.h"
 #include "debug.h"
 
-int test__unit_number__scnprint(int subtest __maybe_unused)
+int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
         struct {
                 u64              n;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 8456175fc234..f6789fb029d6 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/rbtree.h>
 #include <inttypes.h>
@@ -11,7 +12,7 @@
 
 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
 
-int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
+int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         struct rb_node *nd;
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index be95ac6ce845..066bbf0f4a74 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -1 +1,9 @@
+libperf-y += clone.o
+libperf-y += fcntl.o
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
+libperf-y += ioctl.o
+endif
+libperf-y += kcmp.o
+libperf-y += pkey_alloc.o
+libperf-y += prctl.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index cf50be3f17a4..a6dfd04beaee 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -1,13 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_TRACE_BEAUTY_H
 #define _PERF_TRACE_BEAUTY_H
 
+#include <linux/kernel.h>
 #include <linux/types.h>
+#include <sys/types.h>
+
+struct strarray {
+        int         offset;
+        int         nr_entries;
+        const char **entries;
+};
+
+#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
+        .nr_entries = ARRAY_SIZE(array), \
+        .entries = array, \
+}
+
+#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
+        .offset     = off, \
+        .nr_entries = ARRAY_SIZE(array), \
+        .entries = array, \
+}
+
+size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
 
 struct trace;
 struct thread;
 
+size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
+
+/**
+ * @val: value of syscall argument being formatted
+ * @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @thread: tid state (maps, pid, tid, etc)
+ * @trace: 'perf trace' internals: all threads, etc
+ * @parm: private area, may be an strarray, for instance
+ * @idx: syscall arg idx (is this the first?)
+ * @mask: a syscall arg may mask another arg, see syscall_arg__scnprintf_futex_op
+ */
+
 struct syscall_arg {
         unsigned long val;
+        unsigned char *args;
         struct thread *thread;
         struct trace  *trace;
         void          *parm;
@@ -15,10 +50,68 @@ struct syscall_arg {
         u8            mask;
 };
 
+unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx);
+
+size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STRARRAYS syscall_arg__scnprintf_strarrays
+
+size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FD syscall_arg__scnprintf_fd
+
+size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_HEX syscall_arg__scnprintf_hex
+
+size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_INT syscall_arg__scnprintf_int
+
+size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_LONG syscall_arg__scnprintf_long
+
+size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PID syscall_arg__scnprintf_pid
+
+size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_CLONE_FLAGS syscall_arg__scnprintf_clone_flags
+
+size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FCNTL_CMD syscall_arg__scnprintf_fcntl_cmd
+
+size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FCNTL_ARG syscall_arg__scnprintf_fcntl_arg
+
+size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd
+
+size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_KCMP_TYPE syscall_arg__scnprintf_kcmp_type
+
+size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
+
+size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
+
+size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+
+size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option
+
+size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2
+
+size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
 size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
 
+size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size);
+
+void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
+                                    size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg));
+
 #endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
new file mode 100644
index 000000000000..d64d049ab991
--- /dev/null
+++ b/tools/perf/trace/beauty/clone.c
@@ -0,0 +1,75 @@
+/*
+ * trace/beauty/cone.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <uapi/linux/sched.h>
+
+static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+        int printed = 0;
+
+#define P_FLAG(n) \
+        if (flags & CLONE_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                flags &= ~CLONE_##n; \
+        }
+
+        P_FLAG(VM);
+        P_FLAG(FS);
+        P_FLAG(FILES);
+        P_FLAG(SIGHAND);
+        P_FLAG(PTRACE);
+        P_FLAG(VFORK);
+        P_FLAG(PARENT);
+        P_FLAG(THREAD);
+        P_FLAG(NEWNS);
+        P_FLAG(SYSVSEM);
+        P_FLAG(SETTLS);
+        P_FLAG(PARENT_SETTID);
+        P_FLAG(CHILD_CLEARTID);
+        P_FLAG(DETACHED);
+        P_FLAG(UNTRACED);
+        P_FLAG(CHILD_SETTID);
+        P_FLAG(NEWCGROUP);
+        P_FLAG(NEWUTS);
+        P_FLAG(NEWIPC);
+        P_FLAG(NEWUSER);
+        P_FLAG(NEWPID);
+        P_FLAG(NEWNET);
+        P_FLAG(IO);
+#undef P_FLAG
+
+        if (flags)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+        return printed;
+}
+
+size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long flags = arg->val;
+        enum syscall_clone_args {
+                SCC_FLAGS         = (1 << 0),
+                SCC_CHILD_STACK   = (1 << 1),
+                SCC_PARENT_TIDPTR = (1 << 2),
+                SCC_CHILD_TIDPTR  = (1 << 3),
+                SCC_TLS           = (1 << 4),
+        };
+        if (!(flags & CLONE_PARENT_SETTID))
+                arg->mask |= SCC_PARENT_TIDPTR;
+
+        if (!(flags & (CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID)))
+                arg->mask |= SCC_CHILD_TIDPTR;
+
+        if (!(flags & CLONE_SETTLS))
+                arg->mask |= SCC_TLS;
+
+        return clone__scnprintf_flags(flags, bf, size);
+}
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
new file mode 100755
index 000000000000..2149d3a98e42
--- /dev/null
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -0,0 +1,13 @@
+#!/bin/sh
+
+drm_header_dir=$1
+printf "#ifndef DRM_COMMAND_BASE\n"
+grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+printf "#endif\n"
+
+printf "static const char *drm_ioctl_cmds[] = {\n"
+grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+        sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[      ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/     [\2] = "\1",/g'
+grep "^#define DRM_I915_[A-Z_0-9]\+[     ]\+0x" $drm_header_dir/i915_drm.h | \
+        sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[       ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
+printf "};\n"
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index b08f21eb6f4d..5d6a477a6400 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE           1
 #endif
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
new file mode 100644
index 000000000000..9e8900c13cb1
--- /dev/null
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -0,0 +1,100 @@
+/*
+ * trace/beauty/fcntl.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <uapi/linux/fcntl.h>
+
+static size_t fcntl__scnprintf_getfd(unsigned long val, char *bf, size_t size)
+{
+        return scnprintf(bf, size, "%s", val ? "CLOEXEC" : "0");
+}
+
+static size_t syscall_arg__scnprintf_fcntl_getfd(char *bf, size_t size, struct syscall_arg *arg)
+{
+        return fcntl__scnprintf_getfd(arg->val, bf, size);
+}
+
+static size_t fcntl__scnprintf_getlease(unsigned long val, char *bf, size_t size)
+{
+        static const char *fcntl_setlease[] = { "RDLCK", "WRLCK", "UNLCK", };
+        static DEFINE_STRARRAY(fcntl_setlease);
+
+        return strarray__scnprintf(&strarray__fcntl_setlease, bf, size, "%x", val);
+}
+
+static size_t syscall_arg__scnprintf_fcntl_getlease(char *bf, size_t size, struct syscall_arg *arg)
+{
+        return fcntl__scnprintf_getlease(arg->val, bf, size);
+}
+
+size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_arg *arg)
+{
+        if (arg->val == F_GETFL) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_open_flags);
+                goto mask_arg;
+        }
+        if (arg->val == F_GETFD) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fcntl_getfd);
+                goto mask_arg;
+        }
+        if (arg->val == F_DUPFD_CLOEXEC || arg->val == F_DUPFD) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fd);
+                goto out;
+        }
+        if (arg->val == F_GETOWN) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_pid);
+                goto mask_arg;
+        }
+        if (arg->val == F_GETLEASE) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fcntl_getlease);
+                goto mask_arg;
+        }
+        /*
+         * Some commands ignore the third fcntl argument, "arg", so mask it
+         */
+        if (arg->val == F_GET_SEALS ||
+            arg->val == F_GETSIG) {
+mask_arg:
+                arg->mask |= (1 << 2);
+        }
+out:
+        return syscall_arg__scnprintf_strarrays(bf, size, arg);
+}
+
+size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int cmd = syscall_arg__val(arg, 1);
+
+        if (cmd == F_DUPFD)
+                return syscall_arg__scnprintf_fd(bf, size, arg);
+
+        if (cmd == F_SETFD)
+                return fcntl__scnprintf_getfd(arg->val, bf, size);
+
+        if (cmd == F_SETFL)
+                return open__scnprintf_flags(arg->val, bf, size);
+
+        if (cmd == F_SETOWN)
+                return syscall_arg__scnprintf_pid(bf, size, arg);
+
+        if (cmd == F_SETLEASE)
+                return fcntl__scnprintf_getlease(arg->val, bf, size);
+        /*
+         * We still don't grab the contents of pointers on entry or exit,
+         * so just print them as hex numbers
+         */
+        if (cmd == F_SETLK || cmd == F_SETLKW || cmd == F_GETLK ||
+            cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK ||
+            cmd == F_GETOWN_EX || cmd == F_SETOWN_EX ||
+            cmd == F_GET_RW_HINT || cmd == F_SET_RW_HINT ||
+            cmd == F_GET_FILE_RW_HINT || cmd == F_SET_FILE_RW_HINT)
+                return syscall_arg__scnprintf_hex(bf, size, arg);
+
+        return syscall_arg__scnprintf_long(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index 74613703a14e..f9707f57566c 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <fcntl.h>
 
 #ifndef LOCK_MAND
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index bfd3359b09b6..61850fbc85ff 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/futex.h>
 
 #ifndef FUTEX_WAIT_BITSET
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
new file mode 100644
index 000000000000..1be3b4cf0827
--- /dev/null
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -0,0 +1,162 @@
+/*
+ * trace/beauty/ioctl.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+
+/*
+ * FIXME: to support all arches we have to improve this, for
+ * now, to build on older systems without things like TIOCGEXCL,
+ * get it directly from our copy.
+ *
+ * Right now only x86 is being supported for beautifying ioctl args
+ * in 'perf trace', see tools/perf/trace/beauty/Build and builtin-trace.c
+ */
+#include <uapi/asm-generic/ioctls.h>
+
+static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
+{
+        static const char *ioctl_tty_cmd[] = {
+        "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+        "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", "TIOCSCTTY",
+        "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", "TIOCGWINSZ", "TIOCSWINSZ",
+        "TIOCMGET", "TIOCMBIS", "TIOCMBIC", "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR",
+        "FIONREAD", "TIOCLINUX", "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT",
+        "FIONBIO", "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP",
+        [_IOC_NR(TIOCSBRK)] = "TIOCSBRK", "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2",
+        "TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
+        "TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT",
+        "TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER",
+        [_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
+        "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
+        "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
+        "TIOCMIWAIT", "TIOCGICOUNT", };
+        static DEFINE_STRARRAY(ioctl_tty_cmd);
+
+        if (nr < strarray__ioctl_tty_cmd.nr_entries && strarray__ioctl_tty_cmd.entries[nr] != NULL)
+                return scnprintf(bf, size, "%s", strarray__ioctl_tty_cmd.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'T', nr, dir);
+}
+
+static size_t ioctl__scnprintf_drm_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/drm_ioctl_array.c"
+        static DEFINE_STRARRAY(drm_ioctl_cmds);
+
+        if (nr < strarray__drm_ioctl_cmds.nr_entries && strarray__drm_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "DRM_%s", strarray__drm_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'd', nr, dir);
+}
+
+static size_t ioctl__scnprintf_sndrv_pcm_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/sndrv_pcm_ioctl_array.c"
+        static DEFINE_STRARRAY(sndrv_pcm_ioctl_cmds);
+
+        if (nr < strarray__sndrv_pcm_ioctl_cmds.nr_entries && strarray__sndrv_pcm_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "SNDRV_PCM_%s", strarray__sndrv_pcm_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'A', nr, dir);
+}
+
+static size_t ioctl__scnprintf_sndrv_ctl_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/sndrv_ctl_ioctl_array.c"
+        static DEFINE_STRARRAY(sndrv_ctl_ioctl_cmds);
+
+        if (nr < strarray__sndrv_ctl_ioctl_cmds.nr_entries && strarray__sndrv_ctl_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "SNDRV_CTL_%s", strarray__sndrv_ctl_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'U', nr, dir);
+}
+
+static size_t ioctl__scnprintf_kvm_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/kvm_ioctl_array.c"
+        static DEFINE_STRARRAY(kvm_ioctl_cmds);
+
+        if (nr < strarray__kvm_ioctl_cmds.nr_entries && strarray__kvm_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "KVM_%s", strarray__kvm_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir);
+}
+
+static size_t ioctl__scnprintf_vhost_virtio_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/vhost_virtio_ioctl_array.c"
+        static DEFINE_STRARRAY(vhost_virtio_ioctl_cmds);
+        static DEFINE_STRARRAY(vhost_virtio_ioctl_read_cmds);
+        struct strarray *s = (dir & _IOC_READ) ? &strarray__vhost_virtio_ioctl_read_cmds : &strarray__vhost_virtio_ioctl_cmds;
+
+        if (nr < s->nr_entries && s->entries[nr] != NULL)
+                return scnprintf(bf, size, "VHOST_%s", s->entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAF, nr, dir);
+}
+
+static size_t ioctl__scnprintf_perf_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/perf_ioctl_array.c"
+        static DEFINE_STRARRAY(perf_ioctl_cmds);
+
+        if (nr < strarray__perf_ioctl_cmds.nr_entries && strarray__perf_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "PERF_%s", strarray__perf_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir);
+}
+
+static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size)
+{
+        int dir  = _IOC_DIR(cmd),
+            type = _IOC_TYPE(cmd),
+            nr   = _IOC_NR(cmd),
+            sz   = _IOC_SIZE(cmd);
+        int printed = 0;
+        static const struct ioctl_type {
+                int     type;
+                size_t  (*scnprintf)(int nr, int dir, char *bf, size_t size);
+        } ioctl_types[] = { /* Must be ordered by type */
+                              { .type   = '$', .scnprintf = ioctl__scnprintf_perf_cmd, },
+                ['A' - '$'] = { .type   = 'A', .scnprintf = ioctl__scnprintf_sndrv_pcm_cmd, },
+                ['T' - '$'] = { .type   = 'T', .scnprintf = ioctl__scnprintf_tty_cmd, },
+                ['U' - '$'] = { .type   = 'U', .scnprintf = ioctl__scnprintf_sndrv_ctl_cmd, },
+                ['d' - '$'] = { .type   = 'd', .scnprintf = ioctl__scnprintf_drm_cmd, },
+                [0xAE - '$'] = { .type  = 0xAE, .scnprintf = ioctl__scnprintf_kvm_cmd, },
+                [0xAF - '$'] = { .type  = 0xAF, .scnprintf = ioctl__scnprintf_vhost_virtio_cmd, },
+        };
+        const int nr_types = ARRAY_SIZE(ioctl_types);
+
+        if (type >= ioctl_types[0].type && type <= ioctl_types[nr_types - 1].type) {
+                const int index = type - ioctl_types[0].type;
+
+                if (ioctl_types[index].scnprintf != NULL)
+                        return ioctl_types[index].scnprintf(nr, dir, bf, size);
+        }
+
+        printed += scnprintf(bf + printed, size - printed, "%c", '(');
+
+        if (dir == _IOC_NONE) {
+                printed += scnprintf(bf + printed, size - printed, "%s", "NONE");
+        } else {
+                if (dir & _IOC_READ)
+                        printed += scnprintf(bf + printed, size - printed, "%s", "READ");
+                if (dir & _IOC_WRITE)
+                        printed += scnprintf(bf + printed, size - printed, "%s%s", dir & _IOC_READ ? "|" : "", "WRITE");
+        }
+
+        return printed + scnprintf(bf + printed, size - printed, ", %#x, %#x, %#x)", type, nr, sz);
+}
+
+size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long cmd = arg->val;
+
+        return ioctl__scnprintf_cmd(cmd, bf, size);
+}
diff --git a/tools/perf/trace/beauty/kcmp.c b/tools/perf/trace/beauty/kcmp.c
new file mode 100644
index 000000000000..f62040eb9d5c
--- /dev/null
+++ b/tools/perf/trace/beauty/kcmp.c
@@ -0,0 +1,44 @@
+/*
+ * trace/beauty/kcmp.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <machine.h>
+#include <uapi/linux/kcmp.h>
+
+#include "trace/beauty/generated/kcmp_type_array.c"
+
+size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long fd = arg->val;
+        int type = syscall_arg__val(arg, 2);
+        pid_t pid;
+
+        if (type != KCMP_FILE)
+                return syscall_arg__scnprintf_long(bf, size, arg);
+
+        pid = syscall_arg__val(arg, arg->idx == 3 ? 0 : 1); /* idx1 -> pid1, idx2 -> pid2 */
+        return pid__scnprintf_fd(arg->trace, pid, fd, bf, size);
+}
+
+static size_t kcmp__scnprintf_type(int type, char *bf, size_t size)
+{
+        static DEFINE_STRARRAY(kcmp_types);
+        return strarray__scnprintf(&strarray__kcmp_types, bf, size, "%d", type);
+}
+
+size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long type = arg->val;
+
+        if (type != KCMP_FILE)
+                arg->mask |= (1 << 3) | (1 << 4); /* Ignore idx1 and idx2 */
+
+        return kcmp__scnprintf_type(type, bf, size);
+}
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
new file mode 100755
index 000000000000..40d063b8c082
--- /dev/null
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *kcmp_types[] = {\n"
+regex='^[[:space:]]+(KCMP_(\w+)),'
+egrep $regex ${header_dir}/kcmp.h | grep -v KCMP_TYPES, | \
+        sed -r "s/$regex/\1 \2/g" | \
+        xargs printf "\t[%s]\t= \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
new file mode 100755
index 000000000000..bd28817afced
--- /dev/null
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+kvm_header_dir=$1
+
+printf "static const char *kvm_ioctl_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
+egrep $regex ${kvm_header_dir}/kvm.h    | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
new file mode 100755
index 000000000000..60ef8640ee70
--- /dev/null
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *madvise_advices[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/mman-common.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index af1cfde6b97b..9e1668b2c5d7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <uapi/linux/mman.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
@@ -34,6 +35,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 {
         int printed = 0, flags = arg->val;
 
+        if (flags & MAP_ANONYMOUS)
+                arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */
+
 #define P_MMAP_FLAG(n) \
         if (flags & MAP_##n) { \
                 printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
@@ -91,35 +95,21 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 
 #define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
 
+static size_t madvise__scnprintf_behavior(int behavior, char *bf, size_t size)
+{
+#include "trace/beauty/generated/madvise_behavior_array.c"
+       static DEFINE_STRARRAY(madvise_advices);
+
+       if (behavior < strarray__madvise_advices.nr_entries && strarray__madvise_advices.entries[behavior] != NULL)
+               return scnprintf(bf, size, "MADV_%s", strarray__madvise_advices.entries[behavior]);
+
+       return scnprintf(bf, size, "%#", behavior);
+}
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
                                                       struct syscall_arg *arg)
 {
-        int behavior = arg->val;
-
-        switch (behavior) {
-#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
-        P_MADV_BHV(NORMAL);
-        P_MADV_BHV(RANDOM);
-        P_MADV_BHV(SEQUENTIAL);
-        P_MADV_BHV(WILLNEED);
-        P_MADV_BHV(DONTNEED);
-        P_MADV_BHV(FREE);
-        P_MADV_BHV(REMOVE);
-        P_MADV_BHV(DONTFORK);
-        P_MADV_BHV(DOFORK);
-        P_MADV_BHV(HWPOISON);
-        P_MADV_BHV(SOFT_OFFLINE);
-        P_MADV_BHV(MERGEABLE);
-        P_MADV_BHV(UNMERGEABLE);
-        P_MADV_BHV(HUGEPAGE);
-        P_MADV_BHV(NOHUGEPAGE);
-        P_MADV_BHV(DONTDUMP);
-        P_MADV_BHV(DODUMP);
-#undef P_MADV_BHV
-        default: break;
-        }
-
-        return scnprintf(bf, size, "%#x", behavior);
+        return madvise__scnprintf_behavior(arg->val, bf, size);
 }
 
 #define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c
index 930d8fef2400..d929ad7dd97b 100644
--- a/tools/perf/trace/beauty/mode_t.c
+++ b/tools/perf/trace/beauty/mode_t.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index 1106c8960cc4..c064d6aae659 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index f55a4597fc38..6aec6178a99d 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -14,13 +15,16 @@
 #define O_NOATIME       01000000
 #endif
 
-static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
-                                               struct syscall_arg *arg)
-{
-        int printed = 0, flags = arg->val;
+#ifndef O_TMPFILE
+#define O_TMPFILE       020000000
+#endif
 
-        if (!(flags & O_CREAT))
-                arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
+#undef O_LARGEFILE
+#define O_LARGEFILE     00100000
+
+size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+        int printed = 0;
 
         if (flags == 0)
                 return scnprintf(bf, size, "RDONLY");
@@ -30,6 +34,7 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
                 flags &= ~O_##n; \
         }
 
+        P_FLAG(RDWR);
         P_FLAG(APPEND);
         P_FLAG(ASYNC);
         P_FLAG(CLOEXEC);
@@ -38,6 +43,8 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
         P_FLAG(DIRECTORY);
         P_FLAG(EXCL);
         P_FLAG(LARGEFILE);
+        P_FLAG(NOFOLLOW);
+        P_FLAG(TMPFILE);
         P_FLAG(NOATIME);
         P_FLAG(NOCTTY);
 #ifdef O_NONBLOCK
@@ -48,7 +55,6 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 #ifdef O_PATH
         P_FLAG(PATH);
 #endif
-        P_FLAG(RDWR);
 #ifdef O_DSYNC
         if ((flags & O_SYNC) == O_SYNC)
                 printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
@@ -68,4 +74,12 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
         return printed;
 }
 
-#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int flags = arg->val;
+
+        if (!(flags & O_CREAT))
+                arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
+
+        return open__scnprintf_flags(flags, bf, size);
+}
diff --git a/tools/perf/trace/beauty/perf_event_open.c b/tools/perf/trace/beauty/perf_event_open.c
index 311f09dd718d..2bafd7c995ff 100644
--- a/tools/perf/trace/beauty/perf_event_open.c
+++ b/tools/perf/trace/beauty/perf_event_open.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifndef PERF_FLAG_FD_NO_GROUP
 # define PERF_FLAG_FD_NO_GROUP          (1UL << 0)
 #endif
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
new file mode 100755
index 000000000000..faea4237c793
--- /dev/null
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *perf_ioctl_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
+egrep $regex ${header_dir}/perf_event.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
index 07486ea65ae3..0313df342830 100644
--- a/tools/perf/trace/beauty/pid.c
+++ b/tools/perf/trace/beauty/pid.c
@@ -1,4 +1,5 @@
-static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
+// SPDX-License-Identifier: GPL-2.0
+size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
 {
         int pid = arg->val;
         struct trace *trace = arg->trace;
@@ -17,5 +18,3 @@ static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_a
 
         return printed;
 }
-
-#define SCA_PID syscall_arg__scnprintf_pid
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
new file mode 100644
index 000000000000..2ba784a3734a
--- /dev/null
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -0,0 +1,50 @@
+/*
+ * trace/beauty/pkey_alloc.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <linux/log2.h>
+
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+        int i, printed = 0;
+
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+        static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+        if (access_rights == 0) {
+                const char *s = strarray__pkey_alloc_access_rights.entries[0];
+                if (s)
+                        return scnprintf(bf, size, "%s", s);
+                return scnprintf(bf, size, "%d", 0);
+        }
+
+        for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
+                int bit = 1 << (i - 1);
+
+                if (!(access_rights & bit))
+                        continue;
+
+                if (printed != 0)
+                        printed += scnprintf(bf + printed, size - printed, "|");
+
+                if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
+                        printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+                else
+                        printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
+        }
+
+        return printed;
+}
+
+size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long cmd = arg->val;
+
+        return pkey_alloc__scnprintf_access_rights(cmd, bf, size);
+}
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
new file mode 100755
index 000000000000..62e51a02b839
--- /dev/null
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *pkey_alloc_access_rights[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
+egrep $regex ${header_dir}/mman-common.h        | \
+        sed -r "s/$regex/\2 \2 \1/g"    | \
+        sort | xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
new file mode 100644
index 000000000000..246130dad6c4
--- /dev/null
+++ b/tools/perf/trace/beauty/prctl.c
@@ -0,0 +1,82 @@
+/*
+ * trace/beauty/prctl.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <uapi/linux/prctl.h>
+
+#include "trace/beauty/generated/prctl_option_array.c"
+
+static size_t prctl__scnprintf_option(int option, char *bf, size_t size)
+{
+        static DEFINE_STRARRAY(prctl_options);
+        return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", option);
+}
+
+static size_t prctl__scnprintf_set_mm(int option, char *bf, size_t size)
+{
+        static DEFINE_STRARRAY(prctl_set_mm_options);
+        return strarray__scnprintf(&strarray__prctl_set_mm_options, bf, size, "%d", option);
+}
+
+size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int option = syscall_arg__val(arg, 0);
+
+        if (option == PR_SET_MM)
+                return prctl__scnprintf_set_mm(arg->val, bf, size);
+        /*
+         * We still don't grab the contents of pointers on entry or exit,
+         * so just print them as hex numbers
+         */
+        if (option == PR_SET_NAME)
+                return syscall_arg__scnprintf_hex(bf, size, arg);
+
+        return syscall_arg__scnprintf_long(bf, size, arg);
+}
+
+size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int option = syscall_arg__val(arg, 0);
+
+        if (option == PR_SET_MM)
+                return syscall_arg__scnprintf_hex(bf, size, arg);
+
+        return syscall_arg__scnprintf_long(bf, size, arg);
+}
+
+size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long option = arg->val;
+        enum {
+                SPO_ARG2 = (1 << 1),
+                SPO_ARG3 = (1 << 2),
+                SPO_ARG4 = (1 << 3),
+                SPO_ARG5 = (1 << 4),
+                SPO_ARG6 = (1 << 5),
+        };
+        const u8 all_but2 = SPO_ARG3 | SPO_ARG4 | SPO_ARG5 | SPO_ARG6;
+        const u8 all = SPO_ARG2 | all_but2;
+        const u8 masks[] = {
+                [PR_GET_DUMPABLE]        = all,
+                [PR_SET_DUMPABLE]        = all_but2,
+                [PR_SET_NAME]            = all_but2,
+                [PR_GET_CHILD_SUBREAPER] = all_but2,
+                [PR_SET_CHILD_SUBREAPER] = all_but2,
+                [PR_GET_SECUREBITS]      = all,
+                [PR_SET_SECUREBITS]      = all_but2,
+                [PR_SET_MM]              = SPO_ARG4 | SPO_ARG5 | SPO_ARG6,
+                [PR_GET_PDEATHSIG]       = all,
+                [PR_SET_PDEATHSIG]       = all_but2,
+        };
+
+        if (option < ARRAY_SIZE(masks))
+                arg->mask |= masks[option];
+
+        return prctl__scnprintf_option(option, bf, size);
+}
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
new file mode 100755
index 000000000000..0be4138fbe71
--- /dev/null
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *prctl_options[] = {\n"
+regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
+egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
+
+printf "static const char *prctl_set_mm_options[] = {\n"
+regex='^#[[:space:]]+define[[:space:]]+PR_SET_MM_(\w+)[[:space:]]*([[:digit:]]+).*'
+egrep $regex ${header_dir}/prctl.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index 34775295b9b3..ba5096ae76b6 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sched.h>
 
 /*
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index 356441bce27d..b7097fd5fed9 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c
index fde8f2fc6558..bde18a53f090 100644
--- a/tools/perf/trace/beauty/signum.c
+++ b/tools/perf/trace/beauty/signum.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <signal.h>
 
 static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
new file mode 100755
index 000000000000..aad5ab130539
--- /dev/null
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+sound_header_dir=$1
+
+printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+        sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
+printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
new file mode 100755
index 000000000000..b7e9ef6b2f55
--- /dev/null
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+sound_header_dir=$1
+
+printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+        sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
+printf "};\n"
diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c
index 0a5ce818131c..bca26aef4a77 100644
--- a/tools/perf/trace/beauty/socket_type.c
+++ b/tools/perf/trace/beauty/socket_type.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
new file mode 100755
index 000000000000..76f1de697787
--- /dev/null
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+
+vhost_virtio_header_dir=$1
+
+printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
+egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
+
+printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
+egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c
index 7942724adec8..8465281a093d 100644
--- a/tools/perf/trace/beauty/waitid_options.c
+++ b/tools/perf/trace/beauty/waitid_options.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <sys/wait.h>
 
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 83874b0e266c..63399af3049f 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../util.h"
 #include "../string2.h"
 #include "../config.h"
@@ -8,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <linux/string.h>
 #include <stdlib.h>
 #include <sys/ttydefaults.h>
 #include "browser.h"
@@ -563,7 +565,7 @@ static int ui_browser__color_config(const char *var, const char *value,
         int i;
 
         /* same dir for all commands */
-        if (prefixcmp(var, "colors.") != 0)
+        if (!strstarts(var, "colors.") != 0)
                 return 0;
 
         for (i = 0; ui_browser__colorsets[i].name != NULL; ++i) {
@@ -738,6 +740,35 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
                 __ui_browser__line_arrow_down(browser, column, start, end);
 }
 
+void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
+                            unsigned int row, bool arrow_down)
+{
+        unsigned int end_row;
+
+        if (row >= browser->top_idx)
+                end_row = row - browser->top_idx;
+        else
+                return;
+
+        SLsmg_set_char_set(1);
+
+        if (arrow_down) {
+                ui_browser__gotorc(browser, end_row, column - 1);
+                SLsmg_write_char(SLSMG_ULCORN_CHAR);
+                ui_browser__gotorc(browser, end_row, column);
+                SLsmg_draw_hline(2);
+                ui_browser__gotorc(browser, end_row + 1, column - 1);
+                SLsmg_write_char(SLSMG_LTEE_CHAR);
+        } else {
+                ui_browser__gotorc(browser, end_row, column - 1);
+                SLsmg_write_char(SLSMG_LTEE_CHAR);
+                ui_browser__gotorc(browser, end_row, column);
+                SLsmg_draw_hline(2);
+        }
+
+        SLsmg_set_char_set(0);
+}
+
 void ui_browser__init(void)
 {
         int i = 0;
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index be3b70eb5fca..03e1734412b9 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_BROWSER_H_
 #define _PERF_UI_BROWSER_H_ 1
 
@@ -43,6 +44,8 @@ void ui_browser__printf(struct ui_browser *browser, const char *fmt, ...);
 void ui_browser__write_graph(struct ui_browser *browser, int graph);
 void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
                               u64 start, u64 end);
+void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
+                            unsigned int row, bool arrow_down);
 void __ui_browser__show_title(struct ui_browser *browser, const char *title);
 void ui_browser__show_title(struct ui_browser *browser, const char *title);
 int ui_browser__show(struct ui_browser *browser, const char *title,
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 27f41f28dcb4..8f7f59d1a2b5 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../../util/util.h"
 #include "../browser.h"
 #include "../helpline.h"
@@ -9,14 +10,16 @@
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include "../../util/config.h"
+#include "../../util/evlist.h"
 #include <inttypes.h>
 #include <pthread.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <sys/ttydefaults.h>
 
 struct disasm_line_samples {
-        double          percent;
-        u64             nr;
+        double                percent;
+        struct sym_hist_entry he;
 };
 
 #define IPC_WIDTH 6
@@ -40,6 +43,7 @@ static struct annotate_browser_opt {
              jump_arrows,
              show_linenr,
              show_nr_jumps,
+             show_nr_samples,
              show_total_period;
 } annotate_browser__opts = {
         .use_offset     = true,
@@ -108,11 +112,12 @@ static int annotate_browser__set_jumps_percent_color(struct annotate_browser *br
 
 static int annotate_browser__pcnt_width(struct annotate_browser *ab)
 {
-        int w = 7 * ab->nr_events;
+        return (annotate_browser__opts.show_total_period ? 12 : 7) * ab->nr_events;
+}
 
-        if (ab->have_cycles)
-                w += IPC_WIDTH + CYCLES_WIDTH;
-        return w;
+static int annotate_browser__cycles_width(struct annotate_browser *ab)
+{
+        return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0;
 }
 
 static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
@@ -125,7 +130,8 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                              (!current_entry || (browser->use_navkeypressed &&
                                                  !browser->navkeypressed)));
         int width = browser->width, printed;
-        int i, pcnt_width = annotate_browser__pcnt_width(ab);
+        int i, pcnt_width = annotate_browser__pcnt_width(ab),
+               cycles_width = annotate_browser__cycles_width(ab);
         double percent_max = 0.0;
         char bf[256];
         bool show_title = false;
@@ -149,8 +155,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                                                 bdl->samples[i].percent,
                                                 current_entry);
                         if (annotate_browser__opts.show_total_period) {
+                                ui_browser__printf(browser, "%11" PRIu64 " ",
+                                                   bdl->samples[i].he.period);
+                        } else if (annotate_browser__opts.show_nr_samples) {
                                 ui_browser__printf(browser, "%6" PRIu64 " ",
-                                                   bdl->samples[i].nr);
+                                                   bdl->samples[i].he.nr_samples);
                         } else {
                                 ui_browser__printf(browser, "%6.2f ",
                                                    bdl->samples[i].percent);
@@ -160,9 +169,12 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 ui_browser__set_percent_color(browser, 0, current_entry);
 
                 if (!show_title)
-                        ui_browser__write_nstring(browser, " ", 7 * ab->nr_events);
-                else
-                        ui_browser__printf(browser, "%*s", 7, "Percent");
+                        ui_browser__write_nstring(browser, " ", pcnt_width);
+                else {
+                        ui_browser__printf(browser, "%*s", pcnt_width,
+                                           annotate_browser__opts.show_total_period ? "Period" :
+                                           annotate_browser__opts.show_nr_samples ? "Samples" : "Percent");
+                }
         }
         if (ab->have_cycles) {
                 if (dl->ipc)
@@ -188,7 +200,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 width += 1;
 
         if (!*dl->line)
-                ui_browser__write_nstring(browser, " ", width - pcnt_width);
+                ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width);
         else if (dl->offset == -1) {
                 if (dl->line_nr && annotate_browser__opts.show_linenr)
                         printed = scnprintf(bf, sizeof(bf), "%-*d ",
@@ -197,7 +209,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                         printed = scnprintf(bf, sizeof(bf), "%*s  ",
                                     ab->addr_width, " ");
                 ui_browser__write_nstring(browser, bf, printed);
-                ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width + 1);
+                ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width - cycles_width + 1);
         } else {
                 u64 addr = dl->offset;
                 int color = -1;
@@ -254,7 +266,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 }
 
                 disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
-                ui_browser__write_nstring(browser, bf, width - pcnt_width - 3 - printed);
+                ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed);
         }
 
         if (current_entry)
@@ -272,6 +284,25 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
         return true;
 }
 
+static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
+{
+        struct disasm_line *pos = list_prev_entry(cursor, node);
+        const char *name;
+
+        if (!pos)
+                return false;
+
+        if (ins__is_lock(&pos->ins))
+                name = pos->ops.locked.ins.name;
+        else
+                name = pos->ins.name;
+
+        if (!name || !cursor->ins.name)
+                return false;
+
+        return ins__is_fused(ab->arch, name, cursor->ins.name);
+}
+
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 {
         struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
@@ -307,6 +338,13 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
         ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
         __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
                                  from, to);
+
+        if (is_fused(ab, cursor)) {
+                ui_browser__mark_fused(browser,
+                                       pcnt_width + 3 + ab->addr_width,
+                                       from - 1,
+                                       to > from ? true : false);
+        }
 }
 
 static unsigned int annotate_browser__refresh(struct ui_browser *browser)
@@ -422,14 +460,14 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
                 next = disasm__get_next_ip_line(&notes->src->source, pos);
 
                 for (i = 0; i < browser->nr_events; i++) {
-                        u64 nr_samples;
+                        struct sym_hist_entry sample;
 
                         bpos->samples[i].percent = disasm__calc_percent(notes,
                                                 evsel->idx + i,
                                                 pos->offset,
                                                 next ? next->offset : len,
-                                                &path, &nr_samples);
-                        bpos->samples[i].nr = nr_samples;
+                                                &path, &sample);
+                        bpos->samples[i].he = sample;
 
                         if (max_percent < bpos->samples[i].percent)
                                 max_percent = bpos->samples[i].percent;
@@ -792,13 +830,14 @@ static int annotate_browser__run(struct annotate_browser *browser,
                 "q/ESC/CTRL+C  Exit\n\n"
                 "ENTER         Go to target\n"
                 "ESC           Exit\n"
-                "H             Cycle thru hottest instructions\n"
+                "H             Go to hottest instruction\n"
+                "TAB/shift+TAB Cycle thru hottest instructions\n"
                 "j             Toggle showing jump to target arrows\n"
                 "J             Toggle showing number of jump sources on targets\n"
                 "n             Search next string\n"
                 "o             Toggle disassembler output/simplified view\n"
                 "s             Toggle source code view\n"
-                "t             Toggle total period view\n"
+                "t             Circulate percent, total period, samples view\n"
                 "/             Search string\n"
                 "k             Toggle line numbers\n"
                 "r             Run available scripts\n"
@@ -875,8 +914,13 @@ show_sup_ins:
                         }
                         continue;
                 case 't':
-                        annotate_browser__opts.show_total_period =
-                          !annotate_browser__opts.show_total_period;
+                        if (annotate_browser__opts.show_total_period) {
+                                annotate_browser__opts.show_total_period = false;
+                                annotate_browser__opts.show_nr_samples = true;
+                        } else if (annotate_browser__opts.show_nr_samples)
+                                annotate_browser__opts.show_nr_samples = false;
+                        else
+                                annotate_browser__opts.show_total_period = true;
                         annotate_browser__update_addr_width(browser);
                         continue;
                 case K_LEFT:
@@ -899,9 +943,11 @@ out:
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
                              struct hist_browser_timer *hbt)
 {
-        /* Set default value for show_total_period.  */
+        /* Set default value for show_total_period and show_nr_samples  */
         annotate_browser__opts.show_total_period =
-          symbol_conf.show_total_period;
+                symbol_conf.show_total_period;
+        annotate_browser__opts.show_nr_samples =
+                symbol_conf.show_nr_samples;
 
         return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt);
 }
@@ -1074,7 +1120,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
         }
 
         err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                  sizeof_bdl, &browser.arch);
+                                  sizeof_bdl, &browser.arch,
+                                  perf_evsel__env_cpuid(evsel));
         if (err) {
                 char msg[BUFSIZ];
                 symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -1151,6 +1198,7 @@ static struct annotate_config {
         ANNOTATE_CFG(jump_arrows),
         ANNOTATE_CFG(show_linenr),
         ANNOTATE_CFG(show_nr_jumps),
+        ANNOTATE_CFG(show_nr_samples),
         ANNOTATE_CFG(show_total_period),
         ANNOTATE_CFG(use_offset),
 };
@@ -1170,7 +1218,7 @@ static int annotate__config(const char *var, const char *value,
         struct annotate_config *cfg;
         const char *name;
 
-        if (prefixcmp(var, "annotate.") != 0)
+        if (!strstarts(var, "annotate."))
                 return 0;
 
         name = var + 9;
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index e2c9390ff4c5..d75492189acb 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util/cache.h"
 #include "util/debug.h"
 #include "ui/browser.h"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 69f4570bd4f9..68146f4620a5 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
 #include <inttypes.h>
@@ -154,60 +155,9 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
         cl->unfolded = unfold ? cl->has_children : false;
 }
 
-static struct inline_node *inline_node__create(struct map *map, u64 ip)
-{
-        struct dso *dso;
-        struct inline_node *node;
-
-        if (map == NULL)
-                return NULL;
-
-        dso = map->dso;
-        if (dso == NULL)
-                return NULL;
-
-        if (dso->kernel != DSO_TYPE_USER)
-                return NULL;
-
-        node = dso__parse_addr_inlines(dso,
-                                       map__rip_2objdump(map, ip));
-
-        return node;
-}
-
-static int inline__count_rows(struct inline_node *node)
-{
-        struct inline_list *ilist;
-        int i = 0;
-
-        if (node == NULL)
-                return 0;
-
-        list_for_each_entry(ilist, &node->val, list) {
-                if ((ilist->filename != NULL) || (ilist->funcname != NULL))
-                        i++;
-        }
-
-        return i;
-}
-
-static int callchain_list__inline_rows(struct callchain_list *chain)
-{
-        struct inline_node *node;
-        int rows;
-
-        node = inline_node__create(chain->ms.map, chain->ip);
-        if (node == NULL)
-                return 0;
-
-        rows = inline__count_rows(node);
-        inline_node__delete(node);
-        return rows;
-}
-
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
-        int n = 0, inline_rows;
+        int n = 0;
         struct rb_node *nd;
 
         for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
@@ -218,12 +168,6 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
                 list_for_each_entry(chain, &child->val, list) {
                         ++n;
 
-                        if (symbol_conf.inline_name) {
-                                inline_rows =
-                                        callchain_list__inline_rows(chain);
-                                n += inline_rows;
-                        }
-
                         /* We need this because we may not have children */
                         folded_sign = callchain_list__folded(chain);
                         if (folded_sign == '+')
@@ -275,7 +219,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 {
         struct callchain_list *chain;
         bool unfolded = false;
-        int n = 0, inline_rows;
+        int n = 0;
 
         if (callchain_param.mode == CHAIN_FLAT)
                 return callchain_node__count_flat_rows(node);
@@ -284,10 +228,6 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
         list_for_each_entry(chain, &node->val, list) {
                 ++n;
-                if (symbol_conf.inline_name) {
-                        inline_rows = callchain_list__inline_rows(chain);
-                        n += inline_rows;
-                }
 
                 unfolded = chain->unfolded;
         }
@@ -435,19 +375,6 @@ static void hist_entry__init_have_children(struct hist_entry *he)
         he->init_have_children = true;
 }
 
-static void hist_entry_init_inline_node(struct hist_entry *he)
-{
-        if (he->inline_node)
-                return;
-
-        he->inline_node = inline_node__create(he->ms.map, he->ip);
-
-        if (he->inline_node == NULL)
-                return;
-
-        he->has_children = true;
-}
-
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
         struct hist_entry *he = browser->he_selection;
@@ -479,12 +406,8 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 
                 if (he->unfolded) {
                         if (he->leaf)
-                                if (he->inline_node)
-                                        he->nr_rows = inline__count_rows(
-                                                        he->inline_node);
-                                else
-                                        he->nr_rows = callchain__count_rows(
-                                                        &he->sorted_chain);
+                                he->nr_rows = callchain__count_rows(
+                                                &he->sorted_chain);
                         else
                                 he->nr_rows = hierarchy_count_rows(browser, he, false);
 
@@ -844,71 +767,6 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_inline(struct hist_browser *browser,
-                                     struct inline_node *node,
-                                     unsigned short row,
-                                     int offset)
-{
-        struct inline_list *ilist;
-        char buf[1024];
-        int color, width, first_row;
-
-        first_row = row;
-        width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
-        list_for_each_entry(ilist, &node->val, list) {
-                if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
-                        color = HE_COLORSET_NORMAL;
-                        if (ui_browser__is_current_entry(&browser->b, row))
-                                color = HE_COLORSET_SELECTED;
-
-                        if (callchain_param.key == CCKEY_ADDRESS ||
-                            callchain_param.key == CCKEY_SRCLINE) {
-                                if (ilist->filename != NULL)
-                                        scnprintf(buf, sizeof(buf),
-                                                  "%s:%d (inline)",
-                                                  ilist->filename,
-                                                  ilist->line_nr);
-                                else
-                                        scnprintf(buf, sizeof(buf), "??");
-                        } else if (ilist->funcname != NULL)
-                                scnprintf(buf, sizeof(buf), "%s (inline)",
-                                          ilist->funcname);
-                        else if (ilist->filename != NULL)
-                                scnprintf(buf, sizeof(buf),
-                                          "%s:%d (inline)",
-                                          ilist->filename,
-                                          ilist->line_nr);
-                        else
-                                scnprintf(buf, sizeof(buf), "??");
-
-                        ui_browser__set_color(&browser->b, color);
-                        hist_browser__gotorc(browser, row, 0);
-                        ui_browser__write_nstring(&browser->b, " ",
-                                LEVEL_OFFSET_STEP + offset);
-                        ui_browser__write_nstring(&browser->b, buf, width);
-                        row++;
-                }
-        }
-
-        return row - first_row;
-}
-
-static size_t show_inline_list(struct hist_browser *browser, struct map *map,
-                               u64 ip, int row, int offset)
-{
-        struct inline_node *node;
-        int ret;
-
-        node = inline_node__create(map, ip);
-        if (node == NULL)
-                return 0;
-
-        ret = hist_browser__show_inline(browser, node, row, offset);
-
-        inline_node__delete(node);
-        return ret;
-}
-
 static int hist_browser__show_callchain_list(struct hist_browser *browser,
                                              struct callchain_node *node,
                                              struct callchain_list *chain,
@@ -920,7 +778,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         char bf[1024], *alloc_str;
         char buf[64], *alloc_str2;
         const char *str;
-        int inline_rows = 0, ret = 1;
+        int ret = 1;
 
         if (arg->row_offset != 0) {
                 arg->row_offset--;
@@ -934,12 +792,8 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
                                        browser->show_dso);
 
         if (symbol_conf.show_branchflag_count) {
-                if (need_percent)
-                        callchain_list_counts__printf_value(node, chain, NULL,
-                                                            buf, sizeof(buf));
-                else
-                        callchain_list_counts__printf_value(NULL, chain, NULL,
-                                                            buf, sizeof(buf));
+                callchain_list_counts__printf_value(chain, NULL,
+                                                    buf, sizeof(buf));
 
                 if (asprintf(&alloc_str2, "%s%s", str, buf) < 0)
                         str = "Not enough memory!";
@@ -961,12 +815,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         free(alloc_str);
         free(alloc_str2);
 
-        if (symbol_conf.inline_name) {
-                inline_rows = show_inline_list(browser, chain->ms.map,
-                                               chain->ip, row + 1, offset);
-        }
-
-        return ret + inline_rows;
+        return ret;
 }
 
 static bool check_percent_display(struct rb_node *node, u64 parent_total)
@@ -1390,12 +1239,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                 folded_sign = hist_entry__folded(entry);
         }
 
-        if (symbol_conf.inline_name &&
-            (!entry->has_children)) {
-                hist_entry_init_inline_node(entry);
-                folded_sign = hist_entry__folded(entry);
-        }
-
         if (row_offset == 0) {
                 struct hpp_arg arg = {
                         .b              = &browser->b,
@@ -1427,8 +1270,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         }
 
                         if (first) {
-                                if (symbol_conf.use_callchain ||
-                                        symbol_conf.inline_name) {
+                                if (symbol_conf.use_callchain) {
                                         ui_browser__printf(&browser->b, "%c ", folded_sign);
                                         width -= 2;
                                 }
@@ -1470,15 +1312,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         .is_current_entry = current_entry,
                 };
 
-                if (entry->inline_node)
-                        printed += hist_browser__show_inline(browser,
-                                        entry->inline_node, row, 0);
-                else
-                        printed += hist_browser__show_callchain(browser,
-                                        entry, 1, row,
-                                        hist_browser__show_callchain_entry,
-                                        &arg,
-                                        hist_browser__check_output_full);
+                printed += hist_browser__show_callchain(browser,
+                                entry, 1, row,
+                                hist_browser__show_callchain_entry,
+                                &arg,
+                                hist_browser__check_output_full);
         }
 
         return printed;
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index 23d6acb84800..ba431777f559 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_BROWSER_HISTS_H_
 #define _PERF_UI_BROWSER_HISTS_H_ 1
 
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index ffa5addf631d..e03fa75f108a 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <elf.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
diff --git a/tools/perf/ui/browsers/map.h b/tools/perf/ui/browsers/map.h
index 2d58e4b3eb6f..0ed7dbb3a373 100644
--- a/tools/perf/ui/browsers/map.h
+++ b/tools/perf/ui/browsers/map.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_MAP_BROWSER_H_
 #define _PERF_UI_MAP_BROWSER_H_ 1
 struct map;
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index ad6b6ee3770e..90a32ac69e76 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <elf.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index d903fd493416..fc7a2e105bfd 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "gtk.h"
 #include "util/debug.h"
 #include "util/annotate.h"
@@ -34,10 +35,10 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
                 return 0;
 
         symhist = annotation__histogram(symbol__annotation(sym), evidx);
-        if (!symbol_conf.event_group && !symhist->addr[dl->offset])
+        if (!symbol_conf.event_group && !symhist->addr[dl->offset].nr_samples)
                 return 0;
 
-        percent = 100.0 * symhist->addr[dl->offset] / symhist->sum;
+        percent = 100.0 * symhist->addr[dl->offset].nr_samples / symhist->nr_samples;
 
         markup = perf_gtk__get_percent_color(percent);
         if (markup)
@@ -169,7 +170,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
                 return -1;
 
         err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                  0, NULL);
+                                  0, NULL, NULL);
         if (err) {
                 char msg[BUFSIZ];
                 symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index c24d91221290..4820e25ac68d 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../evlist.h"
 #include "../cache.h"
 #include "../evsel.h"
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 0a9173ff9a61..9846ea5c831b 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_GTK_H_
 #define _PERF_GTK_H_ 1
 
diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c
index 3388cbd12186..fbf1ea9ce9a2 100644
--- a/tools/perf/ui/gtk/helpline.c
+++ b/tools/perf/ui/gtk/helpline.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <string.h>
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index e24f83957705..24e1ec201ffd 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../evlist.h"
 #include "../cache.h"
 #include "../evsel.h"
diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c
index b656655fbc39..b6ad8857da78 100644
--- a/tools/perf/ui/gtk/progress.c
+++ b/tools/perf/ui/gtk/progress.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 
 #include "gtk.h"
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 1d57676f8212..506e73b3834c 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "gtk.h"
 #include "../../util/cache.h"
 #include "../../util/debug.h"
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 00b91921edb1..7250d8101c8f 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../util.h"
 #include "../../util/util.h"
 #include "../../util/debug.h"
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 379039ab00d8..b3c421429ed4 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
index d52d0a1a881b..8f775a053ca3 100644
--- a/tools/perf/ui/helpline.h
+++ b/tools/perf/ui/helpline.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_HELPLINE_H_
 #define _PERF_UI_HELPLINE_H_ 1
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ddb2c6fbdf91..706f6f1e9c7d 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <math.h>
 #include <linux/compiler.h>
@@ -532,7 +533,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-        list_del(&format->list);
+        list_del_init(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -606,6 +607,13 @@ next:
 
 static void fmt_free(struct perf_hpp_fmt *fmt)
 {
+        /*
+         * At this point fmt should be completely
+         * unhooked, if not it's a bug.
+         */
+        BUG_ON(!list_empty(&fmt->list));
+        BUG_ON(!list_empty(&fmt->sort_list));
+
         if (fmt->free)
                 fmt->free(fmt);
 }
diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h
index 65092d576b4e..fbfac29077f2 100644
--- a/tools/perf/ui/keysyms.h
+++ b/tools/perf/ui/keysyms.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_KEYSYMS_H_
 #define _PERF_KEYSYMS_H_ 1
 
diff --git a/tools/perf/ui/libslang.h b/tools/perf/ui/libslang.h
index db816695ad97..c0686cda39a5 100644
--- a/tools/perf/ui/libslang.h
+++ b/tools/perf/ui/libslang.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_SLANG_H_
 #define _PERF_UI_SLANG_H_ 1
 /*
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index a0f24c7115c5..bbfbc91a0fa4 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "progress.h"
 
@@ -14,21 +16,29 @@ struct ui_progress_ops *ui_progress__ops = &null_progress__ops;
 
 void ui_progress__update(struct ui_progress *p, u64 adv)
 {
+        u64 last = p->curr;
+
         p->curr += adv;
 
         if (p->curr >= p->next) {
-                p->next += p->step;
+                u64 nr = DIV_ROUND_UP(p->curr - last, p->step);
+
+                p->next += nr * p->step;
                 ui_progress__ops->update(p);
         }
 }
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
+void __ui_progress__init(struct ui_progress *p, u64 total,
+                         const char *title, bool size)
 {
         p->curr = 0;
-        p->next = p->step = total / 16;
+        p->next = p->step = total / 16 ?: 1;
         p->total = total;
         p->title = title;
+        p->size  = size;
 
+        if (ui_progress__ops->init)
+                ui_progress__ops->init(p);
 }
 
 void ui_progress__finish(void)
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
index 717d39d3052b..4f52c37b2f09 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_PROGRESS_H_
 #define _PERF_UI_PROGRESS_H_ 1
 
@@ -8,12 +9,22 @@ void ui_progress__finish(void);
 struct ui_progress {
         const char *title;
         u64 curr, next, step, total;
+        bool size;
 };
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
+void __ui_progress__init(struct ui_progress *p, u64 total,
+                         const char *title, bool size);
+
+#define ui_progress__init(p, total, title) \
+        __ui_progress__init(p, total, title, false)
+
+#define ui_progress__init_size(p, total, title) \
+        __ui_progress__init(p, total, title, true)
+
 void ui_progress__update(struct ui_progress *p, u64 adv);
 
 struct ui_progress_ops {
+        void (*init)(struct ui_progress *p);
         void (*update)(struct ui_progress *p);
         void (*finish)(void);
 };
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index caf1ce6f5152..44fe824e96cd 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <pthread.h>
 #include <dlfcn.h>
 
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 42e432bd2eb4..25dd1e0ecc58 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -1,4 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
+#include <linux/string.h>
 
 #include "../../util/util.h"
 #include "../../util/hist.h"
@@ -20,67 +22,6 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
         return ret;
 }
 
-static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
-                              int depth, int depth_mask, FILE *fp)
-{
-        struct dso *dso;
-        struct inline_node *node;
-        struct inline_list *ilist;
-        int ret = 0, i;
-
-        if (map == NULL)
-                return 0;
-
-        dso = map->dso;
-        if (dso == NULL)
-                return 0;
-
-        if (dso->kernel != DSO_TYPE_USER)
-                return 0;
-
-        node = dso__parse_addr_inlines(dso,
-                                       map__rip_2objdump(map, ip));
-        if (node == NULL)
-                return 0;
-
-        list_for_each_entry(ilist, &node->val, list) {
-                if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
-                        ret += callchain__fprintf_left_margin(fp, left_margin);
-
-                        for (i = 0; i < depth; i++) {
-                                if (depth_mask & (1 << i))
-                                        ret += fprintf(fp, "|");
-                                else
-                                        ret += fprintf(fp, " ");
-                                ret += fprintf(fp, "          ");
-                        }
-
-                        if (callchain_param.key == CCKEY_ADDRESS ||
-                            callchain_param.key == CCKEY_SRCLINE) {
-                                if (ilist->filename != NULL)
-                                        ret += fprintf(fp, "%s:%d (inline)",
-                                                       ilist->filename,
-                                                       ilist->line_nr);
-                                else
-                                        ret += fprintf(fp, "??");
-                        } else if (ilist->funcname != NULL)
-                                ret += fprintf(fp, "%s (inline)",
-                                               ilist->funcname);
-                        else if (ilist->filename != NULL)
-                                ret += fprintf(fp, "%s:%d (inline)",
-                                               ilist->filename,
-                                               ilist->line_nr);
-                        else
-                                ret += fprintf(fp, "??");
-
-                        ret += fprintf(fp, "\n");
-                }
-        }
-
-        inline_node__delete(node);
-        return ret;
-}
-
 static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
                                           int left_margin)
 {
@@ -126,12 +67,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
         str = callchain_list__sym_name(chain, bf, sizeof(bf), false);
 
         if (symbol_conf.show_branchflag_count) {
-                if (!period)
-                        callchain_list_counts__printf_value(node, chain, NULL,
-                                                            buf, sizeof(buf));
-                else
-                        callchain_list_counts__printf_value(NULL, chain, NULL,
-                                                            buf, sizeof(buf));
+                callchain_list_counts__printf_value(chain, NULL,
+                                                    buf, sizeof(buf));
 
                 if (asprintf(&alloc_str, "%s%s", str, buf) < 0)
                         str = "Not enough memory!";
@@ -143,9 +80,6 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
         fputc('\n', fp);
         free(alloc_str);
 
-        if (symbol_conf.inline_name)
-                ret += inline__fprintf(chain->ms.map, chain->ip,
-                                       left_margin, depth, depth_mask, fp);
         return ret;
 }
 
@@ -295,7 +229,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                          * displayed twice.
                          */
                         if (!i++ && field_order == NULL &&
-                            sort_order && !prefixcmp(sort_order, "sym"))
+                            sort_order && strstarts(sort_order, "sym"))
                                 continue;
 
                         if (!printed) {
@@ -315,18 +249,11 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
                         if (symbol_conf.show_branchflag_count)
                                 ret += callchain_list_counts__printf_value(
-                                                NULL, chain, fp, NULL, 0);
+                                                chain, fp, NULL, 0);
                         ret += fprintf(fp, "\n");
 
                         if (++entries_printed == callchain_param.print_limit)
                                 break;
-
-                        if (symbol_conf.inline_name)
-                                ret += inline__fprintf(chain->ms.map,
-                                                       chain->ip,
-                                                       left_margin,
-                                                       0, 0,
-                                                       fp);
                 }
                 root = &cnode->rb_root;
         }
@@ -606,7 +533,6 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 {
         int ret;
         int callchain_ret = 0;
-        int inline_ret = 0;
         struct perf_hpp hpp = {
                 .buf            = bf,
                 .size           = size,
@@ -628,13 +554,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
                 callchain_ret = hist_entry_callchain__fprintf(he, total_period,
                                                               0, fp);
 
-        if (callchain_ret == 0 && symbol_conf.inline_name) {
-                inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
-                ret += inline_ret;
-                if (inline_ret > 0)
-                        ret += fprintf(fp, "\n");
-        } else
-                ret += callchain_ret;
+        ret += callchain_ret;
 
         return ret;
 }
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 88f5143a5981..4ca799aadb4e 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index c4b99008e2c9..bc134b82829d 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,12 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
 #include "tui.h"
+#include "units.h"
 #include "../browser.h"
 
+static void __tui_progress__init(struct ui_progress *p)
+{
+        p->next = p->step = p->total / (SLtt_Screen_Cols - 2) ?: 1;
+}
+
+static int get_title(struct ui_progress *p, char *buf, size_t size)
+{
+        char buf_cur[20];
+        char buf_tot[20];
+        int ret;
+
+        ret  = unit_number__scnprintf(buf_cur, sizeof(buf_cur), p->curr);
+        ret += unit_number__scnprintf(buf_tot, sizeof(buf_tot), p->total);
+
+        return ret + scnprintf(buf, size, "%s [%s/%s]",
+                               p->title, buf_cur, buf_tot);
+}
+
 static void tui_progress__update(struct ui_progress *p)
 {
+        char buf[100], *title = (char *) p->title;
         int bar, y;
         /*
          * FIXME: We should have a per UI backend way of showing progress,
@@ -18,13 +40,18 @@ static void tui_progress__update(struct ui_progress *p)
         if (p->total == 0)
                 return;
 
+        if (p->size) {
+                get_title(p, buf, sizeof(buf));
+                title = buf;
+        }
+
         ui__refresh_dimensions(false);
         pthread_mutex_lock(&ui__lock);
         y = SLtt_Screen_Rows / 2 - 2;
         SLsmg_set_color(0);
         SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
         SLsmg_gotorc(y++, 1);
-        SLsmg_write_string((char *)p->title);
+        SLsmg_write_string(title);
         SLsmg_fill_region(y, 1, 1, SLtt_Screen_Cols - 2, ' ');
         SLsmg_set_color(HE_COLORSET_SELECTED);
         bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;
@@ -49,8 +76,8 @@ static void tui_progress__finish(void)
         pthread_mutex_unlock(&ui__lock);
 }
 
-static struct ui_progress_ops tui_progress__ops =
-{
+static struct ui_progress_ops tui_progress__ops = {
+        .init   = __tui_progress__init,
         .update = tui_progress__update,
         .finish = tui_progress__finish,
 };
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index d9350a1da48b..d4ac41679721 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
diff --git a/tools/perf/ui/tui/tui.h b/tools/perf/ui/tui/tui.h
index 18961c7b6ec5..8de06f634c56 100644
--- a/tools/perf/ui/tui/tui.h
+++ b/tools/perf/ui/tui/tui.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_TUI_H_
 #define _PERF_TUI_H_ 1
 
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index d96ad7c8325d..b9794d6185af 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../../util/util.h"
 #include <signal.h>
 #include <stdbool.h>
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index 4b6fb6c7a542..9b6fdf06e1d2 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_H_
 #define _PERF_UI_H_ 1
 
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
index e3e0a963d03a..63bf06e80ab9 100644
--- a/tools/perf/ui/util.c
+++ b/tools/perf/ui/util.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "../debug.h"
 
diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h
index 361f08c52d37..5e44223b56fa 100644
--- a/tools/perf/ui/util.h
+++ b/tools/perf/ui/util.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UI_UTIL_H_
 #define _PERF_UI_UTIL_H_ 1
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 79dea95a7f68..a3de7916fe63 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -13,6 +13,7 @@ libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
+libperf-y += mmap.o
 libperf-y += memswap.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
@@ -22,6 +23,7 @@ libperf-y += rbtree.o
 libperf-y += libstring.o
 libperf-y += bitmap.o
 libperf-y += hweight.o
+libperf-y += smt.o
 libperf-y += quote.o
 libperf-y += strbuf.o
 libperf-y += string.o
@@ -33,6 +35,7 @@ libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += symbol_fprintf.o
 libperf-y += color.o
+libperf-y += metricgroup.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -77,6 +80,7 @@ libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
 libperf-y += call-path.o
+libperf-y += rwsem.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
@@ -93,6 +97,7 @@ libperf-y += drv_configs.o
 libperf-y += units.o
 libperf-y += time-utils.o
 libperf-y += expr-bison.o
+libperf-y += branch.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -104,6 +109,10 @@ ifndef CONFIG_LIBELF
 libperf-y += symbol-minimal.o
 endif
 
+ifndef CONFIG_SETNS
+libperf-y += setns.o
+endif
+
 libperf-$(CONFIG_DWARF) += probe-finder.o
 libperf-$(CONFIG_DWARF) += dwarf-aux.o
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 39f17507578d..3802cee5e188 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 if [ $# -eq 1 ]  ; then
         OUTPUT=$1
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index be1caabb9290..da1c4c4a0dd8 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -47,7 +47,11 @@ struct arch {
         bool            sorted_instructions;
         bool            initialized;
         void            *priv;
-        int             (*init)(struct arch *arch);
+        unsigned int    model;
+        unsigned int    family;
+        int             (*init)(struct arch *arch, char *cpuid);
+        bool            (*ins_is_fused)(struct arch *arch, const char *ins1,
+                                        const char *ins2);
         struct          {
                 char comment_char;
                 char skip_functions_char;
@@ -127,8 +131,10 @@ static struct arch architectures[] = {
         },
         {
                 .name = "x86",
+                .init = x86__annotate_init,
                 .instructions = x86__instructions,
                 .nr_instructions = ARRAY_SIZE(x86__instructions),
+                .ins_is_fused = x86__ins_is_fused,
                 .objdump =  {
                         .comment_char = '#',
                 },
@@ -171,6 +177,14 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
         return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
+{
+        if (!arch || !arch->ins_is_fused)
+                return false;
+
+        return arch->ins_is_fused(arch, ins1, ins2);
+}
+
 static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
 {
         char *endptr, *tok, *name;
@@ -502,6 +516,11 @@ bool ins__is_ret(const struct ins *ins)
         return ins->ops == &ret_ops;
 }
 
+bool ins__is_lock(const struct ins *ins)
+{
+        return ins->ops == &lock_ops;
+}
+
 static int ins__key_cmp(const void *name, const void *insp)
 {
         const struct ins *ins = insp;
@@ -586,14 +605,24 @@ static struct arch *arch__find(const char *name)
 int symbol__alloc_hist(struct symbol *sym)
 {
         struct annotation *notes = symbol__annotation(sym);
-        const size_t size = symbol__size(sym);
+        size_t size = symbol__size(sym);
         size_t sizeof_sym_hist;
 
+        /*
+         * Add buffer of one element for zero length symbol.
+         * When sample is taken from first instruction of
+         * zero length symbol, perf still resolves it and
+         * shows symbol name in perf report and allows to
+         * annotate it.
+         */
+        if (size == 0)
+                size = 1;
+
         /* Check for overflow when calculating sizeof_sym_hist */
-        if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64))
+        if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry))
                 return -1;
 
-        sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+        sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry));
 
         /* Check for overflow in zalloc argument */
         if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
@@ -677,7 +706,8 @@ static int __symbol__account_cycles(struct annotation *notes,
 }
 
 static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-                                      struct annotation *notes, int evidx, u64 addr)
+                                      struct annotation *notes, int evidx, u64 addr,
+                                      struct perf_sample *sample)
 {
         unsigned offset;
         struct sym_hist *h;
@@ -693,12 +723,15 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
         offset = addr - sym->start;
         h = annotation__histogram(notes, evidx);
-        h->sum++;
-        h->addr[offset]++;
+        h->nr_samples++;
+        h->addr[offset].nr_samples++;
+        h->period += sample->period;
+        h->addr[offset].period += sample->period;
 
         pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
-                  ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name,
-                  addr, addr - sym->start, evidx, h->addr[offset]);
+                  ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n",
+                  sym->start, sym->name, addr, addr - sym->start, evidx,
+                  h->addr[offset].nr_samples, h->addr[offset].period);
         return 0;
 }
 
@@ -718,7 +751,8 @@ static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles
 }
 
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-                                    int evidx, u64 addr)
+                                    int evidx, u64 addr,
+                                    struct perf_sample *sample)
 {
         struct annotation *notes;
 
@@ -727,7 +761,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
         notes = symbol__get_annotation(sym, false);
         if (notes == NULL)
                 return -ENOMEM;
-        return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
+        return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample);
 }
 
 static int symbol__account_cycles(u64 addr, u64 start,
@@ -791,14 +825,16 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
         return err;
 }
 
-int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx)
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
+                                 int evidx)
 {
-        return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr);
+        return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample);
 }
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
+int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
+                                 int evidx, u64 ip)
 {
-        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
+        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample);
 }
 
 static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map)
@@ -908,11 +944,12 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 }
 
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-                            s64 end, const char **path, u64 *nr_samples)
+                            s64 end, const char **path, struct sym_hist_entry *sample)
 {
         struct source_line *src_line = notes->src->lines;
         double percent = 0.0;
-        *nr_samples = 0;
+
+        sample->nr_samples = sample->period = 0;
 
         if (src_line) {
                 size_t sizeof_src_line = sizeof(*src_line) +
@@ -926,19 +963,24 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
                                 *path = src_line->path;
 
                         percent += src_line->samples[evidx].percent;
-                        *nr_samples += src_line->samples[evidx].nr;
+                        sample->nr_samples += src_line->samples[evidx].nr;
                         offset++;
                 }
         } else {
                 struct sym_hist *h = annotation__histogram(notes, evidx);
                 unsigned int hits = 0;
+                u64 period = 0;
 
-                while (offset < end)
-                        hits += h->addr[offset++];
+                while (offset < end) {
+                        hits   += h->addr[offset].nr_samples;
+                        period += h->addr[offset].period;
+                        ++offset;
+                }
 
-                if (h->sum) {
-                        *nr_samples = hits;
-                        percent = 100.0 * hits / h->sum;
+                if (h->nr_samples) {
+                        sample->period     = period;
+                        sample->nr_samples = hits;
+                        percent = 100.0 * hits / h->nr_samples;
                 }
         }
 
@@ -1037,10 +1079,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
         if (dl->offset != -1) {
                 const char *path = NULL;
-                u64 nr_samples;
                 double percent, max_percent = 0.0;
                 double *ppercents = &percent;
-                u64 *psamples = &nr_samples;
+                struct sym_hist_entry sample;
+                struct sym_hist_entry *psamples = &sample;
                 int i, nr_percent = 1;
                 const char *color;
                 struct annotation *notes = symbol__annotation(sym);
@@ -1054,7 +1096,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 if (perf_evsel__is_group_event(evsel)) {
                         nr_percent = evsel->nr_members;
                         ppercents = calloc(nr_percent, sizeof(double));
-                        psamples = calloc(nr_percent, sizeof(u64));
+                        psamples = calloc(nr_percent, sizeof(struct sym_hist_entry));
                         if (ppercents == NULL || psamples == NULL) {
                                 return -1;
                         }
@@ -1065,10 +1107,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                                         notes->src->lines ? i : evsel->idx + i,
                                         offset,
                                         next ? next->offset : (s64) len,
-                                        &path, &nr_samples);
+                                        &path, &sample);
 
                         ppercents[i] = percent;
-                        psamples[i] = nr_samples;
+                        psamples[i] = sample;
                         if (percent > max_percent)
                                 max_percent = percent;
                 }
@@ -1106,12 +1148,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
                 for (i = 0; i < nr_percent; i++) {
                         percent = ppercents[i];
-                        nr_samples = psamples[i];
+                        sample = psamples[i];
                         color = get_percent_color(percent);
 
                         if (symbol_conf.show_total_period)
+                                color_fprintf(stdout, color, " %11" PRIu64,
+                                              sample.period);
+                        else if (symbol_conf.show_nr_samples)
                                 color_fprintf(stdout, color, " %7" PRIu64,
-                                              nr_samples);
+                                              sample.nr_samples);
                         else
                                 color_fprintf(stdout, color, " %7.2f", percent);
                 }
@@ -1127,13 +1172,13 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 if (ppercents != &percent)
                         free(ppercents);
 
-                if (psamples != &nr_samples)
+                if (psamples != &sample)
                         free(psamples);
 
         } else if (max_lines && printed >= max_lines)
                 return 1;
         else {
-                int width = 8;
+                int width = symbol_conf.show_total_period ? 12 : 8;
 
                 if (queue)
                         return -1;
@@ -1327,7 +1372,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
             !dso__is_kcore(dso))
                 return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
 
-        build_id_filename = dso__build_id_filename(dso, NULL, 0);
+        build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
         if (build_id_filename) {
                 __symbol__join_symfs(filename, filename_size, build_id_filename);
                 free(build_id_filename);
@@ -1381,7 +1426,7 @@ static const char *annotate__norm_arch(const char *arch_name)
 
 int symbol__disassemble(struct symbol *sym, struct map *map,
                         const char *arch_name, size_t privsize,
-                        struct arch **parch)
+                        struct arch **parch, char *cpuid)
 {
         struct dso *dso = map->dso;
         char command[PATH_MAX * 2];
@@ -1411,7 +1456,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
                 *parch = arch;
 
         if (arch->init) {
-                err = arch->init(arch);
+                err = arch->init(arch, cpuid);
                 if (err) {
                         pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
                         return err;
@@ -1648,19 +1693,19 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
         struct sym_hist *h = annotation__histogram(notes, evidx);
         struct rb_root tmp_root = RB_ROOT;
         int nr_pcnt = 1;
-        u64 h_sum = h->sum;
+        u64 nr_samples = h->nr_samples;
         size_t sizeof_src_line = sizeof(struct source_line);
 
         if (perf_evsel__is_group_event(evsel)) {
                 for (i = 1; i < evsel->nr_members; i++) {
                         h = annotation__histogram(notes, evidx + i);
-                        h_sum += h->sum;
+                        nr_samples += h->nr_samples;
                 }
                 nr_pcnt = evsel->nr_members;
                 sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
         }
 
-        if (!h_sum)
+        if (!nr_samples)
                 return 0;
 
         src_line = notes->src->lines = calloc(len, sizeof_src_line);
@@ -1670,7 +1715,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
         start = map__rip_2objdump(map, sym->start);
 
         for (i = 0; i < len; i++) {
-                u64 offset, nr_samples;
+                u64 offset;
                 double percent_max = 0.0;
 
                 src_line->nr_pcnt = nr_pcnt;
@@ -1679,9 +1724,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
                         double percent = 0.0;
 
                         h = annotation__histogram(notes, evidx + k);
-                        nr_samples = h->addr[i];
-                        if (h->sum)
-                                percent = 100.0 * nr_samples / h->sum;
+                        nr_samples = h->addr[i].nr_samples;
+                        if (h->nr_samples)
+                                percent = 100.0 * nr_samples / h->nr_samples;
 
                         if (percent > percent_max)
                                 percent_max = percent;
@@ -1750,10 +1795,10 @@ static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
         u64 len = symbol__size(sym), offset;
 
         for (offset = 0; offset < len; ++offset)
-                if (h->addr[offset] != 0)
+                if (h->addr[offset].nr_samples != 0)
                         printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
-                               sym->start + offset, h->addr[offset]);
-        printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+                               sym->start + offset, h->addr[offset].nr_samples);
+        printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples);
 }
 
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
@@ -1771,7 +1816,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
         int printed = 2, queue_len = 0;
         int more = 0;
         u64 len;
-        int width = 8;
+        int width = symbol_conf.show_total_period ? 12 : 8;
         int graph_dotted_len;
 
         filename = strdup(dso->long_name);
@@ -1789,7 +1834,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
                 width *= evsel->nr_members;
 
         graph_dotted_len = printf(" %-*.*s|     Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
-               width, width, "Percent", d_filename, evsel_name, h->sum);
+                                  width, width, symbol_conf.show_total_period ? "Period" :
+                                  symbol_conf.show_nr_samples ? "Samples" : "Percent",
+                                  d_filename, evsel_name, h->nr_samples);
 
         printf("%-*.*s----\n",
                graph_dotted_len, graph_dotted_len, graph_dotted_line);
@@ -1853,10 +1900,10 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
         struct sym_hist *h = annotation__histogram(notes, evidx);
         int len = symbol__size(sym), offset;
 
-        h->sum = 0;
+        h->nr_samples = 0;
         for (offset = 0; offset < len; ++offset) {
-                h->addr[offset] = h->addr[offset] * 7 / 8;
-                h->sum += h->addr[offset];
+                h->addr[offset].nr_samples = h->addr[offset].nr_samples * 7 / 8;
+                h->nr_samples += h->addr[offset].nr_samples;
         }
 }
 
@@ -1907,7 +1954,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
         u64 len;
 
         if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                0, NULL) < 0)
+                                0, NULL, NULL) < 0)
                 return -1;
 
         len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 21055034aedd..f6ba3560de5e 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_ANNOTATE_H
 #define __PERF_ANNOTATE_H
 
@@ -52,7 +53,9 @@ struct ins_ops {
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 bool ins__is_ret(const struct ins *ins);
+bool ins__is_lock(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 struct annotation;
 
@@ -72,16 +75,22 @@ static inline bool disasm_line__has_offset(const struct disasm_line *dl)
         return dl->ops.target.offset_avail;
 }
 
+struct sym_hist_entry {
+        u64             nr_samples;
+        u64             period;
+};
+
 void disasm_line__free(struct disasm_line *dl);
 struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-                            s64 end, const char **path, u64 *nr_samples);
+                            s64 end, const char **path, struct sym_hist_entry *sample);
 
 struct sym_hist {
-        u64             sum;
-        u64             addr[0];
+        u64                   nr_samples;
+        u64                   period;
+        struct sym_hist_entry addr[0];
 };
 
 struct cyc_hist {
@@ -147,20 +156,22 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
         return (void *)sym - symbol_conf.priv_size;
 }
 
-int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
+                                 int evidx);
 
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
                                     struct addr_map_symbol *start,
                                     unsigned cycles);
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
+int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
+                                 int evidx, u64 addr);
 
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__disassemble(struct symbol *sym, struct map *map,
                         const char *arch_name, size_t privsize,
-                        struct arch **parch);
+                        struct arch **parch, char *cpuid);
 
 enum symbol_disassemble_errno {
         SYMBOL_ANNOTATE_ERRNO__SUCCESS          = 0,
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 5547457566a7..a33491416400 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -208,7 +208,7 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues,
 
 static void *auxtrace_copy_data(u64 size, struct perf_session *session)
 {
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         void *p;
         ssize_t ret;
 
@@ -305,7 +305,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
         if (session->one_mmap) {
                 buffer->data = buffer->data_offset - session->one_mmap_offset +
                                session->one_mmap_addr;
-        } else if (perf_data_file__is_pipe(session->file)) {
+        } else if (perf_data__is_pipe(session->data)) {
                 buffer->data = auxtrace_copy_data(buffer->size, session);
                 if (!buffer->data)
                         return -ENOMEM;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 33b5e6cdf38c..d19e11b68de7 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -378,7 +378,7 @@ struct addr_filters {
 static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
 {
         struct perf_event_mmap_page *pc = mm->userpg;
-        u64 head = ACCESS_ONCE(pc->aux_head);
+        u64 head = READ_ONCE(pc->aux_head);
 
         /* Ensure all reads are done after we read the head */
         rmb();
@@ -389,7 +389,7 @@ static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
 {
         struct perf_event_mmap_page *pc = mm->userpg;
 #if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
-        u64 head = ACCESS_ONCE(pc->aux_head);
+        u64 head = READ_ONCE(pc->aux_head);
 #else
         u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
 #endif
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
index 7b3e1d75d803..f1451c987eec 100644
--- a/tools/perf/util/block-range.c
+++ b/tools/perf/util/block-range.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "block-range.h"
 #include "annotate.h"
 
diff --git a/tools/perf/util/block-range.h b/tools/perf/util/block-range.h
index a8c841381131..a5ba719d69fb 100644
--- a/tools/perf/util/block-range.h
+++ b/tools/perf/util/block-range.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_BLOCK_RANGE_H
 #define __PERF_BLOCK_RANGE_H
 
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 4bd2d1d882af..72c107fcbc5a 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * bpf-loader.c
  *
@@ -1246,7 +1247,7 @@ int bpf__config_obj(struct bpf_object *obj,
         if (!obj || !term || !term->config)
                 return -EINVAL;
 
-        if (!prefixcmp(term->config, "map:")) {
+        if (strstarts(term->config, "map:")) {
                 key_scan_pos = sizeof("map:") - 1;
                 err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
                 goto out;
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 48863867878b..5d3aefd6fae7 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015, Huawei Inc.
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 1356220a9f1b..29347756b0af 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * bpf-prologue.c
  *
@@ -58,6 +59,46 @@ check_pos(struct bpf_insn_pos *pos)
         return 0;
 }
 
+/*
+ * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
+ * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM
+ * instruction (BPF_{B,H,W,DW}).
+ */
+static int
+argtype_to_ldx_size(const char *type)
+{
+        int arg_size = type ? atoi(&type[1]) : 64;
+
+        switch (arg_size) {
+        case 8:
+                return BPF_B;
+        case 16:
+                return BPF_H;
+        case 32:
+                return BPF_W;
+        case 64:
+        default:
+                return BPF_DW;
+        }
+}
+
+static const char *
+insn_sz_to_str(int insn_sz)
+{
+        switch (insn_sz) {
+        case BPF_B:
+                return "BPF_B";
+        case BPF_H:
+                return "BPF_H";
+        case BPF_W:
+                return "BPF_W";
+        case BPF_DW:
+                return "BPF_DW";
+        default:
+                return "UNKNOWN";
+        }
+}
+
 /* Give it a shorter name */
 #define ins(i, p) append_insn((i), (p))
 
@@ -258,9 +299,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos,
         }
 
         /* Final pass: read to registers */
-        for (i = 0; i < nargs; i++)
-                ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+        for (i = 0; i < nargs; i++) {
+                int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW;
+
+                pr_debug("prologue: load arg %d, insn_sz is %s\n",
+                         i, insn_sz_to_str(insn_sz));
+                ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i,
                                 BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+        }
 
         ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
 
diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h
index ba564838375f..c50c7358009f 100644
--- a/tools/perf/util/bpf-prologue.h
+++ b/tools/perf/util/bpf-prologue.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2015, He Kuang <hekuang@huawei.com>
  * Copyright (C) 2015, Huawei Inc.
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
new file mode 100644
index 000000000000..a4fce2729e50
--- /dev/null
+++ b/tools/perf/util/branch.c
@@ -0,0 +1,147 @@
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/branch.h"
+
+static bool cross_area(u64 addr1, u64 addr2, int size)
+{
+        u64 align1, align2;
+
+        align1 = addr1 & ~(size - 1);
+        align2 = addr2 & ~(size - 1);
+
+        return (align1 != align2) ? true : false;
+}
+
+#define AREA_4K         4096
+#define AREA_2M         (2 * 1024 * 1024)
+
+void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
+                       u64 from, u64 to)
+{
+        if (flags->type == PERF_BR_UNKNOWN || from == 0)
+                return;
+
+        st->counts[flags->type]++;
+
+        if (flags->type == PERF_BR_COND) {
+                if (to > from)
+                        st->cond_fwd++;
+                else
+                        st->cond_bwd++;
+        }
+
+        if (cross_area(from, to, AREA_2M))
+                st->cross_2m++;
+        else if (cross_area(from, to, AREA_4K))
+                st->cross_4k++;
+}
+
+const char *branch_type_name(int type)
+{
+        const char *branch_names[PERF_BR_MAX] = {
+                "N/A",
+                "COND",
+                "UNCOND",
+                "IND",
+                "CALL",
+                "IND_CALL",
+                "RET",
+                "SYSCALL",
+                "SYSRET",
+                "COND_CALL",
+                "COND_RET"
+        };
+
+        if (type >= 0 && type < PERF_BR_MAX)
+                return branch_names[type];
+
+        return NULL;
+}
+
+void branch_type_stat_display(FILE *fp, struct branch_type_stat *st)
+{
+        u64 total = 0;
+        int i;
+
+        for (i = 0; i < PERF_BR_MAX; i++)
+                total += st->counts[i];
+
+        if (total == 0)
+                return;
+
+        fprintf(fp, "\n#");
+        fprintf(fp, "\n# Branch Statistics:");
+        fprintf(fp, "\n#");
+
+        if (st->cond_fwd > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "COND_FWD",
+                        100.0 * (double)st->cond_fwd / (double)total);
+        }
+
+        if (st->cond_bwd > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "COND_BWD",
+                        100.0 * (double)st->cond_bwd / (double)total);
+        }
+
+        if (st->cross_4k > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "CROSS_4K",
+                        100.0 * (double)st->cross_4k / (double)total);
+        }
+
+        if (st->cross_2m > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "CROSS_2M",
+                        100.0 * (double)st->cross_2m / (double)total);
+        }
+
+        for (i = 0; i < PERF_BR_MAX; i++) {
+                if (st->counts[i] > 0)
+                        fprintf(fp, "\n%8s: %5.1f%%",
+                                branch_type_name(i),
+                                100.0 *
+                                (double)st->counts[i] / (double)total);
+        }
+}
+
+static int count_str_scnprintf(int idx, const char *str, char *bf, int size)
+{
+        return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str);
+}
+
+int branch_type_str(struct branch_type_stat *st, char *bf, int size)
+{
+        int i, j = 0, printed = 0;
+        u64 total = 0;
+
+        for (i = 0; i < PERF_BR_MAX; i++)
+                total += st->counts[i];
+
+        if (total == 0)
+                return 0;
+
+        if (st->cond_fwd > 0)
+                printed += count_str_scnprintf(j++, "COND_FWD", bf + printed, size - printed);
+
+        if (st->cond_bwd > 0)
+                printed += count_str_scnprintf(j++, "COND_BWD", bf + printed, size - printed);
+
+        for (i = 0; i < PERF_BR_MAX; i++) {
+                if (i == PERF_BR_COND)
+                        continue;
+
+                if (st->counts[i] > 0)
+                        printed += count_str_scnprintf(j++, branch_type_name(i), bf + printed, size - printed);
+        }
+
+        if (st->cross_4k > 0)
+                printed += count_str_scnprintf(j++, "CROSS_4K", bf + printed, size - printed);
+
+        if (st->cross_2m > 0)
+                printed += count_str_scnprintf(j++, "CROSS_2M", bf + printed, size - printed);
+
+        return printed;
+}
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
new file mode 100644
index 000000000000..1e3c7c5cdc63
--- /dev/null
+++ b/tools/perf/util/branch.h
@@ -0,0 +1,25 @@
+#ifndef _PERF_BRANCH_H
+#define _PERF_BRANCH_H 1
+
+#include <stdint.h>
+#include "../perf.h"
+
+struct branch_type_stat {
+        bool    branch_to;
+        u64     counts[PERF_BR_MAX];
+        u64     cond_fwd;
+        u64     cond_bwd;
+        u64     cross_4k;
+        u64     cross_2m;
+};
+
+struct branch_flags;
+
+void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
+                       u64 from, u64 to);
+
+const char *branch_type_name(int type);
+void branch_type_stat_display(FILE *fp, struct branch_type_stat *st);
+int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize);
+
+#endif /* _PERF_BRANCH_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e0148b081bdf..7f8553630c4d 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * build-id.c
  *
@@ -243,12 +244,15 @@ static bool build_id_cache__valid_id(char *sbuild_id)
         return result;
 }
 
-static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
+static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso,
+                                            bool is_debug)
 {
-        return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
+        return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : (is_debug ?
+            "debug" : "elf"));
 }
 
-char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+                             bool is_debug)
 {
         bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
         bool is_vdso = dso__is_vdso((struct dso *)dso);
@@ -270,7 +274,8 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
                 ret = asnprintf(&bf, size, "%s", linkname);
         else
                 ret = asnprintf(&bf, size, "%s/%s", linkname,
-                         build_id_cache__basename(is_kallsyms, is_vdso));
+                         build_id_cache__basename(is_kallsyms, is_vdso,
+                                                  is_debug));
         if (ret < 0 || (!alloc && size < (unsigned int)ret))
                 bf = NULL;
         free(linkname);
@@ -285,7 +290,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
                 else
 
 static int write_buildid(const char *name, size_t name_len, u8 *build_id,
-                         pid_t pid, u16 misc, int fd)
+                         pid_t pid, u16 misc, struct feat_fd *fd)
 {
         int err;
         struct build_id_event b;
@@ -300,14 +305,15 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
         b.header.misc = misc;
         b.header.size = sizeof(b) + len;
 
-        err = writen(fd, &b, sizeof(b));
+        err = do_write(fd, &b, sizeof(b));
         if (err < 0)
                 return err;
 
         return write_padded(fd, name, name_len + 1, len);
 }
 
-static int machine__write_buildid_table(struct machine *machine, int fd)
+static int machine__write_buildid_table(struct machine *machine,
+                                        struct feat_fd *fd)
 {
         int err = 0;
         char nm[PATH_MAX];
@@ -352,7 +358,8 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
         return err;
 }
 
-int perf_session__write_buildid_table(struct perf_session *session, int fd)
+int perf_session__write_buildid_table(struct perf_session *session,
+                                      struct feat_fd *fd)
 {
         struct rb_node *nd;
         int err = machine__write_buildid_table(&session->machines.host, fd);
@@ -534,13 +541,14 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id)
 }
 
 char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
-                               bool is_kallsyms, bool is_vdso)
+                               struct nsinfo *nsi, bool is_kallsyms,
+                               bool is_vdso)
 {
         char *realname = (char *)name, *filename;
         bool slash = is_kallsyms || is_vdso;
 
         if (!slash) {
-                realname = realpath(name, NULL);
+                realname = nsinfo__realpath(name, nsi);
                 if (!realname)
                         return NULL;
         }
@@ -556,13 +564,13 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
         return filename;
 }
 
-int build_id_cache__list_build_ids(const char *pathname,
+int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
                                    struct strlist **result)
 {
         char *dir_name;
         int ret = 0;
 
-        dir_name = build_id_cache__cachedir(NULL, pathname, false, false);
+        dir_name = build_id_cache__cachedir(NULL, pathname, nsi, false, false);
         if (!dir_name)
                 return -ENOMEM;
 
@@ -576,16 +584,20 @@ int build_id_cache__list_build_ids(const char *pathname,
 
 #if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT)
 static int build_id_cache__add_sdt_cache(const char *sbuild_id,
-                                          const char *realname)
+                                          const char *realname,
+                                          struct nsinfo *nsi)
 {
         struct probe_cache *cache;
         int ret;
+        struct nscookie nsc;
 
-        cache = probe_cache__new(sbuild_id);
+        cache = probe_cache__new(sbuild_id, nsi);
         if (!cache)
                 return -1;
 
+        nsinfo__mountns_enter(nsi, &nsc);
         ret = probe_cache__scan_sdt(cache, realname);
+        nsinfo__mountns_exit(&nsc);
         if (ret >= 0) {
                 pr_debug4("Found %d SDTs in %s\n", ret, realname);
                 if (probe_cache__commit(cache) < 0)
@@ -595,25 +607,56 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id,
         return ret;
 }
 #else
-#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0)
+#define build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) (0)
 #endif
 
+static char *build_id_cache__find_debug(const char *sbuild_id,
+                                        struct nsinfo *nsi)
+{
+        char *realname = NULL;
+        char *debugfile;
+        struct nscookie nsc;
+        size_t len = 0;
+
+        debugfile = calloc(1, PATH_MAX);
+        if (!debugfile)
+                goto out;
+
+        len = __symbol__join_symfs(debugfile, PATH_MAX,
+                                   "/usr/lib/debug/.build-id/");
+        snprintf(debugfile + len, PATH_MAX - len, "%.2s/%s.debug", sbuild_id,
+                 sbuild_id + 2);
+
+        nsinfo__mountns_enter(nsi, &nsc);
+        realname = realpath(debugfile, NULL);
+        if (realname && access(realname, R_OK))
+                zfree(&realname);
+        nsinfo__mountns_exit(&nsc);
+out:
+        free(debugfile);
+        return realname;
+}
+
 int build_id_cache__add_s(const char *sbuild_id, const char *name,
-                          bool is_kallsyms, bool is_vdso)
+                          struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
 {
         const size_t size = PATH_MAX;
         char *realname = NULL, *filename = NULL, *dir_name = NULL,
              *linkname = zalloc(size), *tmp;
+        char *debugfile = NULL;
         int err = -1;
 
         if (!is_kallsyms) {
-                realname = realpath(name, NULL);
+                if (!is_vdso)
+                        realname = nsinfo__realpath(name, nsi);
+                else
+                        realname = realpath(name, NULL);
                 if (!realname)
                         goto out_free;
         }
 
-        dir_name = build_id_cache__cachedir(sbuild_id, name,
-                                            is_kallsyms, is_vdso);
+        dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms,
+                                            is_vdso);
         if (!dir_name)
                 goto out_free;
 
@@ -627,20 +670,52 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 
         /* Save the allocated buildid dirname */
         if (asprintf(&filename, "%s/%s", dir_name,
-                     build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
+                     build_id_cache__basename(is_kallsyms, is_vdso,
+                     false)) < 0) {
                 filename = NULL;
                 goto out_free;
         }
 
         if (access(filename, F_OK)) {
                 if (is_kallsyms) {
-                         if (copyfile("/proc/kallsyms", filename))
+                        if (copyfile("/proc/kallsyms", filename))
+                                goto out_free;
+                } else if (nsi && nsi->need_setns) {
+                        if (copyfile_ns(name, filename, nsi))
                                 goto out_free;
                 } else if (link(realname, filename) && errno != EEXIST &&
                                 copyfile(name, filename))
                         goto out_free;
         }
 
+        /* Some binaries are stripped, but have .debug files with their symbol
+         * table.  Check to see if we can locate one of those, since the elf
+         * file itself may not be very useful to users of our tools without a
+         * symtab.
+         */
+        if (!is_kallsyms && !is_vdso &&
+            strncmp(".ko", name + strlen(name) - 3, 3)) {
+                debugfile = build_id_cache__find_debug(sbuild_id, nsi);
+                if (debugfile) {
+                        zfree(&filename);
+                        if (asprintf(&filename, "%s/%s", dir_name,
+                            build_id_cache__basename(false, false, true)) < 0) {
+                                filename = NULL;
+                                goto out_free;
+                        }
+                        if (access(filename, F_OK)) {
+                                if (nsi && nsi->need_setns) {
+                                        if (copyfile_ns(debugfile, filename,
+                                                        nsi))
+                                                goto out_free;
+                                } else if (link(debugfile, filename) &&
+                                                errno != EEXIST &&
+                                                copyfile(debugfile, filename))
+                                        goto out_free;
+                        }
+                }
+        }
+
         if (!build_id_cache__linkname(sbuild_id, linkname, size))
                 goto out_free;
         tmp = strrchr(linkname, '/');
@@ -657,27 +732,30 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
                 err = 0;
 
         /* Update SDT cache : error is just warned */
-        if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+        if (realname &&
+            build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) < 0)
                 pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
         if (!is_kallsyms)
                 free(realname);
         free(filename);
+        free(debugfile);
         free(dir_name);
         free(linkname);
         return err;
 }
 
 static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
-                                 const char *name, bool is_kallsyms,
-                                 bool is_vdso)
+                                 const char *name, struct nsinfo *nsi,
+                                 bool is_kallsyms, bool is_vdso)
 {
         char sbuild_id[SBUILD_ID_SIZE];
 
         build_id__sprintf(build_id, build_id_size, sbuild_id);
 
-        return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso);
+        return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms,
+                                     is_vdso);
 }
 
 bool build_id_cache__cached(const char *sbuild_id)
@@ -743,7 +821,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine)
                 name = nm;
         }
         return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
-                                     is_kallsyms, is_vdso);
+                                     dso->nsinfo, is_kallsyms, is_vdso);
 }
 
 static int __dsos__cache_build_ids(struct list_head *head,
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 96690a55c62c..f0c565164a97 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_BUILD_ID_H_
 #define PERF_BUILD_ID_H_ 1
 
@@ -5,10 +6,12 @@
 #define SBUILD_ID_SIZE  (BUILD_ID_SIZE * 2 + 1)
 
 #include "tool.h"
+#include "namespaces.h"
 #include <linux/types.h>
 
 extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
+struct feat_fd;
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
@@ -16,7 +19,8 @@ int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
                                     size_t size);
 
-char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+                             bool is_debug);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
                            struct perf_sample *sample, struct perf_evsel *evsel,
@@ -25,23 +29,26 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 int dsos__hit_all(struct perf_session *session);
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
-int perf_session__write_buildid_table(struct perf_session *session, int fd);
+int perf_session__write_buildid_table(struct perf_session *session,
+                                      struct feat_fd *fd);
 int perf_session__cache_build_ids(struct perf_session *session);
 
 char *build_id_cache__origname(const char *sbuild_id);
 char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
 char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
-                               bool is_kallsyms, bool is_vdso);
+                               struct nsinfo *nsi, bool is_kallsyms,
+                               bool is_vdso);
 
 struct strlist;
 
 struct strlist *build_id_cache__list_all(bool validonly);
 char *build_id_cache__complement(const char *incomplete_sbuild_id);
-int build_id_cache__list_build_ids(const char *pathname,
+int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
                                    struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
 int build_id_cache__add_s(const char *sbuild_id,
-                          const char *name, bool is_kallsyms, bool is_vdso);
+                          const char *name, struct nsinfo *nsi,
+                          bool is_kallsyms, bool is_vdso);
 int build_id_cache__remove_s(const char *sbuild_id);
 
 extern char buildid_dir[];
diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h
index ccafcf72b37a..e513366f2ee0 100644
--- a/tools/perf/util/c++/clang-c.h
+++ b/tools/perf/util/c++/clang-c.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_UTIL_CLANG_C_H
 #define PERF_UTIL_CLANG_C_H
 
diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp
index 9b11e8c82798..a4014d786676 100644
--- a/tools/perf/util/c++/clang-test.cpp
+++ b/tools/perf/util/c++/clang-test.cpp
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "clang.h"
 #include "clang-c.h"
 #include "llvm/IR/Function.h"
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 1e974152cac2..1bfc946e37dc 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * llvm C frontend for perf. Support dynamically compile C file
  *
diff --git a/tools/perf/util/c++/clang.h b/tools/perf/util/c++/clang.h
index dd8b0427550d..6ce33e22f23c 100644
--- a/tools/perf/util/c++/clang.h
+++ b/tools/perf/util/c++/clang.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_UTIL_CLANG_H
 #define PERF_UTIL_CLANG_H
 
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 0175765c05b9..9f2e36ef5072 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index b4204b43ed58..082505d08d72 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com>
  *
@@ -23,6 +24,7 @@
 #include "sort.h"
 #include "machine.h"
 #include "callchain.h"
+#include "branch.h"
 
 #define CALLCHAIN_PARAM_DEFAULT                 \
         .mode           = CHAIN_GRAPH_ABS,      \
@@ -64,8 +66,6 @@ static int parse_callchain_mode(const char *value)
                 callchain_param.mode = CHAIN_FOLDED;
                 return 0;
         }
-
-        pr_err("Invalid callchain mode: %s\n", value);
         return -1;
 }
 
@@ -81,8 +81,6 @@ static int parse_callchain_order(const char *value)
                 callchain_param.order_set = true;
                 return 0;
         }
-
-        pr_err("Invalid callchain order: %s\n", value);
         return -1;
 }
 
@@ -104,8 +102,6 @@ static int parse_callchain_sort_key(const char *value)
                 callchain_param.branch_callstack = 1;
                 return 0;
         }
-
-        pr_err("Invalid callchain sort key: %s\n", value);
         return -1;
 }
 
@@ -123,8 +119,6 @@ static int parse_callchain_value(const char *value)
                 callchain_param.value = CCVAL_COUNT;
                 return 0;
         }
-
-        pr_err("Invalid callchain config key: %s\n", value);
         return -1;
 }
 
@@ -303,7 +297,7 @@ int perf_callchain_config(const char *var, const char *value)
 {
         char *endptr;
 
-        if (prefixcmp(var, "call-graph."))
+        if (!strstarts(var, "call-graph."))
                 return 0;
         var += sizeof("call-graph.") - 1;
 
@@ -318,12 +312,27 @@ int perf_callchain_config(const char *var, const char *value)
 
                 return ret;
         }
-        if (!strcmp(var, "print-type"))
-                return parse_callchain_mode(value);
-        if (!strcmp(var, "order"))
-                return parse_callchain_order(value);
-        if (!strcmp(var, "sort-key"))
-                return parse_callchain_sort_key(value);
+        if (!strcmp(var, "print-type")){
+                int ret;
+                ret = parse_callchain_mode(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain mode: %s\n", value);
+                return ret;
+        }
+        if (!strcmp(var, "order")){
+                int ret;
+                ret = parse_callchain_order(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain order: %s\n", value);
+                return ret;
+        }
+        if (!strcmp(var, "sort-key")){
+                int ret;
+                ret = parse_callchain_sort_key(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain sort key: %s\n", value);
+                return ret;
+        }
         if (!strcmp(var, "threshold")) {
                 callchain_param.min_percent = strtod(value, &endptr);
                 if (value == endptr) {
@@ -558,19 +567,38 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                 call->ip = cursor_node->ip;
                 call->ms.sym = cursor_node->sym;
                 call->ms.map = map__get(cursor_node->map);
+                call->srcline = cursor_node->srcline;
 
                 if (cursor_node->branch) {
                         call->branch_count = 1;
 
-                        if (cursor_node->branch_flags.predicted)
-                                call->predicted_count = 1;
-
-                        if (cursor_node->branch_flags.abort)
-                                call->abort_count = 1;
-
-                        call->cycles_count = cursor_node->branch_flags.cycles;
-                        call->iter_count = cursor_node->nr_loop_iter;
-                        call->samples_count = cursor_node->samples;
+                        if (cursor_node->branch_from) {
+                                /*
+                                 * branch_from is set with value somewhere else
+                                 * to imply it's "to" of a branch.
+                                 */
+                                call->brtype_stat.branch_to = true;
+
+                                if (cursor_node->branch_flags.predicted)
+                                        call->predicted_count = 1;
+
+                                if (cursor_node->branch_flags.abort)
+                                        call->abort_count = 1;
+
+                                branch_type_count(&call->brtype_stat,
+                                                  &cursor_node->branch_flags,
+                                                  cursor_node->branch_from,
+                                                  cursor_node->ip);
+                        } else {
+                                /*
+                                 * It's "from" of a branch
+                                 */
+                                call->brtype_stat.branch_to = false;
+                                call->cycles_count =
+                                        cursor_node->branch_flags.cycles;
+                                call->iter_count = cursor_node->nr_loop_iter;
+                                call->iter_cycles = cursor_node->iter_cycles;
+                        }
                 }
 
                 list_add_tail(&call->list, &node->val);
@@ -618,66 +646,97 @@ enum match_result {
         MATCH_GT,
 };
 
-static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
-                                             struct callchain_list *cnode)
+static enum match_result match_chain_strings(const char *left,
+                                             const char *right)
 {
-        char *left = NULL;
-        char *right = NULL;
         enum match_result ret = MATCH_EQ;
         int cmp;
 
-        if (cnode->ms.map)
-                left = get_srcline(cnode->ms.map->dso,
-                                 map__rip_2objdump(cnode->ms.map, cnode->ip),
-                                 cnode->ms.sym, true, false);
-        if (node->map)
-                right = get_srcline(node->map->dso,
-                                  map__rip_2objdump(node->map, node->ip),
-                                  node->sym, true, false);
-
         if (left && right)
                 cmp = strcmp(left, right);
         else if (!left && right)
                 cmp = 1;
         else if (left && !right)
                 cmp = -1;
-        else if (cnode->ip == node->ip)
-                cmp = 0;
         else
-                cmp = (cnode->ip < node->ip) ? -1 : 1;
+                return MATCH_ERROR;
 
         if (cmp != 0)
                 ret = cmp < 0 ? MATCH_LT : MATCH_GT;
 
-        free_srcline(left);
-        free_srcline(right);
         return ret;
 }
 
+/*
+ * We need to always use relative addresses because we're aggregating
+ * callchains from multiple threads, i.e. different address spaces, so
+ * comparing absolute addresses make no sense as a symbol in a DSO may end up
+ * in a different address when used in a different binary or even the same
+ * binary but with some sort of address randomization technique, thus we need
+ * to compare just relative addresses. -acme
+ */
+static enum match_result match_chain_dso_addresses(struct map *left_map, u64 left_ip,
+                                                   struct map *right_map, u64 right_ip)
+{
+        struct dso *left_dso = left_map ? left_map->dso : NULL;
+        struct dso *right_dso = right_map ? right_map->dso : NULL;
+
+        if (left_dso != right_dso)
+                return left_dso < right_dso ? MATCH_LT : MATCH_GT;
+
+        if (left_ip != right_ip)
+                return left_ip < right_ip ? MATCH_LT : MATCH_GT;
+
+        return MATCH_EQ;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
                                      struct callchain_list *cnode)
 {
-        struct symbol *sym = node->sym;
-        u64 left, right;
-
-        if (callchain_param.key == CCKEY_SRCLINE) {
-                enum match_result match = match_chain_srcline(node, cnode);
+        enum match_result match = MATCH_ERROR;
 
+        switch (callchain_param.key) {
+        case CCKEY_SRCLINE:
+                match = match_chain_strings(cnode->srcline, node->srcline);
                 if (match != MATCH_ERROR)
-                        return match;
+                        break;
+                /* otherwise fall-back to symbol-based comparison below */
+                __fallthrough;
+        case CCKEY_FUNCTION:
+                if (node->sym && cnode->ms.sym) {
+                        /*
+                         * Compare inlined frames based on their symbol name
+                         * because different inlined frames will have the same
+                         * symbol start. Otherwise do a faster comparison based
+                         * on the symbol start address.
+                         */
+                        if (cnode->ms.sym->inlined || node->sym->inlined) {
+                                match = match_chain_strings(cnode->ms.sym->name,
+                                                            node->sym->name);
+                                if (match != MATCH_ERROR)
+                                        break;
+                        } else {
+                                match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start,
+                                                                  node->map, node->sym->start);
+                                break;
+                        }
+                }
+                /* otherwise fall-back to IP-based comparison below */
+                __fallthrough;
+        case CCKEY_ADDRESS:
+        default:
+                match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip);
+                break;
         }
 
-        if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
-                left = cnode->ms.sym->start;
-                right = sym->start;
-        } else {
-                left = cnode->ip;
-                right = node->ip;
-        }
+        if (match == MATCH_EQ && node->branch) {
+                cnode->branch_count++;
 
-        if (left == right) {
-                if (node->branch) {
-                        cnode->branch_count++;
+                if (node->branch_from) {
+                        /*
+                         * It's "to" of a branch
+                         */
+                        cnode->brtype_stat.branch_to = true;
 
                         if (node->branch_flags.predicted)
                                 cnode->predicted_count++;
@@ -685,15 +744,22 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
                         if (node->branch_flags.abort)
                                 cnode->abort_count++;
 
+                        branch_type_count(&cnode->brtype_stat,
+                                          &node->branch_flags,
+                                          node->branch_from,
+                                          node->ip);
+                } else {
+                        /*
+                         * It's "from" of a branch
+                         */
+                        cnode->brtype_stat.branch_to = false;
                         cnode->cycles_count += node->branch_flags.cycles;
                         cnode->iter_count += node->nr_loop_iter;
-                        cnode->samples_count += node->samples;
+                        cnode->iter_cycles += node->iter_cycles;
                 }
-
-                return MATCH_EQ;
         }
 
-        return left > right ? MATCH_GT : MATCH_LT;
+        return match;
 }
 
 /*
@@ -922,7 +988,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
         list_for_each_entry_safe(list, next_list, &src->val, list) {
                 callchain_cursor_append(cursor, list->ip,
                                         list->ms.map, list->ms.sym,
-                                        false, NULL, 0, 0);
+                                        false, NULL, 0, 0, 0, list->srcline);
                 list_del(&list->list);
                 map__zput(list->ms.map);
                 free(list);
@@ -962,7 +1028,8 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
                             u64 ip, struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, int samples)
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+                            const char *srcline)
 {
         struct callchain_cursor_node *node = *cursor->last;
 
@@ -980,12 +1047,14 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
         node->sym = sym;
         node->branch = branch;
         node->nr_loop_iter = nr_loop_iter;
-        node->samples = samples;
+        node->iter_cycles = iter_cycles;
+        node->srcline = srcline;
 
         if (flags)
                 memcpy(&node->branch_flags, flags,
                         sizeof(struct branch_flags));
 
+        node->branch_from = branch_from;
         cursor->nr++;
 
         cursor->last = &node->next;
@@ -998,11 +1067,11 @@ int sample__resolve_callchain(struct perf_sample *sample,
                               struct perf_evsel *evsel, struct addr_location *al,
                               int max_stack)
 {
-        if (sample->callchain == NULL)
+        if (sample->callchain == NULL && !symbol_conf.show_branchflag_count)
                 return 0;
 
         if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
-            perf_hpp_list.parent) {
+            perf_hpp_list.parent || symbol_conf.show_branchflag_count) {
                 return thread__resolve_callchain(al->thread, cursor, evsel, sample,
                                                  parent, al, max_stack);
         }
@@ -1011,7 +1080,8 @@ int sample__resolve_callchain(struct perf_sample *sample,
 
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
 {
-        if (!symbol_conf.use_callchain || sample->callchain == NULL)
+        if ((!symbol_conf.use_callchain || sample->callchain == NULL) &&
+                !symbol_conf.show_branchflag_count)
                 return 0;
         return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
@@ -1021,10 +1091,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 {
         al->map = node->map;
         al->sym = node->sym;
-        if (node->map)
-                al->addr = node->map->map_ip(node->map, node->ip);
-        else
-                al->addr = node->ip;
+        al->srcline = node->srcline;
+        al->addr = node->ip;
 
         if (al->sym == NULL) {
                 if (hide_unresolved)
@@ -1066,16 +1134,15 @@ char *callchain_list__sym_name(struct callchain_list *cl,
         int printed;
 
         if (cl->ms.sym) {
-                if (show_srcline && cl->ms.map && !cl->srcline)
-                        cl->srcline = get_srcline(cl->ms.map->dso,
-                                                  map__rip_2objdump(cl->ms.map,
-                                                                    cl->ip),
-                                                  cl->ms.sym, false, show_addr);
-                if (cl->srcline)
-                        printed = scnprintf(bf, bfsize, "%s %s",
-                                        cl->ms.sym->name, cl->srcline);
+                const char *inlined = cl->ms.sym->inlined ? " (inlined)" : "";
+
+                if (show_srcline && cl->srcline)
+                        printed = scnprintf(bf, bfsize, "%s %s%s",
+                                            cl->ms.sym->name, cl->srcline,
+                                            inlined);
                 else
-                        printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+                        printed = scnprintf(bf, bfsize, "%s%s",
+                                            cl->ms.sym->name, inlined);
         } else
                 printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
 
@@ -1214,95 +1281,124 @@ int callchain_branch_counts(struct callchain_root *root,
                                                   cycles_count);
 }
 
-static int counts_str_build(char *bf, int bfsize,
-                             u64 branch_count, u64 predicted_count,
-                             u64 abort_count, u64 cycles_count,
-                             u64 iter_count, u64 samples_count)
+static int count_pri64_printf(int idx, const char *str, u64 value, char *bf, int bfsize)
 {
-        double predicted_percent = 0.0;
-        const char *null_str = "";
-        char iter_str[32];
-        char cycle_str[32];
-        char *istr, *cstr;
-        u64 cycles;
+        int printed;
 
-        if (branch_count == 0)
-                return scnprintf(bf, bfsize, " (calltrace)");
+        printed = scnprintf(bf, bfsize, "%s%s:%" PRId64 "", (idx) ? " " : " (", str, value);
 
-        cycles = cycles_count / branch_count;
+        return printed;
+}
 
-        if (iter_count && samples_count) {
-                if (cycles > 0)
-                        scnprintf(iter_str, sizeof(iter_str),
-                                 " iterations:%" PRId64 "",
-                                 iter_count / samples_count);
-                else
-                        scnprintf(iter_str, sizeof(iter_str),
-                                 "iterations:%" PRId64 "",
-                                 iter_count / samples_count);
-                istr = iter_str;
-        } else
-                istr = (char *)null_str;
+static int count_float_printf(int idx, const char *str, float value,
+                              char *bf, int bfsize, float threshold)
+{
+        int printed;
 
-        if (cycles > 0) {
-                scnprintf(cycle_str, sizeof(cycle_str),
-                          "cycles:%" PRId64 "", cycles);
-                cstr = cycle_str;
-        } else
-                cstr = (char *)null_str;
+        if (threshold != 0.0 && value < threshold)
+                return 0;
 
-        predicted_percent = predicted_count * 100.0 / branch_count;
+        printed = scnprintf(bf, bfsize, "%s%s:%.1f%%", (idx) ? " " : " (", str, value);
 
-        if ((predicted_count == branch_count) && (abort_count == 0)) {
-                if ((cycles > 0) || (istr != (char *)null_str))
-                        return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
-                else
-                        return scnprintf(bf, bfsize, "%s", (char *)null_str);
-        }
-
-        if ((predicted_count < branch_count) && (abort_count == 0)) {
-                if ((cycles > 0) || (istr != (char *)null_str))
-                        return scnprintf(bf, bfsize,
-                                " (predicted:%.1f%% %s%s)",
-                                predicted_percent, cstr, istr);
-                else {
-                        return scnprintf(bf, bfsize,
-                                " (predicted:%.1f%%)",
-                                predicted_percent);
-                }
+        return printed;
+}
+
+static int branch_to_str(char *bf, int bfsize,
+                         u64 branch_count, u64 predicted_count,
+                         u64 abort_count,
+                         struct branch_type_stat *brtype_stat)
+{
+        int printed, i = 0;
+
+        printed = branch_type_str(brtype_stat, bf, bfsize);
+        if (printed)
+                i++;
+
+        if (predicted_count < branch_count) {
+                printed += count_float_printf(i++, "predicted",
+                                predicted_count * 100.0 / branch_count,
+                                bf + printed, bfsize - printed, 0.0);
         }
 
-        if ((predicted_count == branch_count) && (abort_count > 0)) {
-                if ((cycles > 0) || (istr != (char *)null_str))
-                        return scnprintf(bf, bfsize,
-                                " (abort:%" PRId64 " %s%s)",
-                                abort_count, cstr, istr);
-                else
-                        return scnprintf(bf, bfsize,
-                                " (abort:%" PRId64 ")",
-                                abort_count);
+        if (abort_count) {
+                printed += count_float_printf(i++, "abort",
+                                abort_count * 100.0 / branch_count,
+                                bf + printed, bfsize - printed, 0.1);
         }
 
-        if ((cycles > 0) || (istr != (char *)null_str))
-                return scnprintf(bf, bfsize,
-                        " (predicted:%.1f%% abort:%" PRId64 " %s%s)",
-                        predicted_percent, abort_count, cstr, istr);
+        if (i)
+                printed += scnprintf(bf + printed, bfsize - printed, ")");
 
-        return scnprintf(bf, bfsize,
-                        " (predicted:%.1f%% abort:%" PRId64 ")",
-                        predicted_percent, abort_count);
+        return printed;
+}
+
+static int branch_from_str(char *bf, int bfsize,
+                           u64 branch_count,
+                           u64 cycles_count, u64 iter_count,
+                           u64 iter_cycles)
+{
+        int printed = 0, i = 0;
+        u64 cycles;
+
+        cycles = cycles_count / branch_count;
+        if (cycles) {
+                printed += count_pri64_printf(i++, "cycles",
+                                cycles,
+                                bf + printed, bfsize - printed);
+        }
+
+        if (iter_count) {
+                printed += count_pri64_printf(i++, "iter",
+                                iter_count,
+                                bf + printed, bfsize - printed);
+
+                printed += count_pri64_printf(i++, "avg_cycles",
+                                iter_cycles / iter_count,
+                                bf + printed, bfsize - printed);
+        }
+
+        if (i)
+                printed += scnprintf(bf + printed, bfsize - printed, ")");
+
+        return printed;
+}
+
+static int counts_str_build(char *bf, int bfsize,
+                             u64 branch_count, u64 predicted_count,
+                             u64 abort_count, u64 cycles_count,
+                             u64 iter_count, u64 iter_cycles,
+                             struct branch_type_stat *brtype_stat)
+{
+        int printed;
+
+        if (branch_count == 0)
+                return scnprintf(bf, bfsize, " (calltrace)");
+
+        if (brtype_stat->branch_to) {
+                printed = branch_to_str(bf, bfsize, branch_count,
+                                predicted_count, abort_count, brtype_stat);
+        } else {
+                printed = branch_from_str(bf, bfsize, branch_count,
+                                cycles_count, iter_count, iter_cycles);
+        }
+
+        if (!printed)
+                bf[0] = 0;
+
+        return printed;
 }
 
 static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
                                    u64 branch_count, u64 predicted_count,
                                    u64 abort_count, u64 cycles_count,
-                                   u64 iter_count, u64 samples_count)
+                                   u64 iter_count, u64 iter_cycles,
+                                   struct branch_type_stat *brtype_stat)
 {
-        char str[128];
+        char str[256];
 
         counts_str_build(str, sizeof(str), branch_count,
                          predicted_count, abort_count, cycles_count,
-                         iter_count, samples_count);
+                         iter_count, iter_cycles, brtype_stat);
 
         if (fp)
                 return fprintf(fp, "%s", str);
@@ -1310,31 +1406,24 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
         return scnprintf(bf, bfsize, "%s", str);
 }
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-                                        struct callchain_list *clist,
+int callchain_list_counts__printf_value(struct callchain_list *clist,
                                         FILE *fp, char *bf, int bfsize)
 {
         u64 branch_count, predicted_count;
         u64 abort_count, cycles_count;
-        u64 iter_count = 0, samples_count = 0;
+        u64 iter_count, iter_cycles;
 
         branch_count = clist->branch_count;
         predicted_count = clist->predicted_count;
         abort_count = clist->abort_count;
         cycles_count = clist->cycles_count;
-
-        if (node) {
-                struct callchain_list *call;
-
-                list_for_each_entry(call, &node->val, list) {
-                        iter_count += call->iter_count;
-                        samples_count += call->samples_count;
-                }
-        }
+        iter_count = clist->iter_count;
+        iter_cycles = clist->iter_cycles;
 
         return callchain_counts_printf(fp, bf, bfsize, branch_count,
                                        predicted_count, abort_count,
-                                       cycles_count, iter_count, samples_count);
+                                       cycles_count, iter_count, iter_cycles,
+                                       &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
@@ -1459,7 +1548,9 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
                 rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
                                              node->branch, &node->branch_flags,
-                                             node->nr_loop_iter, node->samples);
+                                             node->nr_loop_iter,
+                                             node->iter_cycles,
+                                             node->branch_from, node->srcline);
                 if (rc)
                         break;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index c56c23dbbf72..b79ef2478a57 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_CALLCHAIN_H
 #define __PERF_CALLCHAIN_H
 
@@ -7,6 +8,7 @@
 #include "event.h"
 #include "map.h"
 #include "symbol.h"
+#include "branch.h"
 
 #define HELP_PAD "\t\t\t\t"
 
@@ -118,8 +120,9 @@ struct callchain_list {
         u64                     abort_count;
         u64                     cycles_count;
         u64                     iter_count;
-        u64                     samples_count;
-        char                   *srcline;
+        u64                     iter_cycles;
+        struct branch_type_stat brtype_stat;
+        const char              *srcline;
         struct list_head        list;
 };
 
@@ -133,10 +136,12 @@ struct callchain_cursor_node {
         u64                             ip;
         struct map                      *map;
         struct symbol                   *sym;
+        const char                      *srcline;
         bool                            branch;
         struct branch_flags             branch_flags;
+        u64                             branch_from;
         int                             nr_loop_iter;
-        int                             samples;
+        u64                             iter_cycles;
         struct callchain_cursor_node    *next;
 };
 
@@ -198,7 +203,8 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
                             struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, int samples);
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+                            const char *srcline);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
@@ -279,8 +285,7 @@ char *callchain_node__scnprintf_value(struct callchain_node *node,
 int callchain_node__fprintf_value(struct callchain_node *node,
                                   FILE *fp, u64 total);
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-                                        struct callchain_list *clist,
+int callchain_list_counts__printf_value(struct callchain_list *clist,
                                         FILE *fp, char *bf, int bfsize);
 
 void free_callchain(struct callchain_root *root);
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 03347748f3fa..d9ffc1e6eb39 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "../perf.h"
 #include <subcmd/parse-options.h>
@@ -98,8 +99,10 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
                 cgrp = counter->cgrp;
                 if (!cgrp)
                         continue;
-                if (!strcmp(cgrp->name, str))
+                if (!strcmp(cgrp->name, str)) {
+                        refcount_inc(&cgrp->refcnt);
                         break;
+                }
 
                 cgrp = NULL;
         }
@@ -110,6 +113,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
                         return -1;
 
                 cgrp->name = str;
+                refcount_set(&cgrp->refcnt, 1);
 
                 cgrp->fd = open_cgroup(str);
                 if (cgrp->fd == -1) {
@@ -128,12 +132,11 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
                         goto found;
                 n++;
         }
-        if (refcount_read(&cgrp->refcnt) == 0)
+        if (refcount_dec_and_test(&cgrp->refcnt))
                 free(cgrp);
 
         return -1;
 found:
-        refcount_inc(&cgrp->refcnt);
         counter->cgrp = cgrp;
         return 0;
 }
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index d91966b97cbd..afafc87e9201 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 4b4f00df58a8..ca0fff6272be 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <sched.h>
 #include "util.h"
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
index 94a5a7d829d5..78216b1015c4 100644
--- a/tools/perf/util/cloexec.h
+++ b/tools/perf/util/cloexec.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_CLOEXEC_H
 #define __PERF_CLOEXEC_H
 
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index dbbf89b050a5..39e628b8938e 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include "cache.h"
 #include "config.h"
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 52122bcc3170..22777b1812ee 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_COLOR_H
 #define __PERF_COLOR_H
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7bc981b6bf29..7798a2cc8a86 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "comm.h"
 #include "util.h"
 #include <errno.h>
@@ -5,6 +6,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include "rwsem.h"
 
 struct comm_str {
         char *str;
@@ -14,6 +16,7 @@ struct comm_str {
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
+static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,};
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
@@ -25,7 +28,9 @@ static struct comm_str *comm_str__get(struct comm_str *cs)
 static void comm_str__put(struct comm_str *cs)
 {
         if (cs && refcount_dec_and_test(&cs->refcnt)) {
+                down_write(&comm_str_lock);
                 rb_erase(&cs->rb_node, &comm_str_root);
+                up_write(&comm_str_lock);
                 zfree(&cs->str);
                 free(cs);
         }
@@ -50,7 +55,8 @@ static struct comm_str *comm_str__alloc(const char *str)
         return cs;
 }
 
-static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+static
+struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 {
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
@@ -81,6 +87,17 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
         return new;
 }
 
+static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+{
+        struct comm_str *cs;
+
+        down_write(&comm_str_lock);
+        cs = __comm_str__findnew(str, root);
+        up_write(&comm_str_lock);
+
+        return cs;
+}
+
 struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
         struct comm *comm = zalloc(sizeof(*comm));
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 71c9c39340d4..3e5c438fe85e 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_COMM_H
 #define __PERF_COMM_H
 
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 67fd1bb7c2b7..ecca688a25fb 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_COMPRESS_H
 #define PERF_COMPRESS_H
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 31a7dea248d0..84eb9393c7db 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * config.c
  *
@@ -19,6 +20,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
+#include <linux/string.h>
 
 #include "sane_ctype.h"
 
@@ -433,22 +435,22 @@ static int perf_ui_config(const char *var, const char *value)
 int perf_default_config(const char *var, const char *value,
                         void *dummy __maybe_unused)
 {
-        if (!prefixcmp(var, "core."))
+        if (strstarts(var, "core."))
                 return perf_default_core_config(var, value);
 
-        if (!prefixcmp(var, "hist."))
+        if (strstarts(var, "hist."))
                 return perf_hist_config(var, value);
 
-        if (!prefixcmp(var, "ui."))
+        if (strstarts(var, "ui."))
                 return perf_ui_config(var, value);
 
-        if (!prefixcmp(var, "call-graph."))
+        if (strstarts(var, "call-graph."))
                 return perf_callchain_config(var, value);
 
-        if (!prefixcmp(var, "llvm."))
+        if (strstarts(var, "llvm."))
                 return perf_llvm_config(var, value);
 
-        if (!prefixcmp(var, "buildid."))
+        if (strstarts(var, "buildid."))
                 return perf_buildid_config(var, value);
 
         /* Add other config variables here. */
@@ -699,10 +701,7 @@ struct perf_config_set *perf_config_set__new(void)
 
         if (set) {
                 INIT_LIST_HEAD(&set->sections);
-                if (perf_config_set__init(set) < 0) {
-                        perf_config_set__delete(set);
-                        set = NULL;
-                }
+                perf_config_set__init(set);
         }
 
         return set;
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index b6bb11f3f165..baf82bf227ac 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_CONFIG_H
 #define __PERF_CONFIG_H
 
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index c4af82ab7808..03032b410c29 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdlib.h>
 #include "evsel.h"
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 34d8baaf558a..0d1050ccc586 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_COUNTS_H
 #define __PERF_COUNTS_H
 
@@ -12,6 +13,7 @@ struct perf_counts_values {
                 };
                 u64 values[3];
         };
+        bool    loaded;
 };
 
 struct perf_counts {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 37b3bb79ee08..1ccbd3342069 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include <api/fs/fs.h>
 #include "../perf.h"
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 6b8bff87481d..ed8999d1a640 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index 4b261c2ec0f1..ee4c1e8ed54b 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Sane locale-independent, ASCII ctype.
  *
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 3149b70799fd..5744c12641a5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -76,6 +76,8 @@ struct ctf_writer {
         struct bt_ctf_event_class       *comm_class;
         struct bt_ctf_event_class       *exit_class;
         struct bt_ctf_event_class       *fork_class;
+        struct bt_ctf_event_class       *mmap_class;
+        struct bt_ctf_event_class       *mmap2_class;
 };
 
 struct convert {
@@ -506,6 +508,81 @@ put_len_type:
         return ret;
 }
 
+static int
+add_callchain_output_values(struct bt_ctf_event_class *event_class,
+                      struct bt_ctf_event *event,
+                      struct ip_callchain *callchain)
+{
+        struct bt_ctf_field_type *len_type, *seq_type;
+        struct bt_ctf_field *len_field, *seq_field;
+        unsigned int nr_elements = callchain->nr;
+        unsigned int i;
+        int ret;
+
+        len_type = bt_ctf_event_class_get_field_by_name(
+                        event_class, "perf_callchain_size");
+        len_field = bt_ctf_field_create(len_type);
+        if (!len_field) {
+                pr_err("failed to create 'perf_callchain_size' for callchain output event\n");
+                ret = -1;
+                goto put_len_type;
+        }
+
+        ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+        if (ret) {
+                pr_err("failed to set field value for perf_callchain_size\n");
+                goto put_len_field;
+        }
+        ret = bt_ctf_event_set_payload(event, "perf_callchain_size", len_field);
+        if (ret) {
+                pr_err("failed to set payload to perf_callchain_size\n");
+                goto put_len_field;
+        }
+
+        seq_type = bt_ctf_event_class_get_field_by_name(
+                        event_class, "perf_callchain");
+        seq_field = bt_ctf_field_create(seq_type);
+        if (!seq_field) {
+                pr_err("failed to create 'perf_callchain' for callchain output event\n");
+                ret = -1;
+                goto put_seq_type;
+        }
+
+        ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+        if (ret) {
+                pr_err("failed to set length of 'perf_callchain'\n");
+                goto put_seq_field;
+        }
+
+        for (i = 0; i < nr_elements; i++) {
+                struct bt_ctf_field *elem_field =
+                        bt_ctf_field_sequence_get_field(seq_field, i);
+
+                ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+                                ((u64 *)(callchain->ips))[i]);
+
+                bt_ctf_field_put(elem_field);
+                if (ret) {
+                        pr_err("failed to set callchain[%d]\n", i);
+                        goto put_seq_field;
+                }
+        }
+
+        ret = bt_ctf_event_set_payload(event, "perf_callchain", seq_field);
+        if (ret)
+                pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+        bt_ctf_field_put(seq_field);
+put_seq_type:
+        bt_ctf_field_type_put(seq_type);
+put_len_field:
+        bt_ctf_field_put(len_field);
+put_len_type:
+        bt_ctf_field_type_put(len_type);
+        return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
                               struct bt_ctf_event *event,
                               struct perf_evsel *evsel,
@@ -519,7 +596,6 @@ static int add_generic_values(struct ctf_writer *cw,
          *   PERF_SAMPLE_TIME         - not needed as we have it in
          *                              ctf event header
          *   PERF_SAMPLE_READ         - TODO
-         *   PERF_SAMPLE_CALLCHAIN    - TODO
          *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
          *   PERF_SAMPLE_BRANCH_STACK - TODO
          *   PERF_SAMPLE_REGS_USER    - TODO
@@ -720,6 +796,7 @@ static int process_sample_event(struct perf_tool *tool,
         struct bt_ctf_event_class *event_class;
         struct bt_ctf_event *event;
         int ret;
+        unsigned long type = evsel->attr.sample_type;
 
         if (WARN_ONCE(!priv, "Failed to setup all events.\n"))
                 return 0;
@@ -751,6 +828,13 @@ static int process_sample_event(struct perf_tool *tool,
                         return -1;
         }
 
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                ret = add_callchain_output_values(event_class,
+                                event, sample->callchain);
+                if (ret)
+                        return -1;
+        }
+
         if (perf_evsel__is_bpf_output(evsel)) {
                 ret = add_bpf_output_values(event_class, event, sample);
                 if (ret)
@@ -833,6 +917,18 @@ __FUNC_PROCESS_NON_SAMPLE(exit,
         __NON_SAMPLE_SET_FIELD(fork, u32, ptid);
         __NON_SAMPLE_SET_FIELD(fork, u64, time);
 )
+__FUNC_PROCESS_NON_SAMPLE(mmap,
+        __NON_SAMPLE_SET_FIELD(mmap, u32, pid);
+        __NON_SAMPLE_SET_FIELD(mmap, u32, tid);
+        __NON_SAMPLE_SET_FIELD(mmap, u64_hex, start);
+        __NON_SAMPLE_SET_FIELD(mmap, string, filename);
+)
+__FUNC_PROCESS_NON_SAMPLE(mmap2,
+        __NON_SAMPLE_SET_FIELD(mmap2, u32, pid);
+        __NON_SAMPLE_SET_FIELD(mmap2, u32, tid);
+        __NON_SAMPLE_SET_FIELD(mmap2, u64_hex, start);
+        __NON_SAMPLE_SET_FIELD(mmap2, string, filename);
+)
 #undef __NON_SAMPLE_SET_FIELD
 #undef __FUNC_PROCESS_NON_SAMPLE
 
@@ -1043,6 +1139,14 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
         if (type & PERF_SAMPLE_TRANSACTION)
                 ADD_FIELD(event_class, cw->data.u64, "perf_transaction");
 
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                ADD_FIELD(event_class, cw->data.u32, "perf_callchain_size");
+                ADD_FIELD(event_class,
+                        bt_ctf_field_type_sequence_create(
+                                cw->data.u64_hex, "perf_callchain_size"),
+                        "perf_callchain");
+        }
+
 #undef ADD_FIELD
         return 0;
 }
@@ -1164,6 +1268,19 @@ __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit,
         __NON_SAMPLE_ADD_FIELD(u64, time);
 )
 
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(u64_hex, start);
+        __NON_SAMPLE_ADD_FIELD(string, filename);
+)
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap2,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(u64_hex, start);
+        __NON_SAMPLE_ADD_FIELD(string, filename);
+)
 #undef __NON_SAMPLE_ADD_FIELD
 #undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS
 
@@ -1181,6 +1298,12 @@ static int setup_non_sample_events(struct ctf_writer *cw,
         ret = add_fork_event(cw);
         if (ret)
                 return ret;
+        ret = add_mmap_event(cw);
+        if (ret)
+                return ret;
+        ret = add_mmap2_event(cw);
+        if (ret)
+                return ret;
         return 0;
 }
 
@@ -1454,10 +1577,10 @@ int bt_convert__perf2ctf(const char *input, const char *path,
                          struct perf_data_convert_opts *opts)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input,
-                .mode = PERF_DATA_MODE_READ,
-                .force = opts->force,
+        struct perf_data data = {
+                .file.path = input,
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = opts->force,
         };
         struct convert c = {
                 .tool = {
@@ -1482,6 +1605,8 @@ int bt_convert__perf2ctf(const char *input, const char *path,
                 c.tool.comm = process_comm_event;
                 c.tool.exit = process_exit_event;
                 c.tool.fork = process_fork_event;
+                c.tool.mmap = process_mmap_event;
+                c.tool.mmap2 = process_mmap2_event;
         }
 
         err = perf_config(convert__config, &c);
@@ -1494,7 +1619,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
         err = -1;
         /* perf.data session */
-        session = perf_session__new(&file, 0, &c.tool);
+        session = perf_session__new(&data, 0, &c.tool);
         if (!session)
                 goto free_writer;
 
@@ -1525,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
         fprintf(stderr,
                 "[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
-                file.path, path);
+                data.file.path, path);
 
         fprintf(stderr,
                 "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h
index 9a3b587f76c1..821674d63c4e 100644
--- a/tools/perf/util/data-convert-bt.h
+++ b/tools/perf/util/data-convert-bt.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __DATA_CONVERT_BT_H
 #define __DATA_CONVERT_BT_H
 #include "data-convert.h"
diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h
index 5314962fe95b..af90b6076c06 100644
--- a/tools/perf/util/data-convert.h
+++ b/tools/perf/util/data-convert.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __DATA_CONVERT_H
 #define __DATA_CONVERT_H
 
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e84bbc8ec058..48094fde0a68 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -1,8 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
 
@@ -10,56 +12,66 @@
 #include "util.h"
 #include "debug.h"
 
-static bool check_pipe(struct perf_data_file *file)
+#ifndef O_CLOEXEC
+#ifdef __sparc__
+#define O_CLOEXEC       0x400000
+#elif defined(__alpha__) || defined(__hppa__)
+#define O_CLOEXEC       010000000
+#else
+#define O_CLOEXEC       02000000
+#endif
+#endif
+
+static bool check_pipe(struct perf_data *data)
 {
         struct stat st;
         bool is_pipe = false;
-        int fd = perf_data_file__is_read(file) ?
+        int fd = perf_data__is_read(data) ?
                  STDIN_FILENO : STDOUT_FILENO;
 
-        if (!file->path) {
+        if (!data->file.path) {
                 if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
                         is_pipe = true;
         } else {
-                if (!strcmp(file->path, "-"))
+                if (!strcmp(data->file.path, "-"))
                         is_pipe = true;
         }
 
         if (is_pipe)
-                file->fd = fd;
+                data->file.fd = fd;
 
-        return file->is_pipe = is_pipe;
+        return data->is_pipe = is_pipe;
 }
 
-static int check_backup(struct perf_data_file *file)
+static int check_backup(struct perf_data *data)
 {
         struct stat st;
 
-        if (!stat(file->path, &st) && st.st_size) {
+        if (!stat(data->file.path, &st) && st.st_size) {
                 /* TODO check errors properly */
                 char oldname[PATH_MAX];
                 snprintf(oldname, sizeof(oldname), "%s.old",
-                         file->path);
+                         data->file.path);
                 unlink(oldname);
-                rename(file->path, oldname);
+                rename(data->file.path, oldname);
         }
 
         return 0;
 }
 
-static int open_file_read(struct perf_data_file *file)
+static int open_file_read(struct perf_data *data)
 {
         struct stat st;
         int fd;
         char sbuf[STRERR_BUFSIZE];
 
-        fd = open(file->path, O_RDONLY);
+        fd = open(data->file.path, O_RDONLY);
         if (fd < 0) {
                 int err = errno;
 
-                pr_err("failed to open %s: %s", file->path,
+                pr_err("failed to open %s: %s", data->file.path,
                         str_error_r(err, sbuf, sizeof(sbuf)));
-                if (err == ENOENT && !strcmp(file->path, "perf.data"))
+                if (err == ENOENT && !strcmp(data->file.path, "perf.data"))
                         pr_err("  (try 'perf record' first)");
                 pr_err("\n");
                 return -err;
@@ -68,19 +80,19 @@ static int open_file_read(struct perf_data_file *file)
         if (fstat(fd, &st) < 0)
                 goto out_close;
 
-        if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+        if (!data->force && st.st_uid && (st.st_uid != geteuid())) {
                 pr_err("File %s not owned by current user or root (use -f to override)\n",
-                       file->path);
+                       data->file.path);
                 goto out_close;
         }
 
         if (!st.st_size) {
-                pr_info("zero-sized file (%s), nothing to do!\n",
-                        file->path);
+                pr_info("zero-sized data (%s), nothing to do!\n",
+                        data->file.path);
                 goto out_close;
         }
 
-        file->size = st.st_size;
+        data->size = st.st_size;
         return fd;
 
  out_close:
@@ -88,48 +100,49 @@ static int open_file_read(struct perf_data_file *file)
         return -1;
 }
 
-static int open_file_write(struct perf_data_file *file)
+static int open_file_write(struct perf_data *data)
 {
         int fd;
         char sbuf[STRERR_BUFSIZE];
 
-        if (check_backup(file))
+        if (check_backup(data))
                 return -1;
 
-        fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+        fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+                  S_IRUSR|S_IWUSR);
 
         if (fd < 0)
-                pr_err("failed to open %s : %s\n", file->path,
+                pr_err("failed to open %s : %s\n", data->file.path,
                         str_error_r(errno, sbuf, sizeof(sbuf)));
 
         return fd;
 }
 
-static int open_file(struct perf_data_file *file)
+static int open_file(struct perf_data *data)
 {
         int fd;
 
-        fd = perf_data_file__is_read(file) ?
-             open_file_read(file) : open_file_write(file);
+        fd = perf_data__is_read(data) ?
+             open_file_read(data) : open_file_write(data);
 
-        file->fd = fd;
+        data->file.fd = fd;
         return fd < 0 ? -1 : 0;
 }
 
-int perf_data_file__open(struct perf_data_file *file)
+int perf_data__open(struct perf_data *data)
 {
-        if (check_pipe(file))
+        if (check_pipe(data))
                 return 0;
 
-        if (!file->path)
-                file->path = "perf.data";
+        if (!data->file.path)
+                data->file.path = "perf.data";
 
-        return open_file(file);
+        return open_file(data);
 }
 
-void perf_data_file__close(struct perf_data_file *file)
+void perf_data__close(struct perf_data *data)
 {
-        close(file->fd);
+        close(data->file.fd);
 }
 
 ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -138,42 +151,48 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
         return writen(file->fd, buf, size);
 }
 
-int perf_data_file__switch(struct perf_data_file *file,
+ssize_t perf_data__write(struct perf_data *data,
+                              void *buf, size_t size)
+{
+        return perf_data_file__write(&data->file, buf, size);
+}
+
+int perf_data__switch(struct perf_data *data,
                            const char *postfix,
                            size_t pos, bool at_exit)
 {
         char *new_filepath;
         int ret;
 
-        if (check_pipe(file))
+        if (check_pipe(data))
                 return -EINVAL;
-        if (perf_data_file__is_read(file))
+        if (perf_data__is_read(data))
                 return -EINVAL;
 
-        if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0)
+        if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0)
                 return -ENOMEM;
 
         /*
          * Only fire a warning, don't return error, continue fill
          * original file.
          */
-        if (rename(file->path, new_filepath))
-                pr_warning("Failed to rename %s to %s\n", file->path, new_filepath);
+        if (rename(data->file.path, new_filepath))
+                pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath);
 
         if (!at_exit) {
-                close(file->fd);
-                ret = perf_data_file__open(file);
+                close(data->file.fd);
+                ret = perf_data__open(data);
                 if (ret < 0)
                         goto out;
 
-                if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) {
+                if (lseek(data->file.fd, pos, SEEK_SET) == (off_t)-1) {
                         ret = -errno;
                         pr_debug("Failed to lseek to %zu: %s",
                                  pos, strerror(errno));
                         goto out;
                 }
         }
-        ret = file->fd;
+        ret = data->file.fd;
 out:
         free(new_filepath);
         return ret;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index ae510ce16cb1..4828f7feea89 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_DATA_H
 #define __PERF_DATA_H
 
@@ -9,51 +10,57 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-        const char              *path;
-        int                      fd;
+        const char      *path;
+        int              fd;
+};
+
+struct perf_data {
+        struct perf_data_file    file;
         bool                     is_pipe;
         bool                     force;
         unsigned long            size;
         enum perf_data_mode      mode;
 };
 
-static inline bool perf_data_file__is_read(struct perf_data_file *file)
+static inline bool perf_data__is_read(struct perf_data *data)
 {
-        return file->mode == PERF_DATA_MODE_READ;
+        return data->mode == PERF_DATA_MODE_READ;
 }
 
-static inline bool perf_data_file__is_write(struct perf_data_file *file)
+static inline bool perf_data__is_write(struct perf_data *data)
 {
-        return file->mode == PERF_DATA_MODE_WRITE;
+        return data->mode == PERF_DATA_MODE_WRITE;
 }
 
-static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+static inline int perf_data__is_pipe(struct perf_data *data)
 {
-        return file->is_pipe;
+        return data->is_pipe;
 }
 
-static inline int perf_data_file__fd(struct perf_data_file *file)
+static inline int perf_data__fd(struct perf_data *data)
 {
-        return file->fd;
+        return data->file.fd;
 }
 
-static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+static inline unsigned long perf_data__size(struct perf_data *data)
 {
-        return file->size;
+        return data->size;
 }
 
-int perf_data_file__open(struct perf_data_file *file);
-void perf_data_file__close(struct perf_data_file *file);
+int perf_data__open(struct perf_data *data);
+void perf_data__close(struct perf_data *data);
+ssize_t perf_data__write(struct perf_data *data,
+                              void *buf, size_t size);
 ssize_t perf_data_file__write(struct perf_data_file *file,
                               void *buf, size_t size);
 /*
  * If at_exit is set, only rename current perf.data to
- * perf.data.<postfix>, continue write on original file.
+ * perf.data.<postfix>, continue write on original data.
  * Set at_exit when flushing the last output.
  *
  * Return value is fd of new output.
  */
-int perf_data_file__switch(struct perf_data_file *file,
+int perf_data__switch(struct perf_data *data,
                            const char *postfix,
                            size_t pos, bool at_exit);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index a5b3777ffee6..f3a71db83947 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* For general debugging purposes */
 
 #include "../perf.h"
@@ -111,50 +112,53 @@ int dump_printf(const char *fmt, ...)
         return ret;
 }
 
-static void trace_event_printer(enum binary_printer_ops op,
-                                unsigned int val, void *extra)
+static int trace_event_printer(enum binary_printer_ops op,
+                               unsigned int val, void *extra, FILE *fp)
 {
         const char *color = PERF_COLOR_BLUE;
         union perf_event *event = (union perf_event *)extra;
         unsigned char ch = (unsigned char)val;
+        int printed = 0;
 
         switch (op) {
         case BINARY_PRINT_DATA_BEGIN:
-                printf(".");
-                color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-                                event->header.size);
+                printed += fprintf(fp, ".");
+                printed += color_fprintf(fp, color, "\n. ... raw event: size %d bytes\n",
+                                         event->header.size);
                 break;
         case BINARY_PRINT_LINE_BEGIN:
-                printf(".");
+                printed += fprintf(fp, ".");
                 break;
         case BINARY_PRINT_ADDR:
-                color_fprintf(stdout, color, "  %04x: ", val);
+                printed += color_fprintf(fp, color, "  %04x: ", val);
                 break;
         case BINARY_PRINT_NUM_DATA:
-                color_fprintf(stdout, color, " %02x", val);
+                printed += color_fprintf(fp, color, " %02x", val);
                 break;
         case BINARY_PRINT_NUM_PAD:
-                color_fprintf(stdout, color, "   ");
+                printed += color_fprintf(fp, color, "   ");
                 break;
         case BINARY_PRINT_SEP:
-                color_fprintf(stdout, color, "  ");
+                printed += color_fprintf(fp, color, "  ");
                 break;
         case BINARY_PRINT_CHAR_DATA:
-                color_fprintf(stdout, color, "%c",
+                printed += color_fprintf(fp, color, "%c",
                               isprint(ch) ? ch : '.');
                 break;
         case BINARY_PRINT_CHAR_PAD:
-                color_fprintf(stdout, color, " ");
+                printed += color_fprintf(fp, color, " ");
                 break;
         case BINARY_PRINT_LINE_END:
-                color_fprintf(stdout, color, "\n");
+                printed += color_fprintf(fp, color, "\n");
                 break;
         case BINARY_PRINT_DATA_END:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 break;
         default:
                 break;
         }
+
+        return printed;
 }
 
 void trace_event(union perf_event *event)
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index c818bdb1c1ab..77445dfc5c7d 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* For debugging general purposes */
 #ifndef __PERF_DEBUG_H
 #define __PERF_DEBUG_H
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
index cb66d334f532..e4c486756053 100644
--- a/tools/perf/util/demangle-java.c
+++ b/tools/perf/util/demangle-java.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <stdio.h>
 #include <string.h>
diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
index a981c1f968fe..f936c8eabe5d 100644
--- a/tools/perf/util/demangle-java.h
+++ b/tools/perf/util/demangle-java.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_DEMANGLE_JAVA
 #define __PERF_DEMANGLE_JAVA 1
 /*
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
index f9dafa888c06..423afbbd386b 100644
--- a/tools/perf/util/demangle-rust.c
+++ b/tools/perf/util/demangle-rust.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 #include "util.h"
 #include "debug.h"
diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h
index 7b41ead7e0dd..2fca618b1aa5 100644
--- a/tools/perf/util/demangle-rust.h
+++ b/tools/perf/util/demangle-rust.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_DEMANGLE_RUST
 #define __PERF_DEMANGLE_RUST 1
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 4e7ab611377a..d5b6f7f5baff 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <asm/bug.h>
 #include <linux/kernel.h>
 #include <sys/time.h>
@@ -6,9 +7,11 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <errno.h>
+#include <fcntl.h>
 #include "compress.h"
 #include "path.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
@@ -32,6 +35,7 @@ char dso__symtab_origin(const struct dso *dso)
                 [DSO_BINARY_TYPE__JAVA_JIT]                     = 'j',
                 [DSO_BINARY_TYPE__DEBUGLINK]                    = 'l',
                 [DSO_BINARY_TYPE__BUILD_ID_CACHE]               = 'B',
+                [DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO]     = 'D',
                 [DSO_BINARY_TYPE__FEDORA_DEBUGINFO]             = 'f',
                 [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]             = 'u',
                 [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]       = 'o',
@@ -97,7 +101,12 @@ int dso__read_binary_type_filename(const struct dso *dso,
                 break;
         }
         case DSO_BINARY_TYPE__BUILD_ID_CACHE:
-                if (dso__build_id_filename(dso, filename, size) == NULL)
+                if (dso__build_id_filename(dso, filename, size, false) == NULL)
+                        ret = -1;
+                break;
+
+        case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
+                if (dso__build_id_filename(dso, filename, size, true) == NULL)
                         ret = -1;
                 break;
 
@@ -504,7 +513,14 @@ static void check_data_close(void);
  */
 static int open_dso(struct dso *dso, struct machine *machine)
 {
-        int fd = __open_dso(dso, machine);
+        int fd;
+        struct nscookie nsc;
+
+        if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
+                nsinfo__mountns_enter(dso->nsinfo, &nsc);
+        fd = __open_dso(dso, machine);
+        if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
+                nsinfo__mountns_exit(&nsc);
 
         if (fd >= 0) {
                 dso__list_add(dso);
@@ -1187,6 +1203,8 @@ struct dso *dso__new(const char *name)
                 for (i = 0; i < MAP__NR_TYPES; ++i)
                         dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
                 dso->data.cache = RB_ROOT;
+                dso->inlined_nodes = RB_ROOT;
+                dso->srclines = RB_ROOT;
                 dso->data.fd = -1;
                 dso->data.status = DSO_DATA_STATUS_UNKNOWN;
                 dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1218,6 +1236,10 @@ void dso__delete(struct dso *dso)
         if (!RB_EMPTY_NODE(&dso->rb_node))
                 pr_err("DSO %s is still in rbtree when being deleted!\n",
                        dso->long_name);
+
+        /* free inlines first, as they reference symbols */
+        inlines__tree_delete(&dso->inlined_nodes);
+        srcline__tree_delete(&dso->srclines);
         for (i = 0; i < MAP__NR_TYPES; ++i)
                 symbols__delete(&dso->symbols[i]);
 
@@ -1236,6 +1258,7 @@ void dso__delete(struct dso *dso)
         dso_cache__free(dso);
         dso__free_a2l(dso);
         zfree(&dso->symsrc_filename);
+        nsinfo__zput(dso->nsinfo);
         pthread_mutex_destroy(&dso->lock);
         free(dso);
 }
@@ -1301,6 +1324,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 {
         bool have_build_id = false;
         struct dso *pos;
+        struct nscookie nsc;
 
         list_for_each_entry(pos, head, node) {
                 if (with_hits && !pos->hit && !dso__is_vdso(pos))
@@ -1309,11 +1333,13 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
                         have_build_id = true;
                         continue;
                 }
+                nsinfo__mountns_enter(pos->nsinfo, &nsc);
                 if (filename__read_build_id(pos->long_name, pos->build_id,
                                             sizeof(pos->build_id)) > 0) {
                         have_build_id     = true;
                         pos->has_build_id = true;
                 }
+                nsinfo__mountns_exit(&nsc);
         }
 
         return have_build_id;
@@ -1348,9 +1374,9 @@ void __dsos__add(struct dsos *dsos, struct dso *dso)
 
 void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-        pthread_rwlock_wrlock(&dsos->lock);
+        down_write(&dsos->lock);
         __dsos__add(dsos, dso);
-        pthread_rwlock_unlock(&dsos->lock);
+        up_write(&dsos->lock);
 }
 
 struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
@@ -1369,9 +1395,9 @@ struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
         struct dso *dso;
-        pthread_rwlock_rdlock(&dsos->lock);
+        down_read(&dsos->lock);
         dso = __dsos__find(dsos, name, cmp_short);
-        pthread_rwlock_unlock(&dsos->lock);
+        up_read(&dsos->lock);
         return dso;
 }
 
@@ -1398,9 +1424,9 @@ struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 struct dso *dsos__findnew(struct dsos *dsos, const char *name)
 {
         struct dso *dso;
-        pthread_rwlock_wrlock(&dsos->lock);
+        down_write(&dsos->lock);
         dso = dso__get(__dsos__findnew(dsos, name));
-        pthread_rwlock_unlock(&dsos->lock);
+        up_write(&dsos->lock);
         return dso;
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index bd061ba7b47c..c229dbe0277a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
@@ -6,10 +7,11 @@
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include <pthread.h>
+#include "rwsem.h"
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
+#include "namespaces.h"
 #include "build-id.h"
 
 enum dso_binary_type {
@@ -20,6 +22,7 @@ enum dso_binary_type {
         DSO_BINARY_TYPE__JAVA_JIT,
         DSO_BINARY_TYPE__DEBUGLINK,
         DSO_BINARY_TYPE__BUILD_ID_CACHE,
+        DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO,
         DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
         DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
         DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
@@ -127,7 +130,7 @@ struct dso_cache {
 struct dsos {
         struct list_head head;
         struct rb_root   root;  /* rbtree root sorted by long name */
-        pthread_rwlock_t lock;
+        struct rw_semaphore lock;
 };
 
 struct auxtrace_cache;
@@ -139,6 +142,8 @@ struct dso {
         struct rb_root   *root;         /* root of rbtree that rb_node is in */
         struct rb_root   symbols[MAP__NR_TYPES];
         struct rb_root   symbol_names[MAP__NR_TYPES];
+        struct rb_root   inlined_nodes;
+        struct rb_root   srclines;
         struct {
                 u64             addr;
                 struct symbol   *symbol;
@@ -187,6 +192,7 @@ struct dso {
                 void     *priv;
                 u64      db_id;
         };
+        struct nsinfo   *nsinfo;
         refcount_t       refcnt;
         char             name[0];
 };
diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c
index ffbdb19f05d0..10988d3de7ce 100644
--- a/tools/perf/util/dump-insn.c
+++ b/tools/perf/util/dump-insn.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include "dump-insn.h"
 
diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h
index 90fb115981cf..0e06280a8860 100644
--- a/tools/perf/util/dump-insn.h
+++ b/tools/perf/util/dump-insn.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_DUMP_INSN_H
 #define __PERF_DUMP_INSN_H 1
 
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index c708395b3cb6..db55eddce8cd 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
  *
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9e21538c42ae..6276b340f893 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "cpumap.h"
 #include "env.h"
 #include "util.h"
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index b164dfd2dcbf..1eb35b190b34 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_ENV_H
 #define __PERF_ENV_H
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dc5c3bb69d73..97a8ef9980db 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,5 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -57,6 +59,7 @@ static const char *perf_event__names[] = {
         [PERF_RECORD_STAT_ROUND]                = "STAT_ROUND",
         [PERF_RECORD_EVENT_UPDATE]              = "EVENT_UPDATE",
         [PERF_RECORD_TIME_CONV]                 = "TIME_CONV",
+        [PERF_RECORD_HEADER_FEATURE]            = "FEATURE",
 };
 
 static const char *perf_ns__names[] = {
@@ -676,21 +679,21 @@ out:
         return err;
 }
 
-int perf_event__synthesize_threads(struct perf_tool *tool,
-                                   perf_event__handler_t process,
-                                   struct machine *machine,
-                                   bool mmap_data,
-                                   unsigned int proc_map_timeout)
+static int __perf_event__synthesize_threads(struct perf_tool *tool,
+                                            perf_event__handler_t process,
+                                            struct machine *machine,
+                                            bool mmap_data,
+                                            unsigned int proc_map_timeout,
+                                            struct dirent **dirent,
+                                            int start,
+                                            int num)
 {
-        DIR *proc;
-        char proc_path[PATH_MAX];
-        struct dirent *dirent;
         union perf_event *comm_event, *mmap_event, *fork_event;
         union perf_event *namespaces_event;
         int err = -1;
-
-        if (machine__is_default_guest(machine))
-                return 0;
+        char *end;
+        pid_t pid;
+        int i;
 
         comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
         if (comm_event == NULL)
@@ -710,31 +713,25 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
         if (namespaces_event == NULL)
                 goto out_free_fork;
 
-        snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-        proc = opendir(proc_path);
-
-        if (proc == NULL)
-                goto out_free_namespaces;
-
-        while ((dirent = readdir(proc)) != NULL) {
-                char *end;
-                pid_t pid = strtol(dirent->d_name, &end, 10);
+        for (i = start; i < start + num; i++) {
+                if (!isdigit(dirent[i]->d_name[0]))
+                        continue;
 
-                if (*end) /* only interested in proper numerical dirents */
+                pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+                /* only interested in proper numerical dirents */
+                if (*end)
                         continue;
                 /*
-                 * We may race with exiting thread, so don't stop just because
-                 * one thread couldn't be synthesized.
-                 */
+                 * We may race with exiting thread, so don't stop just because
+                 * one thread couldn't be synthesized.
+                 */
                 __event__synthesize_thread(comm_event, mmap_event, fork_event,
                                            namespaces_event, pid, 1, process,
                                            tool, machine, mmap_data,
                                            proc_map_timeout);
         }
-
         err = 0;
-        closedir(proc);
-out_free_namespaces:
+
         free(namespaces_event);
 out_free_fork:
         free(fork_event);
@@ -746,6 +743,118 @@ out:
         return err;
 }
 
+struct synthesize_threads_arg {
+        struct perf_tool *tool;
+        perf_event__handler_t process;
+        struct machine *machine;
+        bool mmap_data;
+        unsigned int proc_map_timeout;
+        struct dirent **dirent;
+        int num;
+        int start;
+};
+
+static void *synthesize_threads_worker(void *arg)
+{
+        struct synthesize_threads_arg *args = arg;
+
+        __perf_event__synthesize_threads(args->tool, args->process,
+                                         args->machine, args->mmap_data,
+                                         args->proc_map_timeout, args->dirent,
+                                         args->start, args->num);
+        return NULL;
+}
+
+int perf_event__synthesize_threads(struct perf_tool *tool,
+                                   perf_event__handler_t process,
+                                   struct machine *machine,
+                                   bool mmap_data,
+                                   unsigned int proc_map_timeout,
+                                   unsigned int nr_threads_synthesize)
+{
+        struct synthesize_threads_arg *args = NULL;
+        pthread_t *synthesize_threads = NULL;
+        char proc_path[PATH_MAX];
+        struct dirent **dirent;
+        int num_per_thread;
+        int m, n, i, j;
+        int thread_nr;
+        int base = 0;
+        int err = -1;
+
+
+        if (machine__is_default_guest(machine))
+                return 0;
+
+        snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+        n = scandir(proc_path, &dirent, 0, alphasort);
+        if (n < 0)
+                return err;
+
+        if (nr_threads_synthesize == UINT_MAX)
+                thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
+        else
+                thread_nr = nr_threads_synthesize;
+
+        if (thread_nr <= 1) {
+                err = __perf_event__synthesize_threads(tool, process,
+                                                       machine, mmap_data,
+                                                       proc_map_timeout,
+                                                       dirent, base, n);
+                goto free_dirent;
+        }
+        if (thread_nr > n)
+                thread_nr = n;
+
+        synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+        if (synthesize_threads == NULL)
+                goto free_dirent;
+
+        args = calloc(sizeof(*args), thread_nr);
+        if (args == NULL)
+                goto free_threads;
+
+        num_per_thread = n / thread_nr;
+        m = n % thread_nr;
+        for (i = 0; i < thread_nr; i++) {
+                args[i].tool = tool;
+                args[i].process = process;
+                args[i].machine = machine;
+                args[i].mmap_data = mmap_data;
+                args[i].proc_map_timeout = proc_map_timeout;
+                args[i].dirent = dirent;
+        }
+        for (i = 0; i < m; i++) {
+                args[i].num = num_per_thread + 1;
+                args[i].start = i * args[i].num;
+        }
+        if (i != 0)
+                base = args[i-1].start + args[i-1].num;
+        for (j = i; j < thread_nr; j++) {
+                args[j].num = num_per_thread;
+                args[j].start = base + (j - i) * args[i].num;
+        }
+
+        for (i = 0; i < thread_nr; i++) {
+                if (pthread_create(&synthesize_threads[i], NULL,
+                                   synthesize_threads_worker, &args[i]))
+                        goto out_join;
+        }
+        err = 0;
+out_join:
+        for (i = 0; i < thread_nr; i++)
+                pthread_join(synthesize_threads[i], NULL);
+        free(args);
+free_threads:
+        free(synthesize_threads);
+free_dirent:
+        for (i = 0; i < n; i++)
+                free(dirent[i]);
+        free(dirent);
+
+        return err;
+}
+
 struct process_symbol_args {
         const char *name;
         u64        start;
@@ -1496,6 +1605,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
         al->sym = NULL;
         al->cpu = sample->cpu;
         al->socket = -1;
+        al->srcline = NULL;
 
         if (al->cpu >= 0) {
                 struct perf_env *env = machine->env;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 9967c87af7a6..1ae95efbfb95 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_RECORD_H
 #define __PERF_RECORD_H
 
@@ -142,7 +143,8 @@ struct branch_flags {
         u64 in_tx:1;
         u64 abort:1;
         u64 cycles:16;
-        u64 reserved:44;
+        u64 type:4;
+        u64 reserved:40;
 };
 
 struct branch_entry {
@@ -199,6 +201,7 @@ struct perf_sample {
         u32 cpu;
         u32 raw_size;
         u64 data_src;
+        u64 phys_addr;
         u32 flags;
         u16 insn_len;
         u8  cpumode;
@@ -244,6 +247,7 @@ enum perf_user_event_type { /* above any possible kernel type */
         PERF_RECORD_STAT_ROUND                  = 77,
         PERF_RECORD_EVENT_UPDATE                = 78,
         PERF_RECORD_TIME_CONV                   = 79,
+        PERF_RECORD_HEADER_FEATURE              = 80,
         PERF_RECORD_HEADER_MAX
 };
 
@@ -609,6 +613,12 @@ struct time_conv_event {
         u64 time_zero;
 };
 
+struct feature_event {
+        struct perf_event_header        header;
+        u64                             feat_id;
+        char                            data[];
+};
+
 union perf_event {
         struct perf_event_header        header;
         struct mmap_event               mmap;
@@ -639,6 +649,7 @@ union perf_event {
         struct stat_event               stat;
         struct stat_round_event         stat_round;
         struct time_conv_event          time_conv;
+        struct feature_event            feat;
 };
 
 void perf_event__print_totals(void);
@@ -670,7 +681,8 @@ int perf_event__synthesize_cpu_map(struct perf_tool *tool,
 int perf_event__synthesize_threads(struct perf_tool *tool,
                                    perf_event__handler_t process,
                                    struct machine *machine, bool mmap_data,
-                                   unsigned int proc_map_timeout);
+                                   unsigned int proc_map_timeout,
+                                   unsigned int nr_threads_synthesize);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
                                        perf_event__handler_t process,
                                        struct machine *machine);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 46c0faf6c502..c6c891e154a6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -33,9 +33,6 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_mmap__munmap(struct perf_mmap *map);
-static void perf_mmap__put(struct perf_mmap *map);
-
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
@@ -242,9 +239,9 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
         }
 }
 
-int perf_evlist__add_default(struct perf_evlist *evlist)
+int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
-        struct perf_evsel *evsel = perf_evsel__new_cycles();
+        struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
 
         if (evsel == NULL)
                 return -ENOMEM;
@@ -704,129 +701,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist)
         return perf_evlist__set_paused(evlist, false);
 }
 
-/* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *
-perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
-                u64 end, u64 *prev)
-{
-        unsigned char *data = md->base + page_size;
-        union perf_event *event = NULL;
-        int diff = end - start;
-
-        if (check_messup) {
-                /*
-                 * If we're further behind than half the buffer, there's a chance
-                 * the writer will bite our tail and mess up the samples under us.
-                 *
-                 * If we somehow ended up ahead of the 'end', we got messed up.
-                 *
-                 * In either case, truncate and restart at 'end'.
-                 */
-                if (diff > md->mask / 2 || diff < 0) {
-                        fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-                        /*
-                         * 'end' points to a known good entry, start there.
-                         */
-                        start = end;
-                        diff = 0;
-                }
-        }
-
-        if (diff >= (int)sizeof(event->header)) {
-                size_t size;
-
-                event = (union perf_event *)&data[start & md->mask];
-                size = event->header.size;
-
-                if (size < sizeof(event->header) || diff < (int)size) {
-                        event = NULL;
-                        goto broken_event;
-                }
-
-                /*
-                 * Event straddles the mmap boundary -- header should always
-                 * be inside due to u64 alignment of output.
-                 */
-                if ((start & md->mask) + size != ((start + size) & md->mask)) {
-                        unsigned int offset = start;
-                        unsigned int len = min(sizeof(*event), size), cpy;
-                        void *dst = md->event_copy;
-
-                        do {
-                                cpy = min(md->mask + 1 - (offset & md->mask), len);
-                                memcpy(dst, &data[offset & md->mask], cpy);
-                                offset += cpy;
-                                dst += cpy;
-                                len -= cpy;
-                        } while (len);
-
-                        event = (union perf_event *) md->event_copy;
-                }
-
-                start += size;
-        }
-
-broken_event:
-        if (prev)
-                *prev = start;
-
-        return event;
-}
-
-union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
-{
-        u64 head;
-        u64 old = md->prev;
-
-        /*
-         * Check if event was unmapped due to a POLLHUP/POLLERR.
-         */
-        if (!refcount_read(&md->refcnt))
-                return NULL;
-
-        head = perf_mmap__read_head(md);
-
-        return perf_mmap__read(md, check_messup, old, head, &md->prev);
-}
-
-union perf_event *
-perf_mmap__read_backward(struct perf_mmap *md)
-{
-        u64 head, end;
-        u64 start = md->prev;
-
-        /*
-         * Check if event was unmapped due to a POLLHUP/POLLERR.
-         */
-        if (!refcount_read(&md->refcnt))
-                return NULL;
-
-        head = perf_mmap__read_head(md);
-        if (!head)
-                return NULL;
-
-        /*
-         * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-         * it each time when kernel writes to it, so in fact 'head' is
-         * negative. 'end' pointer is made manually by adding the size of
-         * the ring buffer to 'head' pointer, means the validate data can
-         * read is the whole ring buffer. If 'end' is positive, the ring
-         * buffer has not fully filled, so we must adjust 'end' to 0.
-         *
-         * However, since both 'head' and 'end' is unsigned, we can't
-         * simply compare 'end' against 0. Here we compare '-head' and
-         * the size of the ring buffer, where -head is the number of bytes
-         * kernel write to the ring buffer.
-         */
-        if (-head < (u64)(md->mask + 1))
-                end = 0;
-        else
-                end = head + md->mask + 1;
-
-        return perf_mmap__read(md, false, start, end, &md->prev);
-}
-
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
 {
         struct perf_mmap *md = &evlist->mmap[idx];
@@ -857,96 +731,16 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
         return perf_evlist__mmap_read_forward(evlist, idx);
 }
 
-void perf_mmap__read_catchup(struct perf_mmap *md)
-{
-        u64 head;
-
-        if (!refcount_read(&md->refcnt))
-                return;
-
-        head = perf_mmap__read_head(md);
-        md->prev = head;
-}
-
 void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 {
         perf_mmap__read_catchup(&evlist->mmap[idx]);
 }
 
-static bool perf_mmap__empty(struct perf_mmap *md)
-{
-        return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
-}
-
-static void perf_mmap__get(struct perf_mmap *map)
-{
-        refcount_inc(&map->refcnt);
-}
-
-static void perf_mmap__put(struct perf_mmap *md)
-{
-        BUG_ON(md->base && refcount_read(&md->refcnt) == 0);
-
-        if (refcount_dec_and_test(&md->refcnt))
-                perf_mmap__munmap(md);
-}
-
-void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
-{
-        if (!overwrite) {
-                u64 old = md->prev;
-
-                perf_mmap__write_tail(md, old);
-        }
-
-        if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-                perf_mmap__put(md);
-}
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
         perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
 }
 
-int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
-                               struct auxtrace_mmap_params *mp __maybe_unused,
-                               void *userpg __maybe_unused,
-                               int fd __maybe_unused)
-{
-        return 0;
-}
-
-void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
-{
-}
-
-void __weak auxtrace_mmap_params__init(
-                        struct auxtrace_mmap_params *mp __maybe_unused,
-                        off_t auxtrace_offset __maybe_unused,
-                        unsigned int auxtrace_pages __maybe_unused,
-                        bool auxtrace_overwrite __maybe_unused)
-{
-}
-
-void __weak auxtrace_mmap_params__set_idx(
-                        struct auxtrace_mmap_params *mp __maybe_unused,
-                        struct perf_evlist *evlist __maybe_unused,
-                        int idx __maybe_unused,
-                        bool per_cpu __maybe_unused)
-{
-}
-
-static void perf_mmap__munmap(struct perf_mmap *map)
-{
-        if (map->base != NULL) {
-                munmap(map->base, perf_mmap__mmap_len(map));
-                map->base = NULL;
-                map->fd = -1;
-                refcount_set(&map->refcnt, 0);
-        }
-        auxtrace_mmap__munmap(&map->auxtrace_mmap);
-}
-
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
         int i;
@@ -995,48 +789,6 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
         return map;
 }
 
-struct mmap_params {
-        int prot;
-        int mask;
-        struct auxtrace_mmap_params auxtrace_mp;
-};
-
-static int perf_mmap__mmap(struct perf_mmap *map,
-                           struct mmap_params *mp, int fd)
-{
-        /*
-         * The last one will be done at perf_evlist__mmap_consume(), so that we
-         * make sure we don't prevent tools from consuming every last event in
-         * the ring buffer.
-         *
-         * I.e. we can get the POLLHUP meaning that the fd doesn't exist
-         * anymore, but the last events for it are still in the ring buffer,
-         * waiting to be consumed.
-         *
-         * Tools can chose to ignore this at their own discretion, but the
-         * evlist layer can't just drop it when filtering events in
-         * perf_evlist__filter_pollfd().
-         */
-        refcount_set(&map->refcnt, 2);
-        map->prev = 0;
-        map->mask = mp->mask;
-        map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
-                         MAP_SHARED, fd, 0);
-        if (map->base == MAP_FAILED) {
-                pr_debug2("failed to mmap perf event ring buffer, error %d\n",
-                          errno);
-                map->base = NULL;
-                return -1;
-        }
-        map->fd = fd;
-
-        if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
-                                &mp->auxtrace_mp, map->base, fd))
-                return -1;
-
-        return 0;
-}
-
 static bool
 perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
                          struct perf_evsel *evsel)
@@ -1419,8 +1171,6 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 {
         struct perf_evsel *evsel;
         int err = 0;
-        const int ncpus = cpu_map__nr(evlist->cpus),
-                  nthreads = thread_map__nr(evlist->threads);
 
         evlist__for_each_entry(evlist, evsel) {
                 if (evsel->filter == NULL)
@@ -1430,7 +1180,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
                  * filters only work for tracepoint event, which doesn't have cpu limit.
                  * So evlist and evsel should always be same.
                  */
-                err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter);
+                err = perf_evsel__apply_filter(evsel, evsel->filter);
                 if (err) {
                         *err_evsel = evsel;
                         break;
@@ -1623,13 +1373,9 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 void perf_evlist__close(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
-        int ncpus = cpu_map__nr(evlist->cpus);
-        int nthreads = thread_map__nr(evlist->threads);
 
-        evlist__for_each_entry_reverse(evlist, evsel) {
-                int n = evsel->cpus ? evsel->cpus->nr : ncpus;
-                perf_evsel__close(evsel, n, nthreads);
-        }
+        evlist__for_each_entry_reverse(evlist, evsel)
+                perf_evsel__close(evsel);
 }
 
 static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8d601fbdd8d6..e72ae64c11ac 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
@@ -6,12 +7,13 @@
 #include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
+#include <fcntl.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"
 #include "evsel.h"
+#include "mmap.h"
 #include "util.h"
-#include "auxtrace.h"
 #include <signal.h>
 #include <unistd.h>
 
@@ -23,55 +25,6 @@ struct record_opts;
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
-/**
- * struct perf_mmap - perf's ring buffer mmap details
- *
- * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
- */
-struct perf_mmap {
-        void             *base;
-        int              mask;
-        int              fd;
-        refcount_t       refcnt;
-        u64              prev;
-        struct auxtrace_mmap auxtrace_mmap;
-        char             event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
-};
-
-static inline size_t
-perf_mmap__mmap_len(struct perf_mmap *map)
-{
-        return map->mask + 1 + page_size;
-}
-
-/*
- * State machine of bkw_mmap_state:
- *
- *                     .________________(forbid)_____________.
- *                     |                                     V
- * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
- *                     ^  ^              |   ^               |
- *                     |  |__(forbid)____/   |___(forbid)___/|
- *                     |                                     |
- *                      \_________________(3)_______________/
- *
- * NOTREADY     : Backward ring buffers are not ready
- * RUNNING      : Backward ring buffers are recording
- * DATA_PENDING : We are required to collect data from backward ring buffers
- * EMPTY        : We have collected data from backward ring buffers.
- *
- * (0): Setup backward ring buffer
- * (1): Pause ring buffers for reading
- * (2): Read from ring buffers
- * (3): Resume ring buffers for recording
- */
-enum bkw_mmap_state {
-        BKW_MMAP_NOTREADY,
-        BKW_MMAP_RUNNING,
-        BKW_MMAP_DATA_PENDING,
-        BKW_MMAP_EMPTY,
-};
-
 struct perf_evlist {
         struct list_head entries;
         struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
@@ -115,7 +68,14 @@ void perf_evlist__delete(struct perf_evlist *evlist);
 
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
 void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel);
-int perf_evlist__add_default(struct perf_evlist *evlist);
+
+int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise);
+
+static inline int perf_evlist__add_default(struct perf_evlist *evlist)
+{
+        return __perf_evlist__add_default(evlist, true);
+}
+
 int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
                                      struct perf_event_attr *attrs, size_t nr_attrs);
 
@@ -169,12 +129,6 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
-
-void perf_mmap__read_catchup(struct perf_mmap *md);
-void perf_mmap__consume(struct perf_mmap *md, bool overwrite);
-
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
@@ -258,6 +212,11 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
                                    struct list_head *list);
 
+static inline bool perf_evlist__empty(struct perf_evlist *evlist)
+{
+        return list_empty(&evlist->entries);
+}
+
 static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
 {
         return list_entry(evlist->entries.next, struct perf_evsel, node);
@@ -273,25 +232,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
 int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
 
-static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
-{
-        struct perf_event_mmap_page *pc = mm->base;
-        u64 head = ACCESS_ONCE(pc->data_head);
-        rmb();
-        return head;
-}
-
-static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
-{
-        struct perf_event_mmap_page *pc = md->base;
-
-        /*
-         * ensure all reads are done before we write the tail out.
-         */
-        mb();
-        pc->data_tail = tail;
-}
-
 bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
 void perf_evlist__to_front(struct perf_evlist *evlist,
                            struct perf_evsel *move_evsel);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 413f74df08de..f894893c203d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -49,6 +49,7 @@ static struct {
         bool clockid_wrong;
         bool lbr_flags;
         bool write_backward;
+        bool group_read;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -58,6 +59,8 @@ static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
         return 0;
 }
 
+void __weak test_attr__ready(void) { }
+
 static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
 {
 }
@@ -268,16 +271,24 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
         return evsel;
 }
 
-struct perf_evsel *perf_evsel__new_cycles(void)
+static bool perf_event_can_profile_kernel(void)
+{
+        return geteuid() == 0 || perf_event_paranoid() == -1;
+}
+
+struct perf_evsel *perf_evsel__new_cycles(bool precise)
 {
         struct perf_event_attr attr = {
                 .type   = PERF_TYPE_HARDWARE,
                 .config = PERF_COUNT_HW_CPU_CYCLES,
-                .exclude_kernel = geteuid() != 0,
+                .exclude_kernel = !perf_event_can_profile_kernel(),
         };
         struct perf_evsel *evsel;
 
         event_attr_init(&attr);
+
+        if (!precise)
+                goto new_event;
         /*
          * Unnamed union member, not supported as struct member named
          * initializer in older compilers such as gcc 4.4.7
@@ -292,7 +303,7 @@ struct perf_evsel *perf_evsel__new_cycles(void)
          * to kick in when we return and before perf_evsel__open() is called.
          */
         attr.sample_period = 0;
-
+new_event:
         evsel = perf_evsel__new(&attr);
         if (evsel == NULL)
                 goto out;
@@ -672,7 +683,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
                 if (!function) {
                         perf_evsel__set_sample_bit(evsel, REGS_USER);
                         perf_evsel__set_sample_bit(evsel, STACK_USER);
-                        attr->sample_regs_user = PERF_REGS_MASK;
+                        attr->sample_regs_user |= PERF_REGS_MASK;
                         attr->sample_stack_user = param->dump_size;
                         attr->exclude_callchain_user = 1;
                 } else {
@@ -896,8 +907,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
         if (opts->no_samples)
                 attr->sample_freq = 0;
 
-        if (opts->inherit_stat)
+        if (opts->inherit_stat) {
+                evsel->attr.read_format |=
+                        PERF_FORMAT_TOTAL_TIME_ENABLED |
+                        PERF_FORMAT_TOTAL_TIME_RUNNING |
+                        PERF_FORMAT_ID;
                 attr->inherit_stat = 1;
+        }
 
         if (opts->sample_address) {
                 perf_evsel__set_sample_bit(evsel, ADDR);
@@ -920,6 +936,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
                 perf_evsel__set_sample_bit(evsel, REGS_INTR);
         }
 
+        if (opts->sample_user_regs) {
+                attr->sample_regs_user |= opts->sample_user_regs;
+                perf_evsel__set_sample_bit(evsel, REGS_USER);
+        }
+
         if (target__has_cpu(&opts->target) || opts->sample_cpu)
                 perf_evsel__set_sample_bit(evsel, CPU);
 
@@ -944,6 +965,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
         if (opts->sample_address)
                 perf_evsel__set_sample_bit(evsel, DATA_SRC);
 
+        if (opts->sample_phys_addr)
+                perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+
         if (opts->no_buffering) {
                 attr->watermark = 0;
                 attr->wakeup_events = 1;
@@ -1045,16 +1069,13 @@ static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthread
         return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
-static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads,
+static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
                           int ioc,  void *arg)
 {
         int cpu, thread;
 
-        if (evsel->system_wide)
-                nthreads = 1;
-
-        for (cpu = 0; cpu < ncpus; cpu++) {
-                for (thread = 0; thread < nthreads; thread++) {
+        for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+                for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
                         int fd = FD(evsel, cpu, thread),
                             err = ioctl(fd, ioc, arg);
 
@@ -1066,10 +1087,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
         return 0;
 }
 
-int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
-                             const char *filter)
+int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
 {
-        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+        return perf_evsel__run_ioctl(evsel,
                                      PERF_EVENT_IOC_SET_FILTER,
                                      (void *)filter);
 }
@@ -1116,20 +1136,14 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
 
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-        int nthreads = thread_map__nr(evsel->threads);
-        int ncpus = cpu_map__nr(evsel->cpus);
-
-        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+        return perf_evsel__run_ioctl(evsel,
                                      PERF_EVENT_IOC_ENABLE,
                                      0);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-        int nthreads = thread_map__nr(evsel->threads);
-        int ncpus = cpu_map__nr(evsel->cpus);
-
-        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+        return perf_evsel__run_ioctl(evsel,
                                      PERF_EVENT_IOC_DISABLE,
                                      0);
 }
@@ -1179,15 +1193,12 @@ static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
         }
 }
 
-void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+void perf_evsel__close_fd(struct perf_evsel *evsel)
 {
         int cpu, thread;
 
-        if (evsel->system_wide)
-                nthreads = 1;
-
-        for (cpu = 0; cpu < ncpus; cpu++)
-                for (thread = 0; thread < nthreads; ++thread) {
+        for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
+                for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
                         close(FD(evsel, cpu, thread));
                         FD(evsel, cpu, thread) = -1;
                 }
@@ -1256,20 +1267,148 @@ void perf_counts_values__scale(struct perf_counts_values *count,
                 *pscaled = scaled;
 }
 
+static int perf_evsel__read_size(struct perf_evsel *evsel)
+{
+        u64 read_format = evsel->attr.read_format;
+        int entry = sizeof(u64); /* value */
+        int size = 0;
+        int nr = 1;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                size += sizeof(u64);
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                size += sizeof(u64);
+
+        if (read_format & PERF_FORMAT_ID)
+                entry += sizeof(u64);
+
+        if (read_format & PERF_FORMAT_GROUP) {
+                nr = evsel->nr_members;
+                size += sizeof(u64);
+        }
+
+        size += entry * nr;
+        return size;
+}
+
 int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
                      struct perf_counts_values *count)
 {
+        size_t size = perf_evsel__read_size(evsel);
+
         memset(count, 0, sizeof(*count));
 
         if (FD(evsel, cpu, thread) < 0)
                 return -EINVAL;
 
-        if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0)
+        if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
                 return -errno;
 
         return 0;
 }
 
+static int
+perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread)
+{
+        struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
+
+        return perf_evsel__read(evsel, cpu, thread, count);
+}
+
+static void
+perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread,
+                      u64 val, u64 ena, u64 run)
+{
+        struct perf_counts_values *count;
+
+        count = perf_counts(counter->counts, cpu, thread);
+
+        count->val    = val;
+        count->ena    = ena;
+        count->run    = run;
+        count->loaded = true;
+}
+
+static int
+perf_evsel__process_group_data(struct perf_evsel *leader,
+                               int cpu, int thread, u64 *data)
+{
+        u64 read_format = leader->attr.read_format;
+        struct sample_read_value *v;
+        u64 nr, ena = 0, run = 0, i;
+
+        nr = *data++;
+
+        if (nr != (u64) leader->nr_members)
+                return -EINVAL;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                ena = *data++;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                run = *data++;
+
+        v = (struct sample_read_value *) data;
+
+        perf_evsel__set_count(leader, cpu, thread,
+                              v[0].value, ena, run);
+
+        for (i = 1; i < nr; i++) {
+                struct perf_evsel *counter;
+
+                counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
+                if (!counter)
+                        return -EINVAL;
+
+                perf_evsel__set_count(counter, cpu, thread,
+                                      v[i].value, ena, run);
+        }
+
+        return 0;
+}
+
+static int
+perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
+{
+        struct perf_stat_evsel *ps = leader->priv;
+        u64 read_format = leader->attr.read_format;
+        int size = perf_evsel__read_size(leader);
+        u64 *data = ps->group_data;
+
+        if (!(read_format & PERF_FORMAT_ID))
+                return -EINVAL;
+
+        if (!perf_evsel__is_group_leader(leader))
+                return -EINVAL;
+
+        if (!data) {
+                data = zalloc(size);
+                if (!data)
+                        return -ENOMEM;
+
+                ps->group_data = data;
+        }
+
+        if (FD(leader, cpu, thread) < 0)
+                return -EINVAL;
+
+        if (readn(FD(leader, cpu, thread), data, size) <= 0)
+                return -errno;
+
+        return perf_evsel__process_group_data(leader, cpu, thread, data);
+}
+
+int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread)
+{
+        u64 read_format = evsel->attr.read_format;
+
+        if (read_format & PERF_FORMAT_GROUP)
+                return perf_evsel__read_group(evsel, cpu, thread);
+        else
+                return perf_evsel__read_one(evsel, cpu, thread);
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
                               int cpu, int thread, bool scale)
 {
@@ -1338,7 +1477,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
                 bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
-                bit_name(WEIGHT),
+                bit_name(WEIGHT), bit_name(PHYS_ADDR),
                 { .name = NULL, }
         };
 #undef bit_name
@@ -1545,6 +1684,8 @@ fallback_missing_features:
         if (perf_missing_features.lbr_flags)
                 evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
                                      PERF_SAMPLE_BRANCH_NO_CYCLES);
+        if (perf_missing_features.group_read && evsel->attr.inherit)
+                evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
 retry_sample_id:
         if (perf_missing_features.sample_id_all)
                 evsel->attr.sample_id_all = 0;
@@ -1569,6 +1710,8 @@ retry_open:
                         pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
                                   pid, cpus->map[cpu], group_fd, flags);
 
+                        test_attr__ready();
+
                         fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
                                                  group_fd, flags);
 
@@ -1664,31 +1807,45 @@ try_fallback:
          */
         if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
                 perf_missing_features.write_backward = true;
+                pr_debug2("switching off write_backward\n");
                 goto out_close;
         } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
                 perf_missing_features.clockid_wrong = true;
+                pr_debug2("switching off clockid\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
                 perf_missing_features.clockid = true;
+                pr_debug2("switching off use_clockid\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
                 perf_missing_features.cloexec = true;
+                pr_debug2("switching off cloexec flag\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
                 perf_missing_features.mmap2 = true;
+                pr_debug2("switching off mmap2\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.exclude_guest &&
                    (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
                 perf_missing_features.exclude_guest = true;
+                pr_debug2("switching off exclude_guest, exclude_host\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.sample_id_all) {
                 perf_missing_features.sample_id_all = true;
+                pr_debug2("switching off sample_id_all\n");
                 goto retry_sample_id;
         } else if (!perf_missing_features.lbr_flags &&
                         (evsel->attr.branch_sample_type &
                          (PERF_SAMPLE_BRANCH_NO_CYCLES |
                           PERF_SAMPLE_BRANCH_NO_FLAGS))) {
                 perf_missing_features.lbr_flags = true;
+                pr_debug2("switching off branch sample type no (cycles/flags)\n");
+                goto fallback_missing_features;
+        } else if (!perf_missing_features.group_read &&
+                    evsel->attr.inherit &&
+                   (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+                perf_missing_features.group_read = true;
+                pr_debug2("switching off group read\n");
                 goto fallback_missing_features;
         }
 out_close:
@@ -1702,12 +1859,12 @@ out_close:
         return err;
 }
 
-void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
+void perf_evsel__close(struct perf_evsel *evsel)
 {
         if (evsel->fd == NULL)
                 return;
 
-        perf_evsel__close_fd(evsel, ncpus, nthreads);
+        perf_evsel__close_fd(evsel);
         perf_evsel__free_fd(evsel);
 }
 
@@ -2062,6 +2219,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 }
         }
 
+        data->phys_addr = 0;
+        if (type & PERF_SAMPLE_PHYS_ADDR) {
+                data->phys_addr = *array;
+                array++;
+        }
+
         return 0;
 }
 
@@ -2167,6 +2330,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR)
+                result += sizeof(u64);
+
         return result;
 }
 
@@ -2356,6 +2522,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR) {
+                *array = sample->phys_addr;
+                array++;
+        }
+
         return 0;
 }
 
@@ -2535,7 +2706,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
                  "unprivileged users (without CAP_SYS_ADMIN).\n\n"
                  "The current value is %d:\n\n"
                  "  -1: Allow use of (almost) all events by all users\n"
-                 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+                 "      Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n"
+                 ">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n"
+                 "      Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n"
                  ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
                  ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
                  "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
@@ -2610,3 +2783,10 @@ char *perf_evsel__env_arch(struct perf_evsel *evsel)
                 return evsel->evlist->env->arch;
         return NULL;
 }
+
+char *perf_evsel__env_cpuid(struct perf_evsel *evsel)
+{
+        if (evsel && evsel->evlist && evsel->evlist->env)
+                return evsel->evlist->env->cpuid;
+        return NULL;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d101695c482c..9277df96ffda 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_EVSEL_H
 #define __PERF_EVSEL_H 1
 
@@ -68,6 +69,8 @@ struct perf_evsel_config_term {
         } val;
 };
 
+struct perf_stat_evsel;
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -101,6 +104,7 @@ struct perf_evsel {
         const char              *unit;
         struct event_format     *tp_format;
         off_t                   id_offset;
+        struct perf_stat_evsel  *stats;
         void                    *priv;
         u64                     db_id;
         struct cgroup_sel       *cgrp;
@@ -131,11 +135,13 @@ struct perf_evsel {
         bool                    cmdline_group_boundary;
         struct list_head        config_terms;
         int                     bpf_fd;
+        bool                    auto_merge_stats;
         bool                    merged_stat;
         const char *            metric_expr;
         const char *            metric_name;
         struct perf_evsel       **metric_events;
         bool                    collect_stat;
+        bool                    weak_group;
 };
 
 union u64_swap {
@@ -185,7 +191,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
         return perf_evsel__newtp_idx(sys, name, 0);
 }
 
-struct perf_evsel *perf_evsel__new_cycles(void);
+struct perf_evsel *perf_evsel__new_cycles(bool precise);
 
 struct event_format *event_format__new(const char *sys, const char *name);
 
@@ -226,7 +232,7 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__close_fd(struct perf_evsel *evsel);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
                                   enum perf_event_sample_format bit);
@@ -246,8 +252,7 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__append_addr_filter(struct perf_evsel *evsel,
                                    const char *filter);
-int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
-                             const char *filter);
+int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__enable(struct perf_evsel *evsel);
 int perf_evsel__disable(struct perf_evsel *evsel);
 
@@ -257,7 +262,7 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel,
                                 struct thread_map *threads);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
                      struct thread_map *threads);
-void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__close(struct perf_evsel *evsel);
 
 struct perf_sample;
 
@@ -299,6 +304,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
                      struct perf_counts_values *count);
 
+int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
                               int cpu, int thread, bool scale);
 
@@ -436,5 +443,6 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
                              attr__fprintf_f attr__fprintf, void *priv);
 
 char *perf_evsel__env_arch(struct perf_evsel *evsel);
+char *perf_evsel__env_cpuid(struct perf_evsel *evsel);
 
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 583f3a602506..06dfb027879d 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <stdio.h>
 #include <stdbool.h>
@@ -157,7 +158,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
                                 }
                         }
 
-                        if (print_dso) {
+                        if (print_dso && (!node->sym || !node->sym->inlined)) {
                                 printed += fprintf(fp, " (");
                                 printed += map__fprintf_dsoname(node->map, fp);
                                 printed += fprintf(fp, ")");
@@ -166,41 +167,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
                         if (print_srcline)
                                 printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
 
+                        if (node->sym && node->sym->inlined)
+                                printed += fprintf(fp, " (inlined)");
+
                         if (!print_oneline)
                                 printed += fprintf(fp, "\n");
 
-                        if (symbol_conf.inline_name && node->map) {
-                                struct inline_node *inode;
-
-                                addr = map__rip_2objdump(node->map, node->ip),
-                                inode = dso__parse_addr_inlines(node->map->dso, addr);
-
-                                if (inode) {
-                                        struct inline_list *ilist;
-
-                                        list_for_each_entry(ilist, &inode->val, list) {
-                                                if (print_arrow)
-                                                        printed += fprintf(fp, " <-");
-
-                                                /* IP is same, just skip it */
-                                                if (print_ip)
-                                                        printed += fprintf(fp, "%c%16s",
-                                                                           s, "");
-                                                if (print_sym)
-                                                        printed += fprintf(fp, " %s",
-                                                                           ilist->funcname);
-                                                if (print_srcline)
-                                                        printed += fprintf(fp, "\n  %s:%d",
-                                                                           ilist->filename,
-                                                                           ilist->line_nr);
-                                                if (!print_oneline)
-                                                        printed += fprintf(fp, "\n");
-                                        }
-
-                                        inline_node__delete(inode);
-                                }
-                        }
-
                         if (symbol_conf.bt_stop_list &&
                             node->sym &&
                             strlist__has_entry(symbol_conf.bt_stop_list,
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 9c2760a1a96e..046160831f90 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -1,7 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 8
+#define EXPR_MAX_OTHER 15
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct parse_id {
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 954556bea36e..432b8560cf51 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -4,6 +4,7 @@
 #include "util/debug.h"
 #define IN_EXPR_Y 1
 #include "expr.h"
+#include "smt.h"
 #include <string.h>
 
 #define MAXIDLEN 256
@@ -22,13 +23,15 @@
 
 %token <num> NUMBER
 %token <id> ID
+%token MIN MAX IF ELSE SMT_ON
+%left MIN MAX IF
 %left '|'
 %left '^'
 %left '&'
 %left '-' '+'
 %left '*' '/' '%'
 %left NEG NOT
-%type <num> expr
+%type <num> expr if_expr
 
 %{
 static int expr__lex(YYSTYPE *res, const char **pp);
@@ -57,22 +60,33 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
 %}
 %%
 
-all_expr: expr                  { *final_val = $1; }
+all_expr: if_expr                       { *final_val = $1; }
+        ;
+
+if_expr:
+        expr IF expr ELSE expr { $$ = $3 ? $1 : $5; }
+        | expr
         ;
 
 expr:     NUMBER
         | ID                    { if (lookup_id(ctx, $1, &$$) < 0) {
-                                        pr_debug("%s not found", $1);
+                                        pr_debug("%s not found\n", $1);
                                         YYABORT;
                                   }
                                 }
+        | expr '|' expr         { $$ = (long)$1 | (long)$3; }
+        | expr '&' expr         { $$ = (long)$1 & (long)$3; }
+        | expr '^' expr         { $$ = (long)$1 ^ (long)$3; }
         | expr '+' expr         { $$ = $1 + $3; }
         | expr '-' expr         { $$ = $1 - $3; }
         | expr '*' expr         { $$ = $1 * $3; }
         | expr '/' expr         { if ($3 == 0) YYABORT; $$ = $1 / $3; }
         | expr '%' expr         { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; }
         | '-' expr %prec NEG    { $$ = -$2; }
-        | '(' expr ')'          { $$ = $2; }
+        | '(' if_expr ')'       { $$ = $2; }
+        | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; }
+        | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; }
+        | SMT_ON                 { $$ = smt_on() > 0; }
         ;
 
 %%
@@ -82,13 +96,47 @@ static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
         char *dst = res->id;
         const char *s = p;
 
-        while (isalnum(*p) || *p == '_' || *p == '.') {
+        if (*p == '#')
+                *dst++ = *p++;
+
+        while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') {
                 if (p - s >= MAXIDLEN)
                         return -1;
-                *dst++ = *p++;
+                /*
+                 * Allow @ instead of / to be able to specify pmu/event/ without
+                 * conflicts with normal division.
+                 */
+                if (*p == '@')
+                        *dst++ = '/';
+                else if (*p == '\\')
+                        *dst++ = *++p;
+                else
+                        *dst++ = *p;
+                p++;
         }
         *dst = 0;
         *pp = p;
+        dst = res->id;
+        switch (dst[0]) {
+        case 'm':
+                if (!strcmp(dst, "min"))
+                        return MIN;
+                if (!strcmp(dst, "max"))
+                        return MAX;
+                break;
+        case 'i':
+                if (!strcmp(dst, "if"))
+                        return IF;
+                break;
+        case 'e':
+                if (!strcmp(dst, "else"))
+                        return ELSE;
+                break;
+        case '#':
+                if (!strcasecmp(dst, "#smt_on"))
+                        return SMT_ON;
+                break;
+        }
         return ID;
 }
 
@@ -102,6 +150,7 @@ static int expr__lex(YYSTYPE *res, const char **pp)
                 p++;
         s = p;
         switch (*p++) {
+        case '#':
         case 'a' ... 'z':
         case 'A' ... 'Z':
                 return expr__symbol(res, p - 1, pp);
@@ -132,6 +181,19 @@ void expr__ctx_init(struct parse_ctx *ctx)
         ctx->num_ids = 0;
 }
 
+static bool already_seen(const char *val, const char *one, const char **other,
+                         int num_other)
+{
+        int i;
+
+        if (one && !strcasecmp(one, val))
+                return true;
+        for (i = 0; i < num_other; i++)
+                if (!strcasecmp(other[i], val))
+                        return true;
+        return false;
+}
+
 int expr__find_other(const char *p, const char *one, const char ***other,
                      int *num_otherp)
 {
@@ -151,7 +213,7 @@ int expr__find_other(const char *p, const char *one, const char ***other,
                         err = 0;
                         break;
                 }
-                if (tok == ID && strcasecmp(one, val.id)) {
+                if (tok == ID && !already_seen(val.id, one, *other, num_other)) {
                         if (num_other >= EXPR_MAX_OTHER - 1) {
                                 pr_debug("Too many extra events in %s\n", orig);
                                 break;
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-vdso-map.c
index 95ef1cffc056..d7823e3508fc 100644
--- a/tools/perf/util/find-vdso-map.c
+++ b/tools/perf/util/find-vdso-map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 static int find_vdso_map(void **start, void **end)
 {
         FILE *maps;
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index 2424bd9862a3..de322d51c7fe 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __GENELF_H__
 #define __GENELF_H__
 
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 0ac2037c970c..9bbcec4e3365 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 echo "/* Automatically generated by $0 */
 struct cmdname_help
diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h
index 116debe7a995..f36c7e31780a 100644
--- a/tools/perf/util/group.h
+++ b/tools/perf/util/group.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef GROUP_H
 #define GROUP_H 1
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 76ed7d03e500..7c0e9d587bfa 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include "util.h"
@@ -12,6 +13,7 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <linux/stringify.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/utsname.h>
@@ -34,6 +36,7 @@
 #include "data.h"
 #include <api/fs/fs.h>
 #include "asm/bug.h"
+#include "tool.h"
 
 #include "sane_ctype.h"
 
@@ -59,6 +62,15 @@ struct perf_file_attr {
         struct perf_file_section        ids;
 };
 
+struct feat_fd {
+        struct perf_header      *ph;
+        int                     fd;
+        void                    *buf;   /* Either buf != NULL or fd >= 0 */
+        ssize_t                 offset;
+        size_t                  size;
+        struct perf_evsel       *events;
+};
+
 void perf_header__set_feat(struct perf_header *header, int feat)
 {
         set_bit(feat, header->adds_features);
@@ -74,28 +86,60 @@ bool perf_header__has_feat(const struct perf_header *header, int feat)
         return test_bit(feat, header->adds_features);
 }
 
-static int do_write(int fd, const void *buf, size_t size)
+static int __do_write_fd(struct feat_fd *ff, const void *buf, size_t size)
 {
-        while (size) {
-                int ret = write(fd, buf, size);
+        ssize_t ret = writen(ff->fd, buf, size);
 
-                if (ret < 0)
-                        return -errno;
+        if (ret != (ssize_t)size)
+                return ret < 0 ? (int)ret : -1;
+        return 0;
+}
+
+static int __do_write_buf(struct feat_fd *ff,  const void *buf, size_t size)
+{
+        /* struct perf_event_header::size is u16 */
+        const size_t max_size = 0xffff - sizeof(struct perf_event_header);
+        size_t new_size = ff->size;
+        void *addr;
 
-                size -= ret;
-                buf += ret;
+        if (size + ff->offset > max_size)
+                return -E2BIG;
+
+        while (size > (new_size - ff->offset))
+                new_size <<= 1;
+        new_size = min(max_size, new_size);
+
+        if (ff->size < new_size) {
+                addr = realloc(ff->buf, new_size);
+                if (!addr)
+                        return -ENOMEM;
+                ff->buf = addr;
+                ff->size = new_size;
         }
 
+        memcpy(ff->buf + ff->offset, buf, size);
+        ff->offset += size;
+
         return 0;
 }
 
-int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
+/* Return: 0 if succeded, -ERR if failed. */
+int do_write(struct feat_fd *ff, const void *buf, size_t size)
+{
+        if (!ff->buf)
+                return __do_write_fd(ff, buf, size);
+        return __do_write_buf(ff, buf, size);
+}
+
+/* Return: 0 if succeded, -ERR if failed. */
+int write_padded(struct feat_fd *ff, const void *bf,
+                 size_t count, size_t count_aligned)
 {
         static const char zero_buf[NAME_ALIGN];
-        int err = do_write(fd, bf, count);
+        int err = do_write(ff, bf, count);
 
         if (!err)
-                err = do_write(fd, zero_buf, count_aligned - count);
+                err = do_write(ff, zero_buf, count_aligned - count);
 
         return err;
 }
@@ -103,7 +147,8 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 #define string_size(str)                                                \
         (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32))
 
-static int do_write_string(int fd, const char *str)
+/* Return: 0 if succeded, -ERR if failed. */
+static int do_write_string(struct feat_fd *ff, const char *str)
 {
         u32 len, olen;
         int ret;
@@ -112,32 +157,80 @@ static int do_write_string(int fd, const char *str)
         len = PERF_ALIGN(olen, NAME_ALIGN);
 
         /* write len, incl. \0 */
-        ret = do_write(fd, &len, sizeof(len));
+        ret = do_write(ff, &len, sizeof(len));
         if (ret < 0)
                 return ret;
 
-        return write_padded(fd, str, olen, len);
+        return write_padded(ff, str, olen, len);
 }
 
-static char *do_read_string(int fd, struct perf_header *ph)
+static int __do_read_fd(struct feat_fd *ff, void *addr, ssize_t size)
+{
+        ssize_t ret = readn(ff->fd, addr, size);
+
+        if (ret != size)
+                return ret < 0 ? (int)ret : -1;
+        return 0;
+}
+
+static int __do_read_buf(struct feat_fd *ff, void *addr, ssize_t size)
+{
+        if (size > (ssize_t)ff->size - ff->offset)
+                return -1;
+
+        memcpy(addr, ff->buf + ff->offset, size);
+        ff->offset += size;
+
+        return 0;
+
+}
+
+static int __do_read(struct feat_fd *ff, void *addr, ssize_t size)
+{
+        if (!ff->buf)
+                return __do_read_fd(ff, addr, size);
+        return __do_read_buf(ff, addr, size);
+}
+
+static int do_read_u32(struct feat_fd *ff, u32 *addr)
+{
+        int ret;
+
+        ret = __do_read(ff, addr, sizeof(*addr));
+        if (ret)
+                return ret;
+
+        if (ff->ph->needs_swap)
+                *addr = bswap_32(*addr);
+        return 0;
+}
+
+static int do_read_u64(struct feat_fd *ff, u64 *addr)
+{
+        int ret;
+
+        ret = __do_read(ff, addr, sizeof(*addr));
+        if (ret)
+                return ret;
+
+        if (ff->ph->needs_swap)
+                *addr = bswap_64(*addr);
+        return 0;
+}
+
+static char *do_read_string(struct feat_fd *ff)
 {
-        ssize_t sz, ret;
         u32 len;
         char *buf;
 
-        sz = readn(fd, &len, sizeof(len));
-        if (sz < (ssize_t)sizeof(len))
+        if (do_read_u32(ff, &len))
                 return NULL;
 
-        if (ph->needs_swap)
-                len = bswap_32(len);
-
         buf = malloc(len);
         if (!buf)
                 return NULL;
 
-        ret = readn(fd, buf, len);
-        if (ret == (ssize_t)len) {
+        if (!__do_read(ff, buf, len)) {
                 /*
                  * strings are padded by zeroes
                  * thus the actual strlen of buf
@@ -150,25 +243,30 @@ static char *do_read_string(int fd, struct perf_header *ph)
         return NULL;
 }
 
-static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
-                            struct perf_evlist *evlist)
+static int write_tracing_data(struct feat_fd *ff,
+                              struct perf_evlist *evlist)
 {
-        return read_tracing_data(fd, &evlist->entries);
-}
+        if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                return -1;
 
+        return read_tracing_data(ff->fd, &evlist->entries);
+}
 
-static int write_build_id(int fd, struct perf_header *h,
+static int write_build_id(struct feat_fd *ff,
                           struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_session *session;
         int err;
 
-        session = container_of(h, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
 
         if (!perf_session__read_build_ids(session, true))
                 return -1;
 
-        err = perf_session__write_buildid_table(session, fd);
+        if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                return -1;
+
+        err = perf_session__write_buildid_table(session, ff);
         if (err < 0) {
                 pr_debug("failed to write buildid table\n");
                 return err;
@@ -178,7 +276,7 @@ static int write_build_id(int fd, struct perf_header *h,
         return 0;
 }
 
-static int write_hostname(int fd, struct perf_header *h __maybe_unused,
+static int write_hostname(struct feat_fd *ff,
                           struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
@@ -188,10 +286,10 @@ static int write_hostname(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return -1;
 
-        return do_write_string(fd, uts.nodename);
+        return do_write_string(ff, uts.nodename);
 }
 
-static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
+static int write_osrelease(struct feat_fd *ff,
                            struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
@@ -201,10 +299,10 @@ static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return -1;
 
-        return do_write_string(fd, uts.release);
+        return do_write_string(ff, uts.release);
 }
 
-static int write_arch(int fd, struct perf_header *h __maybe_unused,
+static int write_arch(struct feat_fd *ff,
                       struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
@@ -214,16 +312,16 @@ static int write_arch(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return -1;
 
-        return do_write_string(fd, uts.machine);
+        return do_write_string(ff, uts.machine);
 }
 
-static int write_version(int fd, struct perf_header *h __maybe_unused,
+static int write_version(struct feat_fd *ff,
                          struct perf_evlist *evlist __maybe_unused)
 {
-        return do_write_string(fd, perf_version_string);
+        return do_write_string(ff, perf_version_string);
 }
 
-static int __write_cpudesc(int fd, const char *cpuinfo_proc)
+static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc)
 {
         FILE *file;
         char *buf = NULL;
@@ -273,25 +371,22 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc)
                 }
                 p++;
         }
-        ret = do_write_string(fd, s);
+        ret = do_write_string(ff, s);
 done:
         free(buf);
         fclose(file);
         return ret;
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+static int write_cpudesc(struct feat_fd *ff,
                        struct perf_evlist *evlist __maybe_unused)
 {
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC {"model name", }
-#endif
         const char *cpuinfo_procs[] = CPUINFO_PROC;
         unsigned int i;
 
         for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
                 int ret;
-                ret = __write_cpudesc(fd, cpuinfo_procs[i]);
+                ret = __write_cpudesc(ff, cpuinfo_procs[i]);
                 if (ret >= 0)
                         return ret;
         }
@@ -299,7 +394,7 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
 }
 
 
-static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
+static int write_nrcpus(struct feat_fd *ff,
                         struct perf_evlist *evlist __maybe_unused)
 {
         long nr;
@@ -314,14 +409,14 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
 
         nra = (u32)(nr & UINT_MAX);
 
-        ret = do_write(fd, &nrc, sizeof(nrc));
+        ret = do_write(ff, &nrc, sizeof(nrc));
         if (ret < 0)
                 return ret;
 
-        return do_write(fd, &nra, sizeof(nra));
+        return do_write(ff, &nra, sizeof(nra));
 }
 
-static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
+static int write_event_desc(struct feat_fd *ff,
                             struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
@@ -333,7 +428,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
         /*
          * write number of events
          */
-        ret = do_write(fd, &nre, sizeof(nre));
+        ret = do_write(ff, &nre, sizeof(nre));
         if (ret < 0)
                 return ret;
 
@@ -341,12 +436,12 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
          * size of perf_event_attr struct
          */
         sz = (u32)sizeof(evsel->attr);
-        ret = do_write(fd, &sz, sizeof(sz));
+        ret = do_write(ff, &sz, sizeof(sz));
         if (ret < 0)
                 return ret;
 
         evlist__for_each_entry(evlist, evsel) {
-                ret = do_write(fd, &evsel->attr, sz);
+                ret = do_write(ff, &evsel->attr, sz);
                 if (ret < 0)
                         return ret;
                 /*
@@ -357,27 +452,27 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
                  * type of ids,
                  */
                 nri = evsel->ids;
-                ret = do_write(fd, &nri, sizeof(nri));
+                ret = do_write(ff, &nri, sizeof(nri));
                 if (ret < 0)
                         return ret;
 
                 /*
                  * write event string as passed on cmdline
                  */
-                ret = do_write_string(fd, perf_evsel__name(evsel));
+                ret = do_write_string(ff, perf_evsel__name(evsel));
                 if (ret < 0)
                         return ret;
                 /*
                  * write unique ids for this event
                  */
-                ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
+                ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64));
                 if (ret < 0)
                         return ret;
         }
         return 0;
 }
 
-static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
+static int write_cmdline(struct feat_fd *ff,
                          struct perf_evlist *evlist __maybe_unused)
 {
         char buf[MAXPATHLEN];
@@ -395,16 +490,16 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
         /* account for binary path */
         n = perf_env.nr_cmdline + 1;
 
-        ret = do_write(fd, &n, sizeof(n));
+        ret = do_write(ff, &n, sizeof(n));
         if (ret < 0)
                 return ret;
 
-        ret = do_write_string(fd, buf);
+        ret = do_write_string(ff, buf);
         if (ret < 0)
                 return ret;
 
         for (i = 0 ; i < perf_env.nr_cmdline; i++) {
-                ret = do_write_string(fd, perf_env.cmdline_argv[i]);
+                ret = do_write_string(ff, perf_env.cmdline_argv[i]);
                 if (ret < 0)
                         return ret;
         }
@@ -557,8 +652,8 @@ out_free:
         return tp;
 }
 
-static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_cpu_topology(struct feat_fd *ff,
+                              struct perf_evlist *evlist __maybe_unused)
 {
         struct cpu_topo *tp;
         u32 i;
@@ -568,21 +663,21 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
         if (!tp)
                 return -1;
 
-        ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib));
+        ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib));
         if (ret < 0)
                 goto done;
 
         for (i = 0; i < tp->core_sib; i++) {
-                ret = do_write_string(fd, tp->core_siblings[i]);
+                ret = do_write_string(ff, tp->core_siblings[i]);
                 if (ret < 0)
                         goto done;
         }
-        ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib));
+        ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib));
         if (ret < 0)
                 goto done;
 
         for (i = 0; i < tp->thread_sib; i++) {
-                ret = do_write_string(fd, tp->thread_siblings[i]);
+                ret = do_write_string(ff, tp->thread_siblings[i]);
                 if (ret < 0)
                         break;
         }
@@ -592,11 +687,11 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
                 goto done;
 
         for (j = 0; j < perf_env.nr_cpus_avail; j++) {
-                ret = do_write(fd, &perf_env.cpu[j].core_id,
+                ret = do_write(ff, &perf_env.cpu[j].core_id,
                                sizeof(perf_env.cpu[j].core_id));
                 if (ret < 0)
                         return ret;
-                ret = do_write(fd, &perf_env.cpu[j].socket_id,
+                ret = do_write(ff, &perf_env.cpu[j].socket_id,
                                sizeof(perf_env.cpu[j].socket_id));
                 if (ret < 0)
                         return ret;
@@ -608,8 +703,8 @@ done:
 
 
 
-static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_total_mem(struct feat_fd *ff,
+                           struct perf_evlist *evlist __maybe_unused)
 {
         char *buf = NULL;
         FILE *fp;
@@ -629,7 +724,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
         if (!ret) {
                 n = sscanf(buf, "%*s %"PRIu64, &mem);
                 if (n == 1)
-                        ret = do_write(fd, &mem, sizeof(mem));
+                        ret = do_write(ff, &mem, sizeof(mem));
         } else
                 ret = -1;
         free(buf);
@@ -637,7 +732,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
         return ret;
 }
 
-static int write_topo_node(int fd, int node)
+static int write_topo_node(struct feat_fd *ff, int node)
 {
         char str[MAXPATHLEN];
         char field[32];
@@ -667,11 +762,11 @@ static int write_topo_node(int fd, int node)
         fclose(fp);
         fp = NULL;
 
-        ret = do_write(fd, &mem_total, sizeof(u64));
+        ret = do_write(ff, &mem_total, sizeof(u64));
         if (ret)
                 goto done;
 
-        ret = do_write(fd, &mem_free, sizeof(u64));
+        ret = do_write(ff, &mem_free, sizeof(u64));
         if (ret)
                 goto done;
 
@@ -689,7 +784,7 @@ static int write_topo_node(int fd, int node)
         if (p)
                 *p = '\0';
 
-        ret = do_write_string(fd, buf);
+        ret = do_write_string(ff, buf);
 done:
         free(buf);
         if (fp)
@@ -697,8 +792,8 @@ done:
         return ret;
 }
 
-static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_numa_topology(struct feat_fd *ff,
+                               struct perf_evlist *evlist __maybe_unused)
 {
         char *buf = NULL;
         size_t len = 0;
@@ -725,17 +820,17 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
 
         nr = (u32)node_map->nr;
 
-        ret = do_write(fd, &nr, sizeof(nr));
+        ret = do_write(ff, &nr, sizeof(nr));
         if (ret < 0)
                 goto done;
 
         for (i = 0; i < nr; i++) {
                 j = (u32)node_map->map[i];
-                ret = do_write(fd, &j, sizeof(j));
+                ret = do_write(ff, &j, sizeof(j));
                 if (ret < 0)
                         break;
 
-                ret = write_topo_node(fd, i);
+                ret = write_topo_node(ff, i);
                 if (ret < 0)
                         break;
         }
@@ -758,39 +853,40 @@ done:
  * };
  */
 
-static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
+static int write_pmu_mappings(struct feat_fd *ff,
                               struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_pmu *pmu = NULL;
-        off_t offset = lseek(fd, 0, SEEK_CUR);
-        __u32 pmu_num = 0;
+        u32 pmu_num = 0;
         int ret;
 
-        /* write real pmu_num later */
-        ret = do_write(fd, &pmu_num, sizeof(pmu_num));
+        /*
+         * Do a first pass to count number of pmu to avoid lseek so this
+         * works in pipe mode as well.
+         */
+        while ((pmu = perf_pmu__scan(pmu))) {
+                if (!pmu->name)
+                        continue;
+                pmu_num++;
+        }
+
+        ret = do_write(ff, &pmu_num, sizeof(pmu_num));
         if (ret < 0)
                 return ret;
 
         while ((pmu = perf_pmu__scan(pmu))) {
                 if (!pmu->name)
                         continue;
-                pmu_num++;
 
-                ret = do_write(fd, &pmu->type, sizeof(pmu->type));
+                ret = do_write(ff, &pmu->type, sizeof(pmu->type));
                 if (ret < 0)
                         return ret;
 
-                ret = do_write_string(fd, pmu->name);
+                ret = do_write_string(ff, pmu->name);
                 if (ret < 0)
                         return ret;
         }
 
-        if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
-                /* discard all */
-                lseek(fd, offset, SEEK_SET);
-                return -1;
-        }
-
         return 0;
 }
 
@@ -806,14 +902,14 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
  *      }[nr_groups];
  * };
  */
-static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+static int write_group_desc(struct feat_fd *ff,
                             struct perf_evlist *evlist)
 {
         u32 nr_groups = evlist->nr_groups;
         struct perf_evsel *evsel;
         int ret;
 
-        ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+        ret = do_write(ff, &nr_groups, sizeof(nr_groups));
         if (ret < 0)
                 return ret;
 
@@ -824,15 +920,15 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
                         u32 leader_idx = evsel->idx;
                         u32 nr_members = evsel->nr_members;
 
-                        ret = do_write_string(fd, name);
+                        ret = do_write_string(ff, name);
                         if (ret < 0)
                                 return ret;
 
-                        ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+                        ret = do_write(ff, &leader_idx, sizeof(leader_idx));
                         if (ret < 0)
                                 return ret;
 
-                        ret = do_write(fd, &nr_members, sizeof(nr_members));
+                        ret = do_write(ff, &nr_members, sizeof(nr_members));
                         if (ret < 0)
                                 return ret;
                 }
@@ -849,7 +945,7 @@ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
         return -1;
 }
 
-static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
+static int write_cpuid(struct feat_fd *ff,
                        struct perf_evlist *evlist __maybe_unused)
 {
         char buffer[64];
@@ -861,25 +957,27 @@ static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
 
         return -1;
 write_it:
-        return do_write_string(fd, buffer);
+        return do_write_string(ff, buffer);
 }
 
-static int write_branch_stack(int fd __maybe_unused,
-                              struct perf_header *h __maybe_unused,
-                       struct perf_evlist *evlist __maybe_unused)
+static int write_branch_stack(struct feat_fd *ff __maybe_unused,
+                              struct perf_evlist *evlist __maybe_unused)
 {
         return 0;
 }
 
-static int write_auxtrace(int fd, struct perf_header *h,
+static int write_auxtrace(struct feat_fd *ff,
                           struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_session *session;
         int err;
 
-        session = container_of(h, struct perf_session, header);
+        if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                return -1;
+
+        session = container_of(ff->ph, struct perf_session, header);
 
-        err = auxtrace_index__write(fd, &session->auxtrace_index);
+        err = auxtrace_index__write(ff->fd, &session->auxtrace_index);
         if (err < 0)
                 pr_err("Failed to write auxtrace index\n");
         return err;
@@ -1026,8 +1124,8 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 
 #define MAX_CACHES 2000
 
-static int write_cache(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_cache(struct feat_fd *ff,
+                       struct perf_evlist *evlist __maybe_unused)
 {
         struct cpu_cache_level caches[MAX_CACHES];
         u32 cnt = 0, i, version = 1;
@@ -1039,11 +1137,11 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused,
 
         qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
 
-        ret = do_write(fd, &version, sizeof(u32));
+        ret = do_write(ff, &version, sizeof(u32));
         if (ret < 0)
                 goto out;
 
-        ret = do_write(fd, &cnt, sizeof(u32));
+        ret = do_write(ff, &cnt, sizeof(u32));
         if (ret < 0)
                 goto out;
 
@@ -1051,7 +1149,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused,
                 struct cpu_cache_level *c = &caches[i];
 
                 #define _W(v)                                   \
-                        ret = do_write(fd, &c->v, sizeof(u32)); \
+                        ret = do_write(ff, &c->v, sizeof(u32)); \
                         if (ret < 0)                            \
                                 goto out;
 
@@ -1062,7 +1160,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused,
                 #undef _W
 
                 #define _W(v)                                           \
-                        ret = do_write_string(fd, (const char *) c->v); \
+                        ret = do_write_string(ff, (const char *) c->v); \
                         if (ret < 0)                                    \
                                 goto out;
 
@@ -1078,69 +1176,62 @@ out:
         return ret;
 }
 
-static int write_stat(int fd __maybe_unused,
-                      struct perf_header *h __maybe_unused,
+static int write_stat(struct feat_fd *ff __maybe_unused,
                       struct perf_evlist *evlist __maybe_unused)
 {
         return 0;
 }
 
-static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
-                           FILE *fp)
+static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# hostname : %s\n", ph->env.hostname);
+        fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
 }
 
-static void print_osrelease(struct perf_header *ph, int fd __maybe_unused,
-                            FILE *fp)
+static void print_osrelease(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# os release : %s\n", ph->env.os_release);
+        fprintf(fp, "# os release : %s\n", ff->ph->env.os_release);
 }
 
-static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
+static void print_arch(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# arch : %s\n", ph->env.arch);
+        fprintf(fp, "# arch : %s\n", ff->ph->env.arch);
 }
 
-static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused,
-                          FILE *fp)
+static void print_cpudesc(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc);
+        fprintf(fp, "# cpudesc : %s\n", ff->ph->env.cpu_desc);
 }
 
-static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused,
-                         FILE *fp)
+static void print_nrcpus(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online);
-        fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail);
+        fprintf(fp, "# nrcpus online : %u\n", ff->ph->env.nr_cpus_online);
+        fprintf(fp, "# nrcpus avail : %u\n", ff->ph->env.nr_cpus_avail);
 }
 
-static void print_version(struct perf_header *ph, int fd __maybe_unused,
-                          FILE *fp)
+static void print_version(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# perf version : %s\n", ph->env.version);
+        fprintf(fp, "# perf version : %s\n", ff->ph->env.version);
 }
 
-static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
-                          FILE *fp)
+static void print_cmdline(struct feat_fd *ff, FILE *fp)
 {
         int nr, i;
 
-        nr = ph->env.nr_cmdline;
+        nr = ff->ph->env.nr_cmdline;
 
         fprintf(fp, "# cmdline : ");
 
         for (i = 0; i < nr; i++)
-                fprintf(fp, "%s ", ph->env.cmdline_argv[i]);
+                fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]);
         fputc('\n', fp);
 }
 
-static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
-                               FILE *fp)
+static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 {
+        struct perf_header *ph = ff->ph;
+        int cpu_nr = ph->env.nr_cpus_avail;
         int nr, i;
         char *str;
-        int cpu_nr = ph->env.nr_cpus_avail;
 
         nr = ph->env.nr_sibling_cores;
         str = ph->env.sibling_cores;
@@ -1181,31 +1272,21 @@ static void free_event_desc(struct perf_evsel *events)
         free(events);
 }
 
-static struct perf_evsel *
-read_event_desc(struct perf_header *ph, int fd)
+static struct perf_evsel *read_event_desc(struct feat_fd *ff)
 {
         struct perf_evsel *evsel, *events = NULL;
         u64 *id;
         void *buf = NULL;
         u32 nre, sz, nr, i, j;
-        ssize_t ret;
         size_t msz;
 
         /* number of events */
-        ret = readn(fd, &nre, sizeof(nre));
-        if (ret != (ssize_t)sizeof(nre))
+        if (do_read_u32(ff, &nre))
                 goto error;
 
-        if (ph->needs_swap)
-                nre = bswap_32(nre);
-
-        ret = readn(fd, &sz, sizeof(sz));
-        if (ret != (ssize_t)sizeof(sz))
+        if (do_read_u32(ff, &sz))
                 goto error;
 
-        if (ph->needs_swap)
-                sz = bswap_32(sz);
-
         /* buffer to hold on file attr struct */
         buf = malloc(sz);
         if (!buf)
@@ -1227,25 +1308,23 @@ read_event_desc(struct perf_header *ph, int fd)
                  * must read entire on-file attr struct to
                  * sync up with layout.
                  */
-                ret = readn(fd, buf, sz);
-                if (ret != (ssize_t)sz)
+                if (__do_read(ff, buf, sz))
                         goto error;
 
-                if (ph->needs_swap)
+                if (ff->ph->needs_swap)
                         perf_event__attr_swap(buf);
 
                 memcpy(&evsel->attr, buf, msz);
 
-                ret = readn(fd, &nr, sizeof(nr));
-                if (ret != (ssize_t)sizeof(nr))
+                if (do_read_u32(ff, &nr))
                         goto error;
 
-                if (ph->needs_swap) {
-                        nr = bswap_32(nr);
+                if (ff->ph->needs_swap)
                         evsel->needs_swap = true;
-                }
 
-                evsel->name = do_read_string(fd, ph);
+                evsel->name = do_read_string(ff);
+                if (!evsel->name)
+                        goto error;
 
                 if (!nr)
                         continue;
@@ -1257,11 +1336,8 @@ read_event_desc(struct perf_header *ph, int fd)
                 evsel->id = id;
 
                 for (j = 0 ; j < nr; j++) {
-                        ret = readn(fd, id, sizeof(*id));
-                        if (ret != (ssize_t)sizeof(*id))
+                        if (do_read_u64(ff, id))
                                 goto error;
-                        if (ph->needs_swap)
-                                *id = bswap_64(*id);
                         id++;
                 }
         }
@@ -1280,12 +1356,17 @@ static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val,
         return fprintf(fp, ", %s = %s", name, val);
 }
 
-static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+static void print_event_desc(struct feat_fd *ff, FILE *fp)
 {
-        struct perf_evsel *evsel, *events = read_event_desc(ph, fd);
+        struct perf_evsel *evsel, *events;
         u32 j;
         u64 *id;
 
+        if (ff->events)
+                events = ff->events;
+        else
+                events = read_event_desc(ff);
+
         if (!events) {
                 fprintf(fp, "# event desc: not available or unable to read\n");
                 return;
@@ -1310,22 +1391,21 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
         }
 
         free_event_desc(events);
+        ff->events = NULL;
 }
 
-static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
-                            FILE *fp)
+static void print_total_mem(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem);
+        fprintf(fp, "# total memory : %llu kB\n", ff->ph->env.total_mem);
 }
 
-static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
-                                FILE *fp)
+static void print_numa_topology(struct feat_fd *ff, FILE *fp)
 {
         int i;
         struct numa_node *n;
 
-        for (i = 0; i < ph->env.nr_numa_nodes; i++) {
-                n = &ph->env.numa_nodes[i];
+        for (i = 0; i < ff->ph->env.nr_numa_nodes; i++) {
+                n = &ff->ph->env.numa_nodes[i];
 
                 fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
                             " free = %"PRIu64" kB\n",
@@ -1336,56 +1416,51 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
         }
 }
 
-static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
+static void print_cpuid(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# cpuid : %s\n", ph->env.cpuid);
+        fprintf(fp, "# cpuid : %s\n", ff->ph->env.cpuid);
 }
 
-static void print_branch_stack(struct perf_header *ph __maybe_unused,
-                               int fd __maybe_unused, FILE *fp)
+static void print_branch_stack(struct feat_fd *ff __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains samples with branch stack\n");
 }
 
-static void print_auxtrace(struct perf_header *ph __maybe_unused,
-                           int fd __maybe_unused, FILE *fp)
+static void print_auxtrace(struct feat_fd *ff __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
 }
 
-static void print_stat(struct perf_header *ph __maybe_unused,
-                       int fd __maybe_unused, FILE *fp)
+static void print_stat(struct feat_fd *ff __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains stat data\n");
 }
 
-static void print_cache(struct perf_header *ph __maybe_unused,
-                        int fd __maybe_unused, FILE *fp __maybe_unused)
+static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused)
 {
         int i;
 
         fprintf(fp, "# CPU cache info:\n");
-        for (i = 0; i < ph->env.caches_cnt; i++) {
+        for (i = 0; i < ff->ph->env.caches_cnt; i++) {
                 fprintf(fp, "#  ");
-                cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+                cpu_cache_level__fprintf(fp, &ff->ph->env.caches[i]);
         }
 }
 
-static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
-                               FILE *fp)
+static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
 {
         const char *delimiter = "# pmu mappings: ";
         char *str, *tmp;
         u32 pmu_num;
         u32 type;
 
-        pmu_num = ph->env.nr_pmu_mappings;
+        pmu_num = ff->ph->env.nr_pmu_mappings;
         if (!pmu_num) {
                 fprintf(fp, "# pmu mappings: not available\n");
                 return;
         }
 
-        str = ph->env.pmu_mappings;
+        str = ff->ph->env.pmu_mappings;
 
         while (pmu_num) {
                 type = strtoul(str, &tmp, 0);
@@ -1408,14 +1483,13 @@ error:
         fprintf(fp, "# pmu mappings: unable to read\n");
 }
 
-static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
-                             FILE *fp)
+static void print_group_desc(struct feat_fd *ff, FILE *fp)
 {
         struct perf_session *session;
         struct perf_evsel *evsel;
         u32 nr = 0;
 
-        session = container_of(ph, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
 
         evlist__for_each_entry(session->evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
@@ -1588,113 +1662,61 @@ out:
         return err;
 }
 
-static int process_tracing_data(struct perf_file_section *section __maybe_unused,
-                                struct perf_header *ph __maybe_unused,
-                                int fd, void *data)
-{
-        ssize_t ret = trace_report(fd, data, false);
-        return ret < 0 ? -1 : 0;
-}
-
-static int process_build_id(struct perf_file_section *section,
-                            struct perf_header *ph, int fd,
-                            void *data __maybe_unused)
-{
-        if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
-                pr_debug("Failed to read buildids, continuing...\n");
-        return 0;
+/* Macro for features that simply need to read and store a string. */
+#define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \
+static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \
+{\
+        ff->ph->env.__feat_env = do_read_string(ff); \
+        return ff->ph->env.__feat_env ? 0 : -ENOMEM; \
 }
 
-static int process_hostname(struct perf_file_section *section __maybe_unused,
-                            struct perf_header *ph, int fd,
-                            void *data __maybe_unused)
-{
-        ph->env.hostname = do_read_string(fd, ph);
-        return ph->env.hostname ? 0 : -ENOMEM;
-}
+FEAT_PROCESS_STR_FUN(hostname, hostname);
+FEAT_PROCESS_STR_FUN(osrelease, os_release);
+FEAT_PROCESS_STR_FUN(version, version);
+FEAT_PROCESS_STR_FUN(arch, arch);
+FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc);
+FEAT_PROCESS_STR_FUN(cpuid, cpuid);
 
-static int process_osrelease(struct perf_file_section *section __maybe_unused,
-                             struct perf_header *ph, int fd,
-                             void *data __maybe_unused)
+static int process_tracing_data(struct feat_fd *ff, void *data)
 {
-        ph->env.os_release = do_read_string(fd, ph);
-        return ph->env.os_release ? 0 : -ENOMEM;
-}
+        ssize_t ret = trace_report(ff->fd, data, false);
 
-static int process_version(struct perf_file_section *section __maybe_unused,
-                           struct perf_header *ph, int fd,
-                           void *data __maybe_unused)
-{
-        ph->env.version = do_read_string(fd, ph);
-        return ph->env.version ? 0 : -ENOMEM;
+        return ret < 0 ? -1 : 0;
 }
 
-static int process_arch(struct perf_file_section *section __maybe_unused,
-                        struct perf_header *ph, int fd,
-                        void *data __maybe_unused)
+static int process_build_id(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ph->env.arch = do_read_string(fd, ph);
-        return ph->env.arch ? 0 : -ENOMEM;
+        if (perf_header__read_build_ids(ff->ph, ff->fd, ff->offset, ff->size))
+                pr_debug("Failed to read buildids, continuing...\n");
+        return 0;
 }
 
-static int process_nrcpus(struct perf_file_section *section __maybe_unused,
-                          struct perf_header *ph, int fd,
-                          void *data __maybe_unused)
+static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
-        u32 nr;
-
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
-                return -1;
-
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
-        ph->env.nr_cpus_avail = nr;
-
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
-                return -1;
+        int ret;
+        u32 nr_cpus_avail, nr_cpus_online;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
+        ret = do_read_u32(ff, &nr_cpus_avail);
+        if (ret)
+                return ret;
 
-        ph->env.nr_cpus_online = nr;
+        ret = do_read_u32(ff, &nr_cpus_online);
+        if (ret)
+                return ret;
+        ff->ph->env.nr_cpus_avail = (int)nr_cpus_avail;
+        ff->ph->env.nr_cpus_online = (int)nr_cpus_online;
         return 0;
 }
 
-static int process_cpudesc(struct perf_file_section *section __maybe_unused,
-                           struct perf_header *ph, int fd,
-                           void *data __maybe_unused)
-{
-        ph->env.cpu_desc = do_read_string(fd, ph);
-        return ph->env.cpu_desc ? 0 : -ENOMEM;
-}
-
-static int process_cpuid(struct perf_file_section *section __maybe_unused,
-                         struct perf_header *ph,  int fd,
-                         void *data __maybe_unused)
-{
-        ph->env.cpuid = do_read_string(fd, ph);
-        return ph->env.cpuid ? 0 : -ENOMEM;
-}
-
-static int process_total_mem(struct perf_file_section *section __maybe_unused,
-                             struct perf_header *ph, int fd,
-                             void *data __maybe_unused)
+static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused)
 {
-        uint64_t mem;
-        ssize_t ret;
+        u64 total_mem;
+        int ret;
 
-        ret = readn(fd, &mem, sizeof(mem));
-        if (ret != sizeof(mem))
+        ret = do_read_u64(ff, &total_mem);
+        if (ret)
                 return -1;
-
-        if (ph->needs_swap)
-                mem = bswap_64(mem);
-
-        ph->env.total_mem = mem;
+        ff->ph->env.total_mem = (unsigned long long)total_mem;
         return 0;
 }
 
@@ -1731,43 +1753,42 @@ perf_evlist__set_event_name(struct perf_evlist *evlist,
 }
 
 static int
-process_event_desc(struct perf_file_section *section __maybe_unused,
-                   struct perf_header *header, int fd,
-                   void *data __maybe_unused)
+process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct perf_session *session;
-        struct perf_evsel *evsel, *events = read_event_desc(header, fd);
+        struct perf_evsel *evsel, *events = read_event_desc(ff);
 
         if (!events)
                 return 0;
 
-        session = container_of(header, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
+
+        if (session->data->is_pipe) {
+                /* Save events for reading later by print_event_desc,
+                 * since they can't be read again in pipe mode. */
+                ff->events = events;
+        }
+
         for (evsel = events; evsel->attr.size; evsel++)
                 perf_evlist__set_event_name(session->evlist, evsel);
 
-        free_event_desc(events);
+        if (!session->data->is_pipe)
+                free_event_desc(events);
 
         return 0;
 }
 
-static int process_cmdline(struct perf_file_section *section,
-                           struct perf_header *ph, int fd,
-                           void *data __maybe_unused)
+static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
         char *str, *cmdline = NULL, **argv = NULL;
         u32 nr, i, len = 0;
 
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 return -1;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
-        ph->env.nr_cmdline = nr;
+        ff->ph->env.nr_cmdline = nr;
 
-        cmdline = zalloc(section->size + nr + 1);
+        cmdline = zalloc(ff->size + nr + 1);
         if (!cmdline)
                 return -1;
 
@@ -1776,7 +1797,7 @@ static int process_cmdline(struct perf_file_section *section,
                 goto error;
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1785,8 +1806,8 @@ static int process_cmdline(struct perf_file_section *section,
                 len += strlen(str) + 1;
                 free(str);
         }
-        ph->env.cmdline = cmdline;
-        ph->env.cmdline_argv = (const char **) argv;
+        ff->ph->env.cmdline = cmdline;
+        ff->ph->env.cmdline_argv = (const char **) argv;
         return 0;
 
 error:
@@ -1795,35 +1816,29 @@ error:
         return -1;
 }
 
-static int process_cpu_topology(struct perf_file_section *section,
-                                struct perf_header *ph, int fd,
-                                void *data __maybe_unused)
+static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
         u32 nr, i;
         char *str;
         struct strbuf sb;
-        int cpu_nr = ph->env.nr_cpus_avail;
+        int cpu_nr = ff->ph->env.nr_cpus_avail;
         u64 size = 0;
+        struct perf_header *ph = ff->ph;
 
         ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
         if (!ph->env.cpu)
                 return -1;
 
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 goto free_cpu;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
         ph->env.nr_sibling_cores = nr;
         size += sizeof(u32);
         if (strbuf_init(&sb, 128) < 0)
                 goto free_cpu;
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1835,18 +1850,14 @@ static int process_cpu_topology(struct perf_file_section *section,
         }
         ph->env.sibling_cores = strbuf_detach(&sb, NULL);
 
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 return -1;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
         ph->env.nr_sibling_threads = nr;
         size += sizeof(u32);
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1862,28 +1873,20 @@ static int process_cpu_topology(struct perf_file_section *section,
          * The header may be from old perf,
          * which doesn't include core id and socket id information.
          */
-        if (section->size <= size) {
+        if (ff->size <= size) {
                 zfree(&ph->env.cpu);
                 return 0;
         }
 
         for (i = 0; i < (u32)cpu_nr; i++) {
-                ret = readn(fd, &nr, sizeof(nr));
-                if (ret != sizeof(nr))
+                if (do_read_u32(ff, &nr))
                         goto free_cpu;
 
-                if (ph->needs_swap)
-                        nr = bswap_32(nr);
-
                 ph->env.cpu[i].core_id = nr;
 
-                ret = readn(fd, &nr, sizeof(nr));
-                if (ret != sizeof(nr))
+                if (do_read_u32(ff, &nr))
                         goto free_cpu;
 
-                if (ph->needs_swap)
-                        nr = bswap_32(nr);
-
                 if (nr != (u32)-1 && nr > (u32)cpu_nr) {
                         pr_debug("socket_id number is too big."
                                  "You may need to upgrade the perf tool.\n");
@@ -1902,23 +1905,16 @@ free_cpu:
         return -1;
 }
 
-static int process_numa_topology(struct perf_file_section *section __maybe_unused,
-                                 struct perf_header *ph, int fd,
-                                 void *data __maybe_unused)
+static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct numa_node *nodes, *n;
-        ssize_t ret;
         u32 nr, i;
         char *str;
 
         /* nr nodes */
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 return -1;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
         nodes = zalloc(sizeof(*nodes) * nr);
         if (!nodes)
                 return -ENOMEM;
@@ -1927,25 +1923,16 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
                 n = &nodes[i];
 
                 /* node number */
-                ret = readn(fd, &n->node, sizeof(u32));
-                if (ret != sizeof(n->node))
+                if (do_read_u32(ff, &n->node))
                         goto error;
 
-                ret = readn(fd, &n->mem_total, sizeof(u64));
-                if (ret != sizeof(u64))
+                if (do_read_u64(ff, &n->mem_total))
                         goto error;
 
-                ret = readn(fd, &n->mem_free, sizeof(u64));
-                if (ret != sizeof(u64))
+                if (do_read_u64(ff, &n->mem_free))
                         goto error;
 
-                if (ph->needs_swap) {
-                        n->node      = bswap_32(n->node);
-                        n->mem_total = bswap_64(n->mem_total);
-                        n->mem_free  = bswap_64(n->mem_free);
-                }
-
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1955,8 +1942,8 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 
                 free(str);
         }
-        ph->env.nr_numa_nodes = nr;
-        ph->env.numa_nodes = nodes;
+        ff->ph->env.nr_numa_nodes = nr;
+        ff->ph->env.numa_nodes = nodes;
         return 0;
 
 error:
@@ -1964,39 +1951,30 @@ error:
         return -1;
 }
 
-static int process_pmu_mappings(struct perf_file_section *section __maybe_unused,
-                                struct perf_header *ph, int fd,
-                                void *data __maybe_unused)
+static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
         char *name;
         u32 pmu_num;
         u32 type;
         struct strbuf sb;
 
-        ret = readn(fd, &pmu_num, sizeof(pmu_num));
-        if (ret != sizeof(pmu_num))
+        if (do_read_u32(ff, &pmu_num))
                 return -1;
 
-        if (ph->needs_swap)
-                pmu_num = bswap_32(pmu_num);
-
         if (!pmu_num) {
                 pr_debug("pmu mappings not available\n");
                 return 0;
         }
 
-        ph->env.nr_pmu_mappings = pmu_num;
+        ff->ph->env.nr_pmu_mappings = pmu_num;
         if (strbuf_init(&sb, 128) < 0)
                 return -1;
 
         while (pmu_num) {
-                if (readn(fd, &type, sizeof(type)) != sizeof(type))
+                if (do_read_u32(ff, &type))
                         goto error;
-                if (ph->needs_swap)
-                        type = bswap_32(type);
 
-                name = do_read_string(fd, ph);
+                name = do_read_string(ff);
                 if (!name)
                         goto error;
 
@@ -2007,12 +1985,12 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
                         goto error;
 
                 if (!strcmp(name, "msr"))
-                        ph->env.msr_pmu_type = type;
+                        ff->ph->env.msr_pmu_type = type;
 
                 free(name);
                 pmu_num--;
         }
-        ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
+        ff->ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
         return 0;
 
 error:
@@ -2020,9 +1998,7 @@ error:
         return -1;
 }
 
-static int process_group_desc(struct perf_file_section *section __maybe_unused,
-                              struct perf_header *ph, int fd,
-                              void *data __maybe_unused)
+static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused)
 {
         size_t ret = -1;
         u32 i, nr, nr_groups;
@@ -2034,13 +2010,10 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
                 u32 nr_members;
         } *desc;
 
-        if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
+        if (do_read_u32(ff, &nr_groups))
                 return -1;
 
-        if (ph->needs_swap)
-                nr_groups = bswap_32(nr_groups);
-
-        ph->env.nr_groups = nr_groups;
+        ff->ph->env.nr_groups = nr_groups;
         if (!nr_groups) {
                 pr_debug("group desc not available\n");
                 return 0;
@@ -2051,26 +2024,21 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
                 return -1;
 
         for (i = 0; i < nr_groups; i++) {
-                desc[i].name = do_read_string(fd, ph);
+                desc[i].name = do_read_string(ff);
                 if (!desc[i].name)
                         goto out_free;
 
-                if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+                if (do_read_u32(ff, &desc[i].leader_idx))
                         goto out_free;
 
-                if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+                if (do_read_u32(ff, &desc[i].nr_members))
                         goto out_free;
-
-                if (ph->needs_swap) {
-                        desc[i].leader_idx = bswap_32(desc[i].leader_idx);
-                        desc[i].nr_members = bswap_32(desc[i].nr_members);
-                }
         }
 
         /*
          * Rebuild group relationship based on the group_desc
          */
-        session = container_of(ph, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
         session->evlist->nr_groups = nr_groups;
 
         i = nr = 0;
@@ -2114,44 +2082,34 @@ out_free:
         return ret;
 }
 
-static int process_auxtrace(struct perf_file_section *section,
-                            struct perf_header *ph, int fd,
-                            void *data __maybe_unused)
+static int process_auxtrace(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct perf_session *session;
         int err;
 
-        session = container_of(ph, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
 
-        err = auxtrace_index__process(fd, section->size, session,
-                                      ph->needs_swap);
+        err = auxtrace_index__process(ff->fd, ff->size, session,
+                                      ff->ph->needs_swap);
         if (err < 0)
                 pr_err("Failed to process auxtrace index\n");
         return err;
 }
 
-static int process_cache(struct perf_file_section *section __maybe_unused,
-                         struct perf_header *ph __maybe_unused, int fd __maybe_unused,
-                         void *data __maybe_unused)
+static int process_cache(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct cpu_cache_level *caches;
         u32 cnt, i, version;
 
-        if (readn(fd, &version, sizeof(version)) != sizeof(version))
+        if (do_read_u32(ff, &version))
                 return -1;
 
-        if (ph->needs_swap)
-                version = bswap_32(version);
-
         if (version != 1)
                 return -1;
 
-        if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+        if (do_read_u32(ff, &cnt))
                 return -1;
 
-        if (ph->needs_swap)
-                cnt = bswap_32(cnt);
-
         caches = zalloc(sizeof(*caches) * cnt);
         if (!caches)
                 return -1;
@@ -2160,10 +2118,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused,
                 struct cpu_cache_level c;
 
                 #define _R(v)                                           \
-                        if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+                        if (do_read_u32(ff, &c.v))\
                                 goto out_free_caches;                   \
-                        if (ph->needs_swap)                             \
-                                c.v = bswap_32(c.v);                    \
 
                 _R(level)
                 _R(line_size)
@@ -2171,9 +2127,9 @@ static int process_cache(struct perf_file_section *section __maybe_unused,
                 _R(ways)
                 #undef _R
 
-                #define _R(v)                           \
-                        c.v = do_read_string(fd, ph);   \
-                        if (!c.v)                       \
+                #define _R(v)                                   \
+                        c.v = do_read_string(ff);               \
+                        if (!c.v)                               \
                                 goto out_free_caches;
 
                 _R(type)
@@ -2184,8 +2140,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused,
                 caches[i] = c;
         }
 
-        ph->env.caches = caches;
-        ph->env.caches_cnt = cnt;
+        ff->ph->env.caches = caches;
+        ff->ph->env.caches_cnt = cnt;
         return 0;
 out_free_caches:
         free(caches);
@@ -2193,48 +2149,62 @@ out_free_caches:
 }
 
 struct feature_ops {
-        int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
-        void (*print)(struct perf_header *h, int fd, FILE *fp);
-        int (*process)(struct perf_file_section *section,
-                       struct perf_header *h, int fd, void *data);
+        int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
+        void (*print)(struct feat_fd *ff, FILE *fp);
+        int (*process)(struct feat_fd *ff, void *data);
         const char *name;
         bool full_only;
+        bool synthesize;
 };
 
-#define FEAT_OPA(n, func) \
-        [n] = { .name = #n, .write = write_##func, .print = print_##func }
-#define FEAT_OPP(n, func) \
-        [n] = { .name = #n, .write = write_##func, .print = print_##func, \
-                .process = process_##func }
-#define FEAT_OPF(n, func) \
-        [n] = { .name = #n, .write = write_##func, .print = print_##func, \
-                .process = process_##func, .full_only = true }
+#define FEAT_OPR(n, func, __full_only) \
+        [HEADER_##n] = {                                        \
+                .name       = __stringify(n),                   \
+                .write      = write_##func,                     \
+                .print      = print_##func,                     \
+                .full_only  = __full_only,                      \
+                .process    = process_##func,                   \
+                .synthesize = true                              \
+        }
+
+#define FEAT_OPN(n, func, __full_only) \
+        [HEADER_##n] = {                                        \
+                .name       = __stringify(n),                   \
+                .write      = write_##func,                     \
+                .print      = print_##func,                     \
+                .full_only  = __full_only,                      \
+                .process    = process_##func                    \
+        }
 
 /* feature_ops not implemented: */
 #define print_tracing_data      NULL
 #define print_build_id          NULL
 
+#define process_branch_stack    NULL
+#define process_stat            NULL
+
+
 static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
-        FEAT_OPP(HEADER_TRACING_DATA,   tracing_data),
-        FEAT_OPP(HEADER_BUILD_ID,       build_id),
-        FEAT_OPP(HEADER_HOSTNAME,       hostname),
-        FEAT_OPP(HEADER_OSRELEASE,      osrelease),
-        FEAT_OPP(HEADER_VERSION,        version),
-        FEAT_OPP(HEADER_ARCH,           arch),
-        FEAT_OPP(HEADER_NRCPUS,         nrcpus),
-        FEAT_OPP(HEADER_CPUDESC,        cpudesc),
-        FEAT_OPP(HEADER_CPUID,          cpuid),
-        FEAT_OPP(HEADER_TOTAL_MEM,      total_mem),
-        FEAT_OPP(HEADER_EVENT_DESC,     event_desc),
-        FEAT_OPP(HEADER_CMDLINE,        cmdline),
-        FEAT_OPF(HEADER_CPU_TOPOLOGY,   cpu_topology),
-        FEAT_OPF(HEADER_NUMA_TOPOLOGY,  numa_topology),
-        FEAT_OPA(HEADER_BRANCH_STACK,   branch_stack),
-        FEAT_OPP(HEADER_PMU_MAPPINGS,   pmu_mappings),
-        FEAT_OPP(HEADER_GROUP_DESC,     group_desc),
-        FEAT_OPP(HEADER_AUXTRACE,       auxtrace),
-        FEAT_OPA(HEADER_STAT,           stat),
-        FEAT_OPF(HEADER_CACHE,          cache),
+        FEAT_OPN(TRACING_DATA,  tracing_data,   false),
+        FEAT_OPN(BUILD_ID,      build_id,       false),
+        FEAT_OPR(HOSTNAME,      hostname,       false),
+        FEAT_OPR(OSRELEASE,     osrelease,      false),
+        FEAT_OPR(VERSION,       version,        false),
+        FEAT_OPR(ARCH,          arch,           false),
+        FEAT_OPR(NRCPUS,        nrcpus,         false),
+        FEAT_OPR(CPUDESC,       cpudesc,        false),
+        FEAT_OPR(CPUID,         cpuid,          false),
+        FEAT_OPR(TOTAL_MEM,     total_mem,      false),
+        FEAT_OPR(EVENT_DESC,    event_desc,     false),
+        FEAT_OPR(CMDLINE,       cmdline,        false),
+        FEAT_OPR(CPU_TOPOLOGY,  cpu_topology,   true),
+        FEAT_OPR(NUMA_TOPOLOGY, numa_topology,  true),
+        FEAT_OPN(BRANCH_STACK,  branch_stack,   false),
+        FEAT_OPR(PMU_MAPPINGS,  pmu_mappings,   false),
+        FEAT_OPN(GROUP_DESC,    group_desc,     false),
+        FEAT_OPN(AUXTRACE,      auxtrace,       false),
+        FEAT_OPN(STAT,          stat,           false),
+        FEAT_OPN(CACHE,         cache,          true),
 };
 
 struct header_print_data {
@@ -2247,6 +2217,7 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section,
                                            int feat, int fd, void *data)
 {
         struct header_print_data *hd = data;
+        struct feat_fd ff;
 
         if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
                 pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
@@ -2260,8 +2231,13 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section,
         if (!feat_ops[feat].print)
                 return 0;
 
+        ff = (struct  feat_fd) {
+                .fd = fd,
+                .ph = ph,
+        };
+
         if (!feat_ops[feat].full_only || hd->full)
-                feat_ops[feat].print(ph, fd, hd->fp);
+                feat_ops[feat].print(&ff, hd->fp);
         else
                 fprintf(hd->fp, "# %s info available, use -I to display\n",
                         feat_ops[feat].name);
@@ -2273,7 +2249,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 {
         struct header_print_data hd;
         struct perf_header *header = &session->header;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         struct stat st;
         int ret, bit;
 
@@ -2289,7 +2265,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
         perf_header__process_sections(header, fd, &hd,
                                       perf_file_section__fprintf_info);
 
-        if (session->file->is_pipe)
+        if (session->data->is_pipe)
                 return 0;
 
         fprintf(fp, "# missing features: ");
@@ -2302,29 +2278,32 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
         return 0;
 }
 
-static int do_write_feat(int fd, struct perf_header *h, int type,
+static int do_write_feat(struct feat_fd *ff, int type,
                          struct perf_file_section **p,
                          struct perf_evlist *evlist)
 {
         int err;
         int ret = 0;
 
-        if (perf_header__has_feat(h, type)) {
+        if (perf_header__has_feat(ff->ph, type)) {
                 if (!feat_ops[type].write)
                         return -1;
 
-                (*p)->offset = lseek(fd, 0, SEEK_CUR);
+                if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                        return -1;
 
-                err = feat_ops[type].write(fd, h, evlist);
+                (*p)->offset = lseek(ff->fd, 0, SEEK_CUR);
+
+                err = feat_ops[type].write(ff, evlist);
                 if (err < 0) {
                         pr_debug("failed to write feature %s\n", feat_ops[type].name);
 
                         /* undo anything written */
-                        lseek(fd, (*p)->offset, SEEK_SET);
+                        lseek(ff->fd, (*p)->offset, SEEK_SET);
 
                         return -1;
                 }
-                (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset;
+                (*p)->size = lseek(ff->fd, 0, SEEK_CUR) - (*p)->offset;
                 (*p)++;
         }
         return ret;
@@ -2334,12 +2313,18 @@ static int perf_header__adds_write(struct perf_header *header,
                                    struct perf_evlist *evlist, int fd)
 {
         int nr_sections;
+        struct feat_fd ff;
         struct perf_file_section *feat_sec, *p;
         int sec_size;
         u64 sec_start;
         int feat;
         int err;
 
+        ff = (struct feat_fd){
+                .fd  = fd,
+                .ph = header,
+        };
+
         nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
         if (!nr_sections)
                 return 0;
@@ -2354,7 +2339,7 @@ static int perf_header__adds_write(struct perf_header *header,
         lseek(fd, sec_start + sec_size, SEEK_SET);
 
         for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
-                if (do_write_feat(fd, header, feat, &p, evlist))
+                if (do_write_feat(&ff, feat, &p, evlist))
                         perf_header__clear_feat(header, feat);
         }
 
@@ -2363,7 +2348,7 @@ static int perf_header__adds_write(struct perf_header *header,
          * may write more than needed due to dropped feature, but
          * this is okay, reader will skip the mising entries
          */
-        err = do_write(fd, feat_sec, sec_size);
+        err = do_write(&ff, feat_sec, sec_size);
         if (err < 0)
                 pr_debug("failed to write feature section\n");
         free(feat_sec);
@@ -2373,14 +2358,17 @@ static int perf_header__adds_write(struct perf_header *header,
 int perf_header__write_pipe(int fd)
 {
         struct perf_pipe_file_header f_header;
+        struct feat_fd ff;
         int err;
 
+        ff = (struct feat_fd){ .fd = fd };
+
         f_header = (struct perf_pipe_file_header){
                 .magic     = PERF_MAGIC,
                 .size      = sizeof(f_header),
         };
 
-        err = do_write(fd, &f_header, sizeof(f_header));
+        err = do_write(&ff, &f_header, sizeof(f_header));
         if (err < 0) {
                 pr_debug("failed to write perf pipe header\n");
                 return err;
@@ -2397,21 +2385,23 @@ int perf_session__write_header(struct perf_session *session,
         struct perf_file_attr   f_attr;
         struct perf_header *header = &session->header;
         struct perf_evsel *evsel;
+        struct feat_fd ff;
         u64 attr_offset;
         int err;
 
+        ff = (struct feat_fd){ .fd = fd};
         lseek(fd, sizeof(f_header), SEEK_SET);
 
         evlist__for_each_entry(session->evlist, evsel) {
                 evsel->id_offset = lseek(fd, 0, SEEK_CUR);
-                err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
+                err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64));
                 if (err < 0) {
                         pr_debug("failed to write perf header\n");
                         return err;
                 }
         }
 
-        attr_offset = lseek(fd, 0, SEEK_CUR);
+        attr_offset = lseek(ff.fd, 0, SEEK_CUR);
 
         evlist__for_each_entry(evlist, evsel) {
                 f_attr = (struct perf_file_attr){
@@ -2421,7 +2411,7 @@ int perf_session__write_header(struct perf_session *session,
                                 .size   = evsel->ids * sizeof(u64),
                         }
                 };
-                err = do_write(fd, &f_attr, sizeof(f_attr));
+                err = do_write(&ff, &f_attr, sizeof(f_attr));
                 if (err < 0) {
                         pr_debug("failed to write perf header attribute\n");
                         return err;
@@ -2456,7 +2446,7 @@ int perf_session__write_header(struct perf_session *session,
         memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
 
         lseek(fd, 0, SEEK_SET);
-        err = do_write(fd, &f_header, sizeof(f_header));
+        err = do_write(&ff, &f_header, sizeof(f_header));
         if (err < 0) {
                 pr_debug("failed to write perf header\n");
                 return err;
@@ -2710,6 +2700,13 @@ static int perf_file_section__process(struct perf_file_section *section,
                                       struct perf_header *ph,
                                       int feat, int fd, void *data)
 {
+        struct feat_fd fdd = {
+                .fd     = fd,
+                .ph     = ph,
+                .size   = section->size,
+                .offset = section->offset,
+        };
+
         if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
                 pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
                           "%d, continuing...\n", section->offset, feat);
@@ -2724,13 +2721,17 @@ static int perf_file_section__process(struct perf_file_section *section,
         if (!feat_ops[feat].process)
                 return 0;
 
-        return feat_ops[feat].process(section, ph, fd, data);
+        return feat_ops[feat].process(&fdd, data);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
                                        struct perf_header *ph, int fd,
                                        bool repipe)
 {
+        struct feat_fd ff = {
+                .fd = STDOUT_FILENO,
+                .ph = ph,
+        };
         ssize_t ret;
 
         ret = readn(fd, header, sizeof(*header));
@@ -2745,7 +2746,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
         if (ph->needs_swap)
                 header->size = bswap_64(header->size);
 
-        if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+        if (repipe && do_write(&ff, header, sizeof(*header)) < 0)
                 return -1;
 
         return 0;
@@ -2757,7 +2758,7 @@ static int perf_header__read_pipe(struct perf_session *session)
         struct perf_pipe_file_header f_header;
 
         if (perf_file_header__read_pipe(&f_header, header,
-                                        perf_data_file__fd(session->file),
+                                        perf_data__fd(session->data),
                                         session->repipe) < 0) {
                 pr_debug("incompatible file format\n");
                 return -EINVAL;
@@ -2860,13 +2861,13 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 
 int perf_session__read_header(struct perf_session *session)
 {
-        struct perf_data_file *file = session->file;
+        struct perf_data *data = session->data;
         struct perf_header *header = &session->header;
         struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
         u64                     f_id;
         int nr_attrs, nr_ids, i, j;
-        int fd = perf_data_file__fd(file);
+        int fd = perf_data__fd(data);
 
         session->evlist = perf_evlist__new();
         if (session->evlist == NULL)
@@ -2874,7 +2875,7 @@ int perf_session__read_header(struct perf_session *session)
 
         session->evlist->env = &header->env;
         session->machines.host.env = &header->env;
-        if (perf_data_file__is_pipe(file))
+        if (perf_data__is_pipe(data))
                 return perf_header__read_pipe(session);
 
         if (perf_file_header__read(&f_header, header, fd) < 0)
@@ -2889,7 +2890,7 @@ int perf_session__read_header(struct perf_session *session)
         if (f_header.data.size == 0) {
                 pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
                            "Was the 'perf record' command properly terminated?\n",
-                           file->path);
+                           data->file.path);
         }
 
         nr_attrs = f_header.attrs.size / f_header.attr_size;
@@ -2995,6 +2996,103 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
         return err;
 }
 
+int perf_event__synthesize_features(struct perf_tool *tool,
+                                    struct perf_session *session,
+                                    struct perf_evlist *evlist,
+                                    perf_event__handler_t process)
+{
+        struct perf_header *header = &session->header;
+        struct feat_fd ff;
+        struct feature_event *fe;
+        size_t sz, sz_hdr;
+        int feat, ret;
+
+        sz_hdr = sizeof(fe->header);
+        sz = sizeof(union perf_event);
+        /* get a nice alignment */
+        sz = PERF_ALIGN(sz, page_size);
+
+        memset(&ff, 0, sizeof(ff));
+
+        ff.buf = malloc(sz);
+        if (!ff.buf)
+                return -ENOMEM;
+
+        ff.size = sz - sz_hdr;
+
+        for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+                if (!feat_ops[feat].synthesize) {
+                        pr_debug("No record header feature for header :%d\n", feat);
+                        continue;
+                }
+
+                ff.offset = sizeof(*fe);
+
+                ret = feat_ops[feat].write(&ff, evlist);
+                if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
+                        pr_debug("Error writing feature\n");
+                        continue;
+                }
+                /* ff.buf may have changed due to realloc in do_write() */
+                fe = ff.buf;
+                memset(fe, 0, sizeof(*fe));
+
+                fe->feat_id = feat;
+                fe->header.type = PERF_RECORD_HEADER_FEATURE;
+                fe->header.size = ff.offset;
+
+                ret = process(tool, ff.buf, NULL, NULL);
+                if (ret) {
+                        free(ff.buf);
+                        return ret;
+                }
+        }
+        free(ff.buf);
+        return 0;
+}
+
+int perf_event__process_feature(struct perf_tool *tool,
+                                union perf_event *event,
+                                struct perf_session *session __maybe_unused)
+{
+        struct feat_fd ff = { .fd = 0 };
+        struct feature_event *fe = (struct feature_event *)event;
+        int type = fe->header.type;
+        u64 feat = fe->feat_id;
+
+        if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
+                pr_warning("invalid record type %d in pipe-mode\n", type);
+                return 0;
+        }
+        if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+                pr_warning("invalid record type %d in pipe-mode\n", type);
+                return -1;
+        }
+
+        if (!feat_ops[feat].process)
+                return 0;
+
+        ff.buf  = (void *)fe->data;
+        ff.size = event->header.size - sizeof(event->header);
+        ff.ph = &session->header;
+
+        if (feat_ops[feat].process(&ff, NULL))
+                return -1;
+
+        if (!feat_ops[feat].print || !tool->show_feat_hdr)
+                return 0;
+
+        if (!feat_ops[feat].full_only ||
+            tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
+                feat_ops[feat].print(&ff, stdout);
+        } else {
+                fprintf(stdout, "# %s info available, use -I to display\n",
+                        feat_ops[feat].name);
+        }
+
+        return 0;
+}
+
 static struct event_update_event *
 event_update_event__new(size_t size, u64 type, u64 id)
 {
@@ -3253,6 +3351,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
         union perf_event ev;
         struct tracing_data *tdata;
         ssize_t size = 0, aligned_size = 0, padding;
+        struct feat_fd ff;
         int err __maybe_unused = 0;
 
         /*
@@ -3287,7 +3386,9 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
          */
         tracing_data_put(tdata);
 
-        write_padded(fd, NULL, 0, padding);
+        ff = (struct feat_fd){ .fd = fd };
+        if (write_padded(&ff, NULL, 0, padding))
+                return -1;
 
         return aligned_size;
 }
@@ -3297,7 +3398,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
                                      struct perf_session *session)
 {
         ssize_t size_read, padding, size = event->tracing_data.size;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         off_t offset = lseek(fd, 0, SEEK_CUR);
         char buf[BUFSIZ];
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d30109b421ee..29ccbfdf8724 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
@@ -101,6 +102,15 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
+int perf_event__synthesize_features(struct perf_tool *tool,
+                                    struct perf_session *session,
+                                    struct perf_evlist *evlist,
+                                    perf_event__handler_t process);
+
+int perf_event__process_feature(struct perf_tool *tool,
+                                union perf_event *event,
+                                struct perf_session *session);
+
 int perf_event__synthesize_attr(struct perf_tool *tool,
                                 struct perf_event_attr *attr, u32 ids, u64 *id,
                                 perf_event__handler_t process);
@@ -144,7 +154,12 @@ bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
 
-int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
+struct feat_fd;
+
+int do_write(struct feat_fd *fd, const void *buf, size_t size);
+
+int write_padded(struct feat_fd *fd, const void *bf,
+                 size_t count, size_t count_aligned);
 
 /*
  * arch specific callback
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 15b95300d7f3..4f07a5ba5030 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "cache.h"
 #include "config.h"
 #include <poll.h>
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cf0186a088c1..b6140950301e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -167,6 +168,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                         symlen = unresolved_col_width + 4 + 2;
                         hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
                 }
+
+                hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
+                                   unresolved_col_width + 4 + 2);
+
         } else {
                 symlen = unresolved_col_width + 4 + 2;
                 hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
@@ -592,6 +597,7 @@ __hists__add_entry(struct hists *hists,
                         .map    = al->map,
                         .sym    = al->sym,
                 },
+                .srcline = al->srcline ? strdup(al->srcline) : NULL,
                 .socket  = al->socket,
                 .cpu     = al->cpu,
                 .cpumode = al->cpumode,
@@ -749,12 +755,9 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
 }
 
 static int
-iter_add_single_branch_entry(struct hist_entry_iter *iter,
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
                              struct addr_location *al __maybe_unused)
 {
-        /* to avoid calling callback function */
-        iter->he = NULL;
-
         return 0;
 }
 
@@ -949,6 +952,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
                         .map = al->map,
                         .sym = al->sym,
                 },
+                .srcline = al->srcline ? strdup(al->srcline) : NULL,
                 .parent = iter->parent,
                 .raw_data = sample->raw_data,
                 .raw_size = sample->raw_size,
@@ -1140,11 +1144,6 @@ void hist_entry__delete(struct hist_entry *he)
                 zfree(&he->mem_info);
         }
 
-        if (he->inline_node) {
-                inline_node__delete(he->inline_node);
-                he->inline_node = NULL;
-        }
-
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
         if (he->srcfile && he->srcfile[0])
@@ -1762,6 +1761,8 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
         else
                 use_callchain = symbol_conf.use_callchain;
 
+        use_callchain |= symbol_conf.show_branchflag_count;
+
         output_resort(evsel__hists(evsel), prog, use_callchain, NULL);
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ee3670a388df..f6630cb95eff 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_HIST_H
 #define __PERF_HIST_H
 
@@ -47,6 +48,7 @@ enum hist_column {
         HISTC_GLOBAL_WEIGHT,
         HISTC_MEM_DADDR_SYMBOL,
         HISTC_MEM_DADDR_DSO,
+        HISTC_MEM_PHYS_DADDR,
         HISTC_MEM_LOCKED,
         HISTC_MEM_TLB,
         HISTC_MEM_LVL,
diff --git a/tools/perf/util/include/asm/asm-offsets.h b/tools/perf/util/include/asm/asm-offsets.h
index ed538942523d..3aff4cf44944 100644
--- a/tools/perf/util/include/asm/asm-offsets.h
+++ b/tools/perf/util/include/asm/asm-offsets.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* stub */
diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h
index acffd5e4d1d4..2270481c7e0a 100644
--- a/tools/perf/util/include/asm/cpufeature.h
+++ b/tools/perf/util/include/asm/cpufeature.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef PERF_CPUFEATURE_H
 #define PERF_CPUFEATURE_H
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
index afe38199e922..e9876be63dbf 100644
--- a/tools/perf/util/include/asm/dwarf2.h
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef PERF_DWARF2_H
 #define PERF_DWARF2_H
diff --git a/tools/perf/util/include/asm/uaccess.h b/tools/perf/util/include/asm/uaccess.h
index d0f72b8fcc35..6a6f4b990547 100644
--- a/tools/perf/util/include/asm/uaccess.h
+++ b/tools/perf/util/include/asm/uaccess.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_ASM_UACCESS_H_
 #define _PERF_ASM_UACCESS_H_
 
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 43bfd8da7919..7d99a084e82d 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 06387cffe125..f01d48a8d707 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef PERF_LINUX_LINKAGE_H_
 #define PERF_LINUX_LINKAGE_H_
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 218ee2bac9a5..5325e65f9711 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -500,7 +500,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
         }
 
         if (!buffer->data) {
-                int fd = perf_data_file__fd(btsq->bts->session->file);
+                int fd = perf_data__fd(btsq->bts->session->data);
 
                 buffer->data = auxtrace_buffer__get_data(buffer, fd);
                 if (!buffer->data) {
@@ -664,10 +664,10 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session,
         if (!bts->data_queued) {
                 struct auxtrace_buffer *buffer;
                 off_t data_offset;
-                int fd = perf_data_file__fd(session->file);
+                int fd = perf_data__fd(session->data);
                 int err;
 
-                if (perf_data_file__is_pipe(session->file)) {
+                if (perf_data__is_pipe(session->data)) {
                         data_offset = 0;
                 } else {
                         data_offset = lseek(fd, 0, SEEK_CUR);
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 7aca5d6d7e1f..10e0814bb8d2 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -25,6 +25,6 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in
 
 CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder
 
-ifneq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 1)
   CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init
 endif
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
index 54e961659514..ddd5c4c21129 100644
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
@@ -1,4 +1,5 @@
 #!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
 # gen-insn-attr-x86.awk: Instruction attribute table generator
 # Written by Masami Hiramatsu <mhiramat@redhat.com>
 #
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b58f9fd1e2ee..23f9ba676df0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -271,7 +271,7 @@ next:
         ptq->buffer = buffer;
 
         if (!buffer->data) {
-                int fd = perf_data_file__fd(ptq->pt->session->file);
+                int fd = perf_data__fd(ptq->pt->session->data);
 
                 buffer->data = auxtrace_buffer__get_data(buffer, fd);
                 if (!buffer->data)
@@ -2084,10 +2084,10 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session,
         if (!pt->data_queued) {
                 struct auxtrace_buffer *buffer;
                 off_t data_offset;
-                int fd = perf_data_file__fd(session->file);
+                int fd = perf_data__fd(session->data);
                 int err;
 
-                if (perf_data_file__is_pipe(session->file)) {
+                if (perf_data__is_pipe(session->data)) {
                         data_offset = 0;
                 } else {
                         data_offset = lseek(fd, 0, SEEK_CUR);
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index 020b9ca1b47e..85bab8735fa9 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_INTLIST_H
 #define __PERF_INTLIST_H
 
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
index 3f42ee4d2a0b..6817ffc2a059 100644
--- a/tools/perf/util/jit.h
+++ b/tools/perf/util/jit.h
@@ -1,9 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __JIT_H__
 #define __JIT_H__
 
 #include <data.h>
 
-int jit_process(struct perf_session *session, struct perf_data_file *output,
+int jit_process(struct perf_session *session, struct perf_data *output,
                 struct machine *machine, char *filename, pid_t pid, u64 *nbytes);
 
 int jit_inject_record(const char *filename);
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 9084930e1757..a1863000e972 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <errno.h>
@@ -29,7 +30,7 @@
 #include "sane_ctype.h"
 
 struct jit_buf_desc {
-        struct perf_data_file *output;
+        struct perf_data *output;
         struct perf_session *session;
         struct machine *machine;
         union jr_entry   *entry;
@@ -60,8 +61,8 @@ struct debug_line_info {
 
 struct jit_tool {
         struct perf_tool tool;
-        struct perf_data_file   output;
-        struct perf_data_file   input;
+        struct perf_data        output;
+        struct perf_data        input;
         u64 bytes_written;
 };
 
@@ -356,7 +357,7 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
 {
         ssize_t size;
 
-        size = perf_data_file__write(jd->output, event, event->header.size);
+        size = perf_data__write(jd->output, event, event->header.size);
         if (size < 0)
                 return -1;
 
@@ -751,7 +752,7 @@ jit_detect(char *mmap_name, pid_t pid)
 
 int
 jit_process(struct perf_session *session,
-            struct perf_data_file *output,
+            struct perf_data *output,
             struct machine *machine,
             char *filename,
             pid_t pid,
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index d01e73592f6e..7b1f06567521 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_KVM_STAT_H
 #define __PERF_KVM_STAT_H
 
diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c
index f616e4f65b67..a217ecf0359d 100644
--- a/tools/perf/util/levenshtein.c
+++ b/tools/perf/util/levenshtein.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "levenshtein.h"
 #include <errno.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/levenshtein.h b/tools/perf/util/levenshtein.h
index b0fcb6d8a881..34ca173c557d 100644
--- a/tools/perf/util/levenshtein.h
+++ b/tools/perf/util/levenshtein.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_LEVENSHTEIN_H
 #define __PERF_LEVENSHTEIN_H
 
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index 6559bc586643..66756e6be111 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * This file setups defines to compile arch specific binary from the
  * generic one.
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
index 957ffff72428..c5e568188e19 100644
--- a/tools/perf/util/libunwind/x86_32.c
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * This file setups defines to compile arch specific binary from the
  * generic one.
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index c6a15f204c03..4952b429caa7 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015, Huawei Inc.
@@ -33,7 +34,7 @@ struct llvm_param llvm_param = {
 
 int perf_llvm_config(const char *var, const char *value)
 {
-        if (prefixcmp(var, "llvm."))
+        if (!strstarts(var, "llvm."))
                 return 0;
         var += sizeof("llvm.") - 1;
 
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index c87a2a92a88f..d3ad8deb5db4 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015, Huawei Inc.
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 4ca7c5c6cdcd..07498eaddc08 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <lzma.h>
 #include <stdio.h>
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2e9eb6aa3ce2..6a8d03c3d9b7 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
 #include <inttypes.h>
@@ -30,7 +31,21 @@ static void dsos__init(struct dsos *dsos)
 {
         INIT_LIST_HEAD(&dsos->head);
         dsos->root = RB_ROOT;
-        pthread_rwlock_init(&dsos->lock, NULL);
+        init_rwsem(&dsos->lock);
+}
+
+static void machine__threads_init(struct machine *machine)
+{
+        int i;
+
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+                threads->entries = RB_ROOT;
+                init_rwsem(&threads->lock);
+                threads->nr = 0;
+                INIT_LIST_HEAD(&threads->dead);
+                threads->last_match = NULL;
+        }
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
@@ -40,11 +55,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
         RB_CLEAR_NODE(&machine->rb_node);
         dsos__init(&machine->dsos);
 
-        machine->threads = RB_ROOT;
-        pthread_rwlock_init(&machine->threads_lock, NULL);
-        machine->nr_threads = 0;
-        INIT_LIST_HEAD(&machine->dead_threads);
-        machine->last_match = NULL;
+        machine__threads_init(machine);
 
         machine->vdso_info = NULL;
         machine->env = NULL;
@@ -120,7 +131,7 @@ static void dsos__purge(struct dsos *dsos)
 {
         struct dso *pos, *n;
 
-        pthread_rwlock_wrlock(&dsos->lock);
+        down_write(&dsos->lock);
 
         list_for_each_entry_safe(pos, n, &dsos->head, node) {
                 RB_CLEAR_NODE(&pos->rb_node);
@@ -129,39 +140,49 @@ static void dsos__purge(struct dsos *dsos)
                 dso__put(pos);
         }
 
-        pthread_rwlock_unlock(&dsos->lock);
+        up_write(&dsos->lock);
 }
 
 static void dsos__exit(struct dsos *dsos)
 {
         dsos__purge(dsos);
-        pthread_rwlock_destroy(&dsos->lock);
+        exit_rwsem(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
         struct rb_node *nd;
+        int i;
 
-        pthread_rwlock_wrlock(&machine->threads_lock);
-        nd = rb_first(&machine->threads);
-        while (nd) {
-                struct thread *t = rb_entry(nd, struct thread, rb_node);
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+                down_write(&threads->lock);
+                nd = rb_first(&threads->entries);
+                while (nd) {
+                        struct thread *t = rb_entry(nd, struct thread, rb_node);
 
-                nd = rb_next(nd);
-                __machine__remove_thread(machine, t, false);
+                        nd = rb_next(nd);
+                        __machine__remove_thread(machine, t, false);
+                }
+                up_write(&threads->lock);
         }
-        pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
+        int i;
+
         machine__destroy_kernel_maps(machine);
         map_groups__exit(&machine->kmaps);
         dsos__exit(&machine->dsos);
         machine__exit_vdso(machine);
         zfree(&machine->root_dir);
         zfree(&machine->current_tid);
-        pthread_rwlock_destroy(&machine->threads_lock);
+
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+                exit_rwsem(&threads->lock);
+        }
 }
 
 void machine__delete(struct machine *machine)
@@ -379,10 +400,11 @@ out_err:
  * lookup/new thread inserted.
  */
 static struct thread *____machine__findnew_thread(struct machine *machine,
+                                                  struct threads *threads,
                                                   pid_t pid, pid_t tid,
                                                   bool create)
 {
-        struct rb_node **p = &machine->threads.rb_node;
+        struct rb_node **p = &threads->entries.rb_node;
         struct rb_node *parent = NULL;
         struct thread *th;
 
@@ -391,14 +413,14 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
          * so most of the time we dont have to look up
          * the full rbtree:
          */
-        th = machine->last_match;
+        th = threads->last_match;
         if (th != NULL) {
                 if (th->tid == tid) {
                         machine__update_thread_pid(machine, th, pid);
                         return thread__get(th);
                 }
 
-                machine->last_match = NULL;
+                threads->last_match = NULL;
         }
 
         while (*p != NULL) {
@@ -406,7 +428,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                 th = rb_entry(parent, struct thread, rb_node);
 
                 if (th->tid == tid) {
-                        machine->last_match = th;
+                        threads->last_match = th;
                         machine__update_thread_pid(machine, th, pid);
                         return thread__get(th);
                 }
@@ -423,7 +445,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
         th = thread__new(pid, tid);
         if (th != NULL) {
                 rb_link_node(&th->rb_node, parent, p);
-                rb_insert_color(&th->rb_node, &machine->threads);
+                rb_insert_color(&th->rb_node, &threads->entries);
 
                 /*
                  * We have to initialize map_groups separately
@@ -434,7 +456,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                  * leader and that would screwed the rb tree.
                  */
                 if (thread__init_map_groups(th, machine)) {
-                        rb_erase_init(&th->rb_node, &machine->threads);
+                        rb_erase_init(&th->rb_node, &threads->entries);
                         RB_CLEAR_NODE(&th->rb_node);
                         thread__put(th);
                         return NULL;
@@ -443,8 +465,8 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                  * It is now in the rbtree, get a ref
                  */
                 thread__get(th);
-                machine->last_match = th;
-                ++machine->nr_threads;
+                threads->last_match = th;
+                ++threads->nr;
         }
 
         return th;
@@ -452,27 +474,30 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
 {
-        return ____machine__findnew_thread(machine, pid, tid, true);
+        return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true);
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
                                        pid_t tid)
 {
+        struct threads *threads = machine__threads(machine, tid);
         struct thread *th;
 
-        pthread_rwlock_wrlock(&machine->threads_lock);
+        down_write(&threads->lock);
         th = __machine__findnew_thread(machine, pid, tid);
-        pthread_rwlock_unlock(&machine->threads_lock);
+        up_write(&threads->lock);
         return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
                                     pid_t tid)
 {
+        struct threads *threads = machine__threads(machine, tid);
         struct thread *th;
-        pthread_rwlock_rdlock(&machine->threads_lock);
-        th =  ____machine__findnew_thread(machine, pid, tid, false);
-        pthread_rwlock_unlock(&machine->threads_lock);
+
+        down_read(&threads->lock);
+        th =  ____machine__findnew_thread(machine, threads, pid, tid, false);
+        up_read(&threads->lock);
         return th;
 }
 
@@ -564,7 +589,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 {
         struct dso *dso;
 
-        pthread_rwlock_wrlock(&machine->dsos.lock);
+        down_write(&machine->dsos.lock);
 
         dso = __dsos__find(&machine->dsos, m->name, true);
         if (!dso) {
@@ -578,7 +603,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 
         dso__get(dso);
 out_unlock:
-        pthread_rwlock_unlock(&machine->dsos.lock);
+        up_write(&machine->dsos.lock);
         return dso;
 }
 
@@ -705,7 +730,8 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
         if (kdso->has_build_id) {
                 char filename[PATH_MAX];
-                if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+                if (dso__build_id_filename(kdso, filename, sizeof(filename),
+                                           false))
                         printed += fprintf(fp, "[0] %s\n", filename);
         }
 
@@ -718,21 +744,25 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
 size_t machine__fprintf(struct machine *machine, FILE *fp)
 {
-        size_t ret;
         struct rb_node *nd;
+        size_t ret;
+        int i;
 
-        pthread_rwlock_rdlock(&machine->threads_lock);
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
 
-        ret = fprintf(fp, "Threads: %u\n", machine->nr_threads);
+                down_read(&threads->lock);
 
-        for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-                struct thread *pos = rb_entry(nd, struct thread, rb_node);
+                ret = fprintf(fp, "Threads: %u\n", threads->nr);
 
-                ret += thread__fprintf(pos, fp);
-        }
+                for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+                        struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
-        pthread_rwlock_unlock(&machine->threads_lock);
+                        ret += thread__fprintf(pos, fp);
+                }
 
+                up_read(&threads->lock);
+        }
         return ret;
 }
 
@@ -1137,7 +1167,8 @@ int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
         return 0;
 }
 
-static int machine__create_module(void *arg, const char *name, u64 start)
+static int machine__create_module(void *arg, const char *name, u64 start,
+                                  u64 size)
 {
         struct machine *machine = arg;
         struct map *map;
@@ -1148,6 +1179,7 @@ static int machine__create_module(void *arg, const char *name, u64 start)
         map = machine__findnew_module_map(machine, start, name);
         if (map == NULL)
                 return -1;
+        map->end = start + size;
 
         dso__kernel_module_get_build_id(map->dso, machine->root_dir);
 
@@ -1289,7 +1321,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                 struct dso *kernel = NULL;
                 struct dso *dso;
 
-                pthread_rwlock_rdlock(&machine->dsos.lock);
+                down_read(&machine->dsos.lock);
 
                 list_for_each_entry(dso, &machine->dsos.head, node) {
 
@@ -1319,7 +1351,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                         break;
                 }
 
-                pthread_rwlock_unlock(&machine->dsos.lock);
+                up_read(&machine->dsos.lock);
 
                 if (kernel == NULL)
                         kernel = machine__findnew_dso(machine, kmmap_prefix);
@@ -1392,7 +1424,7 @@ int machine__process_mmap2_event(struct machine *machine,
 
         map = map__new(machine, event->mmap2.start,
                         event->mmap2.len, event->mmap2.pgoff,
-                        event->mmap2.pid, event->mmap2.maj,
+                        event->mmap2.maj,
                         event->mmap2.min, event->mmap2.ino,
                         event->mmap2.ino_generation,
                         event->mmap2.prot,
@@ -1450,7 +1482,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
         map = map__new(machine, event->mmap.start,
                         event->mmap.len, event->mmap.pgoff,
-                        event->mmap.pid, 0, 0, 0, 0, 0, 0,
+                        0, 0, 0, 0, 0, 0,
                         event->mmap.filename,
                         type, thread);
 
@@ -1476,23 +1508,25 @@ out_problem:
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
-        if (machine->last_match == th)
-                machine->last_match = NULL;
+        struct threads *threads = machine__threads(machine, th->tid);
+
+        if (threads->last_match == th)
+                threads->last_match = NULL;
 
         BUG_ON(refcount_read(&th->refcnt) == 0);
         if (lock)
-                pthread_rwlock_wrlock(&machine->threads_lock);
-        rb_erase_init(&th->rb_node, &machine->threads);
+                down_write(&threads->lock);
+        rb_erase_init(&th->rb_node, &threads->entries);
         RB_CLEAR_NODE(&th->rb_node);
-        --machine->nr_threads;
+        --threads->nr;
         /*
          * Move it first to the dead_threads list, then drop the reference,
          * if this is the last reference, then the thread__delete destructor
          * will be called and we will remove it from the dead_threads list.
          */
-        list_add_tail(&th->node, &machine->dead_threads);
+        list_add_tail(&th->node, &threads->dead);
         if (lock)
-                pthread_rwlock_unlock(&machine->threads_lock);
+                up_write(&threads->lock);
         thread__put(th);
 }
 
@@ -1632,10 +1666,12 @@ static void ip__resolve_ams(struct thread *thread,
         ams->al_addr = al.addr;
         ams->sym = al.sym;
         ams->map = al.map;
+        ams->phys_addr = 0;
 }
 
 static void ip__resolve_data(struct thread *thread,
-                             u8 m, struct addr_map_symbol *ams, u64 addr)
+                             u8 m, struct addr_map_symbol *ams,
+                             u64 addr, u64 phys_addr)
 {
         struct addr_location al;
 
@@ -1655,6 +1691,7 @@ static void ip__resolve_data(struct thread *thread,
         ams->al_addr = al.addr;
         ams->sym = al.sym;
         ams->map = al.map;
+        ams->phys_addr = phys_addr;
 }
 
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -1666,12 +1703,38 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
                 return NULL;
 
         ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
-        ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
+        ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+                         sample->addr, sample->phys_addr);
         mi->data_src.val = sample->data_src;
 
         return mi;
 }
 
+static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip)
+{
+        char *srcline = NULL;
+
+        if (!map || callchain_param.key == CCKEY_FUNCTION)
+                return srcline;
+
+        srcline = srcline__tree_find(&map->dso->srclines, ip);
+        if (!srcline) {
+                bool show_sym = false;
+                bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+
+                srcline = get_srcline(map->dso, map__rip_2objdump(map, ip),
+                                      sym, show_sym, show_addr);
+                srcline__tree_insert(&map->dso->srclines, ip, srcline);
+        }
+
+        return srcline;
+}
+
+struct iterations {
+        int nr_loop_iter;
+        u64 cycles;
+};
+
 static int add_callchain_ip(struct thread *thread,
                             struct callchain_cursor *cursor,
                             struct symbol **parent,
@@ -1680,10 +1743,13 @@ static int add_callchain_ip(struct thread *thread,
                             u64 ip,
                             bool branch,
                             struct branch_flags *flags,
-                            int nr_loop_iter,
-                            int samples)
+                            struct iterations *iter,
+                            u64 branch_from)
 {
         struct addr_location al;
+        int nr_loop_iter = 0;
+        u64 iter_cycles = 0;
+        const char *srcline = NULL;
 
         al.filtered = 0;
         al.sym = NULL;
@@ -1733,8 +1799,16 @@ static int add_callchain_ip(struct thread *thread,
 
         if (symbol_conf.hide_unresolved && al.sym == NULL)
                 return 0;
+
+        if (iter) {
+                nr_loop_iter = iter->nr_loop_iter;
+                iter_cycles = iter->cycles;
+        }
+
+        srcline = callchain_srcline(al.map, al.sym, al.addr);
         return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
-                                       branch, flags, nr_loop_iter, samples);
+                                       branch, flags, nr_loop_iter,
+                                       iter_cycles, branch_from, srcline);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -1755,6 +1829,18 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
         return bi;
 }
 
+static void save_iterations(struct iterations *iter,
+                            struct branch_entry *be, int nr)
+{
+        int i;
+
+        iter->nr_loop_iter = nr;
+        iter->cycles = 0;
+
+        for (i = 0; i < nr; i++)
+                iter->cycles += be[i].flags.cycles;
+}
+
 #define CHASHSZ 127
 #define CHASHBITS 7
 #define NO_ENTRY 0xff
@@ -1762,7 +1848,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 #define PERF_MAX_BRANCH_DEPTH 127
 
 /* Remove loops. */
-static int remove_loops(struct branch_entry *l, int nr)
+static int remove_loops(struct branch_entry *l, int nr,
+                        struct iterations *iter)
 {
         int i, j, off;
         unsigned char chash[CHASHSZ];
@@ -1787,8 +1874,18 @@ static int remove_loops(struct branch_entry *l, int nr)
                                         break;
                                 }
                         if (is_loop) {
-                                memmove(l + i, l + i + off,
-                                        (nr - (i + off)) * sizeof(*l));
+                                j = nr - (i + off);
+                                if (j > 0) {
+                                        save_iterations(iter + i + off,
+                                                l + i, off);
+
+                                        memmove(iter + i, iter + i + off,
+                                                j * sizeof(*iter));
+
+                                        memmove(l + i, l + i + off,
+                                                j * sizeof(*l));
+                                }
+
                                 nr -= off;
                         }
                 }
@@ -1813,7 +1910,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
         struct ip_callchain *chain = sample->callchain;
         int chain_nr = min(max_stack, (int)chain->nr), i;
         u8 cpumode = PERF_RECORD_MISC_USER;
-        u64 ip;
+        u64 ip, branch_from = 0;
 
         for (i = 0; i < chain_nr; i++) {
                 if (chain->ips[i] == PERF_CONTEXT_USER)
@@ -1855,6 +1952,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
                                         ip = lbr_stack->entries[0].to;
                                         branch = true;
                                         flags = &lbr_stack->entries[0].flags;
+                                        branch_from =
+                                                lbr_stack->entries[0].from;
                                 }
                         } else {
                                 if (j < lbr_nr) {
@@ -1869,12 +1968,15 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
                                         ip = lbr_stack->entries[0].to;
                                         branch = true;
                                         flags = &lbr_stack->entries[0].flags;
+                                        branch_from =
+                                                lbr_stack->entries[0].from;
                                 }
                         }
 
                         err = add_callchain_ip(thread, cursor, parent,
                                                root_al, &cpumode, ip,
-                                               branch, flags, 0, 0);
+                                               branch, flags, NULL,
+                                               branch_from);
                         if (err)
                                 return (err < 0) ? err : 0;
                 }
@@ -1894,12 +1996,14 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
         struct branch_stack *branch = sample->branch_stack;
         struct ip_callchain *chain = sample->callchain;
-        int chain_nr = chain->nr;
+        int chain_nr = 0;
         u8 cpumode = PERF_RECORD_MISC_USER;
         int i, j, err, nr_entries;
         int skip_idx = -1;
         int first_call = 0;
-        int nr_loop_iter;
+
+        if (chain)
+                chain_nr = chain->nr;
 
         if (perf_evsel__has_branch_callstack(evsel)) {
                 err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
@@ -1929,6 +2033,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
         if (branch && callchain_param.branch_callstack) {
                 int nr = min(max_stack, (int)branch->nr);
                 struct branch_entry be[nr];
+                struct iterations iter[nr];
 
                 if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
                         pr_warning("corrupted branch chain. skipping...\n");
@@ -1938,6 +2043,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
                 for (i = 0; i < nr; i++) {
                         if (callchain_param.order == ORDER_CALLEE) {
                                 be[i] = branch->entries[i];
+
+                                if (chain == NULL)
+                                        continue;
+
                                 /*
                                  * Check for overlap into the callchain.
                                  * The return address is one off compared to
@@ -1955,42 +2064,30 @@ static int thread__resolve_callchain_sample(struct thread *thread,
                                 be[i] = branch->entries[branch->nr - i - 1];
                 }
 
-                nr_loop_iter = nr;
-                nr = remove_loops(be, nr);
-
-                /*
-                 * Get the number of iterations.
-                 * It's only approximation, but good enough in practice.
-                 */
-                if (nr_loop_iter > nr)
-                        nr_loop_iter = nr_loop_iter - nr + 1;
-                else
-                        nr_loop_iter = 0;
+                memset(iter, 0, sizeof(struct iterations) * nr);
+                nr = remove_loops(be, nr, iter);
 
                 for (i = 0; i < nr; i++) {
-                        if (i == nr - 1)
-                                err = add_callchain_ip(thread, cursor, parent,
-                                                       root_al,
-                                                       NULL, be[i].to,
-                                                       true, &be[i].flags,
-                                                       nr_loop_iter, 1);
-                        else
-                                err = add_callchain_ip(thread, cursor, parent,
-                                                       root_al,
-                                                       NULL, be[i].to,
-                                                       true, &be[i].flags,
-                                                       0, 0);
+                        err = add_callchain_ip(thread, cursor, parent,
+                                               root_al,
+                                               NULL, be[i].to,
+                                               true, &be[i].flags,
+                                               NULL, be[i].from);
 
                         if (!err)
                                 err = add_callchain_ip(thread, cursor, parent, root_al,
                                                        NULL, be[i].from,
                                                        true, &be[i].flags,
-                                                       0, 0);
+                                                       &iter[i], 0);
                         if (err == -EINVAL)
                                 break;
                         if (err)
                                 return err;
                 }
+
+                if (chain_nr == 0)
+                        return 0;
+
                 chain_nr -= nr;
         }
 
@@ -2015,7 +2112,7 @@ check_calls:
 
                 err = add_callchain_ip(thread, cursor, parent,
                                        root_al, &cpumode, ip,
-                                       false, NULL, 0, 0);
+                                       false, NULL, NULL, 0);
 
                 if (err)
                         return (err < 0) ? err : 0;
@@ -2024,15 +2121,54 @@ check_calls:
         return 0;
 }
 
+static int append_inlines(struct callchain_cursor *cursor,
+                          struct map *map, struct symbol *sym, u64 ip)
+{
+        struct inline_node *inline_node;
+        struct inline_list *ilist;
+        u64 addr;
+        int ret = 1;
+
+        if (!symbol_conf.inline_name || !map || !sym)
+                return ret;
+
+        addr = map__rip_2objdump(map, ip);
+
+        inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
+        if (!inline_node) {
+                inline_node = dso__parse_addr_inlines(map->dso, addr, sym);
+                if (!inline_node)
+                        return ret;
+                inlines__tree_insert(&map->dso->inlined_nodes, inline_node);
+        }
+
+        list_for_each_entry(ilist, &inline_node->val, list) {
+                ret = callchain_cursor_append(cursor, ip, map,
+                                              ilist->symbol, false,
+                                              NULL, 0, 0, 0, ilist->srcline);
+
+                if (ret != 0)
+                        return ret;
+        }
+
+        return ret;
+}
+
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
         struct callchain_cursor *cursor = arg;
+        const char *srcline = NULL;
 
         if (symbol_conf.hide_unresolved && entry->sym == NULL)
                 return 0;
+
+        if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
+                return 0;
+
+        srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
         return callchain_cursor_append(cursor, entry->ip,
                                        entry->map, entry->sym,
-                                       false, NULL, 0, 0);
+                                       false, NULL, 0, 0, 0, srcline);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
@@ -2096,21 +2232,26 @@ int machine__for_each_thread(struct machine *machine,
                              int (*fn)(struct thread *thread, void *p),
                              void *priv)
 {
+        struct threads *threads;
         struct rb_node *nd;
         struct thread *thread;
         int rc = 0;
+        int i;
 
-        for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-                thread = rb_entry(nd, struct thread, rb_node);
-                rc = fn(thread, priv);
-                if (rc != 0)
-                        return rc;
-        }
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                threads = &machine->threads[i];
+                for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+                        thread = rb_entry(nd, struct thread, rb_node);
+                        rc = fn(thread, priv);
+                        if (rc != 0)
+                                return rc;
+                }
 
-        list_for_each_entry(thread, &machine->dead_threads, node) {
-                rc = fn(thread, priv);
-                if (rc != 0)
-                        return rc;
+                list_for_each_entry(thread, &threads->dead, node) {
+                        rc = fn(thread, priv);
+                        if (rc != 0)
+                                return rc;
+                }
         }
         return rc;
 }
@@ -2139,12 +2280,16 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
                                   struct target *target, struct thread_map *threads,
                                   perf_event__handler_t process, bool data_mmap,
-                                  unsigned int proc_map_timeout)
+                                  unsigned int proc_map_timeout,
+                                  unsigned int nr_threads_synthesize)
 {
         if (target__has_task(target))
                 return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
         else if (target__has_cpu(target))
-                return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
+                return perf_event__synthesize_threads(tool, process,
+                                                      machine, data_mmap,
+                                                      proc_map_timeout,
+                                                      nr_threads_synthesize);
         /* command specified */
         return 0;
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 3cdb1340f917..5ce860b64c74 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_MACHINE_H
 #define __PERF_MACHINE_H
 
@@ -6,6 +7,7 @@
 #include "map.h"
 #include "dso.h"
 #include "event.h"
+#include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
@@ -23,6 +25,17 @@ extern const char *ref_reloc_sym_names[];
 
 struct vdso_info;
 
+#define THREADS__TABLE_BITS     8
+#define THREADS__TABLE_SIZE     (1 << THREADS__TABLE_BITS)
+
+struct threads {
+        struct rb_root    entries;
+        struct rw_semaphore lock;
+        unsigned int      nr;
+        struct list_head  dead;
+        struct thread     *last_match;
+};
+
 struct machine {
         struct rb_node    rb_node;
         pid_t             pid;
@@ -30,11 +43,7 @@ struct machine {
         bool              comm_exec;
         bool              kptr_restrict_warned;
         char              *root_dir;
-        struct rb_root    threads;
-        pthread_rwlock_t  threads_lock;
-        unsigned int      nr_threads;
-        struct list_head  dead_threads;
-        struct thread     *last_match;
+        struct threads    threads[THREADS__TABLE_SIZE];
         struct vdso_info  *vdso_info;
         struct perf_env   *env;
         struct dsos       dsos;
@@ -48,6 +57,12 @@ struct machine {
         };
 };
 
+static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
+{
+        /* Cast it to handle tid == -1 */
+        return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
+}
+
 static inline
 struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
 {
@@ -243,15 +258,18 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
                                   struct target *target, struct thread_map *threads,
                                   perf_event__handler_t process, bool data_mmap,
-                                  unsigned int proc_map_timeout);
+                                  unsigned int proc_map_timeout,
+                                  unsigned int nr_threads_synthesize);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
                                 struct thread_map *threads, bool data_mmap,
-                                unsigned int proc_map_timeout)
+                                unsigned int proc_map_timeout,
+                                unsigned int nr_threads_synthesize)
 {
         return __machine__synthesize_threads(machine, NULL, target, threads,
                                              perf_event__process, data_mmap,
-                                             proc_map_timeout);
+                                             proc_map_timeout,
+                                             nr_threads_synthesize);
 }
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 2179b2deb730..6d40efd74402 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
 #include <errno.h>
 #include <inttypes.h>
@@ -16,6 +17,7 @@
 #include "machine.h"
 #include <linux/string.h>
 #include "srcline.h"
+#include "namespaces.h"
 #include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
@@ -145,11 +147,13 @@ void map__init(struct map *map, enum map_type type,
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
-                     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+                     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
                      u64 ino_gen, u32 prot, u32 flags, char *filename,
                      enum map_type type, struct thread *thread)
 {
         struct map *map = malloc(sizeof(*map));
+        struct nsinfo *nsi = NULL;
+        struct nsinfo *nnsi;
 
         if (map != NULL) {
                 char newfilename[PATH_MAX];
@@ -167,9 +171,11 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
                 map->ino_generation = ino_gen;
                 map->prot = prot;
                 map->flags = flags;
+                nsi = nsinfo__get(thread->nsinfo);
 
-                if ((anon || no_dso) && type == MAP__FUNCTION) {
-                        snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
+                if ((anon || no_dso) && nsi && type == MAP__FUNCTION) {
+                        snprintf(newfilename, sizeof(newfilename),
+                                 "/tmp/perf-%d.map", nsi->pid);
                         filename = newfilename;
                 }
 
@@ -179,6 +185,16 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
                 }
 
                 if (vdso) {
+                        /* The vdso maps are always on the host and not the
+                         * container.  Ensure that we don't use setns to look
+                         * them up.
+                         */
+                        nnsi = nsinfo__copy(nsi);
+                        if (nnsi) {
+                                nsinfo__put(nsi);
+                                nnsi->need_setns = false;
+                                nsi = nnsi;
+                        }
                         pgoff = 0;
                         dso = machine__findnew_vdso(machine, thread);
                 } else
@@ -200,10 +216,12 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
                         if (type != MAP__FUNCTION)
                                 dso__set_loaded(dso, map->type);
                 }
+                dso->nsinfo = nsi;
                 dso__put(dso);
         }
         return map;
 out_delete:
+        nsinfo__put(nsi);
         free(map);
         return NULL;
 }
@@ -471,7 +489,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 static void maps__init(struct maps *maps)
 {
         maps->entries = RB_ROOT;
-        pthread_rwlock_init(&maps->lock, NULL);
+        init_rwsem(&maps->lock);
 }
 
 void map_groups__init(struct map_groups *mg, struct machine *machine)
@@ -500,9 +518,9 @@ static void __maps__purge(struct maps *maps)
 
 static void maps__exit(struct maps *maps)
 {
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
         __maps__purge(maps);
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
@@ -569,7 +587,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
         struct symbol *sym;
         struct rb_node *nd;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
                 struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -585,7 +603,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
         sym = NULL;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return sym;
 }
 
@@ -621,7 +639,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
         size_t printed = 0;
         struct rb_node *nd;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
                 struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -633,7 +651,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
                 }
         }
 
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
 
         return printed;
 }
@@ -665,7 +683,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
         struct rb_node *next;
         int err = 0;
 
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
 
         root = &maps->entries;
         next = rb_first(root);
@@ -733,7 +751,7 @@ put_map:
 
         err = 0;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
         return err;
 }
 
@@ -754,7 +772,7 @@ int map_groups__clone(struct thread *thread,
         struct map *map;
         struct maps *maps = &parent->maps[type];
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (map = maps__first(maps); map; map = map__next(map)) {
                 struct map *new = map__clone(map);
@@ -771,7 +789,7 @@ int map_groups__clone(struct thread *thread,
 
         err = 0;
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return err;
 }
 
@@ -798,9 +816,9 @@ static void __maps__insert(struct maps *maps, struct map *map)
 
 void maps__insert(struct maps *maps, struct map *map)
 {
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
         __maps__insert(maps, map);
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 static void __maps__remove(struct maps *maps, struct map *map)
@@ -811,9 +829,9 @@ static void __maps__remove(struct maps *maps, struct map *map)
 
 void maps__remove(struct maps *maps, struct map *map)
 {
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
         __maps__remove(maps, map);
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 struct map *maps__find(struct maps *maps, u64 ip)
@@ -821,7 +839,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
         struct rb_node **p, *parent = NULL;
         struct map *m;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         p = &maps->entries.rb_node;
         while (*p != NULL) {
@@ -837,7 +855,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
 
         m = NULL;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return m;
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f9e8ac8a52cd..edeb7291c8e1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
@@ -9,6 +10,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include "rwsem.h"
 
 enum map_type {
         MAP__FUNCTION = 0,
@@ -61,7 +63,7 @@ struct kmap {
 
 struct maps {
         struct rb_root   entries;
-        pthread_rwlock_t lock;
+        struct rw_semaphore lock;
 };
 
 struct map_groups {
@@ -141,7 +143,7 @@ struct thread;
 void map__init(struct map *map, enum map_type type,
                u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
-                     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+                     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
                      u64 ino_gen, u32 prot, u32 flags,
                      char *filename, enum map_type type, struct thread *thread);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 06f5a3a4295c..93f74d8d3cdd 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stddef.h>
 #include <stdlib.h>
 #include <string.h>
@@ -166,11 +167,20 @@ static const char * const mem_lvl[] = {
         "Uncached",
 };
 
+static const char * const mem_lvlnum[] = {
+        [PERF_MEM_LVLNUM_ANY_CACHE] = "Any cache",
+        [PERF_MEM_LVLNUM_LFB] = "LFB",
+        [PERF_MEM_LVLNUM_RAM] = "RAM",
+        [PERF_MEM_LVLNUM_PMEM] = "PMEM",
+        [PERF_MEM_LVLNUM_NA] = "N/A",
+};
+
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
         size_t i, l = 0;
         u64 m =  PERF_MEM_LVL_NA;
         u64 hit, miss;
+        int printed;
 
         if (mem_info)
                 m  = mem_info->data_src.mem_lvl;
@@ -184,17 +194,37 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
         /* already taken care of */
         m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
+
+        if (mem_info && mem_info->data_src.mem_remote) {
+                strcat(out, "Remote ");
+                l += 7;
+        }
+
+        printed = 0;
         for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
                 if (!(m & 0x1))
                         continue;
-                if (l) {
+                if (printed++) {
                         strcat(out, " or ");
                         l += 4;
                 }
                 l += scnprintf(out + l, sz - l, mem_lvl[i]);
         }
-        if (*out == '\0')
-                l += scnprintf(out, sz - l, "N/A");
+
+        if (mem_info && mem_info->data_src.mem_lvl_num) {
+                int lvl = mem_info->data_src.mem_lvl_num;
+                if (printed++) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                if (mem_lvlnum[lvl])
+                        l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]);
+                else
+                        l += scnprintf(out + l, sz - l, "L%d", lvl);
+        }
+
+        if (l == 0)
+                l += scnprintf(out + l, sz - l, "N/A");
         if (hit)
                 l += scnprintf(out + l, sz - l, " hit");
         if (miss)
@@ -231,6 +261,14 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
                 }
                 l += scnprintf(out + l, sz - l, snoop_access[i]);
         }
+        if (mem_info &&
+             (mem_info->data_src.mem_snoopx & PERF_MEM_SNOOPX_FWD)) {
+                if (l) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                l += scnprintf(out + l, sz - l, "Fwd");
+        }
 
         if (*out == '\0')
                 l += scnprintf(out, sz - l, "N/A");
@@ -279,6 +317,11 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
         u64 lvl    = data_src->mem_lvl;
         u64 snoop  = data_src->mem_snoop;
         u64 lock   = data_src->mem_lock;
+        /*
+         * Skylake might report unknown remote level via this
+         * bit, consider it when evaluating remote HITMs.
+         */
+        bool mrem  = data_src->mem_remote;
         int err = 0;
 
 #define HITM_INC(__f)           \
@@ -324,7 +367,8 @@ do {				\
                         }
 
                         if ((lvl & P(LVL, REM_RAM1)) ||
-                            (lvl & P(LVL, REM_RAM2))) {
+                            (lvl & P(LVL, REM_RAM2)) ||
+                             mrem) {
                                 stats->rmt_dram++;
                                 if (snoop & P(SNOOP, HIT))
                                         stats->ld_shared++;
@@ -334,7 +378,8 @@ do {				\
                 }
 
                 if ((lvl & P(LVL, REM_CCE1)) ||
-                    (lvl & P(LVL, REM_CCE2))) {
+                    (lvl & P(LVL, REM_CCE2)) ||
+                     mrem) {
                         if (snoop & P(SNOOP, HIT))
                                 stats->rmt_hit++;
                         else if (snoop & P(SNOOP, HITM))
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 40f72ee4f42a..a889ec2fa9f5 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_MEM_EVENTS_H
 #define __PERF_MEM_EVENTS_H
 
diff --git a/tools/perf/util/memswap.c b/tools/perf/util/memswap.c
index 55f7faa8d9ec..c1317e4983bc 100644
--- a/tools/perf/util/memswap.c
+++ b/tools/perf/util/memswap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <byteswap.h>
 #include "memswap.h"
 #include <linux/types.h>
diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h
index 7d1b1c34bb57..1e29ff903ca9 100644
--- a/tools/perf/util/memswap.h
+++ b/tools/perf/util/memswap.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_MEMSWAP_H_
 #define PERF_MEMSWAP_H_
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
new file mode 100644
index 000000000000..0ddd9c199227
--- /dev/null
+++ b/tools/perf/util/metricgroup.c
@@ -0,0 +1,490 @@
+/*
+ * Copyright (c) 2017, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+/* Manage metrics and groups of metrics from JSON files */
+
+#include "metricgroup.h"
+#include "evlist.h"
+#include "strbuf.h"
+#include "pmu.h"
+#include "expr.h"
+#include "rblist.h"
+#include "pmu.h"
+#include <string.h>
+#include <stdbool.h>
+#include <errno.h>
+#include "pmu-events/pmu-events.h"
+#include "strbuf.h"
+#include "strlist.h"
+#include <assert.h>
+#include <ctype.h>
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+                                         struct perf_evsel *evsel,
+                                         bool create)
+{
+        struct rb_node *nd;
+        struct metric_event me = {
+                .evsel = evsel
+        };
+        nd = rblist__find(metric_events, &me);
+        if (nd)
+                return container_of(nd, struct metric_event, nd);
+        if (create) {
+                rblist__add_node(metric_events, &me);
+                nd = rblist__find(metric_events, &me);
+                if (nd)
+                        return container_of(nd, struct metric_event, nd);
+        }
+        return NULL;
+}
+
+static int metric_event_cmp(struct rb_node *rb_node, const void *entry)
+{
+        struct metric_event *a = container_of(rb_node,
+                                              struct metric_event,
+                                              nd);
+        const struct metric_event *b = entry;
+
+        if (a->evsel == b->evsel)
+                return 0;
+        if ((char *)a->evsel < (char *)b->evsel)
+                return -1;
+        return +1;
+}
+
+static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused,
+                                        const void *entry)
+{
+        struct metric_event *me = malloc(sizeof(struct metric_event));
+
+        if (!me)
+                return NULL;
+        memcpy(me, entry, sizeof(struct metric_event));
+        me->evsel = ((struct metric_event *)entry)->evsel;
+        INIT_LIST_HEAD(&me->head);
+        return &me->nd;
+}
+
+static void metricgroup__rblist_init(struct rblist *metric_events)
+{
+        rblist__init(metric_events);
+        metric_events->node_cmp = metric_event_cmp;
+        metric_events->node_new = metric_event_new;
+}
+
+struct egroup {
+        struct list_head nd;
+        int idnum;
+        const char **ids;
+        const char *metric_name;
+        const char *metric_expr;
+};
+
+static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
+                                     const char **ids,
+                                     int idnum,
+                                     struct perf_evsel **metric_events)
+{
+        struct perf_evsel *ev, *start = NULL;
+        int ind = 0;
+
+        evlist__for_each_entry (perf_evlist, ev) {
+                if (!strcmp(ev->name, ids[ind])) {
+                        metric_events[ind] = ev;
+                        if (ind == 0)
+                                start = ev;
+                        if (++ind == idnum) {
+                                metric_events[ind] = NULL;
+                                return start;
+                        }
+                } else {
+                        ind = 0;
+                        start = NULL;
+                }
+        }
+        /*
+         * This can happen when an alias expands to multiple
+         * events, like for uncore events.
+         * We don't support this case for now.
+         */
+        return NULL;
+}
+
+static int metricgroup__setup_events(struct list_head *groups,
+                                     struct perf_evlist *perf_evlist,
+                                     struct rblist *metric_events_list)
+{
+        struct metric_event *me;
+        struct metric_expr *expr;
+        int i = 0;
+        int ret = 0;
+        struct egroup *eg;
+        struct perf_evsel *evsel;
+
+        list_for_each_entry (eg, groups, nd) {
+                struct perf_evsel **metric_events;
+
+                metric_events = calloc(sizeof(void *), eg->idnum + 1);
+                if (!metric_events) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
+                                   metric_events);
+                if (!evsel) {
+                        pr_debug("Cannot resolve %s: %s\n",
+                                        eg->metric_name, eg->metric_expr);
+                        continue;
+                }
+                for (i = 0; i < eg->idnum; i++)
+                        metric_events[i]->collect_stat = true;
+                me = metricgroup__lookup(metric_events_list, evsel, true);
+                if (!me) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                expr = malloc(sizeof(struct metric_expr));
+                if (!expr) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                expr->metric_expr = eg->metric_expr;
+                expr->metric_name = eg->metric_name;
+                expr->metric_events = metric_events;
+                list_add(&expr->nd, &me->head);
+        }
+        return ret;
+}
+
+static bool match_metric(const char *n, const char *list)
+{
+        int len;
+        char *m;
+
+        if (!list)
+                return false;
+        if (!strcmp(list, "all"))
+                return true;
+        if (!n)
+                return !strcasecmp(list, "No_group");
+        len = strlen(list);
+        m = strcasestr(n, list);
+        if (!m)
+                return false;
+        if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
+            (m[len] == 0 || m[len] == ';'))
+                return true;
+        return false;
+}
+
+struct mep {
+        struct rb_node nd;
+        const char *name;
+        struct strlist *metrics;
+};
+
+static int mep_cmp(struct rb_node *rb_node, const void *entry)
+{
+        struct mep *a = container_of(rb_node, struct mep, nd);
+        struct mep *b = (struct mep *)entry;
+
+        return strcmp(a->name, b->name);
+}
+
+static struct rb_node *mep_new(struct rblist *rl __maybe_unused,
+                                        const void *entry)
+{
+        struct mep *me = malloc(sizeof(struct mep));
+
+        if (!me)
+                return NULL;
+        memcpy(me, entry, sizeof(struct mep));
+        me->name = strdup(me->name);
+        if (!me->name)
+                goto out_me;
+        me->metrics = strlist__new(NULL, NULL);
+        if (!me->metrics)
+                goto out_name;
+        return &me->nd;
+out_name:
+        free((char *)me->name);
+out_me:
+        free(me);
+        return NULL;
+}
+
+static struct mep *mep_lookup(struct rblist *groups, const char *name)
+{
+        struct rb_node *nd;
+        struct mep me = {
+                .name = name
+        };
+        nd = rblist__find(groups, &me);
+        if (nd)
+                return container_of(nd, struct mep, nd);
+        rblist__add_node(groups, &me);
+        nd = rblist__find(groups, &me);
+        if (nd)
+                return container_of(nd, struct mep, nd);
+        return NULL;
+}
+
+static void mep_delete(struct rblist *rl __maybe_unused,
+                       struct rb_node *nd)
+{
+        struct mep *me = container_of(nd, struct mep, nd);
+
+        strlist__delete(me->metrics);
+        free((void *)me->name);
+        free(me);
+}
+
+static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
+{
+        struct str_node *sn;
+        int n = 0;
+
+        strlist__for_each_entry (sn, metrics) {
+                if (raw)
+                        printf("%s%s", n > 0 ? " " : "", sn->s);
+                else
+                        printf("  %s\n", sn->s);
+                n++;
+        }
+        if (raw)
+                putchar('\n');
+}
+
+void metricgroup__print(bool metrics, bool metricgroups, char *filter,
+                        bool raw)
+{
+        struct pmu_events_map *map = perf_pmu__find_map();
+        struct pmu_event *pe;
+        int i;
+        struct rblist groups;
+        struct rb_node *node, *next;
+        struct strlist *metriclist = NULL;
+
+        if (!map)
+                return;
+
+        if (!metricgroups) {
+                metriclist = strlist__new(NULL, NULL);
+                if (!metriclist)
+                        return;
+        }
+
+        rblist__init(&groups);
+        groups.node_new = mep_new;
+        groups.node_cmp = mep_cmp;
+        groups.node_delete = mep_delete;
+        for (i = 0; ; i++) {
+                const char *g;
+                pe = &map->table[i];
+
+                if (!pe->name && !pe->metric_group && !pe->metric_name)
+                        break;
+                if (!pe->metric_expr)
+                        continue;
+                g = pe->metric_group;
+                if (!g && pe->metric_name) {
+                        if (pe->name)
+                                continue;
+                        g = "No_group";
+                }
+                if (g) {
+                        char *omg;
+                        char *mg = strdup(g);
+
+                        if (!mg)
+                                return;
+                        omg = mg;
+                        while ((g = strsep(&mg, ";")) != NULL) {
+                                struct mep *me;
+                                char *s;
+
+                                if (*g == 0)
+                                        g = "No_group";
+                                while (isspace(*g))
+                                        g++;
+                                if (filter && !strstr(g, filter))
+                                        continue;
+                                if (raw)
+                                        s = (char *)pe->metric_name;
+                                else {
+                                        if (asprintf(&s, "%s\n\t[%s]",
+                                                     pe->metric_name, pe->desc) < 0)
+                                                return;
+                                }
+
+                                if (!s)
+                                        continue;
+
+                                if (!metricgroups) {
+                                        strlist__add(metriclist, s);
+                                } else {
+                                        me = mep_lookup(&groups, g);
+                                        if (!me)
+                                                continue;
+                                        strlist__add(me->metrics, s);
+                                }
+                        }
+                        free(omg);
+                }
+        }
+
+        if (metricgroups && !raw)
+                printf("\nMetric Groups:\n\n");
+        else if (metrics && !raw)
+                printf("\nMetrics:\n\n");
+
+        for (node = rb_first(&groups.entries); node; node = next) {
+                struct mep *me = container_of(node, struct mep, nd);
+
+                if (metricgroups)
+                        printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n");
+                if (metrics)
+                        metricgroup__print_strlist(me->metrics, raw);
+                next = rb_next(node);
+                rblist__remove_node(&groups, node);
+        }
+        if (!metricgroups)
+                metricgroup__print_strlist(metriclist, raw);
+        strlist__delete(metriclist);
+}
+
+static int metricgroup__add_metric(const char *metric, struct strbuf *events,
+                                   struct list_head *group_list)
+{
+        struct pmu_events_map *map = perf_pmu__find_map();
+        struct pmu_event *pe;
+        int ret = -EINVAL;
+        int i, j;
+
+        if (!map)
+                return 0;
+
+        for (i = 0; ; i++) {
+                pe = &map->table[i];
+
+                if (!pe->name && !pe->metric_group && !pe->metric_name)
+                        break;
+                if (!pe->metric_expr)
+                        continue;
+                if (match_metric(pe->metric_group, metric) ||
+                    match_metric(pe->metric_name, metric)) {
+                        const char **ids;
+                        int idnum;
+                        struct egroup *eg;
+
+                        pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
+
+                        if (expr__find_other(pe->metric_expr,
+                                             NULL, &ids, &idnum) < 0)
+                                continue;
+                        if (events->len > 0)
+                                strbuf_addf(events, ",");
+                        for (j = 0; j < idnum; j++) {
+                                pr_debug("found event %s\n", ids[j]);
+                                strbuf_addf(events, "%s%s",
+                                        j == 0 ? "{" : ",",
+                                        ids[j]);
+                        }
+                        strbuf_addf(events, "}:W");
+
+                        eg = malloc(sizeof(struct egroup));
+                        if (!eg) {
+                                ret = -ENOMEM;
+                                break;
+                        }
+                        eg->ids = ids;
+                        eg->idnum = idnum;
+                        eg->metric_name = pe->metric_name;
+                        eg->metric_expr = pe->metric_expr;
+                        list_add_tail(&eg->nd, group_list);
+                        ret = 0;
+                }
+        }
+        return ret;
+}
+
+static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
+                                        struct list_head *group_list)
+{
+        char *llist, *nlist, *p;
+        int ret = -EINVAL;
+
+        nlist = strdup(list);
+        if (!nlist)
+                return -ENOMEM;
+        llist = nlist;
+
+        strbuf_init(events, 100);
+        strbuf_addf(events, "%s", "");
+
+        while ((p = strsep(&llist, ",")) != NULL) {
+                ret = metricgroup__add_metric(p, events, group_list);
+                if (ret == -EINVAL) {
+                        fprintf(stderr, "Cannot find metric or group `%s'\n",
+                                        p);
+                        break;
+                }
+        }
+        free(nlist);
+        return ret;
+}
+
+static void metricgroup__free_egroups(struct list_head *group_list)
+{
+        struct egroup *eg, *egtmp;
+        int i;
+
+        list_for_each_entry_safe (eg, egtmp, group_list, nd) {
+                for (i = 0; i < eg->idnum; i++)
+                        free((char *)eg->ids[i]);
+                free(eg->ids);
+                free(eg);
+        }
+}
+
+int metricgroup__parse_groups(const struct option *opt,
+                           const char *str,
+                           struct rblist *metric_events)
+{
+        struct parse_events_error parse_error;
+        struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value;
+        struct strbuf extra_events;
+        LIST_HEAD(group_list);
+        int ret;
+
+        if (metric_events->nr_entries == 0)
+                metricgroup__rblist_init(metric_events);
+        ret = metricgroup__add_metric_list(str, &extra_events, &group_list);
+        if (ret)
+                return ret;
+        pr_debug("adding %s\n", extra_events.buf);
+        memset(&parse_error, 0, sizeof(struct parse_events_error));
+        ret = parse_events(perf_evlist, extra_events.buf, &parse_error);
+        if (ret) {
+                parse_events_print_error(&parse_error, extra_events.buf);
+                goto out;
+        }
+        strbuf_release(&extra_events);
+        ret = metricgroup__setup_events(&group_list, perf_evlist,
+                                        metric_events);
+out:
+        metricgroup__free_egroups(&group_list);
+        return ret;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
new file mode 100644
index 000000000000..06854e125ee7
--- /dev/null
+++ b/tools/perf/util/metricgroup.h
@@ -0,0 +1,31 @@
+#ifndef METRICGROUP_H
+#define METRICGROUP_H 1
+
+#include "linux/list.h"
+#include "rblist.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "strbuf.h"
+
+struct metric_event {
+        struct rb_node nd;
+        struct perf_evsel *evsel;
+        struct list_head head; /* list of metric_expr */
+};
+
+struct metric_expr {
+        struct list_head nd;
+        const char *metric_expr;
+        const char *metric_name;
+        struct perf_evsel **metric_events;
+};
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+                                         struct perf_evsel *evsel,
+                                         bool create);
+int metricgroup__parse_groups(const struct option *opt,
+                        const char *str,
+                        struct rblist *metric_events);
+
+void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+#endif
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
new file mode 100644
index 000000000000..9fe5f9c7d577
--- /dev/null
+++ b/tools/perf/util/mmap.c
@@ -0,0 +1,352 @@
+/*
+ * Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/mman.h>
+#include <inttypes.h>
+#include <asm/bug.h>
+#include "debug.h"
+#include "event.h"
+#include "mmap.h"
+#include "util.h" /* page_size */
+
+size_t perf_mmap__mmap_len(struct perf_mmap *map)
+{
+        return map->mask + 1 + page_size;
+}
+
+/* When check_messup is true, 'end' must points to a good entry */
+static union perf_event *perf_mmap__read(struct perf_mmap *map, bool check_messup,
+                                         u64 start, u64 end, u64 *prev)
+{
+        unsigned char *data = map->base + page_size;
+        union perf_event *event = NULL;
+        int diff = end - start;
+
+        if (check_messup) {
+                /*
+                 * If we're further behind than half the buffer, there's a chance
+                 * the writer will bite our tail and mess up the samples under us.
+                 *
+                 * If we somehow ended up ahead of the 'end', we got messed up.
+                 *
+                 * In either case, truncate and restart at 'end'.
+                 */
+                if (diff > map->mask / 2 || diff < 0) {
+                        fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+                        /*
+                         * 'end' points to a known good entry, start there.
+                         */
+                        start = end;
+                        diff = 0;
+                }
+        }
+
+        if (diff >= (int)sizeof(event->header)) {
+                size_t size;
+
+                event = (union perf_event *)&data[start & map->mask];
+                size = event->header.size;
+
+                if (size < sizeof(event->header) || diff < (int)size) {
+                        event = NULL;
+                        goto broken_event;
+                }
+
+                /*
+                 * Event straddles the mmap boundary -- header should always
+                 * be inside due to u64 alignment of output.
+                 */
+                if ((start & map->mask) + size != ((start + size) & map->mask)) {
+                        unsigned int offset = start;
+                        unsigned int len = min(sizeof(*event), size), cpy;
+                        void *dst = map->event_copy;
+
+                        do {
+                                cpy = min(map->mask + 1 - (offset & map->mask), len);
+                                memcpy(dst, &data[offset & map->mask], cpy);
+                                offset += cpy;
+                                dst += cpy;
+                                len -= cpy;
+                        } while (len);
+
+                        event = (union perf_event *)map->event_copy;
+                }
+
+                start += size;
+        }
+
+broken_event:
+        if (prev)
+                *prev = start;
+
+        return event;
+}
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup)
+{
+        u64 head;
+        u64 old = map->prev;
+
+        /*
+         * Check if event was unmapped due to a POLLHUP/POLLERR.
+         */
+        if (!refcount_read(&map->refcnt))
+                return NULL;
+
+        head = perf_mmap__read_head(map);
+
+        return perf_mmap__read(map, check_messup, old, head, &map->prev);
+}
+
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
+{
+        u64 head, end;
+        u64 start = map->prev;
+
+        /*
+         * Check if event was unmapped due to a POLLHUP/POLLERR.
+         */
+        if (!refcount_read(&map->refcnt))
+                return NULL;
+
+        head = perf_mmap__read_head(map);
+        if (!head)
+                return NULL;
+
+        /*
+         * 'head' pointer starts from 0. Kernel minus sizeof(record) form
+         * it each time when kernel writes to it, so in fact 'head' is
+         * negative. 'end' pointer is made manually by adding the size of
+         * the ring buffer to 'head' pointer, means the validate data can
+         * read is the whole ring buffer. If 'end' is positive, the ring
+         * buffer has not fully filled, so we must adjust 'end' to 0.
+         *
+         * However, since both 'head' and 'end' is unsigned, we can't
+         * simply compare 'end' against 0. Here we compare '-head' and
+         * the size of the ring buffer, where -head is the number of bytes
+         * kernel write to the ring buffer.
+         */
+        if (-head < (u64)(map->mask + 1))
+                end = 0;
+        else
+                end = head + map->mask + 1;
+
+        return perf_mmap__read(map, false, start, end, &map->prev);
+}
+
+void perf_mmap__read_catchup(struct perf_mmap *map)
+{
+        u64 head;
+
+        if (!refcount_read(&map->refcnt))
+                return;
+
+        head = perf_mmap__read_head(map);
+        map->prev = head;
+}
+
+static bool perf_mmap__empty(struct perf_mmap *map)
+{
+        return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base;
+}
+
+void perf_mmap__get(struct perf_mmap *map)
+{
+        refcount_inc(&map->refcnt);
+}
+
+void perf_mmap__put(struct perf_mmap *map)
+{
+        BUG_ON(map->base && refcount_read(&map->refcnt) == 0);
+
+        if (refcount_dec_and_test(&map->refcnt))
+                perf_mmap__munmap(map);
+}
+
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
+{
+        if (!overwrite) {
+                u64 old = map->prev;
+
+                perf_mmap__write_tail(map, old);
+        }
+
+        if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map))
+                perf_mmap__put(map);
+}
+
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+                               struct auxtrace_mmap_params *mp __maybe_unused,
+                               void *userpg __maybe_unused,
+                               int fd __maybe_unused)
+{
+        return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_unused,
+                                       off_t auxtrace_offset __maybe_unused,
+                                       unsigned int auxtrace_pages __maybe_unused,
+                                       bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
+                                          struct perf_evlist *evlist __maybe_unused,
+                                          int idx __maybe_unused,
+                                          bool per_cpu __maybe_unused)
+{
+}
+
+void perf_mmap__munmap(struct perf_mmap *map)
+{
+        if (map->base != NULL) {
+                munmap(map->base, perf_mmap__mmap_len(map));
+                map->base = NULL;
+                map->fd = -1;
+                refcount_set(&map->refcnt, 0);
+        }
+        auxtrace_mmap__munmap(&map->auxtrace_mmap);
+}
+
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
+{
+        /*
+         * The last one will be done at perf_evlist__mmap_consume(), so that we
+         * make sure we don't prevent tools from consuming every last event in
+         * the ring buffer.
+         *
+         * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+         * anymore, but the last events for it are still in the ring buffer,
+         * waiting to be consumed.
+         *
+         * Tools can chose to ignore this at their own discretion, but the
+         * evlist layer can't just drop it when filtering events in
+         * perf_evlist__filter_pollfd().
+         */
+        refcount_set(&map->refcnt, 2);
+        map->prev = 0;
+        map->mask = mp->mask;
+        map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+                         MAP_SHARED, fd, 0);
+        if (map->base == MAP_FAILED) {
+                pr_debug2("failed to mmap perf event ring buffer, error %d\n",
+                          errno);
+                map->base = NULL;
+                return -1;
+        }
+        map->fd = fd;
+
+        if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+                                &mp->auxtrace_mp, map->base, fd))
+                return -1;
+
+        return 0;
+}
+
+static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+{
+        struct perf_event_header *pheader;
+        u64 evt_head = head;
+        int size = mask + 1;
+
+        pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+        pheader = (struct perf_event_header *)(buf + (head & mask));
+        *start = head;
+        while (true) {
+                if (evt_head - head >= (unsigned int)size) {
+                        pr_debug("Finished reading backward ring buffer: rewind\n");
+                        if (evt_head - head > (unsigned int)size)
+                                evt_head -= pheader->size;
+                        *end = evt_head;
+                        return 0;
+                }
+
+                pheader = (struct perf_event_header *)(buf + (evt_head & mask));
+
+                if (pheader->size == 0) {
+                        pr_debug("Finished reading backward ring buffer: get start\n");
+                        *end = evt_head;
+                        return 0;
+                }
+
+                evt_head += pheader->size;
+                pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
+        }
+        WARN_ONCE(1, "Shouldn't get here\n");
+        return -1;
+}
+
+static int rb_find_range(void *data, int mask, u64 head, u64 old,
+                         u64 *start, u64 *end, bool backward)
+{
+        if (!backward) {
+                *start = old;
+                *end = head;
+                return 0;
+        }
+
+        return backward_rb_find_range(data, mask, head, start, end);
+}
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+                    void *to, int push(void *to, void *buf, size_t size))
+{
+        u64 head = perf_mmap__read_head(md);
+        u64 old = md->prev;
+        u64 end = head, start = old;
+        unsigned char *data = md->base + page_size;
+        unsigned long size;
+        void *buf;
+        int rc = 0;
+
+        if (rb_find_range(data, md->mask, head, old, &start, &end, backward))
+                return -1;
+
+        if (start == end)
+                return 0;
+
+        size = end - start;
+        if (size > (unsigned long)(md->mask) + 1) {
+                WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+
+                md->prev = head;
+                perf_mmap__consume(md, overwrite || backward);
+                return 0;
+        }
+
+        if ((start & md->mask) + size != (end & md->mask)) {
+                buf = &data[start & md->mask];
+                size = md->mask + 1 - (start & md->mask);
+                start += size;
+
+                if (push(to, buf, size) < 0) {
+                        rc = -1;
+                        goto out;
+                }
+        }
+
+        buf = &data[start & md->mask];
+        size = end - start;
+        start += size;
+
+        if (push(to, buf, size) < 0) {
+                rc = -1;
+                goto out;
+        }
+
+        md->prev = head;
+        perf_mmap__consume(md, overwrite || backward);
+out:
+        return rc;
+}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
new file mode 100644
index 000000000000..efd78b827b05
--- /dev/null
+++ b/tools/perf/util/mmap.h
@@ -0,0 +1,97 @@
+#ifndef __PERF_MMAP_H
+#define __PERF_MMAP_H 1
+
+#include <linux/compiler.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <stdbool.h>
+#include "auxtrace.h"
+#include "event.h"
+
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
+struct perf_mmap {
+        void             *base;
+        int              mask;
+        int              fd;
+        refcount_t       refcnt;
+        u64              prev;
+        struct auxtrace_mmap auxtrace_mmap;
+        char             event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+};
+
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+        BKW_MMAP_NOTREADY,
+        BKW_MMAP_RUNNING,
+        BKW_MMAP_DATA_PENDING,
+        BKW_MMAP_EMPTY,
+};
+
+struct mmap_params {
+        int                         prot, mask;
+        struct auxtrace_mmap_params auxtrace_mp;
+};
+
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd);
+void perf_mmap__munmap(struct perf_mmap *map);
+
+void perf_mmap__get(struct perf_mmap *map);
+void perf_mmap__put(struct perf_mmap *map);
+
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
+
+void perf_mmap__read_catchup(struct perf_mmap *md);
+
+static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
+{
+        struct perf_event_mmap_page *pc = mm->base;
+        u64 head = ACCESS_ONCE(pc->data_head);
+        rmb();
+        return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
+{
+        struct perf_event_mmap_page *pc = md->base;
+
+        /*
+         * ensure all reads are done before we write the tail out.
+         */
+        mb();
+        pc->data_tail = tail;
+}
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+                    void *to, int push(void *to, void *buf, size_t size));
+
+size_t perf_mmap__mmap_len(struct perf_mmap *map);
+
+#endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 67dcbcc73c7d..5be021701f34 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -9,9 +9,15 @@
 #include "namespaces.h"
 #include "util.h"
 #include "event.h"
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <unistd.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
@@ -35,3 +41,209 @@ void namespaces__free(struct namespaces *namespaces)
 {
         free(namespaces);
 }
+
+int nsinfo__init(struct nsinfo *nsi)
+{
+        char oldns[PATH_MAX];
+        char spath[PATH_MAX];
+        char *newns = NULL;
+        char *statln = NULL;
+        struct stat old_stat;
+        struct stat new_stat;
+        FILE *f = NULL;
+        size_t linesz = 0;
+        int rv = -1;
+
+        if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
+                return rv;
+
+        if (asprintf(&newns, "/proc/%d/ns/mnt", nsi->pid) == -1)
+                return rv;
+
+        if (stat(oldns, &old_stat) < 0)
+                goto out;
+
+        if (stat(newns, &new_stat) < 0)
+                goto out;
+
+        /* Check if the mount namespaces differ, if so then indicate that we
+         * want to switch as part of looking up dso/map data.
+         */
+        if (old_stat.st_ino != new_stat.st_ino) {
+                nsi->need_setns = true;
+                nsi->mntns_path = newns;
+                newns = NULL;
+        }
+
+        /* If we're dealing with a process that is in a different PID namespace,
+         * attempt to work out the innermost tgid for the process.
+         */
+        if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
+                goto out;
+
+        f = fopen(spath, "r");
+        if (f == NULL)
+                goto out;
+
+        while (getline(&statln, &linesz, f) != -1) {
+                /* Use tgid if CONFIG_PID_NS is not defined. */
+                if (strstr(statln, "Tgid:") != NULL) {
+                        nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
+                                                     NULL, 10);
+                        nsi->nstgid = nsi->tgid;
+                }
+
+                if (strstr(statln, "NStgid:") != NULL) {
+                        nsi->nstgid = (pid_t)strtol(strrchr(statln, '\t'),
+                                                     NULL, 10);
+                        break;
+                }
+        }
+        rv = 0;
+
+out:
+        if (f != NULL)
+                (void) fclose(f);
+        free(statln);
+        free(newns);
+        return rv;
+}
+
+struct nsinfo *nsinfo__new(pid_t pid)
+{
+        struct nsinfo *nsi;
+
+        if (pid == 0)
+                return NULL;
+
+        nsi = calloc(1, sizeof(*nsi));
+        if (nsi != NULL) {
+                nsi->pid = pid;
+                nsi->tgid = pid;
+                nsi->nstgid = pid;
+                nsi->need_setns = false;
+                /* Init may fail if the process exits while we're trying to look
+                 * at its proc information.  In that case, save the pid but
+                 * don't try to enter the namespace.
+                 */
+                if (nsinfo__init(nsi) == -1)
+                        nsi->need_setns = false;
+
+                refcount_set(&nsi->refcnt, 1);
+        }
+
+        return nsi;
+}
+
+struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
+{
+        struct nsinfo *nnsi;
+
+        nnsi = calloc(1, sizeof(*nnsi));
+        if (nnsi != NULL) {
+                nnsi->pid = nsi->pid;
+                nnsi->tgid = nsi->tgid;
+                nnsi->nstgid = nsi->nstgid;
+                nnsi->need_setns = nsi->need_setns;
+                if (nsi->mntns_path) {
+                        nnsi->mntns_path = strdup(nsi->mntns_path);
+                        if (!nnsi->mntns_path) {
+                                free(nnsi);
+                                return NULL;
+                        }
+                }
+                refcount_set(&nnsi->refcnt, 1);
+        }
+
+        return nnsi;
+}
+
+void nsinfo__delete(struct nsinfo *nsi)
+{
+        zfree(&nsi->mntns_path);
+        free(nsi);
+}
+
+struct nsinfo *nsinfo__get(struct nsinfo *nsi)
+{
+        if (nsi)
+                refcount_inc(&nsi->refcnt);
+        return nsi;
+}
+
+void nsinfo__put(struct nsinfo *nsi)
+{
+        if (nsi && refcount_dec_and_test(&nsi->refcnt))
+                nsinfo__delete(nsi);
+}
+
+void nsinfo__mountns_enter(struct nsinfo *nsi,
+                                  struct nscookie *nc)
+{
+        char curpath[PATH_MAX];
+        int oldns = -1;
+        int newns = -1;
+
+        if (nc == NULL)
+                return;
+
+        nc->oldns = -1;
+        nc->newns = -1;
+
+        if (!nsi || !nsi->need_setns)
+                return;
+
+        if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
+                return;
+
+        oldns = open(curpath, O_RDONLY);
+        if (oldns < 0)
+                return;
+
+        newns = open(nsi->mntns_path, O_RDONLY);
+        if (newns < 0)
+                goto errout;
+
+        if (setns(newns, CLONE_NEWNS) < 0)
+                goto errout;
+
+        nc->oldns = oldns;
+        nc->newns = newns;
+        return;
+
+errout:
+        if (oldns > -1)
+                close(oldns);
+        if (newns > -1)
+                close(newns);
+}
+
+void nsinfo__mountns_exit(struct nscookie *nc)
+{
+        if (nc == NULL || nc->oldns == -1 || nc->newns == -1)
+                return;
+
+        setns(nc->oldns, CLONE_NEWNS);
+
+        if (nc->oldns > -1) {
+                close(nc->oldns);
+                nc->oldns = -1;
+        }
+
+        if (nc->newns > -1) {
+                close(nc->newns);
+                nc->newns = -1;
+        }
+}
+
+char *nsinfo__realpath(const char *path, struct nsinfo *nsi)
+{
+        char *rpath;
+        struct nscookie nsc;
+
+        nsinfo__mountns_enter(nsi, &nsc);
+        rpath = realpath(path, NULL);
+        nsinfo__mountns_exit(&nsc);
+
+        return rpath;
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 468f1e9a1484..760558dcfd18 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -9,8 +9,10 @@
 #ifndef __PERF_NAMESPACES_H
 #define __PERF_NAMESPACES_H
 
-#include "../perf.h"
-#include <linux/list.h>
+#include <sys/types.h>
+#include <linux/perf_event.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
 
 struct namespaces_event;
 
@@ -23,4 +25,41 @@ struct namespaces {
 struct namespaces *namespaces__new(struct namespaces_event *event);
 void namespaces__free(struct namespaces *namespaces);
 
+struct nsinfo {
+        pid_t                   pid;
+        pid_t                   tgid;
+        pid_t                   nstgid;
+        bool                    need_setns;
+        char                    *mntns_path;
+        refcount_t              refcnt;
+};
+
+struct nscookie {
+        int                     oldns;
+        int                     newns;
+};
+
+int nsinfo__init(struct nsinfo *nsi);
+struct nsinfo *nsinfo__new(pid_t pid);
+struct nsinfo *nsinfo__copy(struct nsinfo *nsi);
+void nsinfo__delete(struct nsinfo *nsi);
+
+struct nsinfo *nsinfo__get(struct nsinfo *nsi);
+void nsinfo__put(struct nsinfo *nsi);
+
+void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc);
+void nsinfo__mountns_exit(struct nscookie *nc);
+
+char *nsinfo__realpath(const char *path, struct nsinfo *nsi);
+
+static inline void __nsinfo__zput(struct nsinfo **nsip)
+{
+        if (nsip) {
+                nsinfo__put(*nsip);
+                *nsip = NULL;
+        }
+}
+
+#define nsinfo__zput(nsi) __nsinfo__zput(&nsi)
+
 #endif  /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 4de398cfb577..8e09fd2d842f 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/list.h>
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index e11468a9a6e4..96e5292d88e2 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ORDERED_EVENTS_H
 #define __ORDERED_EVENTS_H
 
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 38fd11504015..bd779d9f4d1e 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
@@ -28,6 +29,7 @@ static const struct branch_mode branch_modes[] = {
         BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
         BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
         BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
+        BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
         BRANCH_END
 };
 
diff --git a/tools/perf/util/parse-branch-options.h b/tools/perf/util/parse-branch-options.h
index 6086fd90eb23..11d1722733f2 100644
--- a/tools/perf/util/parse-branch-options.h
+++ b/tools/perf/util/parse-branch-options.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_PARSE_BRANCH_OPTIONS_H
 #define _PERF_PARSE_BRANCH_OPTIONS_H 1
 #include <stdint.h>
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 01e779b91c8e..a7fcd95961ef 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/hw_breakpoint.h>
 #include <linux/err.h>
 #include <dirent.h>
@@ -28,13 +29,14 @@
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
+#include "metricgroup.h"
 
 #define MAX_NAME_LEN 100
 
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-int parse_events_parse(void *data, void *scanner);
+int parse_events_parse(void *parse_state, void *scanner);
 static int get_config_terms(struct list_head *head_config,
                             struct list_head *head_terms __maybe_unused);
 
@@ -309,10 +311,11 @@ static char *get_config_name(struct list_head *head_terms)
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
             struct perf_event_attr *attr,
-            char *name, struct cpu_map *cpus,
-            struct list_head *config_terms)
+            char *name, struct perf_pmu *pmu,
+            struct list_head *config_terms, bool auto_merge_stats)
 {
         struct perf_evsel *evsel;
+        struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
         event_attr_init(attr);
 
@@ -323,7 +326,8 @@ __add_event(struct list_head *list, int *idx,
         (*idx)++;
         evsel->cpus        = cpu_map__get(cpus);
         evsel->own_cpus    = cpu_map__get(cpus);
-        evsel->system_wide = !!cpus;
+        evsel->system_wide = pmu ? pmu->is_uncore : false;
+        evsel->auto_merge_stats = auto_merge_stats;
 
         if (name)
                 evsel->name = strdup(name);
@@ -339,7 +343,7 @@ static int add_event(struct list_head *list, int *idx,
                      struct perf_event_attr *attr, char *name,
                      struct list_head *config_terms)
 {
-        return __add_event(list, idx, attr, name, NULL, config_terms) ? 0 : -ENOMEM;
+        return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -589,7 +593,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 }
 
 struct __add_bpf_event_param {
-        struct parse_events_evlist *data;
+        struct parse_events_state *parse_state;
         struct list_head *list;
         struct list_head *head_config;
 };
@@ -599,7 +603,7 @@ static int add_bpf_event(const char *group, const char *event, int fd,
 {
         LIST_HEAD(new_evsels);
         struct __add_bpf_event_param *param = _param;
-        struct parse_events_evlist *evlist = param->data;
+        struct parse_events_state *parse_state = param->parse_state;
         struct list_head *list = param->list;
         struct perf_evsel *pos;
         int err;
@@ -607,8 +611,8 @@ static int add_bpf_event(const char *group, const char *event, int fd,
         pr_debug("add bpf event %s:%s and attach bpf program %d\n",
                  group, event, fd);
 
-        err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group,
-                                          event, evlist->error,
+        err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group,
+                                          event, parse_state->error,
                                           param->head_config);
         if (err) {
                 struct perf_evsel *evsel, *tmp;
@@ -632,14 +636,14 @@ static int add_bpf_event(const char *group, const char *event, int fd,
         return 0;
 }
 
-int parse_events_load_bpf_obj(struct parse_events_evlist *data,
+int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
                               struct list_head *list,
                               struct bpf_object *obj,
                               struct list_head *head_config)
 {
         int err;
         char errbuf[BUFSIZ];
-        struct __add_bpf_event_param param = {data, list, head_config};
+        struct __add_bpf_event_param param = {parse_state, list, head_config};
         static bool registered_unprobe_atexit = false;
 
         if (IS_ERR(obj) || !obj) {
@@ -680,13 +684,13 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 
         return 0;
 errout:
-        data->error->help = strdup("(add -v to see detail)");
-        data->error->str = strdup(errbuf);
+        parse_state->error->help = strdup("(add -v to see detail)");
+        parse_state->error->str = strdup(errbuf);
         return err;
 }
 
 static int
-parse_events_config_bpf(struct parse_events_evlist *data,
+parse_events_config_bpf(struct parse_events_state *parse_state,
                         struct bpf_object *obj,
                         struct list_head *head_config)
 {
@@ -705,28 +709,28 @@ parse_events_config_bpf(struct parse_events_evlist *data,
                                  "Invalid config term for BPF object");
                         errbuf[BUFSIZ - 1] = '\0';
 
-                        data->error->idx = term->err_term;
-                        data->error->str = strdup(errbuf);
+                        parse_state->error->idx = term->err_term;
+                        parse_state->error->str = strdup(errbuf);
                         return -EINVAL;
                 }
 
-                err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+                err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos);
                 if (err) {
-                        bpf__strerror_config_obj(obj, term, data->evlist,
+                        bpf__strerror_config_obj(obj, term, parse_state->evlist,
                                                  &error_pos, err, errbuf,
                                                  sizeof(errbuf));
-                        data->error->help = strdup(
+                        parse_state->error->help = strdup(
 "Hint:\tValid config terms:\n"
 "     \tmap:[<arraymap>].value<indices>=[value]\n"
 "     \tmap:[<eventmap>].event<indices>=[event]\n"
 "\n"
 "     \twhere <indices> is something like [0,3...5] or [all]\n"
 "     \t(add -v to see detail)");
-                        data->error->str = strdup(errbuf);
+                        parse_state->error->str = strdup(errbuf);
                         if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
-                                data->error->idx = term->err_val;
+                                parse_state->error->idx = term->err_val;
                         else
-                                data->error->idx = term->err_term + error_pos;
+                                parse_state->error->idx = term->err_term + error_pos;
                         return err;
                 }
         }
@@ -762,7 +766,7 @@ split_bpf_config_terms(struct list_head *evt_head_config,
                         list_move_tail(&term->list, obj_head_config);
 }
 
-int parse_events_load_bpf(struct parse_events_evlist *data,
+int parse_events_load_bpf(struct parse_events_state *parse_state,
                           struct list_head *list,
                           char *bpf_file_name,
                           bool source,
@@ -790,15 +794,15 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
                                                    -err, errbuf,
                                                    sizeof(errbuf));
 
-                data->error->help = strdup("(add -v to see detail)");
-                data->error->str = strdup(errbuf);
+                parse_state->error->help = strdup("(add -v to see detail)");
+                parse_state->error->str = strdup(errbuf);
                 return err;
         }
 
-        err = parse_events_load_bpf_obj(data, list, obj, head_config);
+        err = parse_events_load_bpf_obj(parse_state, list, obj, head_config);
         if (err)
                 return err;
-        err = parse_events_config_bpf(data, obj, &obj_head_config);
+        err = parse_events_config_bpf(parse_state, obj, &obj_head_config);
 
         /*
          * Caller doesn't know anything about obj_head_config,
@@ -1184,7 +1188,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
                                             err, head_config);
 }
 
-int parse_events_add_numeric(struct parse_events_evlist *data,
+int parse_events_add_numeric(struct parse_events_state *parse_state,
                              struct list_head *list,
                              u32 type, u64 config,
                              struct list_head *head_config)
@@ -1197,7 +1201,7 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
         attr.config = config;
 
         if (head_config) {
-                if (config_attr(&attr, head_config, data->error,
+                if (config_attr(&attr, head_config, parse_state->error,
                                 config_term_common))
                         return -EINVAL;
 
@@ -1205,23 +1209,29 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
                         return -ENOMEM;
         }
 
-        return add_event(list, &data->idx, &attr,
+        return add_event(list, &parse_state->idx, &attr,
                          get_config_name(head_config), &config_terms);
 }
 
-int parse_events_add_pmu(struct parse_events_evlist *data,
+static int __parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
-                         struct list_head *head_config)
+                         struct list_head *head_config, bool auto_merge_stats)
 {
         struct perf_event_attr attr;
         struct perf_pmu_info info;
         struct perf_pmu *pmu;
         struct perf_evsel *evsel;
+        struct parse_events_error *err = parse_state->error;
         LIST_HEAD(config_terms);
 
         pmu = perf_pmu__find(name);
-        if (!pmu)
+        if (!pmu) {
+                if (asprintf(&err->str,
+                                "Cannot find PMU `%s'. Missing kernel support?",
+                                name) < 0)
+                        err->str = NULL;
                 return -EINVAL;
+        }
 
         if (pmu->default_config) {
                 memcpy(&attr, pmu->default_config,
@@ -1232,7 +1242,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 
         if (!head_config) {
                 attr.type = pmu->type;
-                evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus, NULL);
+                evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
                 return evsel ? 0 : -ENOMEM;
         }
 
@@ -1243,18 +1253,18 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
          * Configure hardcoded terms first, no need to check
          * return value when called with fail == 0 ;)
          */
-        if (config_attr(&attr, head_config, data->error, config_term_pmu))
+        if (config_attr(&attr, head_config, parse_state->error, config_term_pmu))
                 return -EINVAL;
 
         if (get_config_terms(head_config, &config_terms))
                 return -ENOMEM;
 
-        if (perf_pmu__config(pmu, &attr, head_config, data->error))
+        if (perf_pmu__config(pmu, &attr, head_config, parse_state->error))
                 return -EINVAL;
 
-        evsel = __add_event(list, &data->idx, &attr,
-                            get_config_name(head_config), pmu->cpus,
-                            &config_terms);
+        evsel = __add_event(list, &parse_state->idx, &attr,
+                            get_config_name(head_config), pmu,
+                            &config_terms, auto_merge_stats);
         if (evsel) {
                 evsel->unit = info.unit;
                 evsel->scale = info.scale;
@@ -1267,7 +1277,14 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
         return evsel ? 0 : -ENOMEM;
 }
 
-int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
+                         struct list_head *list, char *name,
+                         struct list_head *head_config)
+{
+        return __parse_events_add_pmu(parse_state, list, name, head_config, false);
+}
+
+int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                char *str, struct list_head **listp)
 {
         struct list_head *head;
@@ -1296,8 +1313,8 @@ int parse_events_multi_pmu_add(struct parse_events_evlist *data,
                                         return -1;
                                 list_add_tail(&term->list, head);
 
-                                if (!parse_events_add_pmu(data, list,
-                                                  pmu->name, head)) {
+                                if (!__parse_events_add_pmu(parse_state, list,
+                                                            pmu->name, head, true)) {
                                         pr_debug("%s -> %s/%s/\n", str,
                                                  pmu->name, alias->str);
                                         ok++;
@@ -1358,6 +1375,7 @@ struct event_modifier {
         int exclude_GH;
         int sample_read;
         int pinned;
+        int weak;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1376,6 +1394,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 
         int exclude = eu | ek | eh;
         int exclude_GH = evsel ? evsel->exclude_GH : 0;
+        int weak = 0;
 
         memset(mod, 0, sizeof(*mod));
 
@@ -1413,6 +1432,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
                         sample_read = 1;
                 } else if (*str == 'D') {
                         pinned = 1;
+                } else if (*str == 'W') {
+                        weak = 1;
                 } else
                         break;
 
@@ -1443,6 +1464,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
         mod->exclude_GH = exclude_GH;
         mod->sample_read = sample_read;
         mod->pinned = pinned;
+        mod->weak = weak;
 
         return 0;
 }
@@ -1456,7 +1478,7 @@ static int check_modifier(char *str)
         char *p = str;
 
         /* The sizeof includes 0 byte as well. */
-        if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1))
+        if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1))
                 return -1;
 
         while (*p) {
@@ -1496,6 +1518,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
                 evsel->exclude_GH          = mod.exclude_GH;
                 evsel->sample_read         = mod.sample_read;
                 evsel->precise_max         = mod.precise_max;
+                evsel->weak_group          = mod.weak;
 
                 if (perf_evsel__is_group_leader(evsel))
                         evsel->attr.pinned = mod.pinned;
@@ -1628,7 +1651,7 @@ perf_pmu__parse_check(const char *name)
         return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
-static int parse_events__scanner(const char *str, void *data, int start_token)
+static int parse_events__scanner(const char *str, void *parse_state, int start_token)
 {
         YY_BUFFER_STATE buffer;
         void *scanner;
@@ -1643,7 +1666,7 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
 #ifdef PARSER_DEBUG
         parse_events_debug = 1;
 #endif
-        ret = parse_events_parse(data, scanner);
+        ret = parse_events_parse(parse_state, scanner);
 
         parse_events__flush_buffer(buffer, scanner);
         parse_events__delete_buffer(buffer, scanner);
@@ -1656,45 +1679,45 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
  */
 int parse_events_terms(struct list_head *terms, const char *str)
 {
-        struct parse_events_terms data = {
+        struct parse_events_state parse_state = {
                 .terms = NULL,
         };
         int ret;
 
-        ret = parse_events__scanner(str, &data, PE_START_TERMS);
+        ret = parse_events__scanner(str, &parse_state, PE_START_TERMS);
         if (!ret) {
-                list_splice(data.terms, terms);
-                zfree(&data.terms);
+                list_splice(parse_state.terms, terms);
+                zfree(&parse_state.terms);
                 return 0;
         }
 
-        parse_events_terms__delete(data.terms);
+        parse_events_terms__delete(parse_state.terms);
         return ret;
 }
 
 int parse_events(struct perf_evlist *evlist, const char *str,
                  struct parse_events_error *err)
 {
-        struct parse_events_evlist data = {
-                .list   = LIST_HEAD_INIT(data.list),
+        struct parse_events_state parse_state = {
+                .list   = LIST_HEAD_INIT(parse_state.list),
                 .idx    = evlist->nr_entries,
                 .error  = err,
                 .evlist = evlist,
         };
         int ret;
 
-        ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+        ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS);
         perf_pmu__parse_cleanup();
         if (!ret) {
                 struct perf_evsel *last;
 
-                if (list_empty(&data.list)) {
+                if (list_empty(&parse_state.list)) {
                         WARN_ONCE(true, "WARNING: event parser found nothing");
                         return -1;
                 }
 
-                perf_evlist__splice_list_tail(evlist, &data.list);
-                evlist->nr_groups += data.nr_groups;
+                perf_evlist__splice_list_tail(evlist, &parse_state.list);
+                evlist->nr_groups += parse_state.nr_groups;
                 last = perf_evlist__last(evlist);
                 last->cmdline_group_boundary = true;
 
@@ -1718,8 +1741,8 @@ static int get_term_width(void)
         return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
 }
 
-static void parse_events_print_error(struct parse_events_error *err,
-                                     const char *event)
+void parse_events_print_error(struct parse_events_error *err,
+                              const char *event)
 {
         const char *str = "invalid or unsupported event: ";
         char _buf[MAX_WIDTH];
@@ -1774,8 +1797,6 @@ static void parse_events_print_error(struct parse_events_error *err,
                 zfree(&err->str);
                 zfree(&err->help);
         }
-
-        fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 }
 
 #undef MAX_WIDTH
@@ -1787,8 +1808,10 @@ int parse_events_option(const struct option *opt, const char *str,
         struct parse_events_error err = { .idx = 0, };
         int ret = parse_events(evlist, str, &err);
 
-        if (ret)
+        if (ret) {
                 parse_events_print_error(&err, str);
+                fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+        }
 
         return ret;
 }
@@ -2124,7 +2147,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
                 return;
         }
         strlist__for_each_entry(nd, bidlist) {
-                pcache = probe_cache__new(nd->s);
+                pcache = probe_cache__new(nd->s, NULL);
                 if (!pcache)
                         continue;
                 list_for_each_entry(ent, &pcache->entries, node) {
@@ -2366,6 +2389,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
         print_tracepoint_events(NULL, NULL, name_only);
 
         print_sdt_events(NULL, NULL, name_only);
+
+        metricgroup__print(true, true, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
@@ -2520,10 +2545,10 @@ void parse_events__clear_array(struct parse_events_array *a)
         zfree(&a->ranges);
 }
 
-void parse_events_evlist_error(struct parse_events_evlist *data,
+void parse_events_evlist_error(struct parse_events_state *parse_state,
                                int idx, const char *str)
 {
-        struct parse_events_error *err = data->error;
+        struct parse_events_error *err = parse_state->error;
 
         if (!err)
                 return;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index a235f4d6d5e5..be337c266697 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_PARSE_EVENTS_H
 #define __PERF_PARSE_EVENTS_H
 /*
@@ -108,16 +109,13 @@ struct parse_events_error {
         char *help;     /* optional help string */
 };
 
-struct parse_events_evlist {
+struct parse_events_state {
         struct list_head           list;
         int                        idx;
         int                        nr_groups;
         struct parse_events_error *error;
         struct perf_evlist        *evlist;
-};
-
-struct parse_events_terms {
-        struct list_head *terms;
+        struct list_head          *terms;
 };
 
 void parse_events__shrink_config_terms(void);
@@ -143,18 +141,18 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
                                 const char *sys, const char *event,
                                 struct parse_events_error *error,
                                 struct list_head *head_config);
-int parse_events_load_bpf(struct parse_events_evlist *data,
+int parse_events_load_bpf(struct parse_events_state *parse_state,
                           struct list_head *list,
                           char *bpf_file_name,
                           bool source,
                           struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
-int parse_events_load_bpf_obj(struct parse_events_evlist *data,
+int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
                               struct list_head *list,
                               struct bpf_object *obj,
                               struct list_head *head_config);
-int parse_events_add_numeric(struct parse_events_evlist *data,
+int parse_events_add_numeric(struct parse_events_state *parse_state,
                              struct list_head *list,
                              u32 type, u64 config,
                              struct list_head *head_config);
@@ -164,11 +162,11 @@ int parse_events_add_cache(struct list_head *list, int *idx,
                            struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct parse_events_evlist *data,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
                          struct list_head *head_config);
 
-int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                char *str,
                                struct list_head **listp);
 
@@ -180,7 +178,7 @@ perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
                                struct list_head *list_all);
-void parse_events_evlist_error(struct parse_events_evlist *data,
+void parse_events_evlist_error(struct parse_events_state *parse_state,
                                int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only, bool quiet,
@@ -205,6 +203,9 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+void parse_events_print_error(struct parse_events_error *err,
+                              const char *event);
+
 #ifdef HAVE_LIBELF_SUPPORT
 /*
  * If the probe point starts with '%',
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 660fca05bc93..655ecff636a8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -5,9 +5,13 @@
 %option stack
 %option bison-locations
 %option yylineno
+%option reject
 
 %{
 #include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -53,6 +57,31 @@ static int str(yyscan_t scanner, int token)
         return token;
 }
 
+static bool isbpf_suffix(char *text)
+{
+        int len = strlen(text);
+
+        if (len < 2)
+                return false;
+        if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
+            text[len - 2] == '.')
+                return true;
+        if (len > 4 && !strcmp(text + len - 4, ".obj"))
+                return true;
+        return false;
+}
+
+static bool isbpf(yyscan_t scanner)
+{
+        char *text = parse_events_get_text(scanner);
+        struct stat st;
+
+        if (!isbpf_suffix(text))
+                return false;
+
+        return stat(text, &st) == 0;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
@@ -126,6 +155,10 @@ do {							\
         yycolumn += yyleng;                             \
 } while (0);
 
+#define USER_REJECT             \
+        yycolumn -= yyleng;     \
+        REJECT
+
 %}
 
 %x mem
@@ -136,8 +169,8 @@ do {							\
 group           [^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu       [^,{}/]+[/][^/]*[/][^,{}/]*
 event           [^,{}/]+
-bpf_object      [^,{}]+\.(o|bpf)
-bpf_source      [^,{}]+\.c
+bpf_object      [^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
+bpf_source      [^,{}]+\.c[a-zA-Z0-9._]*
 
 num_dec         [0-9]+
 num_hex         0x[a-fA-F0-9]+
@@ -146,7 +179,7 @@ name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
 name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term    [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
-modifier_event  [ukhpPGHSDI]+
+modifier_event  [ukhpPGHSDIW]+
 modifier_bp     [rwx]{1,3}
 
 %%
@@ -273,6 +306,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy                                           { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time                                   { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 bpf-output                                      { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
         /*
@@ -307,8 +341,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}               { return value(yyscanner, 16); }
 
 {modifier_event}        { return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}            { return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}            { return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}            { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}            { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
 {name}                  { return pmu_str_check(yyscanner); }
 "/"                     { BEGIN(config); return '/'; }
 -                       { return '-'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 04fd8c9af9f9..e81a20ea8d7d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -1,5 +1,5 @@
 %pure-parser
-%parse-param {void *_data}
+%parse-param {void *_parse_state}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
 %locations
@@ -17,7 +17,7 @@
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
-void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg);
+void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg);
 
 #define ABORT_ON(val) \
 do { \
@@ -33,11 +33,11 @@ do { \
 } while (0)
 
 static void inc_group_count(struct list_head *list,
-                       struct parse_events_evlist *data)
+                       struct parse_events_state *parse_state)
 {
         /* Count groups only have more than 1 members */
         if (!list_is_last(list->next, list))
-                data->nr_groups++;
+                parse_state->nr_groups++;
 }
 
 %}
@@ -115,9 +115,9 @@ PE_START_TERMS  start_terms
 
 start_events: groups
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
 
-        parse_events_update_lists($1, &data->list);
+        parse_events_update_lists($1, &parse_state->list);
 }
 
 groups:
@@ -159,7 +159,7 @@ PE_NAME '{' events '}'
 {
         struct list_head *list = $3;
 
-        inc_group_count(list, _data);
+        inc_group_count(list, _parse_state);
         parse_events__set_leader($1, list);
         $$ = list;
 }
@@ -168,7 +168,7 @@ PE_NAME '{' events '}'
 {
         struct list_head *list = $2;
 
-        inc_group_count(list, _data);
+        inc_group_count(list, _parse_state);
         parse_events__set_leader(NULL, list);
         $$ = list;
 }
@@ -225,14 +225,13 @@ event_def: event_pmu |
 event_pmu:
 PE_NAME opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list, *orig_terms, *terms;
 
         if (parse_events_copy_term_list($2, &orig_terms))
                 YYABORT;
 
         ALLOC_LIST(list);
-        if (parse_events_add_pmu(data, list, $1, $2)) {
+        if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
                 struct perf_pmu *pmu = NULL;
                 int ok = 0;
 
@@ -245,7 +244,7 @@ PE_NAME opt_event_config
                         if (!strncmp($1, name, strlen($1))) {
                                 if (parse_events_copy_term_list(orig_terms, &terms))
                                         YYABORT;
-                                if (!parse_events_add_pmu(data, list, pmu->name, terms))
+                                if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
                                         ok++;
                                 parse_events_terms__delete(terms);
                         }
@@ -262,7 +261,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 {
         struct list_head *list;
 
-        if (parse_events_multi_pmu_add(_data, $1, &list) < 0)
+        if (parse_events_multi_pmu_add(_parse_state, $1, &list) < 0)
                 YYABORT;
         $$ = list;
 }
@@ -273,7 +272,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
         char pmu_name[128];
 
         snprintf(&pmu_name, 128, "%s-%s", $1, $3);
-        if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0)
+        if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0)
                 YYABORT;
         $$ = list;
 }
@@ -286,62 +285,60 @@ PE_VALUE_SYM_SW
 event_legacy_symbol:
 value_sym '/' event_config '/'
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
         int type = $1 >> 16;
         int config = $1 & 255;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, $3));
         parse_events_terms__delete($3);
         $$ = list;
 }
 |
 value_sym sep_slash_dc
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
         int type = $1 >> 16;
         int config = $1 & 255;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL));
         $$ = list;
 }
 
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+        ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6));
         parse_events_terms__delete($6);
         $$ = list;
 }
 |
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+        ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4));
         parse_events_terms__delete($4);
         $$ = list;
 }
 |
 PE_NAME_CACHE_TYPE opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+        ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
@@ -349,44 +346,44 @@ PE_NAME_CACHE_TYPE opt_event_config
 event_legacy_mem:
 PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, $6, $4));
         $$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, NULL, $4));
         $$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, $4, 0));
         $$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, NULL, 0));
         $$ = list;
 }
@@ -394,15 +391,15 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 event_legacy_tracepoint:
 tracepoint_name opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
         if (error)
                 error->idx = @1.first_column;
 
-        if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
+        if (parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event,
                                         error, $2))
                 return -1;
 
@@ -432,11 +429,10 @@ PE_NAME ':' PE_NAME
 event_legacy_numeric:
 PE_VALUE ':' PE_VALUE opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4));
         parse_events_terms__delete($4);
         $$ = list;
 }
@@ -444,11 +440,10 @@ PE_VALUE ':' PE_VALUE opt_event_config
 event_legacy_raw:
 PE_RAW opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
@@ -456,23 +451,22 @@ PE_RAW opt_event_config
 event_bpf_file:
 PE_BPF_OBJECT opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+        ABORT_ON(parse_events_load_bpf(parse_state, list, $1, false, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
 |
 PE_BPF_SOURCE opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+        ABORT_ON(parse_events_load_bpf(_parse_state, list, $1, true, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
@@ -494,8 +488,8 @@ opt_event_config:
 
 start_terms: event_config
 {
-        struct parse_events_terms *data = _data;
-        data->terms = $1;
+        struct parse_events_state *parse_state = _parse_state;
+        parse_state->terms = $1;
 }
 
 event_config:
@@ -685,9 +679,9 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(YYLTYPE *loc, void *data,
+void parse_events_error(YYLTYPE *loc, void *parse_state,
                         void *scanner __maybe_unused,
                         char const *msg __maybe_unused)
 {
-        parse_events_evlist_error(data, loc->last_column, "parser error");
+        parse_events_evlist_error(parse_state, loc->last_column, "parser error");
 }
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index 646ecf736aad..e6599e290f46 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
diff --git a/tools/perf/util/parse-regs-options.h b/tools/perf/util/parse-regs-options.h
index 7d762b188007..cdefb1acf6be 100644
--- a/tools/perf/util/parse-regs-options.h
+++ b/tools/perf/util/parse-regs-options.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_PARSE_REGS_OPTIONS_H
 #define _PERF_PARSE_REGS_OPTIONS_H 1
 struct option;
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 50ec3bc87a60..933f5c6bffb4 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * I'm tired of doing "vsnprintf()" etc just to open a
  * file, so here's a "return static buffer with printf"
diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h
index 9a276a58e3c2..14a254ada7eb 100644
--- a/tools/perf/util/path.h
+++ b/tools/perf/util/path.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_PATH_H
 #define _PERF_PATH_H
 
diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c
index d55092964da2..4f3aa8d99ef4 100644
--- a/tools/perf/util/perf-hooks.c
+++ b/tools/perf/util/perf-hooks.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * perf_hooks.c
  *
diff --git a/tools/perf/util/perf-hooks.h b/tools/perf/util/perf-hooks.h
index 838d5797bc1e..27fbec62d4fe 100644
--- a/tools/perf/util/perf-hooks.h
+++ b/tools/perf/util/perf-hooks.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_UTIL_PERF_HOOKS_H
 #define PERF_UTIL_PERF_HOOKS_H
 
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index b2ae039eff85..2acfcc527cac 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include "perf_regs.h"
 #include "event.h"
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 32b37d19dcc3..c9319f8d17a6 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_REGS_H
 #define __PERF_REGS_H
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ac16a9db1fb5..07cb2ac041d7 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,7 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/list.h>
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -470,17 +472,36 @@ static void pmu_read_sysfs(void)
         closedir(dir);
 }
 
+static struct cpu_map *__pmu_cpumask(const char *path)
+{
+        FILE *file;
+        struct cpu_map *cpus;
+
+        file = fopen(path, "r");
+        if (!file)
+                return NULL;
+
+        cpus = cpu_map__read(file);
+        fclose(file);
+        return cpus;
+}
+
+/*
+ * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
+ * may have a "cpus" file.
+ */
+#define CPUS_TEMPLATE_UNCORE    "%s/bus/event_source/devices/%s/cpumask"
+#define CPUS_TEMPLATE_CPU       "%s/bus/event_source/devices/%s/cpus"
+
 static struct cpu_map *pmu_cpumask(const char *name)
 {
-        struct stat st;
         char path[PATH_MAX];
-        FILE *file;
         struct cpu_map *cpus;
         const char *sysfs = sysfs__mountpoint();
         const char *templates[] = {
-                 "%s/bus/event_source/devices/%s/cpumask",
-                 "%s/bus/event_source/devices/%s/cpus",
-                 NULL
+                CPUS_TEMPLATE_UNCORE,
+                CPUS_TEMPLATE_CPU,
+                NULL
         };
         const char **template;
 
@@ -489,20 +510,25 @@ static struct cpu_map *pmu_cpumask(const char *name)
 
         for (template = templates; *template; template++) {
                 snprintf(path, PATH_MAX, *template, sysfs, name);
-                if (stat(path, &st) == 0)
-                        break;
+                cpus = __pmu_cpumask(path);
+                if (cpus)
+                        return cpus;
         }
 
-        if (!*template)
-                return NULL;
+        return NULL;
+}
 
-        file = fopen(path, "r");
-        if (!file)
-                return NULL;
+static bool pmu_is_uncore(const char *name)
+{
+        char path[PATH_MAX];
+        struct cpu_map *cpus;
+        const char *sysfs = sysfs__mountpoint();
 
-        cpus = cpu_map__read(file);
-        fclose(file);
-        return cpus;
+        snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
+        cpus = __pmu_cpumask(path);
+        cpu_map__put(cpus);
+
+        return !!cpus;
 }
 
 /*
@@ -516,16 +542,8 @@ char * __weak get_cpuid_str(void)
         return NULL;
 }
 
-/*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
- */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static char *perf_pmu__getcpuid(void)
 {
-        int i;
-        struct pmu_events_map *map;
-        struct pmu_event *pe;
         char *cpuid;
         static bool printed;
 
@@ -535,22 +553,50 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
         if (!cpuid)
                 cpuid = get_cpuid_str();
         if (!cpuid)
-                return;
+                return NULL;
 
         if (!printed) {
                 pr_debug("Using CPUID %s\n", cpuid);
                 printed = true;
         }
+        return cpuid;
+}
+
+struct pmu_events_map *perf_pmu__find_map(void)
+{
+        struct pmu_events_map *map;
+        char *cpuid = perf_pmu__getcpuid();
+        int i;
 
         i = 0;
-        while (1) {
+        for (;;) {
                 map = &pmu_events_map[i++];
-                if (!map->table)
-                        goto out;
+                if (!map->table) {
+                        map = NULL;
+                        break;
+                }
 
                 if (!strcmp(map->cpuid, cpuid))
                         break;
         }
+        free(cpuid);
+        return map;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+{
+        int i;
+        struct pmu_events_map *map;
+        struct pmu_event *pe;
+
+        map = perf_pmu__find_map();
+        if (!map)
+                return;
 
         /*
          * Found a matching PMU events table. Create aliases
@@ -560,8 +606,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
                 const char *pname;
 
                 pe = &map->table[i++];
-                if (!pe->name)
+                if (!pe->name) {
+                        if (pe->metric_group || pe->metric_name)
+                                continue;
                         break;
+                }
 
                 pname = pe->pmu ? pe->pmu : "cpu";
                 if (strncmp(pname, name, strlen(pname)))
@@ -575,9 +624,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
                                 (char *)pe->metric_expr,
                                 (char *)pe->metric_name);
         }
-
-out:
-        free(cpuid);
 }
 
 struct perf_event_attr * __weak
@@ -617,6 +663,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
 
         pmu->cpus = pmu_cpumask(name);
 
+        pmu->is_uncore = pmu_is_uncore(name);
+
         INIT_LIST_HEAD(&pmu->format);
         INIT_LIST_HEAD(&pmu->aliases);
         list_splice(&format, &pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 389e9729331f..27c75e635866 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PMU_H
 #define __PMU_H
 
@@ -22,6 +23,7 @@ struct perf_pmu {
         char *name;
         __u32 type;
         bool selectable;
+        bool is_uncore;
         struct perf_event_attr *default_config;
         struct cpu_map *cpus;
         struct list_head format;  /* HEAD struct perf_pmu_format -> list */
@@ -90,4 +92,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
+struct pmu_events_map *perf_pmu__find_map(void);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c
index e908177b9976..23e367063446 100644
--- a/tools/perf/util/print_binary.c
+++ b/tools/perf/util/print_binary.c
@@ -1,41 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "print_binary.h"
 #include <linux/log2.h>
 #include "sane_ctype.h"
 
-void print_binary(unsigned char *data, size_t len,
-                  size_t bytes_per_line, print_binary_t printer,
-                  void *extra)
+int binary__fprintf(unsigned char *data, size_t len,
+                    size_t bytes_per_line, binary__fprintf_t printer,
+                    void *extra, FILE *fp)
 {
         size_t i, j, mask;
+        int printed = 0;
 
         if (!printer)
-                return;
+                return 0;
 
         bytes_per_line = roundup_pow_of_two(bytes_per_line);
         mask = bytes_per_line - 1;
 
-        printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+        printed += printer(BINARY_PRINT_DATA_BEGIN, 0, extra, fp);
         for (i = 0; i < len; i++) {
                 if ((i & mask) == 0) {
-                        printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
-                        printer(BINARY_PRINT_ADDR, i, extra);
+                        printed += printer(BINARY_PRINT_LINE_BEGIN, -1, extra, fp);
+                        printed += printer(BINARY_PRINT_ADDR, i, extra, fp);
                 }
 
-                printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+                printed += printer(BINARY_PRINT_NUM_DATA, data[i], extra, fp);
 
                 if (((i & mask) == mask) || i == len - 1) {
                         for (j = 0; j < mask-(i & mask); j++)
-                                printer(BINARY_PRINT_NUM_PAD, -1, extra);
+                                printed += printer(BINARY_PRINT_NUM_PAD, -1, extra, fp);
 
-                        printer(BINARY_PRINT_SEP, i, extra);
+                        printer(BINARY_PRINT_SEP, i, extra, fp);
                         for (j = i & ~mask; j <= i; j++)
-                                printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+                                printed += printer(BINARY_PRINT_CHAR_DATA, data[j], extra, fp);
                         for (j = 0; j < mask-(i & mask); j++)
-                                printer(BINARY_PRINT_CHAR_PAD, i, extra);
-                        printer(BINARY_PRINT_LINE_END, -1, extra);
+                                printed += printer(BINARY_PRINT_CHAR_PAD, i, extra, fp);
+                        printed += printer(BINARY_PRINT_LINE_END, -1, extra, fp);
                 }
         }
-        printer(BINARY_PRINT_DATA_END, -1, extra);
+        printed += printer(BINARY_PRINT_DATA_END, -1, extra, fp);
+        return printed;
 }
 
 int is_printable_array(char *p, unsigned int len)
diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h
index da0427263d2d..2a1554afc957 100644
--- a/tools/perf/util/print_binary.h
+++ b/tools/perf/util/print_binary.h
@@ -1,7 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_PRINT_BINARY_H
 #define PERF_PRINT_BINARY_H
 
 #include <stddef.h>
+#include <stdio.h>
 
 enum binary_printer_ops {
         BINARY_PRINT_DATA_BEGIN,
@@ -16,12 +18,19 @@ enum binary_printer_ops {
         BINARY_PRINT_DATA_END,
 };
 
-typedef void (*print_binary_t)(enum binary_printer_ops op,
-                               unsigned int val, void *extra);
+typedef int (*binary__fprintf_t)(enum binary_printer_ops op,
+                                 unsigned int val, void *extra, FILE *fp);
 
-void print_binary(unsigned char *data, size_t len,
-                  size_t bytes_per_line, print_binary_t printer,
-                  void *extra);
+int binary__fprintf(unsigned char *data, size_t len,
+                    size_t bytes_per_line, binary__fprintf_t printer,
+                    void *extra, FILE *fp);
+
+static inline void print_binary(unsigned char *data, size_t len,
+                                size_t bytes_per_line, binary__fprintf_t printer,
+                                void *extra)
+{
+        binary__fprintf(data, len, bytes_per_line, printer, extra, stdout);
+}
 
 int is_printable_array(char *p, unsigned int len);
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a2670e9d652d..b7aaf9b2294d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -184,13 +184,19 @@ static struct map *kernel_get_module_map(const char *module)
         return NULL;
 }
 
-struct map *get_target_map(const char *target, bool user)
+struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
 {
         /* Init maps of given executable or kernel */
-        if (user)
-                return dso__new_map(target);
-        else
+        if (user) {
+                struct map *map;
+
+                map = dso__new_map(target);
+                if (map && map->dso)
+                        map->dso->nsinfo = nsinfo__get(nsi);
+                return map;
+        } else {
                 return kernel_get_module_map(target);
+        }
 }
 
 static int convert_exec_to_group(const char *exec, char **result)
@@ -366,7 +372,8 @@ found:
 static int find_alternative_probe_point(struct debuginfo *dinfo,
                                         struct perf_probe_point *pp,
                                         struct perf_probe_point *result,
-                                        const char *target, bool uprobes)
+                                        const char *target, struct nsinfo *nsi,
+                                        bool uprobes)
 {
         struct map *map = NULL;
         struct symbol *sym;
@@ -377,7 +384,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
         if (!pp->function || pp->file)
                 return -ENOTSUP;
 
-        map = get_target_map(target, uprobes);
+        map = get_target_map(target, nsi, uprobes);
         if (!map)
                 return -EINVAL;
 
@@ -421,8 +428,8 @@ static int get_alternative_probe_event(struct debuginfo *dinfo,
 
         memcpy(tmp, &pev->point, sizeof(*tmp));
         memset(&pev->point, 0, sizeof(pev->point));
-        ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
-                                           pev->target, pev->uprobes);
+        ret = find_alternative_probe_point(dinfo, tmp, &pev->point, pev->target,
+                                           pev->nsi, pev->uprobes);
         if (ret < 0)
                 memcpy(&pev->point, tmp, sizeof(*tmp));
 
@@ -444,7 +451,7 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
         if (lr->end != INT_MAX)
                 len = lr->end - lr->start;
         ret = find_alternative_probe_point(dinfo, &pp, &result,
-                                           target, user);
+                                           target, NULL, user);
         if (!ret) {
                 lr->function = result.function;
                 lr->file = result.file;
@@ -457,12 +464,14 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
 }
 
 /* Open new debuginfo of given module */
-static struct debuginfo *open_debuginfo(const char *module, bool silent)
+static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
+                                        bool silent)
 {
         const char *path = module;
         char reason[STRERR_BUFSIZE];
         struct debuginfo *ret = NULL;
         struct dso *dso = NULL;
+        struct nscookie nsc;
         int err;
 
         if (!module || !strchr(module, '/')) {
@@ -480,6 +489,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
                 }
                 path = dso->long_name;
         }
+        nsinfo__mountns_enter(nsi, &nsc);
         ret = debuginfo__new(path);
         if (!ret && !silent) {
                 pr_warning("The %s file has no debug information.\n", path);
@@ -489,6 +499,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
                         pr_warning("Rebuild with -g, ");
                 pr_warning("or install an appropriate debuginfo package.\n");
         }
+        nsinfo__mountns_exit(&nsc);
         return ret;
 }
 
@@ -516,7 +527,7 @@ static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
                 goto out;
         }
 
-        debuginfo_cache = open_debuginfo(module, silent);
+        debuginfo_cache = open_debuginfo(module, NULL, silent);
         if (!debuginfo_cache)
                 zfree(&debuginfo_cache_path);
 out:
@@ -531,14 +542,18 @@ static void debuginfo_cache__exit(void)
 }
 
 
-static int get_text_start_address(const char *exec, unsigned long *address)
+static int get_text_start_address(const char *exec, unsigned long *address,
+                                  struct nsinfo *nsi)
 {
         Elf *elf;
         GElf_Ehdr ehdr;
         GElf_Shdr shdr;
         int fd, ret = -ENOENT;
+        struct nscookie nsc;
 
+        nsinfo__mountns_enter(nsi, &nsc);
         fd = open(exec, O_RDONLY);
+        nsinfo__mountns_exit(&nsc);
         if (fd < 0)
                 return -errno;
 
@@ -582,7 +597,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
                         ret = -EINVAL;
                         goto error;
                 }
-                ret = get_text_start_address(tp->module, &stext);
+                ret = get_text_start_address(tp->module, &stext, NULL);
                 if (ret < 0)
                         goto error;
                 addr += stext;
@@ -659,7 +674,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 
         /* Prepare a map for offline binary */
         map = dso__new_map(pathname);
-        if (!map || get_text_start_address(pathname, &stext) < 0) {
+        if (!map || get_text_start_address(pathname, &stext, NULL) < 0) {
                 pr_warning("Failed to get ELF symbols for %s\n", pathname);
                 return -EINVAL;
         }
@@ -676,7 +691,8 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 }
 
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
-                                          int ntevs, const char *exec)
+                                          int ntevs, const char *exec,
+                                          struct nsinfo *nsi)
 {
         int i, ret = 0;
         unsigned long stext = 0;
@@ -684,7 +700,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
         if (!exec)
                 return 0;
 
-        ret = get_text_start_address(exec, &stext);
+        ret = get_text_start_address(exec, &stext, nsi);
         if (ret < 0)
                 return ret;
 
@@ -715,7 +731,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs,
         if (!module)
                 return 0;
 
-        map = get_target_map(module, false);
+        map = get_target_map(module, NULL, false);
         if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
                 pr_warning("Failed to get ELF symbols for %s\n", module);
                 return -EINVAL;
@@ -802,7 +818,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
         int ret;
 
         if (uprobe)
-                ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
+                ret = add_exec_to_probe_trace_events(tevs, ntevs, module,
+                                                     pev->nsi);
         else if (module)
                 /* Currently ref_reloc_sym based probe is not for drivers */
                 ret = post_process_module_probe_trace_events(tevs, ntevs,
@@ -825,7 +842,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         struct debuginfo *dinfo;
         int ntevs, ret = 0;
 
-        dinfo = open_debuginfo(pev->target, !need_dwarf);
+        dinfo = open_debuginfo(pev->target, pev->nsi, !need_dwarf);
         if (!dinfo) {
                 if (need_dwarf)
                         return -ENOENT;
@@ -945,7 +962,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
         char sbuf[STRERR_BUFSIZE];
 
         /* Search a line range */
-        dinfo = open_debuginfo(module, false);
+        dinfo = open_debuginfo(module, NULL, false);
         if (!dinfo)
                 return -ENOENT;
 
@@ -1021,14 +1038,18 @@ end:
         return ret;
 }
 
-int show_line_range(struct line_range *lr, const char *module, bool user)
+int show_line_range(struct line_range *lr, const char *module,
+                    struct nsinfo *nsi, bool user)
 {
         int ret;
+        struct nscookie nsc;
 
         ret = init_probe_symbol_maps(user);
         if (ret < 0)
                 return ret;
+        nsinfo__mountns_enter(nsi, &nsc);
         ret = __show_line_range(lr, module, user);
+        nsinfo__mountns_exit(&nsc);
         exit_probe_symbol_maps();
 
         return ret;
@@ -1111,7 +1132,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
         if (ret < 0)
                 return ret;
 
-        dinfo = open_debuginfo(pevs->target, false);
+        dinfo = open_debuginfo(pevs->target, pevs->nsi, false);
         if (!dinfo) {
                 ret = -ENOENT;
                 goto out;
@@ -1155,6 +1176,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 int show_line_range(struct line_range *lr __maybe_unused,
                     const char *module __maybe_unused,
+                    struct nsinfo *nsi __maybe_unused,
                     bool user __maybe_unused)
 {
         pr_warning("Debuginfo-analysis is not supported.\n");
@@ -2373,7 +2395,7 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist,
         struct kprobe_blacklist_node *node;
 
         list_for_each_entry(node, blacklist, list) {
-                if (node->start <= address && address <= node->end)
+                if (node->start <= address && address < node->end)
                         return node;
         }
 
@@ -2703,6 +2725,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         struct probe_trace_event *tev = NULL;
         struct probe_cache *cache = NULL;
         struct strlist *namelist[2] = {NULL, NULL};
+        struct nscookie nsc;
 
         up = pev->uprobes ? 1 : 0;
         fd[up] = __open_probe_file_and_namelist(up, &namelist[up]);
@@ -2729,7 +2752,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
                 if (ret < 0)
                         break;
 
+                nsinfo__mountns_enter(pev->nsi, &nsc);
                 ret = probe_file__add_event(fd[up], tev);
+                nsinfo__mountns_exit(&nsc);
                 if (ret < 0)
                         break;
 
@@ -2744,7 +2769,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         if (ret == -EINVAL && pev->uprobes)
                 warn_uprobe_event_compat(tev);
         if (ret == 0 && probe_conf.cache) {
-                cache = probe_cache__new(pev->target);
+                cache = probe_cache__new(pev->target, pev->nsi);
                 if (!cache ||
                     probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 ||
                     probe_cache__commit(cache) < 0)
@@ -2805,7 +2830,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
         int ret, i, j, skipped = 0;
         char *mod_name;
 
-        map = get_target_map(pev->target, pev->uprobes);
+        map = get_target_map(pev->target, pev->nsi, pev->uprobes);
         if (!map) {
                 ret = -EINVAL;
                 goto out;
@@ -3094,7 +3119,7 @@ static int find_cached_events(struct perf_probe_event *pev,
         int ntevs = 0;
         int ret = 0;
 
-        cache = probe_cache__new(target);
+        cache = probe_cache__new(target, pev->nsi);
         /* Return 0 ("not found") if the target has no probe cache. */
         if (!cache)
                 return 0;
@@ -3184,7 +3209,7 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
                 else
                         return find_cached_events(pev, tevs, pev->target);
         }
-        cache = probe_cache__new(pev->target);
+        cache = probe_cache__new(pev->target, pev->nsi);
         if (!cache)
                 return 0;
 
@@ -3345,13 +3370,16 @@ int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
         int i, j;
+        struct perf_probe_event *pev;
 
         /* Loop 3: cleanup and free trace events  */
         for (i = 0; i < npevs; i++) {
+                pev = &pevs[i];
                 for (j = 0; j < pevs[i].ntevs; j++)
                         clear_probe_trace_event(&pevs[i].tevs[j]);
                 zfree(&pevs[i].tevs);
                 pevs[i].ntevs = 0;
+                nsinfo__zput(pev->nsi);
                 clear_perf_probe_event(&pevs[i]);
         }
 }
@@ -3409,8 +3437,8 @@ out:
         return ret;
 }
 
-int show_available_funcs(const char *target, struct strfilter *_filter,
-                                        bool user)
+int show_available_funcs(const char *target, struct nsinfo *nsi,
+                         struct strfilter *_filter, bool user)
 {
         struct rb_node *nd;
         struct map *map;
@@ -3421,7 +3449,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
                 return ret;
 
         /* Get a symbol map */
-        map = get_target_map(target, user);
+        map = get_target_map(target, nsi, user);
         if (!map) {
                 pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
                 return -EINVAL;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5812947418dd..45b14f020558 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -1,9 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PROBE_EVENT_H
 #define _PROBE_EVENT_H
 
 #include <linux/compiler.h>
 #include <stdbool.h>
 #include "intlist.h"
+#include "namespaces.h"
 
 /* Probe related configurations */
 struct probe_conf {
@@ -92,6 +94,7 @@ struct perf_probe_event {
         struct perf_probe_arg   *args;  /* Arguments */
         struct probe_trace_event *tevs;
         int                     ntevs;
+        struct nsinfo           *nsi;   /* Target namespace */
 };
 
 /* Line range */
@@ -163,10 +166,12 @@ int show_perf_probe_event(const char *group, const char *event,
                           struct perf_probe_event *pev,
                           const char *module, bool use_stdout);
 int show_perf_probe_events(struct strfilter *filter);
-int show_line_range(struct line_range *lr, const char *module, bool user);
+int show_line_range(struct line_range *lr, const char *module,
+                    struct nsinfo *nsi, bool user);
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
                         struct strfilter *filter);
-int show_available_funcs(const char *module, struct strfilter *filter, bool user);
+int show_available_funcs(const char *module, struct nsinfo *nsi,
+                         struct strfilter *filter, bool user);
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
                              struct probe_trace_event *tev, struct map *map,
                              struct symbol *sym);
@@ -180,7 +185,7 @@ int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4);
 int copy_to_probe_trace_arg(struct probe_trace_arg *tvar,
                             struct perf_probe_arg *pvar);
 
-struct map *get_target_map(const char *target, bool user);
+struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user);
 
 void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
                                            int ntevs);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index d679389e627c..4ae1123c6794 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -15,6 +15,7 @@
  *
  */
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/uio.h>
@@ -412,13 +413,15 @@ int probe_cache_entry__get_event(struct probe_cache_entry *entry,
 }
 
 /* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */
-static int probe_cache__open(struct probe_cache *pcache, const char *target)
+static int probe_cache__open(struct probe_cache *pcache, const char *target,
+                             struct nsinfo *nsi)
 {
         char cpath[PATH_MAX];
         char sbuildid[SBUILD_ID_SIZE];
         char *dir_name = NULL;
         bool is_kallsyms = false;
         int ret, fd;
+        struct nscookie nsc;
 
         if (target && build_id_cache__cached(target)) {
                 /* This is a cached buildid */
@@ -431,8 +434,11 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
                 target = DSO__NAME_KALLSYMS;
                 is_kallsyms = true;
                 ret = sysfs__sprintf_build_id("/", sbuildid);
-        } else
+        } else {
+                nsinfo__mountns_enter(nsi, &nsc);
                 ret = filename__sprintf_build_id(target, sbuildid);
+                nsinfo__mountns_exit(&nsc);
+        }
 
         if (ret < 0) {
                 pr_debug("Failed to get build-id from %s.\n", target);
@@ -441,7 +447,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
 
         /* If we have no buildid cache, make it */
         if (!build_id_cache__cached(sbuildid)) {
-                ret = build_id_cache__add_s(sbuildid, target,
+                ret = build_id_cache__add_s(sbuildid, target, nsi,
                                             is_kallsyms, NULL);
                 if (ret < 0) {
                         pr_debug("Failed to add build-id cache: %s\n", target);
@@ -449,7 +455,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
                 }
         }
 
-        dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms,
+        dir_name = build_id_cache__cachedir(sbuildid, target, nsi, is_kallsyms,
                                             false);
 found:
         if (!dir_name) {
@@ -554,7 +560,7 @@ void probe_cache__delete(struct probe_cache *pcache)
         free(pcache);
 }
 
-struct probe_cache *probe_cache__new(const char *target)
+struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi)
 {
         struct probe_cache *pcache = probe_cache__alloc();
         int ret;
@@ -562,7 +568,7 @@ struct probe_cache *probe_cache__new(const char *target)
         if (!pcache)
                 return NULL;
 
-        ret = probe_cache__open(pcache, target);
+        ret = probe_cache__open(pcache, target, nsi);
         if (ret < 0) {
                 pr_debug("Cache open error: %d\n", ret);
                 goto out_err;
@@ -974,7 +980,7 @@ int probe_cache__show_all_caches(struct strfilter *filter)
                 return -EINVAL;
         }
         strlist__for_each_entry(nd, bidlist) {
-                pcache = probe_cache__new(nd->s);
+                pcache = probe_cache__new(nd->s, NULL);
                 if (!pcache)
                         continue;
                 if (!list_empty(&pcache->entries)) {
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 5ecc9d3925db..63f29b1d22c1 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PROBE_FILE_H
 #define __PROBE_FILE_H
 
@@ -51,7 +52,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist);
 int probe_cache_entry__get_event(struct probe_cache_entry *entry,
                                  struct probe_trace_event **tevs);
 
-struct probe_cache *probe_cache__new(const char *target);
+struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi);
 int probe_cache__add_entry(struct probe_cache *pcache,
                            struct perf_probe_event *pev,
                            struct probe_trace_event *tevs, int ntevs);
@@ -69,7 +70,7 @@ int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
 #else   /* ! HAVE_LIBELF_SUPPORT */
-static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
+static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
         return NULL;
 }
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 27f061551012..16252980ff00 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PROBE_FINDER_H
 #define _PROBE_FINDER_H
 
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index b234a6e3d0d4..797fe1ae2d2e 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Simple pointer stack
  *
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
index ded7f2e36624..8729b8be061d 100644
--- a/tools/perf/util/pstack.h
+++ b/tools/perf/util/pstack.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_PSTACK_
 #define _PERF_PSTACK_
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 9f3b0d9754a8..b4f2f06722a7 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,8 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/mmap.c
+util/namespaces.c
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index c129e99114ae..8e49d9cafcfc 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <Python.h>
 #include <structmember.h>
 #include <inttypes.h>
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index 1ba8920151d8..22eaa201aa27 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdlib.h>
 #include "strbuf.h"
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index 055ca45bed99..274bf26d3511 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_QUOTE_H
 #define __PERF_QUOTE_H
 
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index 808cc45611fe..a920f702a74d 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_RESORT_RB_H_
 #define _PERF_RESORT_RB_H_
 /*
@@ -143,7 +144,8 @@ struct __name##_sorted *__name = __name##_sorted__new
                                   __ilist->rblist.nr_entries)
 
 /* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine)                    \
-        DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads)
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)       \
+        DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries,     \
+                                  __machine->threads[hash_bucket].nr)
 
 #endif /* _PERF_RESORT_RB_H_ */
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index ff9913b994c2..4c8638a22571 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_RBLIST_H
 #define __PERF_RBLIST_H
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index d91bdf5a1aa4..1e97937b03a9 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "evlist.h"
 #include "evsel.h"
 #include "cpumap.h"
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
new file mode 100644
index 000000000000..5e52e7baa7b6
--- /dev/null
+++ b/tools/perf/util/rwsem.c
@@ -0,0 +1,32 @@
+#include "util.h"
+#include "rwsem.h"
+
+int init_rwsem(struct rw_semaphore *sem)
+{
+        return pthread_rwlock_init(&sem->lock, NULL);
+}
+
+int exit_rwsem(struct rw_semaphore *sem)
+{
+        return pthread_rwlock_destroy(&sem->lock);
+}
+
+int down_read(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock);
+}
+
+int up_read(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
+
+int down_write(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock);
+}
+
+int up_write(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h
new file mode 100644
index 000000000000..94565ad4d494
--- /dev/null
+++ b/tools/perf/util/rwsem.h
@@ -0,0 +1,19 @@
+#ifndef _PERF_RWSEM_H
+#define _PERF_RWSEM_H
+
+#include <pthread.h>
+
+struct rw_semaphore {
+        pthread_rwlock_t lock;
+};
+
+int init_rwsem(struct rw_semaphore *sem);
+int exit_rwsem(struct rw_semaphore *sem);
+
+int down_read(struct rw_semaphore *sem);
+int up_read(struct rw_semaphore *sem);
+
+int down_write(struct rw_semaphore *sem);
+int up_write(struct rw_semaphore *sem);
+
+#endif /* _PERF_RWSEM_H */
diff --git a/tools/perf/util/sane_ctype.h b/tools/perf/util/sane_ctype.h
index 4308c22c22ad..c2b42ff9ff32 100644
--- a/tools/perf/util/sane_ctype.h
+++ b/tools/perf/util/sane_ctype.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_SANE_CTYPE_H
 #define _PERF_SANE_CTYPE_H
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 57b7a00e6f16..c7187f067d31 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -116,6 +116,34 @@ static PyObject *get_handler(const char *handler_name)
         return handler;
 }
 
+static int get_argument_count(PyObject *handler)
+{
+        int arg_count = 0;
+
+        /*
+         * The attribute for the code object is func_code in Python 2,
+         * whereas it is __code__ in Python 3.0+.
+         */
+        PyObject *code_obj = PyObject_GetAttrString(handler,
+                "func_code");
+        if (PyErr_Occurred()) {
+                PyErr_Clear();
+                code_obj = PyObject_GetAttrString(handler,
+                        "__code__");
+        }
+        PyErr_Clear();
+        if (code_obj) {
+                PyObject *arg_count_obj = PyObject_GetAttrString(code_obj,
+                        "co_argcount");
+                if (arg_count_obj) {
+                        arg_count = (int) PyInt_AsLong(arg_count_obj);
+                        Py_DECREF(arg_count_obj);
+                }
+                Py_DECREF(code_obj);
+        }
+        return arg_count;
+}
+
 static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
 {
         PyObject *retval;
@@ -391,13 +419,115 @@ exit:
         return pylist;
 }
 
+static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
+{
+        PyObject *t;
+
+        t = PyTuple_New(2);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+        PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id));
+        PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value));
+        return t;
+}
+
+static void set_sample_read_in_dict(PyObject *dict_sample,
+                                         struct perf_sample *sample,
+                                         struct perf_evsel *evsel)
+{
+        u64 read_format = evsel->attr.read_format;
+        PyObject *values;
+        unsigned int i;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+                pydict_set_item_string_decref(dict_sample, "time_enabled",
+                        PyLong_FromUnsignedLongLong(sample->read.time_enabled));
+        }
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+                pydict_set_item_string_decref(dict_sample, "time_running",
+                        PyLong_FromUnsignedLongLong(sample->read.time_running));
+        }
+
+        if (read_format & PERF_FORMAT_GROUP)
+                values = PyList_New(sample->read.group.nr);
+        else
+                values = PyList_New(1);
+
+        if (!values)
+                Py_FatalError("couldn't create Python list");
+
+        if (read_format & PERF_FORMAT_GROUP) {
+                for (i = 0; i < sample->read.group.nr; i++) {
+                        PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]);
+                        PyList_SET_ITEM(values, i, t);
+                }
+        } else {
+                PyObject *t = get_sample_value_as_tuple(&sample->read.one);
+                PyList_SET_ITEM(values, 0, t);
+        }
+        pydict_set_item_string_decref(dict_sample, "values", values);
+}
+
+static PyObject *get_perf_sample_dict(struct perf_sample *sample,
+                                         struct perf_evsel *evsel,
+                                         struct addr_location *al,
+                                         PyObject *callchain)
+{
+        PyObject *dict, *dict_sample;
+
+        dict = PyDict_New();
+        if (!dict)
+                Py_FatalError("couldn't create Python dictionary");
+
+        dict_sample = PyDict_New();
+        if (!dict_sample)
+                Py_FatalError("couldn't create Python dictionary");
+
+        pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+        pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
+                        (const char *)&evsel->attr, sizeof(evsel->attr)));
+
+        pydict_set_item_string_decref(dict_sample, "pid",
+                        PyInt_FromLong(sample->pid));
+        pydict_set_item_string_decref(dict_sample, "tid",
+                        PyInt_FromLong(sample->tid));
+        pydict_set_item_string_decref(dict_sample, "cpu",
+                        PyInt_FromLong(sample->cpu));
+        pydict_set_item_string_decref(dict_sample, "ip",
+                        PyLong_FromUnsignedLongLong(sample->ip));
+        pydict_set_item_string_decref(dict_sample, "time",
+                        PyLong_FromUnsignedLongLong(sample->time));
+        pydict_set_item_string_decref(dict_sample, "period",
+                        PyLong_FromUnsignedLongLong(sample->period));
+        set_sample_read_in_dict(dict_sample, sample, evsel);
+        pydict_set_item_string_decref(dict, "sample", dict_sample);
+
+        pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
+                        (const char *)sample->raw_data, sample->raw_size));
+        pydict_set_item_string_decref(dict, "comm",
+                        PyString_FromString(thread__comm_str(al->thread)));
+        if (al->map) {
+                pydict_set_item_string_decref(dict, "dso",
+                        PyString_FromString(al->map->dso->name));
+        }
+        if (al->sym) {
+                pydict_set_item_string_decref(dict, "symbol",
+                        PyString_FromString(al->sym->name));
+        }
+
+        pydict_set_item_string_decref(dict, "callchain", callchain);
+
+        return dict;
+}
+
 static void python_process_tracepoint(struct perf_sample *sample,
                                       struct perf_evsel *evsel,
                                       struct addr_location *al)
 {
         struct event_format *event = evsel->tp_format;
         PyObject *handler, *context, *t, *obj = NULL, *callchain;
-        PyObject *dict = NULL;
+        PyObject *dict = NULL, *all_entries_dict = NULL;
         static char handler_name[256];
         struct format_field *field;
         unsigned long s, ns;
@@ -407,10 +537,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
         void *data = sample->raw_data;
         unsigned long long nsecs = sample->time;
         const char *comm = thread__comm_str(al->thread);
-
-        t = PyTuple_New(MAX_FIELDS);
-        if (!t)
-                Py_FatalError("couldn't create Python tuple");
+        const char *default_handler_name = "trace_unhandled";
 
         if (!event) {
                 snprintf(handler_name, sizeof(handler_name),
@@ -427,10 +554,19 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
         handler = get_handler(handler_name);
         if (!handler) {
+                handler = get_handler(default_handler_name);
+                if (!handler)
+                        return;
                 dict = PyDict_New();
                 if (!dict)
                         Py_FatalError("couldn't create Python dict");
         }
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+
         s = nsecs / NSEC_PER_SEC;
         ns = nsecs - s * NSEC_PER_SEC;
 
@@ -444,8 +580,10 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
         /* ip unwinding */
         callchain = python_process_callchain(sample, evsel, al);
+        /* Need an additional reference for the perf_sample dict */
+        Py_INCREF(callchain);
 
-        if (handler) {
+        if (!dict) {
                 PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(s));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
@@ -484,26 +622,35 @@ static void python_process_tracepoint(struct perf_sample *sample,
                 } else { /* FIELD_IS_NUMERIC */
                         obj = get_field_numeric_entry(event, field, data);
                 }
-                if (handler)
+                if (!dict)
                         PyTuple_SetItem(t, n++, obj);
                 else
                         pydict_set_item_string_decref(dict, field->name, obj);
 
         }
 
-        if (!handler)
+        if (dict)
                 PyTuple_SetItem(t, n++, dict);
 
+        if (get_argument_count(handler) == (int) n + 1) {
+                all_entries_dict = get_perf_sample_dict(sample, evsel, al,
+                        callchain);
+                PyTuple_SetItem(t, n++, all_entries_dict);
+        } else {
+                Py_DECREF(callchain);
+        }
+
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
 
-        if (handler) {
+        if (!dict) {
                 call_object(handler, t, handler_name);
         } else {
-                try_call_object("trace_unhandled", t);
+                call_object(handler, t, default_handler_name);
                 Py_DECREF(dict);
         }
 
+        Py_XDECREF(all_entries_dict);
         Py_DECREF(t);
 }
 
@@ -795,10 +942,16 @@ static void python_process_general_event(struct perf_sample *sample,
                                          struct perf_evsel *evsel,
                                          struct addr_location *al)
 {
-        PyObject *handler, *t, *dict, *callchain, *dict_sample;
+        PyObject *handler, *t, *dict, *callchain;
         static char handler_name[64];
         unsigned n = 0;
 
+        snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
+
+        handler = get_handler(handler_name);
+        if (!handler)
+                return;
+
         /*
          * Use the MAX_FIELDS to make the function expandable, though
          * currently there is only one item for the tuple.
@@ -807,61 +960,16 @@ static void python_process_general_event(struct perf_sample *sample,
         if (!t)
                 Py_FatalError("couldn't create Python tuple");
 
-        dict = PyDict_New();
-        if (!dict)
-                Py_FatalError("couldn't create Python dictionary");
-
-        dict_sample = PyDict_New();
-        if (!dict_sample)
-                Py_FatalError("couldn't create Python dictionary");
-
-        snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
-
-        handler = get_handler(handler_name);
-        if (!handler)
-                goto exit;
-
-        pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
-        pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
-                        (const char *)&evsel->attr, sizeof(evsel->attr)));
-
-        pydict_set_item_string_decref(dict_sample, "pid",
-                        PyInt_FromLong(sample->pid));
-        pydict_set_item_string_decref(dict_sample, "tid",
-                        PyInt_FromLong(sample->tid));
-        pydict_set_item_string_decref(dict_sample, "cpu",
-                        PyInt_FromLong(sample->cpu));
-        pydict_set_item_string_decref(dict_sample, "ip",
-                        PyLong_FromUnsignedLongLong(sample->ip));
-        pydict_set_item_string_decref(dict_sample, "time",
-                        PyLong_FromUnsignedLongLong(sample->time));
-        pydict_set_item_string_decref(dict_sample, "period",
-                        PyLong_FromUnsignedLongLong(sample->period));
-        pydict_set_item_string_decref(dict, "sample", dict_sample);
-
-        pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
-                        (const char *)sample->raw_data, sample->raw_size));
-        pydict_set_item_string_decref(dict, "comm",
-                        PyString_FromString(thread__comm_str(al->thread)));
-        if (al->map) {
-                pydict_set_item_string_decref(dict, "dso",
-                        PyString_FromString(al->map->dso->name));
-        }
-        if (al->sym) {
-                pydict_set_item_string_decref(dict, "symbol",
-                        PyString_FromString(al->sym->name));
-        }
-
         /* ip unwinding */
         callchain = python_process_callchain(sample, evsel, al);
-        pydict_set_item_string_decref(dict, "callchain", callchain);
+        dict = get_perf_sample_dict(sample, evsel, al, callchain);
 
         PyTuple_SetItem(t, n++, dict);
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
 
         call_object(handler, t, handler_name);
-exit:
+
         Py_DECREF(dict);
         Py_DECREF(t);
 }
@@ -1259,6 +1367,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 
                         fprintf(ofp, "%s", f->name);
                 }
+                if (not_first++)
+                        fprintf(ofp, ", ");
+                if (++count % 5 == 0)
+                        fprintf(ofp, "\n\t\t");
+                fprintf(ofp, "perf_sample_dict");
+
                 fprintf(ofp, "):\n");
 
                 fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
@@ -1328,6 +1442,9 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 
                 fprintf(ofp, ")\n\n");
 
+                fprintf(ofp, "\t\tprint 'Sample: {'+"
+                        "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+
                 fprintf(ofp, "\t\tfor node in common_callchain:");
                 fprintf(ofp, "\n\t\t\tif 'sym' in node:");
                 fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
@@ -1338,15 +1455,20 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
         }
 
         fprintf(ofp, "def trace_unhandled(event_name, context, "
-                "event_fields_dict):\n");
+                "event_fields_dict, perf_sample_dict):\n");
 
-        fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))"
-                "for k,v in sorted(event_fields_dict.items())])\n\n");
+        fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
+        fprintf(ofp, "\t\tprint 'Sample: {'+"
+                "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
 
         fprintf(ofp, "def print_header("
                 "event_name, cpu, secs, nsecs, pid, comm):\n"
                 "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-                "(event_name, cpu, secs, nsecs, pid, comm),\n");
+                "(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+
+        fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
+                "\treturn delimiter.join"
+                "(['%%s=%%s'%%(k,str(v))for k,v in sorted(a_dict.items())])\n");
 
         fclose(ofp);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d19c40a81040..5c412310f266 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
@@ -32,14 +33,14 @@ static int perf_session__deliver_event(struct perf_session *session,
 
 static int perf_session__open(struct perf_session *session)
 {
-        struct perf_data_file *file = session->file;
+        struct perf_data *data = session->data;
 
         if (perf_session__read_header(session) < 0) {
                 pr_err("incompatible file format (rerun with -v to learn more)\n");
                 return -1;
         }
 
-        if (perf_data_file__is_pipe(file))
+        if (perf_data__is_pipe(data))
                 return 0;
 
         if (perf_header__has_feat(&session->header, HEADER_STAT))
@@ -120,7 +121,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
                                            session->tool, event->file_offset);
 }
 
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
                                        bool repipe, struct perf_tool *tool)
 {
         struct perf_session *session = zalloc(sizeof(*session));
@@ -134,13 +135,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
         machines__init(&session->machines);
         ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
-        if (file) {
-                if (perf_data_file__open(file))
+        if (data) {
+                if (perf_data__open(data))
                         goto out_delete;
 
-                session->file = file;
+                session->data = data;
 
-                if (perf_data_file__is_read(file)) {
+                if (perf_data__is_read(data)) {
                         if (perf_session__open(session) < 0)
                                 goto out_close;
 
@@ -148,7 +149,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                          * set session attributes that are present in perf.data
                          * but not in pipe-mode.
                          */
-                        if (!file->is_pipe) {
+                        if (!data->is_pipe) {
                                 perf_session__set_id_hdr_size(session);
                                 perf_session__set_comm_exec(session);
                         }
@@ -157,7 +158,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                 session->machines.host.env = &perf_env;
         }
 
-        if (!file || perf_data_file__is_write(file)) {
+        if (!data || perf_data__is_write(data)) {
                 /*
                  * In O_RDONLY mode this will be performed when reading the
                  * kernel MMAP event, in perf_event__process_mmap().
@@ -170,7 +171,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
          * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is
          * processed, so perf_evlist__sample_id_all is not meaningful here.
          */
-        if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps &&
+        if ((!data || !data->is_pipe) && tool && tool->ordering_requires_timestamps &&
             tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
                 dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
                 tool->ordered_events = false;
@@ -179,7 +180,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
         return session;
 
  out_close:
-        perf_data_file__close(file);
+        perf_data__close(data);
  out_delete:
         perf_session__delete(session);
  out:
@@ -201,8 +202,8 @@ void perf_session__delete(struct perf_session *session)
         perf_session__delete_threads(session);
         perf_env__exit(&session->header.env);
         machines__exit(&session->machines);
-        if (session->file)
-                perf_data_file__close(session->file);
+        if (session->data)
+                perf_data__close(session->data);
         free(session);
 }
 
@@ -290,8 +291,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
                                        __maybe_unused)
 {
         dump_printf(": unhandled!\n");
-        if (perf_data_file__is_pipe(session->file))
-                skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+        if (perf_data__is_pipe(session->data))
+                skipn(perf_data__fd(session->data), event->auxtrace.size);
         return event->auxtrace.size;
 }
 
@@ -374,6 +375,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->mmap2 = process_event_stub;
         if (tool->comm == NULL)
                 tool->comm = process_event_stub;
+        if (tool->namespaces == NULL)
+                tool->namespaces = process_event_stub;
         if (tool->fork == NULL)
                 tool->fork = process_event_stub;
         if (tool->exit == NULL)
@@ -428,6 +431,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->stat_round = process_stat_round_stub;
         if (tool->time_conv == NULL)
                 tool->time_conv = process_event_op2_stub;
+        if (tool->feature == NULL)
+                tool->feature = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -1118,6 +1123,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
         if (sample_type & PERF_SAMPLE_DATA_SRC)
                 printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
 
+        if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+                printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
+
         if (sample_type & PERF_SAMPLE_TRANSACTION)
                 printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
@@ -1125,6 +1133,30 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
                 sample_read__printf(sample, evsel->attr.read_format);
 }
 
+static void dump_read(struct perf_evsel *evsel, union perf_event *event)
+{
+        struct read_event *read_event = &event->read;
+        u64 read_format;
+
+        if (!dump_trace)
+                return;
+
+        printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
+               evsel ? perf_evsel__name(evsel) : "FAIL",
+               event->read.value);
+
+        read_format = evsel->attr.read_format;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled);
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                printf("... time running : %" PRIu64 "\n", read_event->time_running);
+
+        if (read_format & PERF_FORMAT_ID)
+                printf("... id           : %" PRIu64 "\n", read_event->id);
+}
+
 static struct machine *machines__find_for_cpumode(struct machines *machines,
                                                union perf_event *event,
                                                struct perf_sample *sample)
@@ -1269,6 +1301,7 @@ static int machines__deliver_event(struct machines *machines,
                         evlist->stats.total_lost_samples += event->lost_samples.lost;
                 return tool->lost_samples(tool, event, sample, machine);
         case PERF_RECORD_READ:
+                dump_read(evsel, event);
                 return tool->read(tool, event, sample, evsel, machine);
         case PERF_RECORD_THROTTLE:
                 return tool->throttle(tool, event, sample, machine);
@@ -1317,7 +1350,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 {
         struct ordered_events *oe = &session->ordered_events;
         struct perf_tool *tool = session->tool;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         int err;
 
         dump_event(session->evlist, event, file_offset, NULL);
@@ -1371,6 +1404,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
         case PERF_RECORD_TIME_CONV:
                 session->time_conv = event->time_conv;
                 return tool->time_conv(tool, event, session);
+        case PERF_RECORD_HEADER_FEATURE:
+                return tool->feature(tool, event, session);
         default:
                 return -EINVAL;
         }
@@ -1415,10 +1450,10 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
                 goto out_parse_sample;
         }
 
-        if (perf_data_file__is_pipe(session->file))
+        if (perf_data__is_pipe(session->data))
                 return -1;
 
-        fd = perf_data_file__fd(session->file);
+        fd = perf_data__fd(session->data);
         hdr_sz = sizeof(struct perf_event_header);
 
         if (buf_sz < hdr_sz)
@@ -1653,7 +1688,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 {
         struct ordered_events *oe = &session->ordered_events;
         struct perf_tool *tool = session->tool;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         union perf_event *event;
         uint32_t size, cur_size = 0;
         void *buf = NULL;
@@ -1794,7 +1829,7 @@ static int __perf_session__process_events(struct perf_session *session,
 {
         struct ordered_events *oe = &session->ordered_events;
         struct perf_tool *tool = session->tool;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         u64 head, page_offset, file_offset, file_pos, size;
         int err, mmap_prot, mmap_flags, map_idx = 0;
         size_t  mmap_size;
@@ -1815,7 +1850,7 @@ static int __perf_session__process_events(struct perf_session *session,
         if (data_offset + data_size < file_size)
                 file_size = data_offset + data_size;
 
-        ui_progress__init(&prog, file_size, "Processing events...");
+        ui_progress__init_size(&prog, file_size, "Processing events...");
 
         mmap_size = MMAP_SIZE;
         if (mmap_size > file_size) {
@@ -1911,13 +1946,13 @@ out_err:
 
 int perf_session__process_events(struct perf_session *session)
 {
-        u64 size = perf_data_file__size(session->file);
+        u64 size = perf_data__size(session->data);
         int err;
 
         if (perf_session__register_idle_thread(session) < 0)
                 return -ENOMEM;
 
-        if (!perf_data_file__is_pipe(session->file))
+        if (!perf_data__is_pipe(session->data))
                 err = __perf_session__process_events(session,
                                                      session->header.data_offset,
                                                      session->header.data_size, size);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 47b5e7dbcb18..da1434a7c120 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
@@ -32,13 +33,13 @@ struct perf_session {
         void                    *one_mmap_addr;
         u64                     one_mmap_offset;
         struct ordered_events   ordered_events;
-        struct perf_data_file   *file;
+        struct perf_data        *data;
         struct perf_tool        *tool;
 };
 
 struct perf_tool;
 
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
                                        bool repipe, struct perf_tool *tool);
 void perf_session__delete(struct perf_session *session);
 
@@ -113,7 +114,7 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 extern volatile int session_done;
 
-#define session_done()  ACCESS_ONCE(session_done)
+#define session_done()  READ_ONCE(session_done)
 
 int perf_session__deliver_synth_event(struct perf_session *session,
                                       union perf_event *event,
diff --git a/tools/perf/util/setns.c b/tools/perf/util/setns.c
new file mode 100644
index 000000000000..ce8fc290fce8
--- /dev/null
+++ b/tools/perf/util/setns.c
@@ -0,0 +1,8 @@
+#include "util.h"
+#include <unistd.h>
+#include <sys/syscall.h>
+
+int setns(int fd, int nstype)
+{
+        return syscall(__NR_setns, fd, nstype);
+}
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
new file mode 100644
index 000000000000..453f6f6f29f3
--- /dev/null
+++ b/tools/perf/util/smt.c
@@ -0,0 +1,44 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <linux/bitops.h>
+#include "api/fs/fs.h"
+#include "smt.h"
+
+int smt_on(void)
+{
+        static bool cached;
+        static int cached_result;
+        int cpu;
+        int ncpu;
+
+        if (cached)
+                return cached_result;
+
+        ncpu = sysconf(_SC_NPROCESSORS_CONF);
+        for (cpu = 0; cpu < ncpu; cpu++) {
+                unsigned long long siblings;
+                char *str;
+                size_t strlen;
+                char fn[256];
+
+                snprintf(fn, sizeof fn,
+                        "devices/system/cpu/cpu%d/topology/thread_siblings",
+                        cpu);
+                if (sysfs__read_str(fn, &str, &strlen) < 0)
+                        continue;
+                /* Entry is hex, but does not have 0x, so need custom parser */
+                siblings = strtoull(str, NULL, 16);
+                free(str);
+                if (hweight64(siblings) > 1) {
+                        cached_result = 1;
+                        cached = true;
+                        break;
+                }
+        }
+        if (!cached) {
+                cached_result = 0;
+                cached = true;
+        }
+        return cached_result;
+}
diff --git a/tools/perf/util/smt.h b/tools/perf/util/smt.h
new file mode 100644
index 000000000000..b8414b7bcbc8
--- /dev/null
+++ b/tools/perf/util/smt.h
@@ -0,0 +1,6 @@
+#ifndef SMT_H
+#define SMT_H 1
+
+int smt_on(void);
+
+#endif
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 8b327c955a4f..a00eacdf02ed 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
@@ -225,6 +226,9 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
         if (sym_l == sym_r)
                 return 0;
 
+        if (sym_l->inlined || sym_r->inlined)
+                return strcmp(sym_l->name, sym_r->name);
+
         if (sym_l->start != sym_r->start)
                 return (int64_t)(sym_r->start - sym_l->start);
 
@@ -283,6 +287,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
                         ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
                                                width - ret,
                                                sym->name);
+                        if (sym->inlined)
+                                ret += repsep_snprintf(bf + ret, size - ret,
+                                                       " (inlined)");
                 }
         } else {
                 size_t len = BITS_PER_LONG / 4;
@@ -1316,6 +1323,47 @@ struct sort_entry sort_mem_dcacheline = {
 };
 
 static int64_t
+sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        uint64_t l = 0, r = 0;
+
+        if (left->mem_info)
+                l = left->mem_info->daddr.phys_addr;
+        if (right->mem_info)
+                r = right->mem_info->daddr.phys_addr;
+
+        return (int64_t)(r - l);
+}
+
+static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf,
+                                           size_t size, unsigned int width)
+{
+        uint64_t addr = 0;
+        size_t ret = 0;
+        size_t len = BITS_PER_LONG / 4;
+
+        addr = he->mem_info->daddr.phys_addr;
+
+        ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level);
+
+        ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr);
+
+        ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, "");
+
+        if (ret > width)
+                bf[width] = '\0';
+
+        return width;
+}
+
+struct sort_entry sort_mem_phys_daddr = {
+        .se_header      = "Data Physical Address",
+        .se_cmp         = sort__phys_daddr_cmp,
+        .se_snprintf    = hist_entry__phys_daddr_snprintf,
+        .se_width_idx   = HISTC_MEM_PHYS_DADDR,
+};
+
+static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
         if (!left->branch_info || !right->branch_info)
@@ -1547,6 +1595,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
         DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
         DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
         DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+        DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
 };
 
 #undef DIM
@@ -2563,7 +2612,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist)
 
         BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
-        if (evlist == NULL)
+        if (evlist == NULL || perf_evlist__empty(evlist))
                 goto out_no_evlist;
 
         evlist__for_each_entry(evlist, evsel) {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b7c75597e18f..f5901c10a563 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SORT_H
 #define __PERF_SORT_H
 #include "../builtin.h"
@@ -129,7 +130,6 @@ struct hist_entry {
         };
         char                    *srcline;
         char                    *srcfile;
-        struct inline_node      *inline_node;
         struct symbol           *parent;
         struct branch_info      *branch_info;
         struct hists            *hists;
@@ -245,6 +245,7 @@ enum sort_type {
         SORT_MEM_SNOOP,
         SORT_MEM_DCACHELINE,
         SORT_MEM_IADDR_SYMBOL,
+        SORT_MEM_PHYS_DADDR,
 };
 
 /*
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index ebc88a74e67b..d19f05c56de6 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -10,7 +11,7 @@
 #include "util/debug.h"
 #include "util/callchain.h"
 #include "srcline.h"
-
+#include "string2.h"
 #include "symbol.h"
 
 bool srcline_full_filename;
@@ -33,28 +34,17 @@ static const char *dso__name(struct dso *dso)
         return dso_name;
 }
 
-static int inline_list__append(char *filename, char *funcname, int line_nr,
-                               struct inline_node *node, struct dso *dso)
+static int inline_list__append(struct symbol *symbol, char *srcline,
+                               struct inline_node *node)
 {
         struct inline_list *ilist;
-        char *demangled;
 
         ilist = zalloc(sizeof(*ilist));
         if (ilist == NULL)
                 return -1;
 
-        ilist->filename = filename;
-        ilist->line_nr = line_nr;
-
-        if (dso != NULL) {
-                demangled = dso__demangle_sym(dso, 0, funcname);
-                if (demangled == NULL) {
-                        ilist->funcname = funcname;
-                } else {
-                        ilist->funcname = demangled;
-                        free(funcname);
-                }
-        }
+        ilist->symbol = symbol;
+        ilist->srcline = srcline;
 
         if (callchain_param.order == ORDER_CALLEE)
                 list_add_tail(&ilist->list, &node->val);
@@ -64,6 +54,65 @@ static int inline_list__append(char *filename, char *funcname, int line_nr,
         return 0;
 }
 
+/* basename version that takes a const input string */
+static const char *gnu_basename(const char *path)
+{
+        const char *base = strrchr(path, '/');
+
+        return base ? base + 1 : path;
+}
+
+static char *srcline_from_fileline(const char *file, unsigned int line)
+{
+        char *srcline;
+
+        if (!file)
+                return NULL;
+
+        if (!srcline_full_filename)
+                file = gnu_basename(file);
+
+        if (asprintf(&srcline, "%s:%u", file, line) < 0)
+                return NULL;
+
+        return srcline;
+}
+
+static struct symbol *new_inline_sym(struct dso *dso,
+                                     struct symbol *base_sym,
+                                     const char *funcname)
+{
+        struct symbol *inline_sym;
+        char *demangled = NULL;
+
+        if (dso) {
+                demangled = dso__demangle_sym(dso, 0, funcname);
+                if (demangled)
+                        funcname = demangled;
+        }
+
+        if (base_sym && strcmp(funcname, base_sym->name) == 0) {
+                /* reuse the real, existing symbol */
+                inline_sym = base_sym;
+                /* ensure that we don't alias an inlined symbol, which could
+                 * lead to double frees in inline_node__delete
+                 */
+                assert(!base_sym->inlined);
+        } else {
+                /* create a fake symbol for the inline frame */
+                inline_sym = symbol__new(base_sym ? base_sym->start : 0,
+                                         base_sym ? base_sym->end : 0,
+                                         base_sym ? base_sym->binding : 0,
+                                         funcname);
+                if (inline_sym)
+                        inline_sym->inlined = 1;
+        }
+
+        free(demangled);
+
+        return inline_sym;
+}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -155,6 +204,9 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data)
         a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma,
                                            &a2l->filename, &a2l->funcname,
                                            &a2l->line);
+
+        if (a2l->filename && !strlen(a2l->filename))
+                a2l->filename = NULL;
 }
 
 static struct a2l_data *addr2line_init(const char *path)
@@ -204,18 +256,23 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 #define MAX_INLINE_NEST 1024
 
 static int inline_list__append_dso_a2l(struct dso *dso,
-                                       struct inline_node *node)
+                                       struct inline_node *node,
+                                       struct symbol *sym)
 {
         struct a2l_data *a2l = dso->a2l;
-        char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL;
-        char *filename = a2l->filename ? strdup(a2l->filename) : NULL;
+        struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname);
+        char *srcline = NULL;
 
-        return inline_list__append(filename, funcname, a2l->line, node, dso);
+        if (a2l->filename)
+                srcline = srcline_from_fileline(a2l->filename, a2l->line);
+
+        return inline_list__append(inline_sym, srcline, node);
 }
 
 static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line, struct dso *dso,
-                     bool unwind_inlines, struct inline_node *node)
+                     bool unwind_inlines, struct inline_node *node,
+                     struct symbol *sym)
 {
         int ret = 0;
         struct a2l_data *a2l = dso->a2l;
@@ -241,15 +298,18 @@ static int addr2line(const char *dso_name, u64 addr,
         if (unwind_inlines) {
                 int cnt = 0;
 
-                if (node && inline_list__append_dso_a2l(dso, node))
+                if (node && inline_list__append_dso_a2l(dso, node, sym))
                         return 0;
 
                 while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
                                              &a2l->funcname, &a2l->line) &&
                        cnt++ < MAX_INLINE_NEST) {
 
+                        if (a2l->filename && !strlen(a2l->filename))
+                                a2l->filename = NULL;
+
                         if (node != NULL) {
-                                if (inline_list__append_dso_a2l(dso, node))
+                                if (inline_list__append_dso_a2l(dso, node, sym))
                                         return 0;
                                 // found at least one inline frame
                                 ret = 1;
@@ -281,7 +341,7 @@ void dso__free_a2l(struct dso *dso)
 }
 
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
-        struct dso *dso)
+                                        struct dso *dso, struct symbol *sym)
 {
         struct inline_node *node;
 
@@ -294,17 +354,8 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
         INIT_LIST_HEAD(&node->val);
         node->addr = addr;
 
-        if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node))
-                goto out_free_inline_node;
-
-        if (list_empty(&node->val))
-                goto out_free_inline_node;
-
+        addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym);
         return node;
-
-out_free_inline_node:
-        inline_node__delete(node);
-        return NULL;
 }
 
 #else /* HAVE_LIBBFD_SUPPORT */
@@ -334,7 +385,8 @@ static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line_nr,
                      struct dso *dso __maybe_unused,
                      bool unwind_inlines __maybe_unused,
-                     struct inline_node *node __maybe_unused)
+                     struct inline_node *node __maybe_unused,
+                     struct symbol *sym __maybe_unused)
 {
         FILE *fp;
         char cmd[PATH_MAX];
@@ -374,16 +426,18 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 }
 
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
-        struct dso *dso __maybe_unused)
+                                        struct dso *dso __maybe_unused,
+                                        struct symbol *sym)
 {
         FILE *fp;
         char cmd[PATH_MAX];
         struct inline_node *node;
         char *filename = NULL;
-        size_t len;
+        char *funcname = NULL;
+        size_t filelen, funclen;
         unsigned int line_nr = 0;
 
-        scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+        scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64,
                   dso_name, addr);
 
         fp = popen(cmd, "r");
@@ -401,26 +455,34 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
         INIT_LIST_HEAD(&node->val);
         node->addr = addr;
 
-        while (getline(&filename, &len, fp) != -1) {
-                if (filename_split(filename, &line_nr) != 1) {
-                        free(filename);
+        /* addr2line -f generates two lines for each inlined functions */
+        while (getline(&funcname, &funclen, fp) != -1) {
+                char *srcline;
+                struct symbol *inline_sym;
+
+                rtrim(funcname);
+
+                if (getline(&filename, &filelen, fp) == -1)
                         goto out;
-                }
 
-                if (inline_list__append(filename, NULL, line_nr, node,
-                                        NULL) != 0)
+                if (filename_split(filename, &line_nr) != 1)
                         goto out;
 
-                filename = NULL;
+                srcline = srcline_from_fileline(filename, line_nr);
+                inline_sym = new_inline_sym(dso, sym, funcname);
+
+                if (inline_list__append(inline_sym, srcline, node) != 0) {
+                        free(srcline);
+                        if (inline_sym && inline_sym->inlined)
+                                symbol__delete(inline_sym);
+                        goto out;
+                }
         }
 
 out:
         pclose(fp);
-
-        if (list_empty(&node->val)) {
-                inline_node__delete(node);
-                return NULL;
-        }
+        free(filename);
+        free(funcname);
 
         return node;
 }
@@ -448,19 +510,18 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
         if (dso_name == NULL)
                 goto out;
 
-        if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
+        if (!addr2line(dso_name, addr, &file, &line, dso,
+                       unwind_inlines, NULL, sym))
                 goto out;
 
-        if (asprintf(&srcline, "%s:%u",
-                                srcline_full_filename ? file : basename(file),
-                                line) < 0) {
-                free(file);
+        srcline = srcline_from_fileline(file, line);
+        free(file);
+
+        if (!srcline)
                 goto out;
-        }
 
         dso->a2l_fails = 0;
 
-        free(file);
         return srcline;
 
 out:
@@ -494,7 +555,74 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
         return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
 }
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
+struct srcline_node {
+        u64                     addr;
+        char                    *srcline;
+        struct rb_node          rb_node;
+};
+
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
+{
+        struct rb_node **p = &tree->rb_node;
+        struct rb_node *parent = NULL;
+        struct srcline_node *i, *node;
+
+        node = zalloc(sizeof(struct srcline_node));
+        if (!node) {
+                perror("not enough memory for the srcline node");
+                return;
+        }
+
+        node->addr = addr;
+        node->srcline = srcline;
+
+        while (*p != NULL) {
+                parent = *p;
+                i = rb_entry(parent, struct srcline_node, rb_node);
+                if (addr < i->addr)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+        rb_link_node(&node->rb_node, parent, p);
+        rb_insert_color(&node->rb_node, tree);
+}
+
+char *srcline__tree_find(struct rb_root *tree, u64 addr)
+{
+        struct rb_node *n = tree->rb_node;
+
+        while (n) {
+                struct srcline_node *i = rb_entry(n, struct srcline_node,
+                                                  rb_node);
+
+                if (addr < i->addr)
+                        n = n->rb_left;
+                else if (addr > i->addr)
+                        n = n->rb_right;
+                else
+                        return i->srcline;
+        }
+
+        return NULL;
+}
+
+void srcline__tree_delete(struct rb_root *tree)
+{
+        struct srcline_node *pos;
+        struct rb_node *next = rb_first(tree);
+
+        while (next) {
+                pos = rb_entry(next, struct srcline_node, rb_node);
+                next = rb_next(&pos->rb_node);
+                rb_erase(&pos->rb_node, tree);
+                free_srcline(pos->srcline);
+                zfree(&pos);
+        }
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+                                            struct symbol *sym)
 {
         const char *dso_name;
 
@@ -502,7 +630,7 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
         if (dso_name == NULL)
                 return NULL;
 
-        return addr2inlines(dso_name, addr, dso);
+        return addr2inlines(dso_name, addr, dso, sym);
 }
 
 void inline_node__delete(struct inline_node *node)
@@ -511,10 +639,63 @@ void inline_node__delete(struct inline_node *node)
 
         list_for_each_entry_safe(ilist, tmp, &node->val, list) {
                 list_del_init(&ilist->list);
-                zfree(&ilist->filename);
-                zfree(&ilist->funcname);
+                free_srcline(ilist->srcline);
+                /* only the inlined symbols are owned by the list */
+                if (ilist->symbol && ilist->symbol->inlined)
+                        symbol__delete(ilist->symbol);
                 free(ilist);
         }
 
         free(node);
 }
+
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
+{
+        struct rb_node **p = &tree->rb_node;
+        struct rb_node *parent = NULL;
+        const u64 addr = inlines->addr;
+        struct inline_node *i;
+
+        while (*p != NULL) {
+                parent = *p;
+                i = rb_entry(parent, struct inline_node, rb_node);
+                if (addr < i->addr)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+        rb_link_node(&inlines->rb_node, parent, p);
+        rb_insert_color(&inlines->rb_node, tree);
+}
+
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
+{
+        struct rb_node *n = tree->rb_node;
+
+        while (n) {
+                struct inline_node *i = rb_entry(n, struct inline_node,
+                                                 rb_node);
+
+                if (addr < i->addr)
+                        n = n->rb_left;
+                else if (addr > i->addr)
+                        n = n->rb_right;
+                else
+                        return i;
+        }
+
+        return NULL;
+}
+
+void inlines__tree_delete(struct rb_root *tree)
+{
+        struct inline_node *pos;
+        struct rb_node *next = rb_first(tree);
+
+        while (next) {
+                pos = rb_entry(next, struct inline_node, rb_node);
+                next = rb_next(&pos->rb_node);
+                rb_erase(&pos->rb_node, tree);
+                inline_node__delete(pos);
+        }
+}
diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h
index 7b52ba88676e..847b7086182c 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -1,7 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_SRCLINE_H
 #define PERF_SRCLINE_H
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct dso;
@@ -14,21 +16,38 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
                   bool show_sym, bool show_addr, bool unwind_inlines);
 void free_srcline(char *srcline);
 
+/* insert the srcline into the DSO, which will take ownership */
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline);
+/* find previously inserted srcline */
+char *srcline__tree_find(struct rb_root *tree, u64 addr);
+/* delete all srclines within the tree */
+void srcline__tree_delete(struct rb_root *tree);
+
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
 struct inline_list {
-        char                    *filename;
-        char                    *funcname;
-        unsigned int            line_nr;
+        struct symbol           *symbol;
+        char                    *srcline;
         struct list_head        list;
 };
 
 struct inline_node {
         u64                     addr;
         struct list_head        val;
+        struct rb_node          rb_node;
 };
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+/* parse inlined frames for the given address */
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+                                            struct symbol *sym);
+/* free resources associated to the inline node list */
 void inline_node__delete(struct inline_node *node);
 
+/* insert the inline node list into the DSO, which will take ownership */
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+/* find previously inserted inline node list */
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+/* delete all nodes within the tree of inline_node s */
+void inlines__tree_delete(struct rb_root *tree);
+
 #endif /* PERF_SRCLINE_H */
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 719d6cb86952..855e35cbb1dc 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include "evsel.h"
 #include "stat.h"
@@ -6,6 +7,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
+#include "metricgroup.h"
 
 enum {
         CTX_BIT_USER    = 1 << 0,
@@ -55,7 +57,6 @@ struct saved_value {
         struct rb_node rb_node;
         struct perf_evsel *evsel;
         int cpu;
-        int ctx;
         struct stats stats;
 };
 
@@ -66,11 +67,13 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
                                              rb_node);
         const struct saved_value *b = entry;
 
-        if (a->ctx != b->ctx)
-                return a->ctx - b->ctx;
         if (a->cpu != b->cpu)
                 return a->cpu - b->cpu;
-        return a->evsel - b->evsel;
+        if (a->evsel == b->evsel)
+                return 0;
+        if ((char *)a->evsel < (char *)b->evsel)
+                return -1;
+        return +1;
 }
 
 static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
@@ -85,13 +88,12 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
 }
 
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
-                                              int cpu, int ctx,
+                                              int cpu,
                                               bool create)
 {
         struct rb_node *nd;
         struct saved_value dm = {
                 .cpu = cpu,
-                .ctx = ctx,
                 .evsel = evsel,
         };
         nd = rblist__find(&runtime_saved_values, &dm);
@@ -177,59 +179,60 @@ void perf_stat__reset_shadow_stats(void)
  * more semantic information such as miss/hit ratios,
  * instruction rates, etc:
  */
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
                                     int cpu)
 {
         int ctx = evsel_context(counter);
 
+        count *= counter->scale;
+
         if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
             perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
-                update_stats(&runtime_nsecs_stats[cpu], count[0]);
+                update_stats(&runtime_nsecs_stats[cpu], count);
         else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-                update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_cycles_stats[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-                update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, TRANSACTION_START))
-                update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_transaction_stats[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, ELISION_START))
-                update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_elision_stats[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
-                update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+                update_stats(&runtime_topdown_total_slots[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
-                update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+                update_stats(&runtime_topdown_slots_issued[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
-                update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+                update_stats(&runtime_topdown_slots_retired[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
-                update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+                update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
-                update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
+                update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count);
         else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-                update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-                update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-                update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_branches_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-                update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_cacherefs_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-                update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_l1_dcache_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-                update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-                update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-                update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-                update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_itlb_cache_stats[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, SMI_NUM))
-                update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_smi_num_stats[ctx][cpu], count);
         else if (perf_stat_evsel__is(counter, APERF))
-                update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_aperf_stats[ctx][cpu], count);
 
         if (counter->collect_stat) {
-                struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
-                                                           true);
-                update_stats(&v->stats, count[0]);
+                struct saved_value *v = saved_value_lookup(counter, cpu, true);
+                update_stats(&v->stats, count);
         }
 }
 
@@ -623,15 +626,68 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
         out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
+static void generic_metric(const char *metric_expr,
+                           struct perf_evsel **metric_events,
+                           char *name,
+                           const char *metric_name,
+                           double avg,
+                           int cpu,
+                           struct perf_stat_output_ctx *out)
+{
+        print_metric_t print_metric = out->print_metric;
+        struct parse_ctx pctx;
+        double ratio;
+        int i;
+        void *ctxp = out->ctx;
+
+        expr__ctx_init(&pctx);
+        expr__add_id(&pctx, name, avg);
+        for (i = 0; metric_events[i]; i++) {
+                struct saved_value *v;
+                struct stats *stats;
+                double scale;
+
+                if (!strcmp(metric_events[i]->name, "duration_time")) {
+                        stats = &walltime_nsecs_stats;
+                        scale = 1e-9;
+                } else {
+                        v = saved_value_lookup(metric_events[i], cpu, false);
+                        if (!v)
+                                break;
+                        stats = &v->stats;
+                        scale = 1.0;
+                }
+                expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
+        }
+        if (!metric_events[i]) {
+                const char *p = metric_expr;
+
+                if (expr__parse(&ratio, &pctx, &p) == 0)
+                        print_metric(ctxp, NULL, "%8.1f",
+                                metric_name ?
+                                metric_name :
+                                out->force_header ?  name : "",
+                                ratio);
+                else
+                        print_metric(ctxp, NULL, NULL,
+                                     out->force_header ?
+                                     (metric_name ? metric_name : name) : "", 0);
+        } else
+                print_metric(ctxp, NULL, NULL, "", 0);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                    double avg, int cpu,
-                                   struct perf_stat_output_ctx *out)
+                                   struct perf_stat_output_ctx *out,
+                                   struct rblist *metric_events)
 {
         void *ctxp = out->ctx;
         print_metric_t print_metric = out->print_metric;
         double total, ratio = 0.0, total2;
         const char *color = NULL;
         int ctx = evsel_context(evsel);
+        struct metric_event *me;
+        int num = 1;
 
         if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
                 total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
@@ -815,33 +871,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 else
                         print_metric(ctxp, NULL, NULL, name, 0);
         } else if (evsel->metric_expr) {
-                struct parse_ctx pctx;
-                int i;
-
-                expr__ctx_init(&pctx);
-                expr__add_id(&pctx, evsel->name, avg);
-                for (i = 0; evsel->metric_events[i]; i++) {
-                        struct saved_value *v;
-
-                        v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
-                        if (!v)
-                                break;
-                        expr__add_id(&pctx, evsel->metric_events[i]->name,
-                                             avg_stats(&v->stats));
-                }
-                if (!evsel->metric_events[i]) {
-                        const char *p = evsel->metric_expr;
-
-                        if (expr__parse(&ratio, &pctx, &p) == 0)
-                                print_metric(ctxp, NULL, "%8.1f",
-                                        evsel->metric_name ?
-                                        evsel->metric_name :
-                                        out->force_header ?  evsel->name : "",
-                                        ratio);
-                        else
-                                print_metric(ctxp, NULL, NULL, "", 0);
-                } else
-                        print_metric(ctxp, NULL, NULL, "", 0);
+                generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+                                evsel->metric_name, avg, cpu, out);
         } else if (runtime_nsecs_stats[cpu].n != 0) {
                 char unit = 'M';
                 char unit_buf[10];
@@ -859,6 +890,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
         } else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
                 print_smi_cost(cpu, evsel, out);
         } else {
-                print_metric(ctxp, NULL, NULL, NULL, 0);
+                num = 0;
         }
+
+        if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
+                struct metric_expr *mexp;
+
+                list_for_each_entry (mexp, &me->head, nd) {
+                        if (num++ > 0)
+                                out->new_line(ctxp);
+                        generic_metric(mexp->metric_expr, mexp->metric_events,
+                                        evsel->name, mexp->metric_name,
+                                        avg, cpu, out);
+                }
+        }
+        if (num == 0)
+                print_metric(ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 53b9a994a3dc..151e9efd7286 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
 #include <math.h>
@@ -69,7 +70,7 @@ double rel_stddev_stats(double stddev, double avg)
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
                            enum perf_stat_evsel_id id)
 {
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
 
         return ps->id == id;
 }
@@ -93,7 +94,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 
 void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 {
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
         int i;
 
         /* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
@@ -109,7 +110,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
         int i;
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
 
         for (i = 0; i < 3; i++)
                 init_stats(&ps->res_stats[i]);
@@ -119,8 +120,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
-        evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
-        if (evsel->priv == NULL)
+        evsel->stats = zalloc(sizeof(struct perf_stat_evsel));
+        if (evsel->stats == NULL)
                 return -ENOMEM;
         perf_evsel__reset_stat_priv(evsel);
         return 0;
@@ -128,7 +129,11 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
-        zfree(&evsel->priv);
+        struct perf_stat_evsel *ps = evsel->stats;
+
+        if (ps)
+                free(ps->group_data);
+        zfree(&evsel->stats);
 }
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
@@ -273,7 +278,9 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
                         perf_evsel__compute_deltas(evsel, cpu, thread, count);
                 perf_counts_values__scale(count, config->scale, NULL);
                 if (config->aggr_mode == AGGR_NONE)
-                        perf_stat__update_shadow_stats(evsel, count->values, cpu);
+                        perf_stat__update_shadow_stats(evsel, count->val, cpu);
+                if (config->aggr_mode == AGGR_THREAD)
+                        perf_stat__update_shadow_stats(evsel, count->val, 0);
                 break;
         case AGGR_GLOBAL:
                 aggr->val += count->val;
@@ -314,9 +321,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
                               struct perf_evsel *counter)
 {
         struct perf_counts_values *aggr = &counter->counts->aggr;
-        struct perf_stat_evsel *ps = counter->priv;
+        struct perf_stat_evsel *ps = counter->stats;
         u64 *count = counter->counts->aggr.values;
-        u64 val;
         int i, ret;
 
         aggr->val = aggr->ena = aggr->run = 0;
@@ -356,8 +362,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
         /*
          * Save the full runtime - to allow normalization during printout:
          */
-        val = counter->scale * *count;
-        perf_stat__update_shadow_stats(counter, &val, 0);
+        perf_stat__update_shadow_stats(counter, *count, 0);
 
         return 0;
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 7522bf10b03e..eefca5c981fd 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_STATS_H
 #define __PERF_STATS_H
 
@@ -28,8 +29,9 @@ enum perf_stat_evsel_id {
 };
 
 struct perf_stat_evsel {
-        struct stats            res_stats[3];
-        enum perf_stat_evsel_id id;
+        struct stats             res_stats[3];
+        enum perf_stat_evsel_id  id;
+        u64                     *group_data;
 };
 
 enum aggr_mode {
@@ -81,7 +83,7 @@ typedef void (*new_line_t )(void *ctx);
 
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
                                     int cpu);
 struct perf_stat_output_ctx {
         void *ctx;
@@ -90,9 +92,11 @@ struct perf_stat_output_ctx {
         bool force_header;
 };
 
+struct rblist;
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                    double avg, int cpu,
-                                   struct perf_stat_output_ctx *out);
+                                   struct perf_stat_output_ctx *out,
+                                   struct rblist *metric_events);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index aafe908b82b5..3d1cf5bf7f18 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "debug.h"
 #include "util.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 802d743378af..ea94d8628980 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_STRBUF_H
 #define __PERF_STRBUF_H
 
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 4dc0af669a30..7f3253d44afd 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "string2.h"
 #include "strfilter.h"
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
index cff5eda88728..e0c25a40f796 100644
--- a/tools/perf/util/strfilter.h
+++ b/tools/perf/util/strfilter.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_STRFILTER_H
 #define __PERF_STRFILTER_H
 /* General purpose glob matching filter */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index cca53b693a48..aaa08ee8c717 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "string2.h"
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 2f619681bd6a..ee14ca5451ab 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_STRING_H
 #define PERF_STRING_H
 
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index 19207e50fce5..d58f1e08b170 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_STRLIST_H
 #define __PERF_STRLIST_H
 
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index 946fdf2db97c..e55338d5c3bd 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SVGHELPER_H
 #define __PERF_SVGHELPER_H
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 502505cf236a..2de770511e70 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <fcntl.h>
 #include <stdio.h>
 #include <errno.h>
@@ -259,7 +260,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 {
         uint32_t nr_rel_entries, idx;
         GElf_Sym sym;
-        u64 plt_offset;
+        u64 plt_offset, plt_header_size, plt_entry_size;
         GElf_Shdr shdr_plt;
         struct symbol *f;
         GElf_Shdr shdr_rel_plt, shdr_dynsym;
@@ -326,6 +327,23 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 
         nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
         plt_offset = shdr_plt.sh_offset;
+        switch (ehdr.e_machine) {
+                case EM_ARM:
+                        plt_header_size = 20;
+                        plt_entry_size = 12;
+                        break;
+
+                case EM_AARCH64:
+                        plt_header_size = 32;
+                        plt_entry_size = 16;
+                        break;
+
+                default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+                        plt_header_size = shdr_plt.sh_entsize;
+                        plt_entry_size = shdr_plt.sh_entsize;
+                        break;
+        }
+        plt_offset += plt_header_size;
 
         if (shdr_rel_plt.sh_type == SHT_RELA) {
                 GElf_Rela pos_mem, *pos;
@@ -335,7 +353,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                         const char *elf_name = NULL;
                         char *demangled = NULL;
                         symidx = GELF_R_SYM(pos->r_info);
-                        plt_offset += shdr_plt.sh_entsize;
                         gelf_getsym(syms, symidx, &sym);
 
                         elf_name = elf_sym__name(&sym, symstrs);
@@ -346,11 +363,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                                  "%s@plt", elf_name);
                         free(demangled);
 
-                        f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+                        f = symbol__new(plt_offset, plt_entry_size,
                                         STB_GLOBAL, sympltname);
                         if (!f)
                                 goto out_elf_end;
 
+                        plt_offset += plt_entry_size;
                         symbols__insert(&dso->symbols[map->type], f);
                         ++nr;
                 }
@@ -361,7 +379,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                         const char *elf_name = NULL;
                         char *demangled = NULL;
                         symidx = GELF_R_SYM(pos->r_info);
-                        plt_offset += shdr_plt.sh_entsize;
                         gelf_getsym(syms, symidx, &sym);
 
                         elf_name = elf_sym__name(&sym, symstrs);
@@ -372,11 +389,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                                  "%s@plt", elf_name);
                         free(demangled);
 
-                        f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+                        f = symbol__new(plt_offset, plt_entry_size,
                                         STB_GLOBAL, sympltname);
                         if (!f)
                                 goto out_elf_end;
 
+                        plt_offset += plt_entry_size;
                         symbols__insert(&dso->symbols[map->type], f);
                         ++nr;
                 }
@@ -391,7 +409,7 @@ out_elf_end:
         return 0;
 }
 
-char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name)
+char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 {
         return demangle_sym(dso, kmodule, elf_name);
 }
@@ -1442,7 +1460,7 @@ static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
 
 static int kcore_copy__process_modules(void *arg,
                                        const char *name __maybe_unused,
-                                       u64 start)
+                                       u64 start, u64 size __maybe_unused)
 {
         struct kcore_copy_info *kci = arg;
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 40bf5d4c0bfd..ff48d0d49584 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
 #include "util.h"
 
@@ -377,7 +378,7 @@ void symbol__elf_init(void)
 
 char *dso__demangle_sym(struct dso *dso __maybe_unused,
                         int kmodule __maybe_unused,
-                        char *elf_name __maybe_unused)
+                        const char *elf_name __maybe_unused)
 {
         return NULL;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e7a98dbd2aed..1b67a8639dfe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
 #include <stdlib.h>
@@ -18,6 +19,7 @@
 #include "symbol.h"
 #include "strlist.h"
 #include "intlist.h"
+#include "namespaces.h"
 #include "header.h"
 #include "path.h"
 #include "sane_ctype.h"
@@ -44,6 +46,7 @@ struct symbol_conf symbol_conf = {
         .show_hist_headers      = true,
         .symfs                  = "",
         .event_group            = true,
+        .inline_name            = true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -52,6 +55,7 @@ static enum dso_binary_type binary_type_symtab[] = {
         DSO_BINARY_TYPE__JAVA_JIT,
         DSO_BINARY_TYPE__DEBUGLINK,
         DSO_BINARY_TYPE__BUILD_ID_CACHE,
+        DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO,
         DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
         DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
         DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
@@ -224,14 +228,15 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
         struct maps *maps = &mg->maps[type];
         struct map *next, *curr;
 
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
 
         curr = maps__first(maps);
         if (curr == NULL)
                 goto out_unlock;
 
         for (next = map__next(curr); next; next = map__next(curr)) {
-                curr->end = next->start;
+                if (!curr->end)
+                        curr->end = next->start;
                 curr = next;
         }
 
@@ -239,10 +244,11 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
          * We still haven't the actual symbols, so guess the
          * last map final address.
          */
-        curr->end = ~0ULL;
+        if (!curr->end)
+                curr->end = ~0ULL;
 
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -550,7 +556,7 @@ void dso__sort_by_name(struct dso *dso, enum map_type type)
 
 int modules__parse(const char *filename, void *arg,
                    int (*process_module)(void *arg, const char *name,
-                                         u64 start))
+                                         u64 start, u64 size))
 {
         char *line = NULL;
         size_t n;
@@ -563,8 +569,8 @@ int modules__parse(const char *filename, void *arg,
 
         while (1) {
                 char name[PATH_MAX];
-                u64 start;
-                char *sep;
+                u64 start, size;
+                char *sep, *endptr;
                 ssize_t line_len;
 
                 line_len = getline(&line, &n, file);
@@ -596,7 +602,11 @@ int modules__parse(const char *filename, void *arg,
 
                 scnprintf(name, sizeof(name), "[%s]", line);
 
-                err = process_module(arg, name, start);
+                size = strtoul(sep + 1, &endptr, 0);
+                if (*endptr != ' ' && *endptr != '\t')
+                        continue;
+
+                err = process_module(arg, name, start, size);
                 if (err)
                         break;
         }
@@ -943,7 +953,8 @@ static struct module_info *find_module(const char *name,
         return NULL;
 }
 
-static int __read_proc_modules(void *arg, const char *name, u64 start)
+static int __read_proc_modules(void *arg, const char *name, u64 start,
+                               u64 size __maybe_unused)
 {
         struct rb_root *modules = arg;
         struct module_info *mi;
@@ -1325,14 +1336,15 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
         return __dso__load_kallsyms(dso, filename, map, false);
 }
 
-static int dso__load_perf_map(struct dso *dso, struct map *map)
+static int dso__load_perf_map(const char *map_path, struct dso *dso,
+                              struct map *map)
 {
         char *line = NULL;
         size_t n;
         FILE *file;
         int nr_syms = 0;
 
-        file = fopen(dso->long_name, "r");
+        file = fopen(map_path, "r");
         if (file == NULL)
                 goto out_failure;
 
@@ -1416,6 +1428,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
                 return kmod && dso->symtab_type == type;
 
         case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+        case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
                 return true;
 
         case DSO_BINARY_TYPE__NOT_FOUND:
@@ -1424,6 +1437,44 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
         }
 }
 
+/* Checks for the existence of the perf-<pid>.map file in two different
+ * locations.  First, if the process is a separate mount namespace, check in
+ * that namespace using the pid of the innermost pid namespace.  If's not in a
+ * namespace, or the file can't be found there, try in the mount namespace of
+ * the tracing process using our view of its pid.
+ */
+static int dso__find_perf_map(char *filebuf, size_t bufsz,
+                              struct nsinfo **nsip)
+{
+        struct nscookie nsc;
+        struct nsinfo *nsi;
+        struct nsinfo *nnsi;
+        int rc = -1;
+
+        nsi = *nsip;
+
+        if (nsi->need_setns) {
+                snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsi->nstgid);
+                nsinfo__mountns_enter(nsi, &nsc);
+                rc = access(filebuf, R_OK);
+                nsinfo__mountns_exit(&nsc);
+                if (rc == 0)
+                        return rc;
+        }
+
+        nnsi = nsinfo__copy(nsi);
+        if (nnsi) {
+                nsinfo__put(nsi);
+
+                nnsi->need_setns = false;
+                snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nnsi->tgid);
+                *nsip = nnsi;
+                rc = 0;
+        }
+
+        return rc;
+}
+
 int dso__load(struct dso *dso, struct map *map)
 {
         char *name;
@@ -1435,8 +1486,21 @@ int dso__load(struct dso *dso, struct map *map)
         struct symsrc ss_[2];
         struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
         bool kmod;
+        bool perfmap;
         unsigned char build_id[BUILD_ID_SIZE];
+        struct nscookie nsc;
+        char newmapname[PATH_MAX];
+        const char *map_path = dso->long_name;
+
+        perfmap = strncmp(dso->name, "/tmp/perf-", 10) == 0;
+        if (perfmap) {
+                if (dso->nsinfo && (dso__find_perf_map(newmapname,
+                    sizeof(newmapname), &dso->nsinfo) == 0)) {
+                        map_path = newmapname;
+                }
+        }
 
+        nsinfo__mountns_enter(dso->nsinfo, &nsc);
         pthread_mutex_lock(&dso->lock);
 
         /* check again under the dso->lock */
@@ -1461,19 +1525,19 @@ int dso__load(struct dso *dso, struct map *map)
 
         dso->adjust_symbols = 0;
 
-        if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+        if (perfmap) {
                 struct stat st;
 
-                if (lstat(dso->name, &st) < 0)
+                if (lstat(map_path, &st) < 0)
                         goto out;
 
                 if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) {
                         pr_warning("File %s not owned by current user or root, "
-                                   "ignoring it (use -f to override).\n", dso->name);
+                                   "ignoring it (use -f to override).\n", map_path);
                         goto out;
                 }
 
-                ret = dso__load_perf_map(dso, map);
+                ret = dso__load_perf_map(map_path, dso, map);
                 dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
                                              DSO_BINARY_TYPE__NOT_FOUND;
                 goto out;
@@ -1511,9 +1575,15 @@ int dso__load(struct dso *dso, struct map *map)
         for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
                 struct symsrc *ss = &ss_[ss_pos];
                 bool next_slot = false;
+                bool is_reg;
+                bool nsexit;
+                int sirc;
 
                 enum dso_binary_type symtab_type = binary_type_symtab[i];
 
+                nsexit = (symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE ||
+                    symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO);
+
                 if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type))
                         continue;
 
@@ -1521,12 +1591,20 @@ int dso__load(struct dso *dso, struct map *map)
                                                    root_dir, name, PATH_MAX))
                         continue;
 
-                if (!is_regular_file(name))
-                        continue;
+                if (nsexit)
+                        nsinfo__mountns_exit(&nsc);
+
+                is_reg = is_regular_file(name);
+                sirc = symsrc__init(ss, dso, name, symtab_type);
 
-                /* Name is now the name of the next image to try */
-                if (symsrc__init(ss, dso, name, symtab_type) < 0)
+                if (nsexit)
+                        nsinfo__mountns_enter(dso->nsinfo, &nsc);
+
+                if (!is_reg || sirc < 0) {
+                        if (sirc >= 0)
+                                symsrc__destroy(ss);
                         continue;
+                }
 
                 if (!syms_ss && symsrc__has_symtab(ss)) {
                         syms_ss = ss;
@@ -1584,6 +1662,7 @@ out_free:
 out:
         dso__set_loaded(dso, map->type);
         pthread_mutex_unlock(&dso->lock);
+        nsinfo__mountns_exit(&nsc);
 
         return ret;
 }
@@ -1594,7 +1673,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
         struct maps *maps = &mg->maps[type];
         struct map *map;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (map = maps__first(maps); map; map = map__next(map)) {
                 if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1604,7 +1683,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
         map = NULL;
 
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return map;
 }
 
@@ -1660,7 +1739,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map)
         }
 
         if (!symbol_conf.ignore_vmlinux_buildid)
-                filename = dso__build_id_filename(dso, NULL, 0);
+                filename = dso__build_id_filename(dso, NULL, 0, false);
         if (filename != NULL) {
                 err = dso__load_vmlinux(dso, map, filename, true);
                 if (err > 0)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 41ebba9a2eb2..a4f0075b4e5c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SYMBOL
 #define __PERF_SYMBOL 1
 
@@ -59,6 +60,7 @@ struct symbol {
         u8              binding;
         u8              idle:1;
         u8              ignore:1;
+        u8              inlined:1;
         u8              arch_sym;
         char            name[0];
 };
@@ -186,6 +188,7 @@ struct addr_map_symbol {
         struct symbol *sym;
         u64           addr;
         u64           al_addr;
+        u64           phys_addr;
 };
 
 struct branch_info {
@@ -207,6 +210,7 @@ struct addr_location {
         struct thread *thread;
         struct map    *map;
         struct symbol *sym;
+        const char    *srcline;
         u64           addr;
         char          level;
         u8            filtered;
@@ -273,7 +277,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int modules__parse(const char *filename, void *arg,
                    int (*process_module)(void *arg, const char *name,
-                                         u64 start));
+                                         u64 start, u64 size));
 int filename__read_debuglink(const char *filename, char *debuglink,
                              size_t size);
 
@@ -306,7 +310,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
                                 struct map *map);
 
-char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name);
+char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
 
 void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 63694e174e5c..6dd2cb88ccbe 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <elf.h>
 #include <inttypes.h>
 #include <stdio.h>
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index bbb4c1957578..6eea7cff3d4e 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -15,10 +15,11 @@
 
 #include "syscalltbl.h"
 #include <stdlib.h>
+#include <linux/compiler.h>
 
 #ifdef HAVE_SYSCALL_TABLE
-#include <linux/compiler.h>
 #include <string.h>
+#include "string2.h"
 #include "util.h"
 
 #if defined(__x86_64__)
@@ -105,6 +106,27 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
         return sc ? sc->id : -1;
 }
 
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        int i;
+        struct syscall *syscalls = tbl->syscalls.entries;
+
+        for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) {
+                if (strglobmatch(syscalls[i].name, syscall_glob)) {
+                        *idx = i;
+                        return syscalls[i].id;
+                }
+        }
+
+        return -1;
+}
+
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        *idx = -1;
+        return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
+}
+
 #else /* HAVE_SYSCALL_TABLE */
 
 #include <libaudit.h>
@@ -131,4 +153,15 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
 {
         return audit_name_to_syscall(name, tbl->audit_machine);
 }
+
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused,
+                                  const char *syscall_glob __maybe_unused, int *idx __maybe_unused)
+{
+        return -1;
+}
+
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
+}
 #endif /* HAVE_SYSCALL_TABLE */
diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h
index e2951510484f..c8e7e9ce0f01 100644
--- a/tools/perf/util/syscalltbl.h
+++ b/tools/perf/util/syscalltbl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SYSCALLTBL_H
 #define __PERF_SYSCALLTBL_H
 
@@ -17,4 +18,7 @@ void syscalltbl__delete(struct syscalltbl *tbl);
 const char *syscalltbl__name(const struct syscalltbl *tbl, int id);
 int syscalltbl__id(struct syscalltbl *tbl, const char *name);
 
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx);
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx);
+
 #endif /* __PERF_SYSCALLTBL_H */
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 7381b1ca4041..446aa7a56f25 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_TARGET_H
 #define _PERF_TARGET_H
 
diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c
index 8f254a74d97d..e7aa82c06c76 100644
--- a/tools/perf/util/term.c
+++ b/tools/perf/util/term.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "term.h"
 #include <stdlib.h>
 #include <termios.h>
diff --git a/tools/perf/util/term.h b/tools/perf/util/term.h
index 2c06a61846a1..607b170a9017 100644
--- a/tools/perf/util/term.h
+++ b/tools/perf/util/term.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_TERM_H
 #define __PERF_TERM_H
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 378c418ca0c1..68b65b10579b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../perf.h"
 #include <errno.h>
 #include <stdlib.h>
@@ -45,6 +46,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                 thread->cpu = -1;
                 INIT_LIST_HEAD(&thread->namespaces_list);
                 INIT_LIST_HEAD(&thread->comm_list);
+                init_rwsem(&thread->namespaces_lock);
+                init_rwsem(&thread->comm_lock);
 
                 comm_str = malloc(32);
                 if (!comm_str)
@@ -59,6 +62,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                 list_add(&comm->list, &thread->comm_list);
                 refcount_set(&thread->refcnt, 1);
                 RB_CLEAR_NODE(&thread->rb_node);
+                /* Thread holds first ref to nsdata. */
+                thread->nsinfo = nsinfo__new(pid);
         }
 
         return thread;
@@ -81,17 +86,26 @@ void thread__delete(struct thread *thread)
                 map_groups__put(thread->mg);
                 thread->mg = NULL;
         }
+        down_write(&thread->namespaces_lock);
         list_for_each_entry_safe(namespaces, tmp_namespaces,
                                  &thread->namespaces_list, list) {
                 list_del(&namespaces->list);
                 namespaces__free(namespaces);
         }
+        up_write(&thread->namespaces_lock);
+
+        down_write(&thread->comm_lock);
         list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
                 list_del(&comm->list);
                 comm__free(comm);
         }
+        up_write(&thread->comm_lock);
+
         unwind__finish_access(thread);
+        nsinfo__zput(thread->nsinfo);
 
+        exit_rwsem(&thread->namespaces_lock);
+        exit_rwsem(&thread->comm_lock);
         free(thread);
 }
 
@@ -122,8 +136,8 @@ struct namespaces *thread__namespaces(const struct thread *thread)
         return list_first_entry(&thread->namespaces_list, struct namespaces, list);
 }
 
-int thread__set_namespaces(struct thread *thread, u64 timestamp,
-                           struct namespaces_event *event)
+static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
+                                    struct namespaces_event *event)
 {
         struct namespaces *new, *curr = thread__namespaces(thread);
 
@@ -146,6 +160,17 @@ int thread__set_namespaces(struct thread *thread, u64 timestamp,
         return 0;
 }
 
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+                           struct namespaces_event *event)
+{
+        int ret;
+
+        down_write(&thread->namespaces_lock);
+        ret = __thread__set_namespaces(thread, timestamp, event);
+        up_write(&thread->namespaces_lock);
+        return ret;
+}
+
 struct comm *thread__comm(const struct thread *thread)
 {
         if (list_empty(&thread->comm_list))
@@ -167,8 +192,8 @@ struct comm *thread__exec_comm(const struct thread *thread)
         return last;
 }
 
-int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
-                       bool exec)
+static int ____thread__set_comm(struct thread *thread, const char *str,
+                                u64 timestamp, bool exec)
 {
         struct comm *new, *curr = thread__comm(thread);
 
@@ -192,6 +217,17 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
         return 0;
 }
 
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+                       bool exec)
+{
+        int ret;
+
+        down_write(&thread->comm_lock);
+        ret = ____thread__set_comm(thread, str, timestamp, exec);
+        up_write(&thread->comm_lock);
+        return ret;
+}
+
 int thread__set_comm_from_proc(struct thread *thread)
 {
         char path[64];
@@ -209,7 +245,7 @@ int thread__set_comm_from_proc(struct thread *thread)
         return err;
 }
 
-const char *thread__comm_str(const struct thread *thread)
+static const char *__thread__comm_str(const struct thread *thread)
 {
         const struct comm *comm = thread__comm(thread);
 
@@ -219,6 +255,17 @@ const char *thread__comm_str(const struct thread *thread)
         return comm__str(comm);
 }
 
+const char *thread__comm_str(const struct thread *thread)
+{
+        const char *str;
+
+        down_read((struct rw_semaphore *)&thread->comm_lock);
+        str = __thread__comm_str(thread);
+        up_read((struct rw_semaphore *)&thread->comm_lock);
+
+        return str;
+}
+
 /* CHECKME: it should probably better return the max comm len from its comm list */
 int thread__comm_len(struct thread *thread)
 {
@@ -261,7 +308,7 @@ static int __thread__prepare_access(struct thread *thread)
                 struct maps *maps = &thread->mg->maps[i];
                 struct map *map;
 
-                pthread_rwlock_rdlock(&maps->lock);
+                down_read(&maps->lock);
 
                 for (map = maps__first(maps); map; map = map__next(map)) {
                         err = unwind__prepare_access(thread, map, &initialized);
@@ -269,7 +316,7 @@ static int __thread__prepare_access(struct thread *thread)
                                 break;
                 }
 
-                pthread_rwlock_unlock(&maps->lock);
+                up_read(&maps->lock);
         }
 
         return err;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 4eb849e9098f..40cfa36c022a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_THREAD_H
 #define __PERF_THREAD_H
 
@@ -9,6 +10,7 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
+#include "rwsem.h"
 
 struct thread_stack;
 struct unwind_libunwind_ops;
@@ -29,11 +31,14 @@ struct thread {
         int                     comm_len;
         bool                    dead; /* if set thread has exited */
         struct list_head        namespaces_list;
+        struct rw_semaphore     namespaces_lock;
         struct list_head        comm_list;
+        struct rw_semaphore     comm_lock;
         u64                     db_id;
 
         void                    *priv;
         struct thread_stack     *ts;
+        struct nsinfo           *nsinfo;
 #ifdef HAVE_LIBUNWIND_SUPPORT
         void                            *addr_space;
         struct unwind_libunwind_ops     *unwind_libunwind_ops;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 63ead7b06324..be0d5a736dea 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
 #include <limits.h>
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index bd34d7a0b9fa..f15803985435 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_THREAD_MAP_H
 #define __PERF_THREAD_MAP_H
 
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 5b5d0214debd..81927d027417 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <string.h>
 #include <sys/time.h>
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 8656be08513b..15b475c50ccf 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TIME_UTILS_H_
 #define _TIME_UTILS_H_
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 829471a1c6d7..2532b558099b 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_TOOL_H
 #define __PERF_TOOL_H
 
@@ -34,6 +35,12 @@ typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
                          struct perf_session *session);
 
+enum show_feature_header {
+        SHOW_FEAT_NO_HEADER = 0,
+        SHOW_FEAT_HEADER,
+        SHOW_FEAT_HEADER_FULL_INFO,
+};
+
 struct perf_tool {
         event_sample    sample,
                         read;
@@ -63,11 +70,13 @@ struct perf_tool {
                         cpu_map,
                         stat_config,
                         stat,
-                        stat_round;
+                        stat_round,
+                        feature;
         event_op3       auxtrace;
         bool            ordered_events;
         bool            ordering_requires_timestamps;
         bool            namespace_events;
+        enum show_feature_header show_feat_hdr;
 };
 
 #endif /* __PERF_TOOL_H */
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 9bdfb78a9a35..9892323cdd7c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_TOP_H
 #define __PERF_TOP_H 1
 
@@ -37,6 +38,7 @@ struct perf_top {
         int                sym_pcnt_filter;
         const char         *sym_filter;
         float              min_percent;
+        unsigned int       nr_threads_synthesize;
 };
 
 #define CONSOLE_CLEAR ""
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index e7d60d05596d..d7f2113462fb 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -28,7 +28,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 8a9a677f7576..40b425949aa3 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -27,7 +27,6 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 #include <sys/mman.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index c330780674fc..16a776371d03 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 1fbc044f9eb0..dcbdb53dc702 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_UTIL_TRACE_EVENT_H
 #define _PERF_UTIL_TRACE_EVENT_H
 
diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
index e97d7016d771..370138e7e35c 100644
--- a/tools/perf/util/trigger.h
+++ b/tools/perf/util/trigger.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TRIGGER_H_
 #define __TRIGGER_H_ 1
 
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 1b741646eed0..bfa782421cbd 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/types.h>
 
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index d5b11e2b85e0..e0c3af34ac8d 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_TSC_H
 #define __PERF_TSC_H
 
diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c
index 4767ec2c5ef6..a46762aec4c9 100644
--- a/tools/perf/util/units.c
+++ b/tools/perf/util/units.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "units.h"
 #include <inttypes.h>
 #include <limits.h>
diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h
index f02c87317150..99263b6a23f7 100644
--- a/tools/perf/util/units.h
+++ b/tools/perf/util/units.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERF_UNIT_H
 #define PERF_UNIT_H
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7755a5e0fe5e..1e9c974faf67 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <elfutils/libdw.h>
 #include <elfutils/libdwfl.h>
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 4a2b269a7b3b..0cbd2650e280 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_UNWIND_LIBDW_H
 #define __PERF_UNWIND_LIBDW_H
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 672c2ada9357..7a42f703e858 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
  *
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 8aef572d0889..647a1e6b4c7b 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "unwind.h"
 #include "thread.h"
 #include "session.h"
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index bfbdcc6198c9..8a44a1569a21 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __UNWIND_H
 #define __UNWIND_H
 
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 6cc9d9888ce0..070d25ceea6a 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * usage.c
  *
diff --git a/tools/perf/util/util-cxx.h b/tools/perf/util/util-cxx.h
index 0e0e019c9f34..80a99e458d4e 100644
--- a/tools/perf/util/util-cxx.h
+++ b/tools/perf/util/util-cxx.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Support C++ source use utilities defined in util.h
  */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 988111e0bab5..a789f952b3e9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "../perf.h"
 #include "util.h"
 #include "debug.h"
@@ -6,6 +7,7 @@
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <dirent.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <signal.h>
 #include <stdio.h>
@@ -22,6 +24,19 @@
 /*
  * XXX We need to find a better place for these things...
  */
+
+bool perf_singlethreaded = true;
+
+void perf_set_singlethreaded(void)
+{
+        perf_singlethreaded = true;
+}
+
+void perf_set_multithreaded(void)
+{
+        perf_singlethreaded = false;
+}
+
 unsigned int page_size;
 int cacheline_size;
 
@@ -143,13 +158,17 @@ out:
         return list;
 }
 
-static int slow_copyfile(const char *from, const char *to)
+static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi)
 {
         int err = -1;
         char *line = NULL;
         size_t n;
-        FILE *from_fp = fopen(from, "r"), *to_fp;
+        FILE *from_fp, *to_fp;
+        struct nscookie nsc;
 
+        nsinfo__mountns_enter(nsi, &nsc);
+        from_fp = fopen(from, "r");
+        nsinfo__mountns_exit(&nsc);
         if (from_fp == NULL)
                 goto out;
 
@@ -170,7 +189,7 @@ out:
         return err;
 }
 
-int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
         void *ptr;
         loff_t pgoff;
@@ -198,15 +217,21 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
         return size ? -1 : 0;
 }
 
-int copyfile_mode(const char *from, const char *to, mode_t mode)
+static int copyfile_mode_ns(const char *from, const char *to, mode_t mode,
+                            struct nsinfo *nsi)
 {
         int fromfd, tofd;
         struct stat st;
-        int err = -1;
+        int err;
         char *tmp = NULL, *ptr = NULL;
+        struct nscookie nsc;
 
-        if (stat(from, &st))
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = stat(from, &st);
+        nsinfo__mountns_exit(&nsc);
+        if (err)
                 goto out;
+        err = -1;
 
         /* extra 'x' at the end is to reserve space for '.' */
         if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
@@ -227,11 +252,13 @@ int copyfile_mode(const char *from, const char *to, mode_t mode)
                 goto out_close_to;
 
         if (st.st_size == 0) { /* /proc? do it slowly... */
-                err = slow_copyfile(from, tmp);
+                err = slow_copyfile(from, tmp, nsi);
                 goto out_close_to;
         }
 
+        nsinfo__mountns_enter(nsi, &nsc);
         fromfd = open(from, O_RDONLY);
+        nsinfo__mountns_exit(&nsc);
         if (fromfd < 0)
                 goto out_close_to;
 
@@ -248,6 +275,16 @@ out:
         return err;
 }
 
+int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi)
+{
+        return copyfile_mode_ns(from, to, 0755, nsi);
+}
+
+int copyfile_mode(const char *from, const char *to, mode_t mode)
+{
+        return copyfile_mode_ns(from, to, mode, NULL);
+}
+
 int copyfile(const char *from, const char *to)
 {
         return copyfile_mode(from, to, 0755);
@@ -259,6 +296,7 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
         size_t left = n;
 
         while (left) {
+                /* buf must be treated as const if !is_read. */
                 ssize_t ret = is_read ? read(fd, buf, left) :
                                         write(fd, buf, left);
 
@@ -286,9 +324,10 @@ ssize_t readn(int fd, void *buf, size_t n)
 /*
  * Write exactly 'n' bytes or return an error.
  */
-ssize_t writen(int fd, void *buf, size_t n)
+ssize_t writen(int fd, const void *buf, size_t n)
 {
-        return ion(false, fd, buf, n);
+        /* ion does not modify buf. */
+        return ion(false, fd, (void *)buf, n);
 }
 
 size_t hex_width(u64 v)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2c9e58a45310..01434509c2e9 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef GIT_COMPAT_UTIL_H
 #define GIT_COMPAT_UTIL_H
 
@@ -5,13 +6,13 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
-#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
 #include <stdarg.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include "namespaces.h"
 
 /* General helper functions */
 void usage(const char *err) __noreturn;
@@ -33,10 +34,10 @@ struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dire
 bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
-int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
+int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
 
 ssize_t readn(int fd, void *buf, size_t n);
-ssize_t writen(int fd, void *buf, size_t n);
+ssize_t writen(int fd, const void *buf, size_t n);
 
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
@@ -58,4 +59,13 @@ const char *perf_tip(const char *dirpath);
 int sched_getcpu(void);
 #endif
 
+#ifndef HAVE_SETNS_SUPPORT
+int setns(int fd, int nstype);
+#endif
+
+extern bool perf_singlethreaded;
+
+void perf_set_singlethreaded(void);
+void perf_set_multithreaded(void);
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 5de2e15e2eda..4b7a303e4ba8 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -12,7 +13,7 @@ int perf_read_values_init(struct perf_read_values *values)
         values->threads_max = 16;
         values->pid = malloc(values->threads_max * sizeof(*values->pid));
         values->tid = malloc(values->threads_max * sizeof(*values->tid));
-        values->value = malloc(values->threads_max * sizeof(*values->value));
+        values->value = zalloc(values->threads_max * sizeof(*values->value));
         if (!values->pid || !values->tid || !values->value) {
                 pr_debug("failed to allocate read_values threads arrays");
                 goto out_free_pid;
@@ -98,15 +99,16 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values,
                         return i;
         }
 
-        i = values->threads + 1;
-        values->value[i] = malloc(values->counters_max * sizeof(**values->value));
+        i = values->threads;
+
+        values->value[i] = zalloc(values->counters_max * sizeof(**values->value));
         if (!values->value[i]) {
                 pr_debug("failed to allocate read_values counters array");
                 return -ENOMEM;
         }
         values->pid[i] = pid;
         values->tid[i] = tid;
-        values->threads = i;
+        values->threads = i + 1;
 
         return i;
 }
@@ -130,12 +132,16 @@ static int perf_read_values__enlarge_counters(struct perf_read_values *values)
 
         for (i = 0; i < values->threads; i++) {
                 u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+                int j;
 
-                if (value) {
+                if (!value) {
                         pr_debug("failed to enlarge read_values ->values array");
                         goto out_free_name;
                 }
 
+                for (j = values->counters_max; j < counters_max; j++)
+                        value[j] = 0;
+
                 values->value[i] = value;
         }
 
@@ -187,7 +193,7 @@ int perf_read_values_add_value(struct perf_read_values *values,
         if (cindex < 0)
                 return cindex;
 
-        values->value[tindex][cindex] = value;
+        values->value[tindex][cindex] += value;
         return 0;
 }
 
diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h
index 808ff9c73bf5..8c41f22f42cf 100644
--- a/tools/perf/util/values.h
+++ b/tools/perf/util/values.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_VALUES_H
 #define __PERF_VALUES_H
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index d3c39eec89a8..0acb1ec0e2f0 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -319,7 +320,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
         struct vdso_info *vdso_info;
         struct dso *dso = NULL;
 
-        pthread_rwlock_wrlock(&machine->dsos.lock);
+        down_write(&machine->dsos.lock);
         if (!machine->vdso_info)
                 machine->vdso_info = vdso_info__new();
 
@@ -347,7 +348,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 
 out_unlock:
         dso__get(dso);
-        pthread_rwlock_unlock(&machine->dsos.lock);
+        up_write(&machine->dsos.lock);
         return dso;
 }
 
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index cdc4fabfc212..bc74ace603ae 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_VDSO__
 #define __PERF_VDSO__
 
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index 7251fdbabced..dc95154f5646 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "xyarray.h"
 #include "util.h"
 #include <stdlib.h>
@@ -12,6 +13,8 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
                 xy->entry_size = entry_size;
                 xy->row_size   = row_size;
                 xy->entries    = xlen * ylen;
+                xy->max_x      = xlen;
+                xy->max_y      = ylen;
         }
 
         return xy;
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 7f30af371b7e..7ffe562e7ae7 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PERF_XYARRAY_H_
 #define _PERF_XYARRAY_H_ 1
 
@@ -7,6 +8,8 @@ struct xyarray {
         size_t row_size;
         size_t entry_size;
         size_t entries;
+        size_t max_x;
+        size_t max_y;
         char contents[];
 };
 
@@ -19,4 +22,14 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
         return &xy->contents[x * xy->row_size + y * xy->entry_size];
 }
 
+static inline int xyarray__max_y(struct xyarray *xy)
+{
+        return xy->max_y;
+}
+
+static inline int xyarray__max_x(struct xyarray *xy)
+{
+        return xy->max_x;
+}
+
 #endif /* _PERF_XYARRAY_H_ */
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 1329d843eb7b..a725b958cf31 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/stat.h>
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index 82a2ff896a95..52a39ecf5ca1 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -759,7 +759,7 @@ static acpi_status osl_list_bios_tables(void)
 
                 /* Skip NULL entries in RSDT/XSDT */
 
-                if (!table_address) {
+                if (table_address == 0) {
                         continue;
                 }
 
@@ -808,7 +808,8 @@ osl_get_bios_table(char *signature,
         u8 number_of_tables;
         u8 item_size;
         u32 current_instance = 0;
-        acpi_physical_address table_address = 0;
+        acpi_physical_address table_address;
+        acpi_physical_address first_table_address = 0;
         u32 table_length = 0;
         acpi_status status = AE_OK;
         u32 i;
@@ -820,9 +821,10 @@ osl_get_bios_table(char *signature,
             ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT) ||
             ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT) ||
             ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) {
-                if (instance > 0) {
-                        return (AE_LIMIT);
-                }
+
+find_next_instance:
+
+                table_address = 0;
 
                 /*
                  * Get the appropriate address, either 32-bit or 64-bit. Be very
@@ -830,41 +832,66 @@ osl_get_bios_table(char *signature,
                  * Note: The 64-bit addresses have priority.
                  */
                 if (ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT)) {
-                        if ((gbl_fadt->header.length >= MIN_FADT_FOR_XDSDT) &&
-                            gbl_fadt->Xdsdt) {
-                                table_address =
-                                    (acpi_physical_address)gbl_fadt->Xdsdt;
-                        } else
-                            if ((gbl_fadt->header.length >= MIN_FADT_FOR_DSDT)
-                                && gbl_fadt->dsdt) {
-                                table_address =
-                                    (acpi_physical_address)gbl_fadt->dsdt;
+                        if (current_instance < 2) {
+                                if ((gbl_fadt->header.length >=
+                                     MIN_FADT_FOR_XDSDT) && gbl_fadt->Xdsdt
+                                    && current_instance == 0) {
+                                        table_address =
+                                            (acpi_physical_address)gbl_fadt->
+                                            Xdsdt;
+                                } else
+                                    if ((gbl_fadt->header.length >=
+                                         MIN_FADT_FOR_DSDT)
+                                        && gbl_fadt->dsdt !=
+                                        first_table_address) {
+                                        table_address =
+                                            (acpi_physical_address)gbl_fadt->
+                                            dsdt;
+                                }
                         }
                 } else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) {
-                        if ((gbl_fadt->header.length >= MIN_FADT_FOR_XFACS) &&
-                            gbl_fadt->Xfacs) {
-                                table_address =
-                                    (acpi_physical_address)gbl_fadt->Xfacs;
-                        } else
-                            if ((gbl_fadt->header.length >= MIN_FADT_FOR_FACS)
-                                && gbl_fadt->facs) {
-                                table_address =
-                                    (acpi_physical_address)gbl_fadt->facs;
+                        if (current_instance < 2) {
+                                if ((gbl_fadt->header.length >=
+                                     MIN_FADT_FOR_XFACS) && gbl_fadt->Xfacs
+                                    && current_instance == 0) {
+                                        table_address =
+                                            (acpi_physical_address)gbl_fadt->
+                                            Xfacs;
+                                } else
+                                    if ((gbl_fadt->header.length >=
+                                         MIN_FADT_FOR_FACS)
+                                        && gbl_fadt->facs !=
+                                        first_table_address) {
+                                        table_address =
+                                            (acpi_physical_address)gbl_fadt->
+                                            facs;
+                                }
                         }
                 } else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT)) {
                         if (!gbl_revision) {
                                 return (AE_BAD_SIGNATURE);
                         }
-                        table_address =
-                            (acpi_physical_address)gbl_rsdp.
-                            xsdt_physical_address;
+                        if (current_instance == 0) {
+                                table_address =
+                                    (acpi_physical_address)gbl_rsdp.
+                                    xsdt_physical_address;
+                        }
                 } else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_RSDT)) {
-                        table_address =
-                            (acpi_physical_address)gbl_rsdp.
-                            rsdt_physical_address;
+                        if (current_instance == 0) {
+                                table_address =
+                                    (acpi_physical_address)gbl_rsdp.
+                                    rsdt_physical_address;
+                        }
                 } else {
-                        table_address = (acpi_physical_address)gbl_rsdp_address;
-                        signature = ACPI_SIG_RSDP;
+                        if (current_instance == 0) {
+                                table_address =
+                                    (acpi_physical_address)gbl_rsdp_address;
+                                signature = ACPI_SIG_RSDP;
+                        }
+                }
+
+                if (table_address == 0) {
+                        goto exit_find_table;
                 }
 
                 /* Now we can get the requested special table */
@@ -875,6 +902,18 @@ osl_get_bios_table(char *signature,
                 }
 
                 table_length = ap_get_table_length(mapped_table);
+                if (first_table_address == 0) {
+                        first_table_address = table_address;
+                }
+
+                /* Match table instance */
+
+                if (current_instance != instance) {
+                        osl_unmap_table(mapped_table);
+                        mapped_table = NULL;
+                        current_instance++;
+                        goto find_next_instance;
+                }
         } else {                /* Case for a normal ACPI table */
 
                 if (osl_can_use_xsdt()) {
@@ -913,7 +952,7 @@ osl_get_bios_table(char *signature,
 
                         /* Skip NULL entries in RSDT/XSDT */
 
-                        if (!table_address) {
+                        if (table_address == 0) {
                                 continue;
                         }
 
@@ -946,6 +985,8 @@ osl_get_bios_table(char *signature,
                 }
         }
 
+exit_find_table:
+
         if (!mapped_table) {
                 return (AE_LIMIT);
         }
diff --git a/tools/power/acpi/tools/acpidump/Makefile b/tools/power/acpi/tools/acpidump/Makefile
index f7c7af1f9258..b436f8675f6a 100644
--- a/tools/power/acpi/tools/acpidump/Makefile
+++ b/tools/power/acpi/tools/acpidump/Makefile
@@ -39,6 +39,7 @@ TOOL_OBJS = \
         utnonansi.o\
         utprint.o\
         utstring.o\
+        utstrsuppt.o\
         utstrtoul64.o\
         utxferror.o\
         oslinuxtbl.o\
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 60df1fbd4a77..0634449156d8 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -287,8 +287,7 @@ int ap_dump_table_by_address(char *ascii_address)
 
         /* Convert argument to an integer physical address */
 
-        status = acpi_ut_strtoul64(ascii_address, ACPI_STRTOUL_64BIT,
-                                   &long_address);
+        status = acpi_ut_strtoul64(ascii_address, &long_address);
         if (ACPI_FAILURE(status)) {
                 fprintf(stderr, "%s: Could not convert to a physical address\n",
                         ascii_address);
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index 31b5a7f74015..d686e11936c4 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -61,7 +61,7 @@ static int ap_is_existing_file(char *pathname);
 
 static int ap_is_existing_file(char *pathname)
 {
-#ifndef _GNU_EFI
+#if !defined(_GNU_EFI) && !defined(_EDK2_EFI)
         struct stat stat_info;
 
         if (!stat(pathname, &stat_info)) {
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index dd82afa897bd..22c3b4ee1617 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -208,9 +208,7 @@ static int ap_do_options(int argc, char **argv)
                 case 'r':       /* Dump tables from specified RSDP */
 
                         status =
-                            acpi_ut_strtoul64(acpi_gbl_optarg,
-                                              ACPI_STRTOUL_64BIT,
-                                              &gbl_rsdp_base);
+                            acpi_ut_strtoul64(acpi_gbl_optarg, &gbl_rsdp_base);
                         if (ACPI_FAILURE(status)) {
                                 fprintf(stderr,
                                         "%s: Could not convert to a physical address\n",
@@ -300,7 +298,7 @@ static int ap_do_options(int argc, char **argv)
  *
  ******************************************************************************/
 
-#ifndef _GNU_EFI
+#if !defined(_GNU_EFI) && !defined(_EDK2_EFI)
 int ACPI_SYSTEM_XFACE main(int argc, char *argv[])
 #else
 int ACPI_SYSTEM_XFACE acpi_main(int argc, char *argv[])
diff --git a/tools/power/cpupower/.gitignore b/tools/power/cpupower/.gitignore
index d42073f12609..1f9977cc609c 100644
--- a/tools/power/cpupower/.gitignore
+++ b/tools/power/cpupower/.gitignore
@@ -1,7 +1,6 @@
 .libs
 libcpupower.so
-libcpupower.so.0
-libcpupower.so.0.0.0
+libcpupower.so.*
 build/ccdv
 cpufreq-info
 cpufreq-set
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index d6e1c02ddcfe..1dd5f4fcffd5 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -26,10 +26,12 @@ endif
 
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
-OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+OUTDIR := $(shell cd $(OUTPUT) && pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
+include ../../scripts/Makefile.arch
+
 # --- CONFIGURATION BEGIN ---
 
 # Set the following to `true' to make a unstripped, unoptimized
@@ -79,7 +81,11 @@ bindir ?=	/usr/bin
 sbindir ?=      /usr/sbin
 mandir ?=       /usr/man
 includedir ?=   /usr/include
+ifeq ($(IS_64_BIT), 1)
+libdir ?=       /usr/lib64
+else
 libdir ?=       /usr/lib
+endif
 localedir ?=    /usr/share/locale
 docdir ?=       /usr/share/doc/packages/cpupower
 confdir ?=      /etc/
diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index 3e59f1aa3947..d79ab161cc75 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 OUTPUT := ./
 ifeq ("$(origin O)", "command line")
 ifneq ($(O),)
diff --git a/tools/power/cpupower/debug/i386/Makefile b/tools/power/cpupower/debug/i386/Makefile
index c05cc0ac80c7..b3f771039b17 100644
--- a/tools/power/cpupower/debug/i386/Makefile
+++ b/tools/power/cpupower/debug/i386/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 OUTPUT=./
 ifeq ("$(origin O)", "command line")
         OUTPUT := $(O)/
diff --git a/tools/power/cpupower/debug/kernel/Makefile b/tools/power/cpupower/debug/kernel/Makefile
index a8a6f8eec5c2..c23e5a6ceb7e 100644
--- a/tools/power/cpupower/debug/kernel/Makefile
+++ b/tools/power/cpupower/debug/kernel/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-m   :=
 
 KDIR    := /lib/modules/$(shell uname -r)/build
diff --git a/tools/power/cpupower/debug/x86_64/Makefile b/tools/power/cpupower/debug/x86_64/Makefile
index 1c5214526716..59af84b8ef45 100644
--- a/tools/power/cpupower/debug/x86_64/Makefile
+++ b/tools/power/cpupower/debug/x86_64/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 OUTPUT=./
 ifeq ("$(origin O)", "command line")
         OUTPUT := $(O)/
diff --git a/tools/power/cpupower/lib/cpuidle.h b/tools/power/cpupower/lib/cpuidle.h
index 04eb3cfa6e42..2e10fead2e1e 100644
--- a/tools/power/cpupower/lib/cpuidle.h
+++ b/tools/power/cpupower/lib/cpuidle.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CPUPOWER_CPUIDLE_H__
 #define __CPUPOWER_CPUIDLE_H__
 
diff --git a/tools/power/cpupower/lib/cpupower.h b/tools/power/cpupower/lib/cpupower.h
index fa031fcc7710..e4e4292eacec 100644
--- a/tools/power/cpupower/lib/cpupower.h
+++ b/tools/power/cpupower/lib/cpupower.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CPUPOWER_CPUPOWER_H__
 #define __CPUPOWER_CPUPOWER_H__
 
diff --git a/tools/power/cpupower/lib/cpupower_intern.h b/tools/power/cpupower/lib/cpupower_intern.h
index f8ec4009621c..92affdfbe417 100644
--- a/tools/power/cpupower/lib/cpupower_intern.h
+++ b/tools/power/cpupower/lib/cpupower_intern.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #define PATH_TO_CPU "/sys/devices/system/cpu/"
 #define MAX_LINE_LEN 4096
 #define SYSFS_PATH_MAX 255
diff --git a/tools/power/cpupower/utils/builtin.h b/tools/power/cpupower/utils/builtin.h
index 2284c8ea4e2a..f7065ae60a14 100644
--- a/tools/power/cpupower/utils/builtin.h
+++ b/tools/power/cpupower/utils/builtin.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BUILTIN_H
 #define BUILTIN_H
 
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index 3e701f0e9c14..df43cd45d810 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -93,8 +93,6 @@ static void print_speed(unsigned long speed)
                 if (speed > 1000000)
                         printf("%u.%06u GHz", ((unsigned int) speed/1000000),
                                 ((unsigned int) speed%1000000));
-                else if (speed > 100000)
-                        printf("%u MHz", (unsigned int) speed);
                 else if (speed > 1000)
                         printf("%u.%03u MHz", ((unsigned int) speed/1000),
                                 (unsigned int) (speed%1000));
diff --git a/tools/power/cpupower/utils/cpuidle-set.c b/tools/power/cpupower/utils/cpuidle-set.c
index 691c24d50ef4..569f268f4c7f 100644
--- a/tools/power/cpupower/utils/cpuidle-set.c
+++ b/tools/power/cpupower/utils/cpuidle-set.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <unistd.h>
 #include <stdio.h>
 #include <errno.h>
diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c
index 9ea914378985..2dccf4998599 100644
--- a/tools/power/cpupower/utils/cpupower.c
+++ b/tools/power/cpupower/utils/cpupower.c
@@ -12,6 +12,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <errno.h>
+#include <sched.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/utsname.h>
@@ -31,6 +32,7 @@ static int cmd_help(int argc, const char **argv);
  */
 struct cpupower_cpu_info cpupower_cpu_info;
 int run_as_root;
+int base_cpu;
 /* Affected cpus chosen by -c/--cpu param */
 struct bitmask *cpus_chosen;
 
@@ -174,6 +176,7 @@ int main(int argc, const char *argv[])
         unsigned int i, ret;
         struct stat statbuf;
         struct utsname uts;
+        char pathname[32];
 
         cpus_chosen = bitmask_alloc(sysconf(_SC_NPROCESSORS_CONF));
 
@@ -198,17 +201,23 @@ int main(int argc, const char *argv[])
                 argv[0] = cmd = "help";
         }
 
-        get_cpu_info(0, &cpupower_cpu_info);
+        base_cpu = sched_getcpu();
+        if (base_cpu < 0) {
+                fprintf(stderr, _("No valid cpus found.\n"));
+                return EXIT_FAILURE;
+        }
+
+        get_cpu_info(&cpupower_cpu_info);
         run_as_root = !geteuid();
         if (run_as_root) {
                 ret = uname(&uts);
+                sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
                 if (!ret && !strcmp(uts.machine, "x86_64") &&
-                    stat("/dev/cpu/0/msr", &statbuf) != 0) {
+                    stat(pathname, &statbuf) != 0) {
                         if (system("modprobe msr") == -1)
         fprintf(stderr, _("MSR access not available.\n"));
                 }
         }
-                
 
         for (i = 0; i < ARRAY_SIZE(commands); i++) {
                 struct cmd_struct *p = commands + i;
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index 5fd5c5b8c7b8..bb41cdd0df6b 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #if defined(__i386__) || defined(__x86_64__)
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/power/cpupower/utils/helpers/bitmask.c b/tools/power/cpupower/utils/helpers/bitmask.c
index 5c074c60f904..6c7932f5bd66 100644
--- a/tools/power/cpupower/utils/helpers/bitmask.c
+++ b/tools/power/cpupower/utils/helpers/bitmask.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/power/cpupower/utils/helpers/bitmask.h b/tools/power/cpupower/utils/helpers/bitmask.h
index eb289df41053..b98d93a44e1b 100644
--- a/tools/power/cpupower/utils/helpers/bitmask.h
+++ b/tools/power/cpupower/utils/helpers/bitmask.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CPUPOWER_BITMASK__
 #define __CPUPOWER_BITMASK__
 
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 39c2c7d067bb..732b0b41ba26 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <errno.h>
 #include <string.h>
@@ -42,7 +43,7 @@ cpuid_func(edx);
  *
  * TBD: Should there be a cpuid alternative for this if /proc is not mounted?
  */
-int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info)
+int get_cpu_info(struct cpupower_cpu_info *cpu_info)
 {
         FILE *fp;
         char value[64];
@@ -70,7 +71,7 @@ int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info)
                 if (!strncmp(value, "processor\t: ", 12))
                         sscanf(value, "processor\t: %u", &proc);
 
-                if (proc != cpu)
+                if (proc != (unsigned int)base_cpu)
                         continue;
 
                 /* Get CPU vendor */
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 799a18be60aa..41da392be448 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -34,6 +34,7 @@
 /* Internationalization ****************************/
 
 extern int run_as_root;
+extern int base_cpu;
 extern struct bitmask *cpus_chosen;
 
 /* Global verbose (-d) stuff *********************************/
@@ -87,11 +88,11 @@ struct cpupower_cpu_info {
  *
  * Extract CPU vendor, family, model, stepping info from /proc/cpuinfo
  *
- * Returns 0 on success or a negativ error code
+ * Returns 0 on success or a negative error code
  * Only used on x86, below global's struct values are zero/unknown on
  * other archs
  */
-extern int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info);
+extern int get_cpu_info(struct cpupower_cpu_info *cpu_info);
 extern struct cpupower_cpu_info cpupower_cpu_info;
 /* cpuid and cpuinfo helpers  **************************/
 
diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c
index 601d719d4e60..80fdf55f414d 100644
--- a/tools/power/cpupower/utils/helpers/misc.c
+++ b/tools/power/cpupower/utils/helpers/misc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #if defined(__i386__) || defined(__x86_64__)
 
 #include "helpers/helpers.h"
@@ -13,7 +14,7 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active,
 
         *support = *active = *states = 0;
 
-        ret = get_cpu_info(0, &cpu_info);
+        ret = get_cpu_info(&cpu_info);
         if (ret)
                 return ret;
 
diff --git a/tools/power/cpupower/utils/helpers/msr.c b/tools/power/cpupower/utils/helpers/msr.c
index 31a4b24a8bc6..ab9950748838 100644
--- a/tools/power/cpupower/utils/helpers/msr.c
+++ b/tools/power/cpupower/utils/helpers/msr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #if defined(__i386__) || defined(__x86_64__)
 
 #include <fcntl.h>
diff --git a/tools/power/cpupower/utils/helpers/pci.c b/tools/power/cpupower/utils/helpers/pci.c
index 8b278983cfc5..113f3da2a203 100644
--- a/tools/power/cpupower/utils/helpers/pci.c
+++ b/tools/power/cpupower/utils/helpers/pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #if defined(__i386__) || defined(__x86_64__)
 
 #include <helpers/helpers.h>
diff --git a/tools/power/cpupower/utils/helpers/sysfs.h b/tools/power/cpupower/utils/helpers/sysfs.h
index d28f11fedbda..0f0b9ad97e4a 100644
--- a/tools/power/cpupower/utils/helpers/sysfs.h
+++ b/tools/power/cpupower/utils/helpers/sysfs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CPUPOWER_HELPERS_SYSFS_H__
 #define __CPUPOWER_HELPERS_SYSFS_H__
 
diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
index ebeaba6571a3..f794d6bbb7e9 100644
--- a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
@@ -123,7 +123,7 @@ static int hsw_ext_start(void)
                         previous_count[num][cpu] = val;
                 }
         }
-        hsw_ext_get_count(TSC, &tsc_at_measure_start, 0);
+        hsw_ext_get_count(TSC, &tsc_at_measure_start, base_cpu);
         return 0;
 }
 
@@ -132,7 +132,7 @@ static int hsw_ext_stop(void)
         unsigned long long val;
         int num, cpu;
 
-        hsw_ext_get_count(TSC, &tsc_at_measure_end, 0);
+        hsw_ext_get_count(TSC, &tsc_at_measure_end, base_cpu);
 
         for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) {
                 for (cpu = 0; cpu < cpu_count; cpu++) {
diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
index c83f1606970b..d7c2a6d13dea 100644
--- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
@@ -80,7 +80,8 @@ static int *is_valid;
 static int mperf_get_tsc(unsigned long long *tsc)
 {
         int ret;
-        ret = read_msr(0, MSR_TSC, tsc);
+
+        ret = read_msr(base_cpu, MSR_TSC, tsc);
         if (ret)
                 dprint("Reading TSC MSR failed, returning %llu\n", *tsc);
         return ret;
diff --git a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c
index d2a91dd0d563..abf8cb5f7349 100644
--- a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c
@@ -129,7 +129,7 @@ static int nhm_start(void)
         int num, cpu;
         unsigned long long dbg, val;
 
-        nhm_get_count(TSC, &tsc_at_measure_start, 0);
+        nhm_get_count(TSC, &tsc_at_measure_start, base_cpu);
 
         for (num = 0; num < NHM_CSTATE_COUNT; num++) {
                 for (cpu = 0; cpu < cpu_count; cpu++) {
@@ -137,7 +137,7 @@ static int nhm_start(void)
                         previous_count[num][cpu] = val;
                 }
         }
-        nhm_get_count(TSC, &dbg, 0);
+        nhm_get_count(TSC, &dbg, base_cpu);
         dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start);
         return 0;
 }
@@ -148,7 +148,7 @@ static int nhm_stop(void)
         unsigned long long dbg;
         int num, cpu;
 
-        nhm_get_count(TSC, &tsc_at_measure_end, 0);
+        nhm_get_count(TSC, &tsc_at_measure_end, base_cpu);
 
         for (num = 0; num < NHM_CSTATE_COUNT; num++) {
                 for (cpu = 0; cpu < cpu_count; cpu++) {
@@ -156,7 +156,7 @@ static int nhm_stop(void)
                         current_count[num][cpu] = val;
                 }
         }
-        nhm_get_count(TSC, &dbg, 0);
+        nhm_get_count(TSC, &dbg, base_cpu);
         dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end);
 
         return 0;
diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
index efc8a69c9aba..a2b45219648d 100644
--- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
@@ -120,7 +120,7 @@ static int snb_start(void)
                         previous_count[num][cpu] = val;
                 }
         }
-        snb_get_count(TSC, &tsc_at_measure_start, 0);
+        snb_get_count(TSC, &tsc_at_measure_start, base_cpu);
         return 0;
 }
 
@@ -129,7 +129,7 @@ static int snb_stop(void)
         unsigned long long val;
         int num, cpu;
 
-        snb_get_count(TSC, &tsc_at_measure_end, 0);
+        snb_get_count(TSC, &tsc_at_measure_end, base_cpu);
 
         for (num = 0; num < SNB_CSTATE_COUNT; num++) {
                 for (cpu = 0; cpu < cpu_count; cpu++) {
diff --git a/tools/power/cpupower/utils/version-gen.sh b/tools/power/cpupower/utils/version-gen.sh
index 5ec41c556992..c70de2eabffb 100755
--- a/tools/power/cpupower/utils/version-gen.sh
+++ b/tools/power/cpupower/utils/version-gen.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 #
 # Script which prints out the version to use for building cpupowerutils.
 # Must be called from tools/power/cpupower/
diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile
index 4d0ccc89e6c6..4e1e999e7b05 100644
--- a/tools/power/pm-graph/Makefile
+++ b/tools/power/pm-graph/Makefile
@@ -1,10 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
 PREFIX          ?= /usr
 DESTDIR         ?=
 
 all:
         @echo "Nothing to build"
 
-install :
+install : uninstall
         install -d  $(DESTDIR)$(PREFIX)/lib/pm-graph
         install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph
         install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph
@@ -17,12 +18,15 @@ install :
         install sleepgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
 
 uninstall :
-        rm $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8
-        rm $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8
+        rm -f $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8
+        rm -f $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8
 
-        rm $(DESTDIR)$(PREFIX)/bin/bootgraph
-        rm $(DESTDIR)$(PREFIX)/bin/sleepgraph
+        rm -f $(DESTDIR)$(PREFIX)/bin/bootgraph
+        rm -f $(DESTDIR)$(PREFIX)/bin/sleepgraph
 
-        rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py
-        rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py
-        rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph
+        rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py
+        rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py
+        rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/*.pyc
+        if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph ] ; then \
+                rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph; \
+        fi;
diff --git a/tools/power/pm-graph/analyze_boot.py b/tools/power/pm-graph/analyze_boot.py
index 3e1dcbbf1adc..e83df141a597 100755
--- a/tools/power/pm-graph/analyze_boot.py
+++ b/tools/power/pm-graph/analyze_boot.py
@@ -42,7 +42,7 @@ import analyze_suspend as aslib
 #        store system values and test parameters
 class SystemValues(aslib.SystemValues):
         title = 'BootGraph'
-        version = 2.0
+        version = '2.1'
         hostname = 'localhost'
         testtime = ''
         kernel = ''
@@ -50,9 +50,14 @@ class SystemValues(aslib.SystemValues):
         ftracefile = ''
         htmlfile = 'bootgraph.html'
         outfile = ''
-        phoronix = False
-        addlogs = False
+        testdir = ''
+        testdirprefix = 'boot'
+        embedded = False
+        testlog = False
+        dmesglog = False
+        ftracelog = False
         useftrace = False
+        usecallgraph = False
         usedevsrc = True
         suspendmode = 'boot'
         max_graph_depth = 2
@@ -61,10 +66,12 @@ class SystemValues(aslib.SystemValues):
         manual = False
         iscronjob = False
         timeformat = '%.6f'
+        bootloader = 'grub'
+        blexec = []
         def __init__(self):
                 if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ):
-                        self.phoronix = True
-                        self.addlogs = True
+                        self.embedded = True
+                        self.dmesglog = True
                         self.outfile = os.environ['LOG_FILE']
                         self.htmlfile = os.environ['LOG_FILE']
                 self.hostname = platform.node()
@@ -76,42 +83,80 @@ class SystemValues(aslib.SystemValues):
                         self.kernel = self.kernelVersion(val)
                 else:
                         self.kernel = 'unknown'
+                self.testdir = datetime.now().strftime('boot-%y%m%d-%H%M%S')
         def kernelVersion(self, msg):
                 return msg.split()[2]
+        def checkFtraceKernelVersion(self):
+                val = tuple(map(int, self.kernel.split('-')[0].split('.')))
+                if val >= (4, 10, 0):
+                        return True
+                return False
         def kernelParams(self):
                 cmdline = 'initcall_debug log_buf_len=32M'
                 if self.useftrace:
-                        cmdline += ' trace_buf_size=128M trace_clock=global '\
+                        if self.cpucount > 0:
+                                bs = min(self.memtotal / 2, 2*1024*1024) / self.cpucount
+                        else:
+                                bs = 131072
+                        cmdline += ' trace_buf_size=%dK trace_clock=global '\
                         'trace_options=nooverwrite,funcgraph-abstime,funcgraph-cpu,'\
                         'funcgraph-duration,funcgraph-proc,funcgraph-tail,'\
                         'nofuncgraph-overhead,context-info,graph-time '\
                         'ftrace=function_graph '\
                         'ftrace_graph_max_depth=%d '\
                         'ftrace_graph_filter=%s' % \
-                                (self.max_graph_depth, self.graph_filter)
+                                (bs, self.max_graph_depth, self.graph_filter)
                 return cmdline
         def setGraphFilter(self, val):
-                fp = open(self.tpath+'available_filter_functions')
-                master = fp.read().split('\n')
-                fp.close()
+                master = self.getBootFtraceFilterFunctions()
+                fs = ''
                 for i in val.split(','):
                         func = i.strip()
+                        if func == '':
+                                doError('badly formatted filter function string')
+                        if '[' in func or ']' in func:
+                                doError('loadable module functions not allowed - "%s"' % func)
+                        if ' ' in func:
+                                doError('spaces found in filter functions - "%s"' % func)
                         if func not in master:
                                 doError('function "%s" not available for ftrace' % func)
-                self.graph_filter = val
+                        if not fs:
+                                fs = func
+                        else:
+                                fs += ','+func
+                if not fs:
+                        doError('badly formatted filter function string')
+                self.graph_filter = fs
+        def getBootFtraceFilterFunctions(self):
+                self.rootCheck(True)
+                fp = open(self.tpath+'available_filter_functions')
+                fulllist = fp.read().split('\n')
+                fp.close()
+                list = []
+                for i in fulllist:
+                        if not i or ' ' in i or '[' in i or ']' in i:
+                                continue
+                        list.append(i)
+                return list
+        def myCronJob(self, line):
+                if '@reboot' not in line:
+                        return False
+                if 'bootgraph' in line or 'analyze_boot.py' in line or '-cronjob' in line:
+                        return True
+                return False
         def cronjobCmdString(self):
                 cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0])
                 args = iter(sys.argv[1:])
                 for arg in args:
                         if arg in ['-h', '-v', '-cronjob', '-reboot']:
                                 continue
-                        elif arg in ['-o', '-dmesg', '-ftrace', '-filter']:
+                        elif arg in ['-o', '-dmesg', '-ftrace', '-func']:
                                 args.next()
                                 continue
                         cmdline += ' '+arg
                 if self.graph_filter != 'do_one_initcall':
-                        cmdline += ' -filter "%s"' % self.graph_filter
-                cmdline += ' -o "%s"' % os.path.abspath(self.htmlfile)
+                        cmdline += ' -func "%s"' % self.graph_filter
+                cmdline += ' -o "%s"' % os.path.abspath(self.testdir)
                 return cmdline
         def manualRebootRequired(self):
                 cmdline = self.kernelParams()
@@ -121,6 +166,39 @@ class SystemValues(aslib.SystemValues):
                 print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n'
                 print 'CMDLINE="%s"' % cmdline
                 sys.exit()
+        def getExec(self, cmd):
+                dirlist = ['/sbin', '/bin', '/usr/sbin', '/usr/bin',
+                        '/usr/local/sbin', '/usr/local/bin']
+                for path in dirlist:
+                        cmdfull = os.path.join(path, cmd)
+                        if os.path.exists(cmdfull):
+                                return cmdfull
+                return ''
+        def blGrub(self):
+                blcmd = ''
+                for cmd in ['update-grub', 'grub-mkconfig', 'grub2-mkconfig']:
+                        if blcmd:
+                                break
+                        blcmd = self.getExec(cmd)
+                if not blcmd:
+                        doError('[GRUB] missing update command')
+                if not os.path.exists('/etc/default/grub'):
+                        doError('[GRUB] missing /etc/default/grub')
+                if 'grub2' in blcmd:
+                        cfg = '/boot/grub2/grub.cfg'
+                else:
+                        cfg = '/boot/grub/grub.cfg'
+                if not os.path.exists(cfg):
+                        doError('[GRUB] missing %s' % cfg)
+                if 'update-grub' in blcmd:
+                        self.blexec = [blcmd]
+                else:
+                        self.blexec = [blcmd, '-o', cfg]
+        def getBootLoader(self):
+                if self.bootloader == 'grub':
+                        self.blGrub()
+                else:
+                        doError('unknown boot loader: %s' % self.bootloader)
 
 sysvals = SystemValues()
 
@@ -136,20 +214,23 @@ class Data(aslib.Data):
         idstr = ''
         html_device_id = 0
         valid = False
-        initstart = 0.0
+        tUserMode = 0.0
         boottime = ''
-        phases = ['boot']
+        phases = ['kernel', 'user']
         do_one_initcall = False
         def __init__(self, num):
                 self.testnumber = num
                 self.idstr = 'a'
                 self.dmesgtext = []
                 self.dmesg = {
-                        'boot': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, 'color': '#dddddd'}
+                        'kernel': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0,
+                                'order': 0, 'color': 'linear-gradient(to bottom, #fff, #bcf)'},
+                        'user': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0,
+                                'order': 1, 'color': '#fff'}
                 }
         def deviceTopology(self):
                 return ''
-        def newAction(self, phase, name, start, end, ret, ulen):
+        def newAction(self, phase, name, pid, start, end, ret, ulen):
                 # new device callback for a specific phase
                 self.html_device_id += 1
                 devid = '%s%d' % (self.idstr, self.html_device_id)
@@ -163,41 +244,46 @@ class Data(aslib.Data):
                         name = '%s[%d]' % (origname, i)
                         i += 1
                 list[name] = {'name': name, 'start': start, 'end': end,
-                        'pid': 0, 'length': length, 'row': 0, 'id': devid,
+                        'pid': pid, 'length': length, 'row': 0, 'id': devid,
                         'ret': ret, 'ulen': ulen }
                 return name
-        def deviceMatch(self, cg):
+        def deviceMatch(self, pid, cg):
                 if cg.end - cg.start == 0:
                         return True
-                list = self.dmesg['boot']['list']
-                for devname in list:
-                        dev = list[devname]
-                        if cg.name == 'do_one_initcall':
-                                if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0):
-                                        dev['ftrace'] = cg
-                                        self.do_one_initcall = True
-                                        return True
-                        else:
-                                if(cg.start > dev['start'] and cg.end < dev['end']):
-                                        if 'ftraces' not in dev:
-                                                dev['ftraces'] = []
-                                        dev['ftraces'].append(cg)
-                                        return True
+                for p in data.phases:
+                        list = self.dmesg[p]['list']
+                        for devname in list:
+                                dev = list[devname]
+                                if pid != dev['pid']:
+                                        continue
+                                if cg.name == 'do_one_initcall':
+                                        if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0):
+                                                dev['ftrace'] = cg
+                                                self.do_one_initcall = True
+                                                return True
+                                else:
+                                        if(cg.start > dev['start'] and cg.end < dev['end']):
+                                                if 'ftraces' not in dev:
+                                                        dev['ftraces'] = []
+                                                dev['ftraces'].append(cg)
+                                                return True
                 return False
 
 # ----------------- FUNCTIONS --------------------
 
-# Function: loadKernelLog
+# Function: parseKernelLog
 # Description:
-#        Load a raw kernel log from dmesg
-def loadKernelLog():
+#        parse a kernel log for boot data
+def parseKernelLog():
+        phase = 'kernel'
         data = Data(0)
-        data.dmesg['boot']['start'] = data.start = ktime = 0.0
+        data.dmesg['kernel']['start'] = data.start = ktime = 0.0
         sysvals.stamp = {
                 'time': datetime.now().strftime('%B %d %Y, %I:%M:%S %p'),
                 'host': sysvals.hostname,
                 'mode': 'boot', 'kernel': ''}
 
+        tp = aslib.TestProps()
         devtemp = dict()
         if(sysvals.dmesgfile):
                 lf = open(sysvals.dmesgfile, 'r')
@@ -205,6 +291,13 @@ def loadKernelLog():
                 lf = Popen('dmesg', stdout=PIPE).stdout
         for line in lf:
                 line = line.replace('\r\n', '')
+                # grab the stamp and sysinfo
+                if re.match(tp.stampfmt, line):
+                        tp.stamp = line
+                        continue
+                elif re.match(tp.sysinfofmt, line):
+                        tp.sysinfo = line
+                        continue
                 idx = line.find('[')
                 if idx > 1:
                         line = line[idx:]
@@ -215,7 +308,6 @@ def loadKernelLog():
                 if(ktime > 120):
                         break
                 msg = m.group('msg')
-                data.end = data.initstart = ktime
                 data.dmesgtext.append(line)
                 if(ktime == 0.0 and re.match('^Linux version .*', msg)):
                         if(not sysvals.stamp['kernel']):
@@ -228,43 +320,39 @@ def loadKernelLog():
                         data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S')
                         sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p')
                         continue
-                m = re.match('^calling *(?P<f>.*)\+.*', msg)
+                m = re.match('^calling *(?P<f>.*)\+.* @ (?P<p>[0-9]*)', msg)
                 if(m):
-                        devtemp[m.group('f')] = ktime
+                        func = m.group('f')
+                        pid = int(m.group('p'))
+                        devtemp[func] = (ktime, pid)
                         continue
                 m = re.match('^initcall *(?P<f>.*)\+.* returned (?P<r>.*) after (?P<t>.*) usecs', msg)
                 if(m):
                         data.valid = True
+                        data.end = ktime
                         f, r, t = m.group('f', 'r', 't')
                         if(f in devtemp):
-                                data.newAction('boot', f, devtemp[f], ktime, int(r), int(t))
-                                data.end = ktime
+                                start, pid = devtemp[f]
+                                data.newAction(phase, f, pid, start, ktime, int(r), int(t))
                                 del devtemp[f]
                         continue
                 if(re.match('^Freeing unused kernel memory.*', msg)):
-                        break
-
-        data.dmesg['boot']['end'] = data.end
+                        data.tUserMode = ktime
+                        data.dmesg['kernel']['end'] = ktime
+                        data.dmesg['user']['start'] = ktime
+                        phase = 'user'
+
+        if tp.stamp:
+                sysvals.stamp = 0
+                tp.parseStamp(data, sysvals)
+        data.dmesg['user']['end'] = data.end
         lf.close()
         return data
 
-# Function: loadTraceLog
+# Function: parseTraceLog
 # Description:
 #        Check if trace is available and copy to a temp file
-def loadTraceLog(data):
-        # load the data to a temp file if none given
-        if not sysvals.ftracefile:
-                lib = aslib.sysvals
-                aslib.rootCheck(True)
-                if not lib.verifyFtrace():
-                        doError('ftrace not available')
-                if lib.fgetVal('current_tracer').strip() != 'function_graph':
-                        doError('ftrace not configured for a boot callgraph')
-                sysvals.ftracefile = '/tmp/boot_ftrace.%s.txt' % os.getpid()
-                call('cat '+lib.tpath+'trace > '+sysvals.ftracefile, shell=True)
-        if not sysvals.ftracefile:
-                doError('No trace data available')
-
+def parseTraceLog(data):
         # parse the trace log
         ftemp = dict()
         tp = aslib.TestProps()
@@ -306,9 +394,29 @@ def loadTraceLog(data):
                                 print('Sanity check failed for %s-%d' % (proc, pid))
                                 continue
                         # match cg data to devices
-                        if not data.deviceMatch(cg):
+                        if not data.deviceMatch(pid, cg):
                                 print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end)
 
+# Function: retrieveLogs
+# Description:
+#        Create copies of dmesg and/or ftrace for later processing
+def retrieveLogs():
+        # check ftrace is configured first
+        if sysvals.useftrace:
+                tracer = sysvals.fgetVal('current_tracer').strip()
+                if tracer != 'function_graph':
+                        doError('ftrace not configured for a boot callgraph')
+        # create the folder and get dmesg
+        sysvals.systemInfo(aslib.dmidecode(sysvals.mempath))
+        sysvals.initTestOutput('boot')
+        sysvals.writeDatafileHeader(sysvals.dmesgfile)
+        call('dmesg >> '+sysvals.dmesgfile, shell=True)
+        if not sysvals.useftrace:
+                return
+        # get ftrace
+        sysvals.writeDatafileHeader(sysvals.ftracefile)
+        call('cat '+sysvals.tpath+'trace >> '+sysvals.ftracefile, shell=True)
+
 # Function: colorForName
 # Description:
 #        Generate a repeatable color from a list for a given name
@@ -353,18 +461,19 @@ def cgOverview(cg, minlen):
 #        testruns: array of Data objects from parseKernelLog or parseTraceLog
 # Output:
 #        True if the html file was created, false if it failed
-def createBootGraph(data, embedded):
+def createBootGraph(data):
         # html function templates
         html_srccall = '<div id={6} title="{5}" class="srccall" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{0}</div>\n'
         html_timetotal = '<table class="time1">\n<tr>'\
-                '<td class="blue">Time from Kernel Boot to start of User Mode: <b>{0} ms</b></td>'\
+                '<td class="blue">Init process starts @ <b>{0} ms</b></td>'\
+                '<td class="blue">Last initcall ends @ <b>{1} ms</b></td>'\
                 '</tr>\n</table>\n'
 
         # device timeline
         devtl = aslib.Timeline(100, 20)
 
         # write the test title and general info header
-        devtl.createHeader(sysvals, 'noftrace')
+        devtl.createHeader(sysvals)
 
         # Generate the header for this timeline
         t0 = data.start
@@ -373,84 +482,98 @@ def createBootGraph(data, embedded):
         if(tTotal == 0):
                 print('ERROR: No timeline data')
                 return False
-        boot_time = '%.0f'%(tTotal*1000)
-        devtl.html += html_timetotal.format(boot_time)
+        user_mode = '%.0f'%(data.tUserMode*1000)
+        last_init = '%.0f'%(tTotal*1000)
+        devtl.html += html_timetotal.format(user_mode, last_init)
 
         # determine the maximum number of rows we need to draw
-        phase = 'boot'
-        list = data.dmesg[phase]['list']
         devlist = []
-        for devname in list:
-                d = aslib.DevItem(0, phase, list[devname])
-                devlist.append(d)
-        devtl.getPhaseRows(devlist)
+        for p in data.phases:
+                list = data.dmesg[p]['list']
+                for devname in list:
+                        d = aslib.DevItem(0, p, list[devname])
+                        devlist.append(d)
+                devtl.getPhaseRows(devlist, 0, 'start')
         devtl.calcTotalRows()
 
         # draw the timeline background
         devtl.createZoomBox()
-        boot = data.dmesg[phase]
-        length = boot['end']-boot['start']
-        left = '%.3f' % (((boot['start']-t0)*100.0)/tTotal)
-        width = '%.3f' % ((length*100.0)/tTotal)
-        devtl.html += devtl.html_tblock.format(phase, left, width, devtl.scaleH)
-        devtl.html += devtl.html_phase.format('0', '100', \
-                '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
-                'white', '')
+        devtl.html += devtl.html_tblock.format('boot', '0', '100', devtl.scaleH)
+        for p in data.phases:
+                phase = data.dmesg[p]
+                length = phase['end']-phase['start']
+                left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal)
+                width = '%.3f' % ((length*100.0)/tTotal)
+                devtl.html += devtl.html_phase.format(left, width, \
+                        '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
+                        phase['color'], '')
 
         # draw the device timeline
         num = 0
         devstats = dict()
-        for devname in sorted(list):
-                cls, color = colorForName(devname)
-                dev = list[devname]
-                info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0,
-                        dev['ulen']/1000.0, dev['ret'])
-                devstats[dev['id']] = {'info':info}
-                dev['color'] = color
-                height = devtl.phaseRowHeight(0, phase, dev['row'])
-                top = '%.6f' % ((dev['row']*height) + devtl.scaleH)
-                left = '%.6f' % (((dev['start']-t0)*100)/tTotal)
-                width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal)
-                length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
-                devtl.html += devtl.html_device.format(dev['id'],
-                        devname+length+'kernel_mode', left, top, '%.3f'%height,
-                        width, devname, ' '+cls, '')
-                rowtop = devtl.phaseRowTop(0, phase, dev['row'])
-                height = '%.6f' % (devtl.rowH / 2)
-                top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2))
-                if data.do_one_initcall:
-                        if('ftrace' not in dev):
+        for phase in data.phases:
+                list = data.dmesg[phase]['list']
+                for devname in sorted(list):
+                        cls, color = colorForName(devname)
+                        dev = list[devname]
+                        info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0,
+                                dev['ulen']/1000.0, dev['ret'])
+                        devstats[dev['id']] = {'info':info}
+                        dev['color'] = color
+                        height = devtl.phaseRowHeight(0, phase, dev['row'])
+                        top = '%.6f' % ((dev['row']*height) + devtl.scaleH)
+                        left = '%.6f' % (((dev['start']-t0)*100)/tTotal)
+                        width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal)
+                        length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
+                        devtl.html += devtl.html_device.format(dev['id'],
+                                devname+length+phase+'_mode', left, top, '%.3f'%height,
+                                width, devname, ' '+cls, '')
+                        rowtop = devtl.phaseRowTop(0, phase, dev['row'])
+                        height = '%.6f' % (devtl.rowH / 2)
+                        top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2))
+                        if data.do_one_initcall:
+                                if('ftrace' not in dev):
+                                        continue
+                                cg = dev['ftrace']
+                                large, stats = cgOverview(cg, 0.001)
+                                devstats[dev['id']]['fstat'] = stats
+                                for l in large:
+                                        left = '%f' % (((l.time-t0)*100)/tTotal)
+                                        width = '%f' % (l.length*100/tTotal)
+                                        title = '%s (%0.3fms)' % (l.name, l.length * 1000.0)
+                                        devtl.html += html_srccall.format(l.name, left,
+                                                top, height, width, title, 'x%d'%num)
+                                        num += 1
+                                continue
+                        if('ftraces' not in dev):
                                 continue
-                        cg = dev['ftrace']
-                        large, stats = cgOverview(cg, 0.001)
-                        devstats[dev['id']]['fstat'] = stats
-                        for l in large:
-                                left = '%f' % (((l.time-t0)*100)/tTotal)
-                                width = '%f' % (l.length*100/tTotal)
-                                title = '%s (%0.3fms)' % (l.name, l.length * 1000.0)
-                                devtl.html += html_srccall.format(l.name, left,
-                                        top, height, width, title, 'x%d'%num)
+                        for cg in dev['ftraces']:
+                                left = '%f' % (((cg.start-t0)*100)/tTotal)
+                                width = '%f' % ((cg.end-cg.start)*100/tTotal)
+                                cglen = (cg.end - cg.start) * 1000.0
+                                title = '%s (%0.3fms)' % (cg.name, cglen)
+                                cg.id = 'x%d' % num
+                                devtl.html += html_srccall.format(cg.name, left,
+                                        top, height, width, title, dev['id']+cg.id)
                                 num += 1
-                        continue
-                if('ftraces' not in dev):
-                        continue
-                for cg in dev['ftraces']:
-                        left = '%f' % (((cg.start-t0)*100)/tTotal)
-                        width = '%f' % ((cg.end-cg.start)*100/tTotal)
-                        cglen = (cg.end - cg.start) * 1000.0
-                        title = '%s (%0.3fms)' % (cg.name, cglen)
-                        cg.id = 'x%d' % num
-                        devtl.html += html_srccall.format(cg.name, left,
-                                top, height, width, title, dev['id']+cg.id)
-                        num += 1
 
         # draw the time scale, try to make the number of labels readable
-        devtl.createTimeScale(t0, tMax, tTotal, phase)
+        devtl.createTimeScale(t0, tMax, tTotal, 'boot')
         devtl.html += '</div>\n'
 
         # timeline is finished
         devtl.html += '</div>\n</div>\n'
 
+        # draw a legend which describes the phases by color
+        devtl.html += '<div class="legend">\n'
+        pdelta = 20.0
+        pmargin = 36.0
+        for phase in data.phases:
+                order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
+                devtl.html += devtl.html_legend.format(order, \
+                        data.dmesg[phase]['color'], phase+'_mode', phase[0])
+        devtl.html += '</div>\n'
+
         if(sysvals.outfile == sysvals.htmlfile):
                 hf = open(sysvals.htmlfile, 'a')
         else:
@@ -474,7 +597,7 @@ def createBootGraph(data, embedded):
                 .fstat td {text-align:left;width:35px;}\n\
                 .srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
                 .srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n'
-        if(not embedded):
+        if(not sysvals.embedded):
                 aslib.addCSS(hf, sysvals, 1, False, extra)
 
         # write the device timeline
@@ -495,9 +618,11 @@ def createBootGraph(data, embedded):
         html = \
                 '<div id="devicedetailtitle"></div>\n'\
                 '<div id="devicedetail" style="display:none;">\n'\
-                '<div id="devicedetail0">\n'\
-                '<div id="kernel_mode" class="phaselet" style="left:0%;width:100%;background:#DDDDDD"></div>\n'\
-                '</div>\n</div>\n'\
+                '<div id="devicedetail0">\n'
+        for p in data.phases:
+                phase = data.dmesg[p]
+                html += devtl.html_phaselet.format(p+'_mode', '0', '100', phase['color'])
+        html += '</div>\n</div>\n'\
                 '<script type="text/javascript">\n'+statinfo+\
                 '</script>\n'
         hf.write(html)
@@ -507,21 +632,21 @@ def createBootGraph(data, embedded):
                 aslib.addCallgraphs(sysvals, hf, data)
 
         # add the dmesg log as a hidden div
-        if sysvals.addlogs:
+        if sysvals.dmesglog:
                 hf.write('<div id="dmesglog" style="display:none;">\n')
                 for line in data.dmesgtext:
                         line = line.replace('<', '&lt').replace('>', '&gt')
                         hf.write(line)
                 hf.write('</div>\n')
 
-        if(not embedded):
+        if(not sysvals.embedded):
                 # write the footer and close
                 aslib.addScriptCode(hf, [data])
                 hf.write('</body>\n</html>\n')
         else:
                 # embedded out will be loaded in a page, skip the js
                 hf.write('<div id=bounds style=display:none>%f,%f</div>' % \
-                        (data.start*1000, data.initstart*1000))
+                        (data.start*1000, data.end*1000))
         hf.close()
         return True
 
@@ -533,17 +658,20 @@ def updateCron(restore=False):
         if not restore:
                 sysvals.rootUser(True)
         crondir = '/var/spool/cron/crontabs/'
-        cronfile = crondir+'root'
-        backfile = crondir+'root-analyze_boot-backup'
+        if not os.path.exists(crondir):
+                crondir = '/var/spool/cron/'
         if not os.path.exists(crondir):
                 doError('%s not found' % crondir)
-        out = Popen(['which', 'crontab'], stdout=PIPE).stdout.read()
-        if not out:
+        cronfile = crondir+'root'
+        backfile = crondir+'root-analyze_boot-backup'
+        cmd = sysvals.getExec('crontab')
+        if not cmd:
                 doError('crontab not found')
         # on restore: move the backup cron back into place
         if restore:
                 if os.path.exists(backfile):
                         shutil.move(backfile, cronfile)
+                        call([cmd, cronfile])
                 return
         # backup current cron and install new one with reboot
         if os.path.exists(cronfile):
@@ -556,13 +684,13 @@ def updateCron(restore=False):
                 fp = open(backfile, 'r')
                 op = open(cronfile, 'w')
                 for line in fp:
-                        if '@reboot' not in line:
+                        if not sysvals.myCronJob(line):
                                 op.write(line)
                                 continue
                 fp.close()
                 op.write('@reboot python %s\n' % sysvals.cronjobCmdString())
                 op.close()
-                res = call('crontab %s' % cronfile, shell=True)
+                res = call([cmd, cronfile])
         except Exception, e:
                 print 'Exception: %s' % str(e)
                 shutil.move(backfile, cronfile)
@@ -577,25 +705,16 @@ def updateGrub(restore=False):
         # call update-grub on restore
         if restore:
                 try:
-                        call(['update-grub'], stderr=PIPE, stdout=PIPE,
+                        call(sysvals.blexec, stderr=PIPE, stdout=PIPE,
                                 env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'})
                 except Exception, e:
                         print 'Exception: %s\n' % str(e)
                 return
-        # verify we can do this
-        sysvals.rootUser(True)
-        grubfile = '/etc/default/grub'
-        if not os.path.exists(grubfile):
-                print 'ERROR: Unable to set the kernel parameters via grub.\n'
-                sysvals.manualRebootRequired()
-        out = Popen(['which', 'update-grub'], stdout=PIPE).stdout.read()
-        if not out:
-                print 'ERROR: Unable to set the kernel parameters via grub.\n'
-                sysvals.manualRebootRequired()
-
         # extract the option and create a grub config without it
+        sysvals.rootUser(True)
         tgtopt = 'GRUB_CMDLINE_LINUX_DEFAULT'
         cmdline = ''
+        grubfile = '/etc/default/grub'
         tempfile = '/etc/default/grub.analyze_boot'
         shutil.move(grubfile, tempfile)
         res = -1
@@ -622,7 +741,7 @@ def updateGrub(restore=False):
                 # if the target option value is in quotes, strip them
                 sp = '"'
                 val = cmdline.strip()
-                if val[0] == '\'' or val[0] == '"':
+                if val and (val[0] == '\'' or val[0] == '"'):
                         sp = val[0]
                         val = val.strip(sp)
                 cmdline = val
@@ -633,7 +752,7 @@ def updateGrub(restore=False):
                 # write out the updated target option
                 op.write('\n%s=%s%s%s\n' % (tgtopt, sp, cmdline, sp))
                 op.close()
-                res = call('update-grub')
+                res = call(sysvals.blexec)
                 os.remove(grubfile)
         except Exception, e:
                 print 'Exception: %s' % str(e)
@@ -641,10 +760,18 @@ def updateGrub(restore=False):
         # cleanup
         shutil.move(tempfile, grubfile)
         if res != 0:
-                doError('update-grub failed')
+                doError('update grub failed')
 
-# Function: doError
+# Function: updateKernelParams
 # Description:
+#        update boot conf for all kernels with our parameters
+def updateKernelParams(restore=False):
+        # find the boot loader
+        sysvals.getBootLoader()
+        if sysvals.bootloader == 'grub':
+                updateGrub(restore)
+
+# Function: doError Description:
 #        generic error function for catastrphic failures
 # Arguments:
 #        msg: the error message to print
@@ -660,7 +787,7 @@ def doError(msg, help=False):
 #        print out the help text
 def printHelp():
         print('')
-        print('%s v%.1f' % (sysvals.title, sysvals.version))
+        print('%s v%s' % (sysvals.title, sysvals.version))
         print('Usage: bootgraph <options> <command>')
         print('')
         print('Description:')
@@ -669,13 +796,19 @@ def printHelp():
         print('  the start of the init process.')
         print('')
         print('  If no specific command is given the tool reads the current dmesg')
-        print('  and/or ftrace log and outputs bootgraph.html')
+        print('  and/or ftrace log and creates a timeline')
+        print('')
+        print('  Generates output files in subdirectory: boot-yymmdd-HHMMSS')
+        print('   HTML output:                    <hostname>_boot.html')
+        print('   raw dmesg output:               <hostname>_boot_dmesg.txt')
+        print('   raw ftrace output:              <hostname>_boot_ftrace.txt')
         print('')
         print('Options:')
         print('  -h            Print this help text')
         print('  -v            Print the current tool version')
         print('  -addlogs      Add the dmesg log to the html output')
-        print('  -o file       Html timeline name (default: bootgraph.html)')
+        print('  -o name       Overrides the output subdirectory name when running a new test')
+        print('                default: boot-{date}-{time}')
         print(' [advanced]')
         print('  -f            Use ftrace to add function detail (default: disabled)')
         print('  -callgraph    Add callgraph detail, can be very large (default: disabled)')
@@ -683,13 +816,18 @@ def printHelp():
         print('  -mincg ms     Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
         print('  -timeprec N   Number of significant digits in timestamps (0:S, 3:ms, [6:us])')
         print('  -expandcg     pre-expand the callgraph data in the html output (default: disabled)')
-        print('  -filter list  Limit ftrace to comma-delimited list of functions (default: do_one_initcall)')
-        print(' [commands]')
+        print('  -func list    Limit ftrace to comma-delimited list of functions (default: do_one_initcall)')
+        print('  -cgfilter S   Filter the callgraph output in the timeline')
+        print('  -bl name      Use the following boot loader for kernel params (default: grub)')
         print('  -reboot       Reboot the machine automatically and generate a new timeline')
-        print('  -manual       Show the requirements to generate a new timeline manually')
-        print('  -dmesg file   Load a stored dmesg file (used with -ftrace)')
-        print('  -ftrace file  Load a stored ftrace file (used with -dmesg)')
+        print('  -manual       Show the steps to generate a new timeline manually (used with -reboot)')
+        print('')
+        print('Other commands:')
         print('  -flistall     Print all functions capable of being captured in ftrace')
+        print('  -sysinfo      Print out system info extracted from BIOS')
+        print(' [redo]')
+        print('  -dmesg file   Create HTML output using dmesg input (used with -ftrace)')
+        print('  -ftrace file  Create HTML output using ftrace input (used with -dmesg)')
         print('')
         return True
 
@@ -698,14 +836,15 @@ def printHelp():
 if __name__ == '__main__':
         # loop through the command line arguments
         cmd = ''
-        simplecmds = ['-updategrub', '-flistall']
+        testrun = True
+        simplecmds = ['-sysinfo', '-kpupdate', '-flistall', '-checkbl']
         args = iter(sys.argv[1:])
         for arg in args:
                 if(arg == '-h'):
                         printHelp()
                         sys.exit()
                 elif(arg == '-v'):
-                        print("Version %.1f" % sysvals.version)
+                        print("Version %s" % sysvals.version)
                         sys.exit()
                 elif(arg in simplecmds):
                         cmd = arg[1:]
@@ -716,16 +855,32 @@ if __name__ == '__main__':
                         sysvals.usecallgraph = True
                 elif(arg == '-mincg'):
                         sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0)
+                elif(arg == '-cgfilter'):
+                        try:
+                                val = args.next()
+                        except:
+                                doError('No callgraph functions supplied', True)
+                        sysvals.setDeviceFilter(val)
+                elif(arg == '-bl'):
+                        try:
+                                val = args.next()
+                        except:
+                                doError('No boot loader name supplied', True)
+                        if val.lower() not in ['grub']:
+                                doError('Unknown boot loader: %s' % val, True)
+                        sysvals.bootloader = val.lower()
                 elif(arg == '-timeprec'):
                         sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6))
                 elif(arg == '-maxdepth'):
                         sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000)
-                elif(arg == '-filter'):
+                elif(arg == '-func'):
                         try:
                                 val = args.next()
                         except:
                                 doError('No filter functions supplied', True)
-                        aslib.rootCheck(True)
+                        sysvals.useftrace = True
+                        sysvals.usecallgraph = True
+                        sysvals.rootCheck(True)
                         sysvals.setGraphFilter(val)
                 elif(arg == '-ftrace'):
                         try:
@@ -734,9 +889,10 @@ if __name__ == '__main__':
                                 doError('No ftrace file supplied', True)
                         if(os.path.exists(val) == False):
                                 doError('%s does not exist' % val)
+                        testrun = False
                         sysvals.ftracefile = val
                 elif(arg == '-addlogs'):
-                        sysvals.addlogs = True
+                        sysvals.dmesglog = True
                 elif(arg == '-expandcg'):
                         sysvals.cgexp = True
                 elif(arg == '-dmesg'):
@@ -748,18 +904,15 @@ if __name__ == '__main__':
                                 doError('%s does not exist' % val)
                         if(sysvals.htmlfile == val or sysvals.outfile == val):
                                 doError('Output filename collision')
+                        testrun = False
                         sysvals.dmesgfile = val
                 elif(arg == '-o'):
                         try:
                                 val = args.next()
                         except:
-                                doError('No HTML filename supplied', True)
-                        if(sysvals.dmesgfile == val or sysvals.ftracefile == val):
-                                doError('Output filename collision')
-                        sysvals.htmlfile = val
+                                doError('No subdirectory name supplied', True)
+                        sysvals.testdir = sysvals.setOutputFolder(val)
                 elif(arg == '-reboot'):
-                        if sysvals.iscronjob:
-                                doError('-reboot and -cronjob are incompatible')
                         sysvals.reboot = True
                 elif(arg == '-manual'):
                         sysvals.reboot = True
@@ -767,58 +920,93 @@ if __name__ == '__main__':
                 # remaining options are only for cron job use
                 elif(arg == '-cronjob'):
                         sysvals.iscronjob = True
-                        if sysvals.reboot:
-                                doError('-reboot and -cronjob are incompatible')
                 else:
                         doError('Invalid argument: '+arg, True)
 
+        # compatibility errors and access checks
+        if(sysvals.iscronjob and (sysvals.reboot or \
+                sysvals.dmesgfile or sysvals.ftracefile or cmd)):
+                doError('-cronjob is meant for batch purposes only')
+        if(sysvals.reboot and (sysvals.dmesgfile or sysvals.ftracefile)):
+                doError('-reboot and -dmesg/-ftrace are incompatible')
+        if cmd or sysvals.reboot or sysvals.iscronjob or testrun:
+                sysvals.rootCheck(True)
+        if (testrun and sysvals.useftrace) or cmd == 'flistall':
+                if not sysvals.verifyFtrace():
+                        doError('Ftrace is not properly enabled')
+
+        # run utility commands
+        sysvals.cpuInfo()
         if cmd != '':
-                if cmd == 'updategrub':
-                        updateGrub()
+                if cmd == 'kpupdate':
+                        updateKernelParams()
                 elif cmd == 'flistall':
-                        sysvals.getFtraceFilterFunctions(False)
+                        for f in sysvals.getBootFtraceFilterFunctions():
+                                print f
+                elif cmd == 'checkbl':
+                        sysvals.getBootLoader()
+                        print 'Boot Loader: %s\n%s' % (sysvals.bootloader, sysvals.blexec)
+                elif(cmd == 'sysinfo'):
+                        sysvals.printSystemInfo()
                 sys.exit()
 
-        # update grub, setup a cronjob, and reboot
+        # reboot: update grub, setup a cronjob, and reboot
         if sysvals.reboot:
+                if (sysvals.useftrace or sysvals.usecallgraph) and \
+                        not sysvals.checkFtraceKernelVersion():
+                        doError('Ftrace functionality requires kernel v4.10 or newer')
                 if not sysvals.manual:
-                        updateGrub()
+                        updateKernelParams()
                         updateCron()
                         call('reboot')
                 else:
                         sysvals.manualRebootRequired()
                 sys.exit()
 
-        # disable the cronjob
+        # cronjob: remove the cronjob, grub changes, and disable ftrace
         if sysvals.iscronjob:
                 updateCron(True)
-                updateGrub(True)
+                updateKernelParams(True)
+                try:
+                        sysvals.fsetVal('0', 'tracing_on')
+                except:
+                        pass
 
-        data = loadKernelLog()
-        if sysvals.useftrace:
-                loadTraceLog(data)
-                if sysvals.iscronjob:
-                        try:
-                                sysvals.fsetVal('0', 'tracing_on')
-                        except:
-                                pass
+        # testrun: generate copies of the logs
+        if testrun:
+                retrieveLogs()
+        else:
+                sysvals.setOutputFile()
 
-        if(sysvals.outfile and sysvals.phoronix):
-                fp = open(sysvals.outfile, 'w')
-                fp.write('pass %s initstart %.3f end %.3f boot %s\n' %
-                        (data.valid, data.initstart*1000, data.end*1000, data.boottime))
-                fp.close()
-        if(not data.valid):
-                if sysvals.dmesgfile:
+        # process the log data
+        if sysvals.dmesgfile:
+                data = parseKernelLog()
+                if(not data.valid):
                         doError('No initcall data found in %s' % sysvals.dmesgfile)
-                else:
-                        doError('No initcall data found, is initcall_debug enabled?')
+                if sysvals.useftrace and sysvals.ftracefile:
+                        parseTraceLog(data)
+        else:
+                doError('dmesg file required')
 
         print('          Host: %s' % sysvals.hostname)
         print('     Test time: %s' % sysvals.testtime)
         print('     Boot time: %s' % data.boottime)
         print('Kernel Version: %s' % sysvals.kernel)
         print('  Kernel start: %.3f' % (data.start * 1000))
-        print('    init start: %.3f' % (data.initstart * 1000))
+        print('Usermode start: %.3f' % (data.tUserMode * 1000))
+        print('Last Init Call: %.3f' % (data.end * 1000))
+
+        # handle embedded output logs
+        if(sysvals.outfile and sysvals.embedded):
+                fp = open(sysvals.outfile, 'w')
+                fp.write('pass %s initstart %.3f end %.3f boot %s\n' %
+                        (data.valid, data.tUserMode*1000, data.end*1000, data.boottime))
+                fp.close()
+
+        createBootGraph(data)
 
-        createBootGraph(data, sysvals.phoronix)
+        # if running as root, change output dir owner to sudo_user
+        if testrun and os.path.isdir(sysvals.testdir) and \
+                os.getuid() == 0 and 'SUDO_USER' in os.environ:
+                cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1'
+                call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True)
diff --git a/tools/power/pm-graph/analyze_suspend.py b/tools/power/pm-graph/analyze_suspend.py
index a9206e67fc1f..1b60fe203741 100755
--- a/tools/power/pm-graph/analyze_suspend.py
+++ b/tools/power/pm-graph/analyze_suspend.py
@@ -68,10 +68,12 @@ from subprocess import call, Popen, PIPE
 #        store system values and test parameters
 class SystemValues:
         title = 'SleepGraph'
-        version = '4.6'
+        version = '4.7'
         ansi = False
         verbose = False
-        addlogs = False
+        testlog = True
+        dmesglog = False
+        ftracelog = False
         mindevlen = 0.0
         mincglen = 0.0
         cgphase = ''
@@ -79,10 +81,11 @@ class SystemValues:
         max_graph_depth = 0
         callloopmaxgap = 0.0001
         callloopmaxlen = 0.005
+        cpucount = 0
+        memtotal = 204800
         srgap = 0
         cgexp = False
-        outdir = ''
-        testdir = '.'
+        testdir = ''
         tpath = '/sys/kernel/debug/tracing/'
         fpdtpath = '/sys/firmware/acpi/tables/FPDT'
         epath = '/sys/kernel/debug/tracing/events/power/'
@@ -95,14 +98,17 @@ class SystemValues:
         testcommand = ''
         mempath = '/dev/mem'
         powerfile = '/sys/power/state'
+        mempowerfile = '/sys/power/mem_sleep'
         suspendmode = 'mem'
+        memmode = ''
         hostname = 'localhost'
         prefix = 'test'
         teststamp = ''
+        sysstamp = ''
         dmesgstart = 0.0
         dmesgfile = ''
         ftracefile = ''
-        htmlfile = ''
+        htmlfile = 'output.html'
         embedded = False
         rtcwake = True
         rtcwaketime = 15
@@ -127,9 +133,6 @@ class SystemValues:
         devpropfmt = '# Device Properties: .*'
         tracertypefmt = '# tracer: (?P<t>.*)'
         firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$'
-        stampfmt = '# suspend-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\
-                                '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\
-                                ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$'
         tracefuncs = {
                 'sys_sync': dict(),
                 'pm_prepare_console': dict(),
@@ -218,7 +221,7 @@ class SystemValues:
                 # if this is a phoronix test run, set some default options
                 if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ):
                         self.embedded = True
-                        self.addlogs = True
+                        self.dmesglog = self.ftracelog = True
                         self.htmlfile = os.environ['LOG_FILE']
                 self.archargs = 'args_'+platform.machine()
                 self.hostname = platform.node()
@@ -233,6 +236,13 @@ class SystemValues:
                         self.rtcpath = rtc
                 if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()):
                         self.ansi = True
+                self.testdir = datetime.now().strftime('suspend-%y%m%d-%H%M%S')
+        def rootCheck(self, fatal=True):
+                if(os.access(self.powerfile, os.W_OK)):
+                        return True
+                if fatal:
+                        doError('This command requires sysfs mount and root access')
+                return False
         def rootUser(self, fatal=False):
                 if 'USER' in os.environ and os.environ['USER'] == 'root':
                         return True
@@ -249,30 +259,60 @@ class SystemValues:
                 args['date'] = n.strftime('%y%m%d')
                 args['time'] = n.strftime('%H%M%S')
                 args['hostname'] = self.hostname
-                self.outdir = value.format(**args)
+                return value.format(**args)
         def setOutputFile(self):
-                if((self.htmlfile == '') and (self.dmesgfile != '')):
+                if self.dmesgfile != '':
                         m = re.match('(?P<name>.*)_dmesg\.txt$', self.dmesgfile)
                         if(m):
                                 self.htmlfile = m.group('name')+'.html'
-                if((self.htmlfile == '') and (self.ftracefile != '')):
+                if self.ftracefile != '':
                         m = re.match('(?P<name>.*)_ftrace\.txt$', self.ftracefile)
                         if(m):
                                 self.htmlfile = m.group('name')+'.html'
-                if(self.htmlfile == ''):
-                        self.htmlfile = 'output.html'
-        def initTestOutput(self, subdir, testpath=''):
+        def systemInfo(self, info):
+                p = c = m = b = ''
+                if 'baseboard-manufacturer' in info:
+                        m = info['baseboard-manufacturer']
+                elif 'system-manufacturer' in info:
+                        m = info['system-manufacturer']
+                if 'baseboard-product-name' in info:
+                        p = info['baseboard-product-name']
+                elif 'system-product-name' in info:
+                        p = info['system-product-name']
+                if 'processor-version' in info:
+                        c = info['processor-version']
+                if 'bios-version' in info:
+                        b = info['bios-version']
+                self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | numcpu:%d | memsz:%d' % \
+                        (m, p, c, b, self.cpucount, self.memtotal)
+        def printSystemInfo(self):
+                self.rootCheck(True)
+                out = dmidecode(self.mempath, True)
+                fmt = '%-24s: %s'
+                for name in sorted(out):
+                        print fmt % (name, out[name])
+                print fmt % ('cpucount', ('%d' % self.cpucount))
+                print fmt % ('memtotal', ('%d kB' % self.memtotal))
+        def cpuInfo(self):
+                self.cpucount = 0
+                fp = open('/proc/cpuinfo', 'r')
+                for line in fp:
+                        if re.match('^processor[ \t]*:[ \t]*[0-9]*', line):
+                                self.cpucount += 1
+                fp.close()
+                fp = open('/proc/meminfo', 'r')
+                for line in fp:
+                        m = re.match('^MemTotal:[ \t]*(?P<sz>[0-9]*) *kB', line)
+                        if m:
+                                self.memtotal = int(m.group('sz'))
+                                break
+                fp.close()
+        def initTestOutput(self, name):
                 self.prefix = self.hostname
                 v = open('/proc/version', 'r').read().strip()
                 kver = string.split(v)[2]
-                n = datetime.now()
-                testtime = n.strftime('suspend-%m%d%y-%H%M%S')
-                if not testpath:
-                        testpath = n.strftime('suspend-%y%m%d-%H%M%S')
-                if(subdir != "."):
-                        self.testdir = subdir+"/"+testpath
-                else:
-                        self.testdir = testpath
+                fmt = name+'-%m%d%y-%H%M%S'
+                testtime = datetime.now().strftime(fmt)
                 self.teststamp = \
                         '# '+testtime+' '+self.prefix+' '+self.suspendmode+' '+kver
                 if(self.embedded):
@@ -355,7 +395,7 @@ class SystemValues:
                                 continue
                         self.tracefuncs[i] = dict()
         def getFtraceFilterFunctions(self, current):
-                rootCheck(True)
+                self.rootCheck(True)
                 if not current:
                         call('cat '+self.tpath+'available_filter_functions', shell=True)
                         return
@@ -453,7 +493,7 @@ class SystemValues:
                 val += '\nr:%s_ret %s $retval\n' % (name, func)
                 return val
         def addKprobes(self, output=False):
-                if len(sysvals.kprobes) < 1:
+                if len(self.kprobes) < 1:
                         return
                 if output:
                         print('    kprobe functions in this kernel:')
@@ -525,7 +565,7 @@ class SystemValues:
                         fp.flush()
                         fp.close()
                 except:
-                        pass
+                        return False
                 return True
         def fgetVal(self, path):
                 file = self.tpath+path
@@ -566,9 +606,15 @@ class SystemValues:
                 self.cleanupFtrace()
                 # set the trace clock to global
                 self.fsetVal('global', 'trace_clock')
-                # set trace buffer to a huge value
                 self.fsetVal('nop', 'current_tracer')
-                self.fsetVal('131073', 'buffer_size_kb')
+                # set trace buffer to a huge value
+                if self.usecallgraph or self.usedevsrc:
+                        tgtsize = min(self.memtotal / 2, 2*1024*1024)
+                        maxbuf = '%d' % (tgtsize / max(1, self.cpucount))
+                        if self.cpucount < 1 or not self.fsetVal(maxbuf, 'buffer_size_kb'):
+                                self.fsetVal('131072', 'buffer_size_kb')
+                else:
+                        self.fsetVal('16384', 'buffer_size_kb')
                 # go no further if this is just a status check
                 if testing:
                         return
@@ -641,6 +687,15 @@ class SystemValues:
                 if not self.ansi:
                         return str
                 return '\x1B[%d;40m%s\x1B[m' % (color, str)
+        def writeDatafileHeader(self, filename, fwdata=[]):
+                fp = open(filename, 'w')
+                fp.write(self.teststamp+'\n')
+                fp.write(self.sysstamp+'\n')
+                if(self.suspendmode == 'mem' or self.suspendmode == 'command'):
+                        for fw in fwdata:
+                                if(fw):
+                                        fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
+                fp.close()
 
 sysvals = SystemValues()
 suspendmodename = {
@@ -1008,6 +1063,12 @@ class Data:
                         else:
                                 self.trimTime(self.tSuspended, \
                                         self.tResumed-self.tSuspended, False)
+        def getTimeValues(self):
+                sktime = (self.dmesg['suspend_machine']['end'] - \
+                        self.tKernSus) * 1000
+                rktime = (self.dmesg['resume_complete']['end'] - \
+                        self.dmesg['resume_machine']['start']) * 1000
+                return (sktime, rktime)
         def setPhase(self, phase, ktime, isbegin):
                 if(isbegin):
                         self.dmesg[phase]['start'] = ktime
@@ -1517,7 +1578,7 @@ class FTraceCallGraph:
                         prelinedep += 1
                 last = 0
                 lasttime = line.time
-                virtualfname = 'execution_misalignment'
+                virtualfname = 'missing_function_name'
                 if len(self.list) > 0:
                         last = self.list[-1]
                         lasttime = last.time
@@ -1773,24 +1834,30 @@ class Timeline:
         html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
         html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n'
         html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
+        html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}">&nbsp;{2}</div>\n'
         def __init__(self, rowheight, scaleheight):
                 self.rowH = rowheight
                 self.scaleH = scaleheight
                 self.html = ''
-        def createHeader(self, sv, suppress=''):
+        def createHeader(self, sv):
                 if(not sv.stamp['time']):
                         return
                 self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \
                         % (sv.title, sv.version)
-                if sv.logmsg and 'log' not in suppress:
-                        self.html += '<button id="showtest" class="logbtn">log</button>'
-                if sv.addlogs and 'dmesg' not in suppress:
-                        self.html += '<button id="showdmesg" class="logbtn">dmesg</button>'
-                if sv.addlogs and sv.ftracefile and 'ftrace' not in suppress:
-                        self.html += '<button id="showftrace" class="logbtn">ftrace</button>'
+                if sv.logmsg and sv.testlog:
+                        self.html += '<button id="showtest" class="logbtn btnfmt">log</button>'
+                if sv.dmesglog:
+                        self.html += '<button id="showdmesg" class="logbtn btnfmt">dmesg</button>'
+                if sv.ftracelog:
+                        self.html += '<button id="showftrace" class="logbtn btnfmt">ftrace</button>'
                 headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
                 self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'],
                         sv.stamp['mode'], sv.stamp['time'])
+                if 'man' in sv.stamp and 'plat' in sv.stamp and 'cpu' in sv.stamp:
+                        headline_sysinfo = '<div class="stamp sysinfo">{0} {1} <i>with</i> {2}</div>\n'
+                        self.html += headline_sysinfo.format(sv.stamp['man'],
+                                sv.stamp['plat'], sv.stamp['cpu'])
+
         # Function: getDeviceRows
         # Description:
         #    determine how may rows the device funcs will take
@@ -1839,7 +1906,7 @@ class Timeline:
         #        devlist: the list of devices/actions in a group of contiguous phases
         # Output:
         #        The total number of rows needed to display this phase of the timeline
-        def getPhaseRows(self, devlist, row=0):
+        def getPhaseRows(self, devlist, row=0, sortby='length'):
                 # clear all rows and set them to undefined
                 remaining = len(devlist)
                 rowdata = dict()
@@ -1852,8 +1919,12 @@ class Timeline:
                         if tp not in myphases:
                                 myphases.append(tp)
                         dev['row'] = -1
-                        # sort by length 1st, then name 2nd
-                        sortdict[item] = (float(dev['end']) - float(dev['start']), item.dev['name'])
+                        if sortby == 'start':
+                                # sort by start 1st, then length 2nd
+                                sortdict[item] = (-1*float(dev['start']), float(dev['end']) - float(dev['start']))
+                        else:
+                                # sort by length 1st, then name 2nd
+                                sortdict[item] = (float(dev['end']) - float(dev['start']), item.dev['name'])
                         if 'src' in dev:
                                 dev['devrows'] = self.getDeviceRows(dev['src'])
                 # sort the devlist by length so that large items graph on top
@@ -1995,8 +2066,13 @@ class Timeline:
 #        A list of values describing the properties of these test runs
 class TestProps:
         stamp = ''
+        sysinfo = ''
         S0i3 = False
         fwdata = []
+        stampfmt = '# [a-z]*-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\
+                                '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\
+                                ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$'
+        sysinfofmt = '^# sysinfo .*'
         ftrace_line_fmt_fg = \
                 '^ *(?P<time>[0-9\.]*) *\| *(?P<cpu>[0-9]*)\)'+\
                 ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\|'+\
@@ -2019,6 +2095,36 @@ class TestProps:
                         self.ftrace_line_fmt = self.ftrace_line_fmt_nop
                 else:
                         doError('Invalid tracer format: [%s]' % tracer)
+        def parseStamp(self, data, sv):
+                m = re.match(self.stampfmt, self.stamp)
+                data.stamp = {'time': '', 'host': '', 'mode': ''}
+                dt = datetime(int(m.group('y'))+2000, int(m.group('m')),
+                        int(m.group('d')), int(m.group('H')), int(m.group('M')),
+                        int(m.group('S')))
+                data.stamp['time'] = dt.strftime('%B %d %Y, %I:%M:%S %p')
+                data.stamp['host'] = m.group('host')
+                data.stamp['mode'] = m.group('mode')
+                data.stamp['kernel'] = m.group('kernel')
+                if re.match(self.sysinfofmt, self.sysinfo):
+                        for f in self.sysinfo.split('|'):
+                                if '#' in f:
+                                        continue
+                                tmp = f.strip().split(':', 1)
+                                key = tmp[0]
+                                val = tmp[1]
+                                data.stamp[key] = val
+                sv.hostname = data.stamp['host']
+                sv.suspendmode = data.stamp['mode']
+                if sv.suspendmode == 'command' and sv.ftracefile != '':
+                        modes = ['on', 'freeze', 'standby', 'mem']
+                        out = Popen(['grep', 'suspend_enter', sv.ftracefile],
+                                stderr=PIPE, stdout=PIPE).stdout.read()
+                        m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out)
+                        if m and m.group('mode') in ['1', '2', '3']:
+                                sv.suspendmode = modes[int(m.group('mode'))]
+                                data.stamp['mode'] = sv.suspendmode
+                if not sv.stamp:
+                        sv.stamp = data.stamp
 
 # Class: TestRun
 # Description:
@@ -2090,35 +2196,6 @@ def vprint(msg):
         if(sysvals.verbose):
                 print(msg)
 
-# Function: parseStamp
-# Description:
-#        Pull in the stamp comment line from the data file(s),
-#        create the stamp, and add it to the global sysvals object
-# Arguments:
-#        m: the valid re.match output for the stamp line
-def parseStamp(line, data):
-        m = re.match(sysvals.stampfmt, line)
-        data.stamp = {'time': '', 'host': '', 'mode': ''}
-        dt = datetime(int(m.group('y'))+2000, int(m.group('m')),
-                int(m.group('d')), int(m.group('H')), int(m.group('M')),
-                int(m.group('S')))
-        data.stamp['time'] = dt.strftime('%B %d %Y, %I:%M:%S %p')
-        data.stamp['host'] = m.group('host')
-        data.stamp['mode'] = m.group('mode')
-        data.stamp['kernel'] = m.group('kernel')
-        sysvals.hostname = data.stamp['host']
-        sysvals.suspendmode = data.stamp['mode']
-        if sysvals.suspendmode == 'command' and sysvals.ftracefile != '':
-                modes = ['on', 'freeze', 'standby', 'mem']
-                out = Popen(['grep', 'suspend_enter', sysvals.ftracefile],
-                        stderr=PIPE, stdout=PIPE).stdout.read()
-                m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out)
-                if m and m.group('mode') in ['1', '2', '3']:
-                        sysvals.suspendmode = modes[int(m.group('mode'))]
-                        data.stamp['mode'] = sysvals.suspendmode
-        if not sysvals.stamp:
-                sysvals.stamp = data.stamp
-
 # Function: doesTraceLogHaveTraceEvents
 # Description:
 #        Quickly determine if the ftrace log has some or all of the trace events
@@ -2136,11 +2213,6 @@ def doesTraceLogHaveTraceEvents():
                 sysvals.usekprobes = True
         out = Popen(['head', '-1', sysvals.ftracefile],
                 stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '')
-        m = re.match(sysvals.stampfmt, out)
-        if m and m.group('mode') == 'command':
-                sysvals.usetraceeventsonly = True
-                sysvals.usetraceevents = True
-                return
         # figure out what level of trace events are supported
         sysvals.usetraceeventsonly = True
         sysvals.usetraceevents = False
@@ -2182,11 +2254,13 @@ def appendIncompleteTraceLog(testruns):
         for line in tf:
                 # remove any latent carriage returns
                 line = line.replace('\r\n', '')
-                # grab the time stamp
-                m = re.match(sysvals.stampfmt, line)
-                if(m):
+                # grab the stamp and sysinfo
+                if re.match(tp.stampfmt, line):
                         tp.stamp = line
                         continue
+                elif re.match(tp.sysinfofmt, line):
+                        tp.sysinfo = line
+                        continue
                 # determine the trace data type (required for further parsing)
                 m = re.match(sysvals.tracertypefmt, line)
                 if(m):
@@ -2219,7 +2293,7 @@ def appendIncompleteTraceLog(testruns):
                 # look for the suspend start marker
                 if(t.startMarker()):
                         data = testrun[testidx].data
-                        parseStamp(tp.stamp, data)
+                        tp.parseStamp(data, sysvals)
                         data.setStart(t.time)
                         continue
                 if(not data):
@@ -2389,11 +2463,13 @@ def parseTraceLog():
         for line in tf:
                 # remove any latent carriage returns
                 line = line.replace('\r\n', '')
-                # stamp line: each stamp means a new test run
-                m = re.match(sysvals.stampfmt, line)
-                if(m):
+                # stamp and sysinfo lines
+                if re.match(tp.stampfmt, line):
                         tp.stamp = line
                         continue
+                elif re.match(tp.sysinfofmt, line):
+                        tp.sysinfo = line
+                        continue
                 # firmware line: pull out any firmware data
                 m = re.match(sysvals.firmwarefmt, line)
                 if(m):
@@ -2439,7 +2515,7 @@ def parseTraceLog():
                         testdata.append(data)
                         testrun = TestRun(data)
                         testruns.append(testrun)
-                        parseStamp(tp.stamp, data)
+                        tp.parseStamp(data, sysvals)
                         data.setStart(t.time)
                         data.tKernSus = t.time
                         continue
@@ -2820,10 +2896,13 @@ def loadKernelLog(justtext=False):
                 idx = line.find('[')
                 if idx > 1:
                         line = line[idx:]
-                m = re.match(sysvals.stampfmt, line)
-                if(m):
+                # grab the stamp and sysinfo
+                if re.match(tp.stampfmt, line):
                         tp.stamp = line
                         continue
+                elif re.match(tp.sysinfofmt, line):
+                        tp.sysinfo = line
+                        continue
                 m = re.match(sysvals.firmwarefmt, line)
                 if(m):
                         tp.fwdata.append((int(m.group('s')), int(m.group('r'))))
@@ -2839,7 +2918,7 @@ def loadKernelLog(justtext=False):
                         if(data):
                                 testruns.append(data)
                         data = Data(len(testruns))
-                        parseStamp(tp.stamp, data)
+                        tp.parseStamp(data, sysvals)
                         if len(tp.fwdata) > data.testnumber:
                                 data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
                                 if(data.fwSuspend > 0 or data.fwResume > 0):
@@ -3170,6 +3249,8 @@ def addCallgraphs(sv, hf, data):
                         continue
                 list = data.dmesg[p]['list']
                 for devname in data.sortedDevices(p):
+                        if len(sv.devicefilter) > 0 and devname not in sv.devicefilter:
+                                continue
                         dev = list[devname]
                         color = 'white'
                         if 'color' in data.dmesg[p]:
@@ -3309,7 +3390,6 @@ def createHTML(testruns):
         html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR&rarr;</div>\n'
         html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n'
         html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n'
-        html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}">&nbsp;{2}</div>\n'
         html_timetotal = '<table class="time1">\n<tr>'\
                 '<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\
                 '<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\
@@ -3346,10 +3426,7 @@ def createHTML(testruns):
         # Generate the header for this timeline
         for data in testruns:
                 tTotal = data.end - data.start
-                sktime = (data.dmesg['suspend_machine']['end'] - \
-                        data.tKernSus) * 1000
-                rktime = (data.dmesg['resume_complete']['end'] - \
-                        data.dmesg['resume_machine']['start']) * 1000
+                sktime, rktime = data.getTimeValues()
                 if(tTotal == 0):
                         print('ERROR: No timeline data')
                         sys.exit()
@@ -3581,7 +3658,7 @@ def createHTML(testruns):
                                 id += tmp[1][0]
                         order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
                         name = string.replace(phase, '_', ' &nbsp;')
-                        devtl.html += html_legend.format(order, \
+                        devtl.html += devtl.html_legend.format(order, \
                                 data.dmesg[phase]['color'], name, id)
                 devtl.html += '</div>\n'
 
@@ -3628,10 +3705,10 @@ def createHTML(testruns):
                 addCallgraphs(sysvals, hf, data)
 
         # add the test log as a hidden div
-        if sysvals.logmsg:
+        if sysvals.testlog and sysvals.logmsg:
                 hf.write('<div id="testlog" style="display:none;">\n'+sysvals.logmsg+'</div>\n')
         # add the dmesg log as a hidden div
-        if sysvals.addlogs and sysvals.dmesgfile:
+        if sysvals.dmesglog and sysvals.dmesgfile:
                 hf.write('<div id="dmesglog" style="display:none;">\n')
                 lf = open(sysvals.dmesgfile, 'r')
                 for line in lf:
@@ -3640,7 +3717,7 @@ def createHTML(testruns):
                 lf.close()
                 hf.write('</div>\n')
         # add the ftrace log as a hidden div
-        if sysvals.addlogs and sysvals.ftracefile:
+        if sysvals.ftracelog and sysvals.ftracefile:
                 hf.write('<div id="ftracelog" style="display:none;">\n')
                 lf = open(sysvals.ftracefile, 'r')
                 for line in lf:
@@ -3701,6 +3778,7 @@ def addCSS(hf, sv, testcount=1, kerror=False, extra=''):
         <style type=\'text/css\'>\n\
                 body {overflow-y:scroll;}\n\
                 .stamp {width:100%;text-align:center;background:gray;line-height:30px;color:white;font:25px Arial;}\n\
+                .stamp.sysinfo {font:10px Arial;}\n\
                 .callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
                 .callgraph article * {padding-left:28px;}\n\
                 h1 {color:black;font:bold 30px Times;}\n\
@@ -3746,7 +3824,7 @@ def addCSS(hf, sv, testcount=1, kerror=False, extra=''):
                 .legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
                 .legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
                 button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
-                .logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
+                .btnfmt {position:relative;float:right;height:25px;width:auto;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
                 .devlist {position:'+devlistpos+';width:190px;}\n\
                 a:link {color:white;text-decoration:none;}\n\
                 a:visited {color:white;}\n\
@@ -4084,8 +4162,6 @@ def addScriptCode(hf, testruns):
         '               win.document.write(title+"<pre>"+log.innerHTML+"</pre>");\n'\
         '               win.document.close();\n'\
         '       }\n'\
-        '       function onClickPhase(e) {\n'\
-        '       }\n'\
         '       function onMouseDown(e) {\n'\
         '               dragval[0] = e.clientX;\n'\
         '               dragval[1] = document.getElementById("dmesgzoombox").scrollLeft;\n'\
@@ -4120,9 +4196,6 @@ def addScriptCode(hf, testruns):
         '               document.getElementById("zoomin").onclick = zoomTimeline;\n'\
         '               document.getElementById("zoomout").onclick = zoomTimeline;\n'\
         '               document.getElementById("zoomdef").onclick = zoomTimeline;\n'\
-        '               var list = document.getElementsByClassName("square");\n'\
-        '               for (var i = 0; i < list.length; i++)\n'\
-        '                       list[i].onclick = onClickPhase;\n'\
         '               var list = document.getElementsByClassName("err");\n'\
         '               for (var i = 0; i < list.length; i++)\n'\
         '                       list[i].onclick = errWindow;\n'\
@@ -4193,8 +4266,14 @@ def executeSuspend():
                 if sysvals.testcommand != '':
                         call(sysvals.testcommand+' 2>&1', shell=True);
                 else:
+                        mode = sysvals.suspendmode
+                        if sysvals.memmode and os.path.exists(sysvals.mempowerfile):
+                                mode = 'mem'
+                                pf = open(sysvals.mempowerfile, 'w')
+                                pf.write(sysvals.memmode)
+                                pf.close()
                         pf = open(sysvals.powerfile, 'w')
-                        pf.write(sysvals.suspendmode)
+                        pf.write(mode)
                         # execution will pause here
                         try:
                                 pf.close()
@@ -4219,24 +4298,15 @@ def executeSuspend():
                         pm.stop()
                 sysvals.fsetVal('0', 'tracing_on')
                 print('CAPTURING TRACE')
-                writeDatafileHeader(sysvals.ftracefile, fwdata)
+                sysvals.writeDatafileHeader(sysvals.ftracefile, fwdata)
                 call('cat '+tp+'trace >> '+sysvals.ftracefile, shell=True)
                 sysvals.fsetVal('', 'trace')
                 devProps()
         # grab a copy of the dmesg output
         print('CAPTURING DMESG')
-        writeDatafileHeader(sysvals.dmesgfile, fwdata)
+        sysvals.writeDatafileHeader(sysvals.dmesgfile, fwdata)
         sysvals.getdmesg()
 
-def writeDatafileHeader(filename, fwdata):
-        fp = open(filename, 'a')
-        fp.write(sysvals.teststamp+'\n')
-        if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'):
-                for fw in fwdata:
-                        if(fw):
-                                fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
-        fp.close()
-
 # Function: setUSBDevicesAuto
 # Description:
 #        Set the autosuspend control parameter of all USB devices to auto
@@ -4244,7 +4314,7 @@ def writeDatafileHeader(filename, fwdata):
 #        to always-on since the kernel cant determine if the device can
 #        properly autosuspend
 def setUSBDevicesAuto():
-        rootCheck(True)
+        sysvals.rootCheck(True)
         for dirname, dirnames, filenames in os.walk('/sys/devices'):
                 if(re.match('.*/usb[0-9]*.*', dirname) and
                         'idVendor' in filenames and 'idProduct' in filenames):
@@ -4467,13 +4537,146 @@ def devProps(data=0):
 # Output:
 #        A string list of the available modes
 def getModes():
-        modes = ''
+        modes = []
         if(os.path.exists(sysvals.powerfile)):
                 fp = open(sysvals.powerfile, 'r')
                 modes = string.split(fp.read())
                 fp.close()
+        if(os.path.exists(sysvals.mempowerfile)):
+                deep = False
+                fp = open(sysvals.mempowerfile, 'r')
+                for m in string.split(fp.read()):
+                        memmode = m.strip('[]')
+                        if memmode == 'deep':
+                                deep = True
+                        else:
+                                modes.append('mem-%s' % memmode)
+                fp.close()
+                if 'mem' in modes and not deep:
+                        modes.remove('mem')
         return modes
 
+# Function: dmidecode
+# Description:
+#        Read the bios tables and pull out system info
+# Arguments:
+#        mempath: /dev/mem or custom mem path
+#        fatal: True to exit on error, False to return empty dict
+# Output:
+#        A dict object with all available key/values
+def dmidecode(mempath, fatal=False):
+        out = dict()
+
+        # the list of values to retrieve, with hardcoded (type, idx)
+        info = {
+                'bios-vendor': (0, 4),
+                'bios-version': (0, 5),
+                'bios-release-date': (0, 8),
+                'system-manufacturer': (1, 4),
+                'system-product-name': (1, 5),
+                'system-version': (1, 6),
+                'system-serial-number': (1, 7),
+                'baseboard-manufacturer': (2, 4),
+                'baseboard-product-name': (2, 5),
+                'baseboard-version': (2, 6),
+                'baseboard-serial-number': (2, 7),
+                'chassis-manufacturer': (3, 4),
+                'chassis-type': (3, 5),
+                'chassis-version': (3, 6),
+                'chassis-serial-number': (3, 7),
+                'processor-manufacturer': (4, 7),
+                'processor-version': (4, 16),
+        }
+        if(not os.path.exists(mempath)):
+                if(fatal):
+                        doError('file does not exist: %s' % mempath)
+                return out
+        if(not os.access(mempath, os.R_OK)):
+                if(fatal):
+                        doError('file is not readable: %s' % mempath)
+                return out
+
+        # by default use legacy scan, but try to use EFI first
+        memaddr = 0xf0000
+        memsize = 0x10000
+        for ep in ['/sys/firmware/efi/systab', '/proc/efi/systab']:
+                if not os.path.exists(ep) or not os.access(ep, os.R_OK):
+                        continue
+                fp = open(ep, 'r')
+                buf = fp.read()
+                fp.close()
+                i = buf.find('SMBIOS=')
+                if i >= 0:
+                        try:
+                                memaddr = int(buf[i+7:], 16)
+                                memsize = 0x20
+                        except:
+                                continue
+
+        # read in the memory for scanning
+        fp = open(mempath, 'rb')
+        try:
+                fp.seek(memaddr)
+                buf = fp.read(memsize)
+        except:
+                if(fatal):
+                        doError('DMI table is unreachable, sorry')
+                else:
+                        return out
+        fp.close()
+
+        # search for either an SM table or DMI table
+        i = base = length = num = 0
+        while(i < memsize):
+                if buf[i:i+4] == '_SM_' and i < memsize - 16:
+                        length = struct.unpack('H', buf[i+22:i+24])[0]
+                        base, num = struct.unpack('IH', buf[i+24:i+30])
+                        break
+                elif buf[i:i+5] == '_DMI_':
+                        length = struct.unpack('H', buf[i+6:i+8])[0]
+                        base, num = struct.unpack('IH', buf[i+8:i+14])
+                        break
+                i += 16
+        if base == 0 and length == 0 and num == 0:
+                if(fatal):
+                        doError('Neither SMBIOS nor DMI were found')
+                else:
+                        return out
+
+        # read in the SM or DMI table
+        fp = open(mempath, 'rb')
+        try:
+                fp.seek(base)
+                buf = fp.read(length)
+        except:
+                if(fatal):
+                        doError('DMI table is unreachable, sorry')
+                else:
+                        return out
+        fp.close()
+
+        # scan the table for the values we want
+        count = i = 0
+        while(count < num and i <= len(buf) - 4):
+                type, size, handle = struct.unpack('BBH', buf[i:i+4])
+                n = i + size
+                while n < len(buf) - 1:
+                        if 0 == struct.unpack('H', buf[n:n+2])[0]:
+                                break
+                        n += 1
+                data = buf[i+size:n+2].split('\0')
+                for name in info:
+                        itype, idxadr = info[name]
+                        if itype == type:
+                                idx = struct.unpack('B', buf[i+idxadr])[0]
+                                if idx > 0 and idx < len(data) - 1:
+                                        s = data[idx-1].strip()
+                                        if s and s.lower() != 'to be filled by o.e.m.':
+                                                out[name] = data[idx-1]
+                i = n + 2
+                count += 1
+        return out
+
 # Function: getFPDT
 # Description:
 #        Read the acpi bios tables and pull out FPDT, the firmware data
@@ -4487,7 +4690,7 @@ def getFPDT(output):
         prectype[0] = 'Basic S3 Resume Performance Record'
         prectype[1] = 'Basic S3 Suspend Performance Record'
 
-        rootCheck(True)
+        sysvals.rootCheck(True)
         if(not os.path.exists(sysvals.fpdtpath)):
                 if(output):
                         doError('file does not exist: %s' % sysvals.fpdtpath)
@@ -4617,7 +4820,7 @@ def statusCheck(probecheck=False):
 
         # check we have root access
         res = sysvals.colorText('NO (No features of this tool will work!)')
-        if(rootCheck(False)):
+        if(sysvals.rootCheck(False)):
                 res = 'YES'
         print('    have root access: %s' % res)
         if(res != 'YES'):
@@ -4716,16 +4919,6 @@ def doError(msg, help=False):
         print('ERROR: %s\n') % msg
         sys.exit()
 
-# Function: rootCheck
-# Description:
-#        quick check to see if we have root access
-def rootCheck(fatal):
-        if(os.access(sysvals.powerfile, os.W_OK)):
-                return True
-        if fatal:
-                doError('This command requires sysfs mount and root access')
-        return False
-
 # Function: getArgInt
 # Description:
 #        pull out an integer argument from the command line with checks
@@ -4779,6 +4972,7 @@ def processData():
                 if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)):
                         appendIncompleteTraceLog(testruns)
         createHTML(testruns)
+        return testruns
 
 # Function: rerunTest
 # Description:
@@ -4790,17 +4984,20 @@ def rerunTest():
                 doError('recreating this html output requires a dmesg file')
         sysvals.setOutputFile()
         vprint('Output file: %s' % sysvals.htmlfile)
-        if(os.path.exists(sysvals.htmlfile) and not os.access(sysvals.htmlfile, os.W_OK)):
-                doError('missing permission to write to %s' % sysvals.htmlfile)
-        processData()
+        if os.path.exists(sysvals.htmlfile):
+                if not os.path.isfile(sysvals.htmlfile):
+                        doError('a directory already exists with this name: %s' % sysvals.htmlfile)
+                elif not os.access(sysvals.htmlfile, os.W_OK):
+                        doError('missing permission to write to %s' % sysvals.htmlfile)
+        return processData()
 
 # Function: runTest
 # Description:
 #        execute a suspend/resume, gather the logs, and generate the output
-def runTest(subdir, testpath=''):
+def runTest():
         # prepare for the test
         sysvals.initFtrace()
-        sysvals.initTestOutput(subdir, testpath)
+        sysvals.initTestOutput('suspend')
         vprint('Output files:\n\t%s\n\t%s\n\t%s' % \
                 (sysvals.dmesgfile, sysvals.ftracefile, sysvals.htmlfile))
 
@@ -4897,7 +5094,7 @@ def configFromFile(file):
                         if(opt.lower() == 'verbose'):
                                 sysvals.verbose = checkArgBool(value)
                         elif(opt.lower() == 'addlogs'):
-                                sysvals.addlogs = checkArgBool(value)
+                                sysvals.dmesglog = sysvals.ftracelog = checkArgBool(value)
                         elif(opt.lower() == 'dev'):
                                 sysvals.usedevsrc = checkArgBool(value)
                         elif(opt.lower() == 'proc'):
@@ -4947,7 +5144,7 @@ def configFromFile(file):
                         elif(opt.lower() == 'mincg'):
                                 sysvals.mincglen = getArgFloat('-mincg', value, 0.0, 10000.0, False)
                         elif(opt.lower() == 'output-dir'):
-                                sysvals.setOutputFolder(value)
+                                sysvals.testdir = sysvals.setOutputFolder(value)
 
         if sysvals.suspendmode == 'command' and not sysvals.testcommand:
                 doError('No command supplied for mode "command"')
@@ -5030,8 +5227,6 @@ def configFromFile(file):
 # Description:
 #        print out the help text
 def printHelp():
-        modes = getModes()
-
         print('')
         print('%s v%s' % (sysvals.title, sysvals.version))
         print('Usage: sudo sleepgraph <options> <commands>')
@@ -5048,7 +5243,7 @@ def printHelp():
         print('  If no specific command is given, the default behavior is to initiate')
         print('  a suspend/resume and capture the dmesg/ftrace output as an html timeline.')
         print('')
-        print('  Generates output files in subdirectory: suspend-mmddyy-HHMMSS')
+        print('  Generates output files in subdirectory: suspend-yymmdd-HHMMSS')
         print('   HTML output:                    <hostname>_<mode>.html')
         print('   raw dmesg output:               <hostname>_<mode>_dmesg.txt')
         print('   raw ftrace output:              <hostname>_<mode>_ftrace.txt')
@@ -5058,8 +5253,9 @@ def printHelp():
         print('   -v           Print the current tool version')
         print('   -config fn   Pull arguments and config options from file fn')
         print('   -verbose     Print extra information during execution and analysis')
-        print('   -m mode      Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
-        print('   -o subdir    Override the output subdirectory')
+        print('   -m mode      Mode to initiate for suspend (default: %s)') % (sysvals.suspendmode)
+        print('   -o name      Overrides the output subdirectory name when running a new test')
+        print('                default: suspend-{date}-{time}')
         print('   -rtcwake t   Wakeup t seconds after suspend, set t to "off" to disable (default: 15)')
         print('   -addlogs     Add the dmesg and ftrace logs to the html output')
         print('   -srgap       Add a visible gap in the timeline between sus/res (default: disabled)')
@@ -5084,17 +5280,20 @@ def printHelp():
         print('   -cgphase P   Only show callgraph data for phase P (e.g. suspend_late)')
         print('   -cgtest N    Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)')
         print('   -timeprec N  Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
-        print('  [commands]')
-        print('   -ftrace ftracefile  Create HTML output using ftrace input (used with -dmesg)')
-        print('   -dmesg dmesgfile    Create HTML output using dmesg (used with -ftrace)')
-        print('   -summary directory  Create a summary of all test in this dir')
+        print('')
+        print('Other commands:')
         print('   -modes       List available suspend modes')
         print('   -status      Test to see if the system is enabled to run this tool')
         print('   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table')
+        print('   -sysinfo     Print out system info extracted from BIOS')
         print('   -usbtopo     Print out the current USB topology with power info')
         print('   -usbauto     Enable autosuspend for all connected USB devices')
         print('   -flist       Print the list of functions currently being captured in ftrace')
         print('   -flistall    Print all functions capable of being captured in ftrace')
+        print('   -summary directory  Create a summary of all test in this dir')
+        print('  [redo]')
+        print('   -ftrace ftracefile  Create HTML output using ftrace input (used with -dmesg)')
+        print('   -dmesg dmesgfile    Create HTML output using dmesg (used with -ftrace)')
         print('')
         return True
 
@@ -5102,9 +5301,9 @@ def printHelp():
 # exec start (skipped if script is loaded as library)
 if __name__ == '__main__':
         cmd = ''
-        cmdarg = ''
+        outdir = ''
         multitest = {'run': False, 'count': 0, 'delay': 0}
-        simplecmds = ['-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status']
+        simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status']
         # loop through the command line arguments
         args = iter(sys.argv[1:])
         for arg in args:
@@ -5135,7 +5334,7 @@ if __name__ == '__main__':
                 elif(arg == '-f'):
                         sysvals.usecallgraph = True
                 elif(arg == '-addlogs'):
-                        sysvals.addlogs = True
+                        sysvals.dmesglog = sysvals.ftracelog = True
                 elif(arg == '-verbose'):
                         sysvals.verbose = True
                 elif(arg == '-proc'):
@@ -5195,7 +5394,7 @@ if __name__ == '__main__':
                                 val = args.next()
                         except:
                                 doError('No subdirectory name supplied', True)
-                        sysvals.setOutputFolder(val)
+                        outdir = sysvals.setOutputFolder(val)
                 elif(arg == '-config'):
                         try:
                                 val = args.next()
@@ -5236,7 +5435,7 @@ if __name__ == '__main__':
                         except:
                                 doError('No directory supplied', True)
                         cmd = 'summary'
-                        cmdarg = val
+                        outdir = val
                         sysvals.notestrun = True
                         if(os.path.isdir(val) == False):
                                 doError('%s is not accesible' % val)
@@ -5260,11 +5459,14 @@ if __name__ == '__main__':
                 sysvals.mincglen = sysvals.mindevlen
 
         # just run a utility command and exit
+        sysvals.cpuInfo()
         if(cmd != ''):
                 if(cmd == 'status'):
                         statusCheck(True)
                 elif(cmd == 'fpdt'):
                         getFPDT(True)
+                elif(cmd == 'sysinfo'):
+                        sysvals.printSystemInfo()
                 elif(cmd == 'usbtopo'):
                         detectUSB()
                 elif(cmd == 'modes'):
@@ -5276,7 +5478,7 @@ if __name__ == '__main__':
                 elif(cmd == 'usbauto'):
                         setUSBDevicesAuto()
                 elif(cmd == 'summary'):
-                        runSummary(cmdarg, True)
+                        runSummary(outdir, True)
                 sys.exit()
 
         # if instructed, re-analyze existing data files
@@ -5289,21 +5491,43 @@ if __name__ == '__main__':
                 print('Check FAILED, aborting the test run!')
                 sys.exit()
 
+        # extract mem modes and convert
+        mode = sysvals.suspendmode
+        if 'mem' == mode[:3]:
+                if '-' in mode:
+                        memmode = mode.split('-')[-1]
+                else:
+                        memmode = 'deep'
+                if memmode == 'shallow':
+                        mode = 'standby'
+                elif memmode ==  's2idle':
+                        mode = 'freeze'
+                else:
+                        mode = 'mem'
+                sysvals.memmode = memmode
+                sysvals.suspendmode = mode
+
+        sysvals.systemInfo(dmidecode(sysvals.mempath))
+
         if multitest['run']:
                 # run multiple tests in a separate subdirectory
-                s = 'x%d' % multitest['count']
-                if not sysvals.outdir:
-                        sysvals.outdir = datetime.now().strftime('suspend-'+s+'-%m%d%y-%H%M%S')
-                if not os.path.isdir(sysvals.outdir):
-                        os.mkdir(sysvals.outdir)
+                if not outdir:
+                        s = 'suspend-x%d' % multitest['count']
+                        outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S')
+                if not os.path.isdir(outdir):
+                        os.mkdir(outdir)
                 for i in range(multitest['count']):
                         if(i != 0):
                                 print('Waiting %d seconds...' % (multitest['delay']))
                                 time.sleep(multitest['delay'])
                         print('TEST (%d/%d) START' % (i+1, multitest['count']))
-                        runTest(sysvals.outdir)
+                        fmt = 'suspend-%y%m%d-%H%M%S'
+                        sysvals.testdir = os.path.join(outdir, datetime.now().strftime(fmt))
+                        runTest()
                         print('TEST (%d/%d) COMPLETE' % (i+1, multitest['count']))
-                runSummary(sysvals.outdir, False)
+                runSummary(outdir, False)
         else:
+                if outdir:
+                        sysvals.testdir = outdir
                 # run the test in the current directory
-                runTest('.', sysvals.outdir)
+                runTest()
diff --git a/tools/power/pm-graph/bootgraph.8 b/tools/power/pm-graph/bootgraph.8
index 55272a67b0e7..dbdafcf546df 100644
--- a/tools/power/pm-graph/bootgraph.8
+++ b/tools/power/pm-graph/bootgraph.8
@@ -8,14 +8,23 @@ bootgraph \- Kernel boot timing analysis
 .RB [ COMMAND ]
 .SH DESCRIPTION
 \fBbootgraph \fP reads the dmesg log from kernel boot and
-creates an html representation of the initcall timeline up to the start
-of the init process.
+creates an html representation of the initcall timeline. It graphs
+every module init call found, through both kernel and user modes. The
+timeline is split into two phases: kernel mode & user mode. kernel mode
+represents a single process run on a single cpu with serial init calls.
+Once user mode begins, the init process is called, and the init calls
+start working in parallel.
 .PP
 If no specific command is given, the tool reads the current dmesg log and
-outputs bootgraph.html.
+outputs a new timeline.
 .PP
 The tool can also augment the timeline with ftrace data on custom target
 functions as well as full trace callgraphs.
+.PP
+Generates output files in subdirectory: boot-yymmdd-HHMMSS
+   html timeline   :     <hostname>_boot.html
+   raw dmesg file  :     <hostname>_boot_dmesg.txt
+   raw ftrace file :     <hostname>_boot_ftrace.txt
 .SH OPTIONS
 .TP
 \fB-h\fR
@@ -28,15 +37,18 @@ Print the current tool version
 Add the dmesg log to the html output. It will be viewable by
 clicking a button in the timeline.
 .TP
-\fB-o \fIfile\fR
-Override the HTML output filename (default: bootgraph.html)
-.SS "Ftrace Debug"
+\fB-o \fIname\fR
+Overrides the output subdirectory name when running a new test.
+Use {date}, {time}, {hostname} for current values.
+.sp
+e.g. boot-{hostname}-{date}-{time}
+.SS "advanced"
 .TP
 \fB-f\fR
 Use ftrace to add function detail (default: disabled)
 .TP
 \fB-callgraph\fR
-Use ftrace to create initcall callgraphs (default: disabled). If -filter
+Use ftrace to create initcall callgraphs (default: disabled). If -func
 is not used there will be one callgraph per initcall. This can produce
 very large outputs, i.e. 10MB - 100MB.
 .TP
@@ -50,16 +62,19 @@ This reduces the html file size as there can be many tiny callgraphs
 which are barely visible in the timeline.
 The value is a float: e.g. 0.001 represents 1 us.
 .TP
+\fB-cgfilter \fI"func1,func2,..."\fR
+Reduce callgraph output in the timeline by limiting it to a list of calls. The
+argument can be a single function name or a comma delimited list.
+(default: none)
+.TP
 \fB-timeprec \fIn\fR
 Number of significant digits in timestamps (0:S, 3:ms, [6:us])
 .TP
 \fB-expandcg\fR
 pre-expand the callgraph data in the html output (default: disabled)
 .TP
-\fB-filter \fI"func1,func2,..."\fR
+\fB-func \fI"func1,func2,..."\fR
 Instead of tracing each initcall, trace a custom list of functions (default: do_one_initcall)
-
-.SH COMMANDS
 .TP
 \fB-reboot\fR
 Reboot the machine and generate a new timeline automatically. Works in 4 steps.
@@ -73,16 +88,23 @@ Show the requirements to generate a new timeline manually. Requires 3 steps.
   1. append the string to the kernel command line via your native boot manager.
   2. reboot the system
   3. after startup, re-run the tool with the same arguments and no command
+
+.SH COMMANDS
+.SS "rebuild"
 .TP
 \fB-dmesg \fIfile\fR
 Create HTML output from an existing dmesg file.
 .TP
 \fB-ftrace \fIfile\fR
 Create HTML output from an existing ftrace file (used with -dmesg).
+.SS "other"
 .TP
 \fB-flistall\fR
 Print all ftrace functions capable of being captured. These are all the
-possible values you can add to trace via the -filter argument.
+possible values you can add to trace via the -func argument.
+.TP
+\fB-sysinfo\fR
+Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode.
 
 .SH EXAMPLES
 Create a timeline using the current dmesg log.
@@ -93,13 +115,13 @@ Create a timeline using the current dmesg and ftrace log.
 .IP
 \f(CW$ bootgraph -callgraph\fR
 .PP
-Create a timeline using the current dmesg, add the log to the html and change the name.
+Create a timeline using the current dmesg, add the log to the html and change the folder.
 .IP
-\f(CW$ bootgraph -addlogs -o myboot.html\fR
+\f(CW$ bootgraph -addlogs -o "myboot-{date}-{time}"\fR
 .PP
 Capture a new boot timeline by automatically rebooting the machine.
 .IP
-\f(CW$ sudo bootgraph -reboot -addlogs -o latestboot.html\fR
+\f(CW$ sudo bootgraph -reboot -addlogs -o "latest-{hostname)"\fR
 .PP
 Capture a new boot timeline with function trace data.
 .IP
@@ -111,7 +133,7 @@ Capture a new boot timeline with trace & callgraph data. Skip callgraphs smaller
 .PP
 Capture a new boot timeline with callgraph data over custom functions.
 .IP
-\f(CW$ sudo bootgraph -reboot -callgraph -filter "acpi_ps_parse_aml,msleep"\fR
+\f(CW$ sudo bootgraph -reboot -callgraph -func "acpi_ps_parse_aml,msleep"\fR
 .PP
 Capture a brand new boot timeline with manual reboot.
 .IP
@@ -123,6 +145,15 @@ Capture a brand new boot timeline with manual reboot.
 .IP
 \f(CW$ sudo bootgraph -callgraph # re-run the tool after restart\fR
 .PP
+.SS "rebuild timeline from logs"
+.PP
+Rebuild the html from a previous run's logs, using the same options.
+.IP
+\f(CW$ bootgraph -dmesg dmesg.txt -ftrace ftrace.txt -callgraph\fR
+.PP
+Rebuild the html with different options.
+.IP
+\f(CW$ bootgraph -dmesg dmesg.txt -ftrace ftrace.txt -addlogs\fR
 
 .SH "SEE ALSO"
 dmesg(1), update-grub(8), crontab(1), reboot(8)
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
index 610e72ebbc06..fbe7bd3eae8e 100644
--- a/tools/power/pm-graph/sleepgraph.8
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -39,8 +39,9 @@ Pull arguments and config options from a file.
 \fB-m \fImode\fR
 Mode to initiate for suspend e.g. standby, freeze, mem (default: mem).
 .TP
-\fB-o \fIsubdir\fR
-Override the output subdirectory. Use {date}, {time}, {hostname} for current values.
+\fB-o \fIname\fR
+Overrides the output subdirectory name when running a new test.
+Use {date}, {time}, {hostname} for current values.
 .sp
 e.g. suspend-{hostname}-{date}-{time}
 .TP
@@ -52,7 +53,7 @@ disable rtcwake and require a user keypress to resume.
 Add the dmesg and ftrace logs to the html output. They will be viewable by
 clicking buttons in the timeline.
 
-.SS "Advanced"
+.SS "advanced"
 .TP
 \fB-cmd \fIstr\fR
 Run the timeline over a custom suspend command, e.g. pm-suspend. By default
@@ -91,7 +92,7 @@ Include \fIt\fR ms delay after last resume (default: 0 ms).
 Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will
 be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}.
 
-.SS "Ftrace Debug"
+.SS "ftrace debug"
 .TP
 \fB-f\fR
 Use ftrace to create device callgraphs (default: disabled). This can produce
@@ -124,12 +125,6 @@ Number of significant digits in timestamps (0:S, [3:ms], 6:us).
 
 .SH COMMANDS
 .TP
-\fB-ftrace \fIfile\fR
-Create HTML output from an existing ftrace file.
-.TP
-\fB-dmesg \fIfile\fR
-Create HTML output from an existing dmesg file.
-.TP
 \fB-summary \fIindir\fR
 Create a summary page of all tests in \fIindir\fR. Creates summary.html
 in the current folder. The output page is a table of tests with
@@ -146,6 +141,9 @@ with any options you intend to use to see if they will work.
 \fB-fpdt\fR
 Print out the contents of the ACPI Firmware Performance Data Table.
 .TP
+\fB-sysinfo\fR
+Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode.
+.TP
 \fB-usbtopo\fR
 Print out the current USB topology with power info.
 .TP
@@ -162,9 +160,16 @@ with -fadd they will also be checked.
 \fB-flistall\fR
 Print all ftrace functions capable of being captured. These are all the
 possible values you can add to trace via the -fadd argument.
+.SS "rebuild"
+.TP
+\fB-ftrace \fIfile\fR
+Create HTML output from an existing ftrace file.
+.TP
+\fB-dmesg \fIfile\fR
+Create HTML output from an existing dmesg file.
 
 .SH EXAMPLES
-.SS "Simple Commands"
+.SS "simple commands"
 Check which suspend modes are currently supported.
 .IP
 \f(CW$ sleepgraph -modes\fR
@@ -185,12 +190,8 @@ Generate a summary of all timelines in a particular folder.
 .IP
 \f(CW$ sleepgraph -summary ~/workspace/myresults/\fR
 .PP
-Re-generate the html output from a previous run's dmesg and ftrace log.
-.IP
-\f(CW$ sleepgraph -dmesg myhost_mem_dmesg.txt -ftrace myhost_mem_ftrace.txt\fR
-.PP
 
-.SS "Capturing Simple Timelines"
+.SS "capturing basic timelines"
 Execute a mem suspend with a 15 second wakeup. Include the logs in the html.
 .IP
 \f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR
@@ -204,7 +205,7 @@ Execute a freeze with no wakeup (require keypress). Change output folder name.
 \f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR
 .PP
 
-.SS "Capturing Advanced Timelines"
+.SS "capturing advanced timelines"
 Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger.
 .IP
 \f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR
@@ -222,8 +223,7 @@ Execute a suspend using a custom command.
 \f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
 .PP
 
-
-.SS "Capturing Timelines with Callgraph Data"
+.SS "adding callgraph data"
 Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger.
 .IP
 \f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR
@@ -235,6 +235,16 @@ Capture a full callgraph across all suspend, then filter the html by a single ph
 \f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume
 .PP
 
+.SS "rebuild timeline from logs"
+.PP
+Rebuild the html from a previous run's logs, using the same options.
+.IP
+\f(CW$ sleepgraph -dmesg dmesg.txt -ftrace ftrace.txt -callgraph\fR
+.PP
+Rebuild the html with different options.
+.IP
+\f(CW$ sleepgraph -dmesg dmesg.txt -ftrace ftrace.txt -addlogs -srgap\fR
+
 .SH "SEE ALSO"
 dmesg(1)
 .PP
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 8792ad8dbf83..a9bc914a8fe8 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC              = $(CROSS_COMPILE)gcc
 BUILD_OUTPUT    := $(CURDIR)
 PREFIX          ?= /usr
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dafba2c1e7d..bd9c6b31a504 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -92,7 +92,6 @@ unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
-int do_migrate;
 double discover_bclk(unsigned int family, unsigned int model);
 unsigned int has_hwp;   /* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
                         /* IA32_HWP_REQUEST, IA32_HWP_STATUS */
@@ -303,9 +302,6 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 
 int cpu_migrate(int cpu)
 {
-        if (!do_migrate)
-                return 0;
-
         CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
         CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set);
         if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1)
@@ -5007,7 +5003,6 @@ void cmdline(int argc, char **argv)
                 {"hide",        required_argument,      0, 'H'},        // meh, -h taken by --help
                 {"Joules",      no_argument,            0, 'J'},
                 {"list",        no_argument,            0, 'l'},
-                {"migrate",     no_argument,            0, 'm'},
                 {"out",         required_argument,      0, 'o'},
                 {"quiet",       no_argument,            0, 'q'},
                 {"show",        required_argument,      0, 's'},
@@ -5019,7 +5014,7 @@ void cmdline(int argc, char **argv)
 
         progname = argv[0];
 
-        while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:Jmo:qST:v",
+        while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
                                 long_options, &option_index)) != -1) {
                 switch (opt) {
                 case 'a':
@@ -5062,9 +5057,6 @@ void cmdline(int argc, char **argv)
                         list_header_only++;
                         quiet++;
                         break;
-                case 'm':
-                        do_migrate = 1;
-                        break;
                 case 'o':
                         outf = fopen_or_die(optarg, "w");
                         break;
diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile
index a711eec0c895..2447b1bbaacf 100644
--- a/tools/power/x86/x86_energy_perf_policy/Makefile
+++ b/tools/power/x86/x86_energy_perf_policy/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC              = $(CROSS_COMPILE)gcc
 BUILD_OUTPUT    := $(CURDIR)
 PREFIX          := /usr
diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch
index ad85b921a607..78d90a249e88 100644
--- a/tools/scripts/Makefile.arch
+++ b/tools/scripts/Makefile.arch
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e s/sun4u/sparc/ -e s/sparc64/sparc/ \
                                   -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ccad8ce925e4..3fab179b1aba 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifneq ($(O),)
 ifeq ($(origin O), command line)
         dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
@@ -12,7 +13,7 @@ endif
 
 # check that the output directory actually exists
 ifneq ($(OUTPUT),)
-OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+OUTDIR := $(shell cd $(OUTPUT) && pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
@@ -39,7 +40,9 @@ EXTRA_WARNINGS += -Wundef
 EXTRA_WARNINGS += -Wwrite-strings
 EXTRA_WARNINGS += -Wformat
 
-ifneq ($(CC), clang)
+CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
+
+ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 endif
 
diff --git a/tools/spi/Build b/tools/spi/Build
new file mode 100644
index 000000000000..8e8466033d99
--- /dev/null
+++ b/tools/spi/Build
@@ -0,0 +1,2 @@
+spidev_test-y += spidev_test.o
+spidev_fdx-y += spidev_fdx.o
diff --git a/tools/spi/Makefile b/tools/spi/Makefile
index 3815b18ba070..90615e10c79a 100644
--- a/tools/spi/Makefile
+++ b/tools/spi/Makefile
@@ -1,6 +1,66 @@
+include ../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
 CC = $(CROSS_COMPILE)gcc
+LD = $(CROSS_COMPILE)ld
+CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+
+ALL_TARGETS := spidev_test spidev_fdx
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
 
-all: spidev_test spidev_fdx
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/spi/spidev.h: ../../include/uapi/linux/spi/spidev.h
+        mkdir -p $(OUTPUT)include/linux/spi 2>&1 || true
+        ln -sf $(CURDIR)/../../include/uapi/linux/spi/spidev.h $@
+
+prepare: $(OUTPUT)include/linux/spi/spidev.h
+
+#
+# spidev_test
+#
+SPIDEV_TEST_IN := $(OUTPUT)spidev_test-in.o
+$(SPIDEV_TEST_IN): prepare FORCE
+        $(Q)$(MAKE) $(build)=spidev_test
+$(OUTPUT)spidev_test: $(SPIDEV_TEST_IN)
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
+#
+# spidev_fdx
+#
+SPIDEV_FDX_IN := $(OUTPUT)spidev_fdx-in.o
+$(SPIDEV_FDX_IN): prepare FORCE
+        $(Q)$(MAKE) $(build)=spidev_fdx
+$(OUTPUT)spidev_fdx: $(SPIDEV_FDX_IN)
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
 
 clean:
-        $(RM) spidev_test spidev_fdx
+        rm -f $(ALL_PROGRAMS)
+        rm -f $(OUTPUT)include/linux/spi/spidev.h
+        find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+
+install: $(ALL_PROGRAMS)
+        install -d -m 755 $(DESTDIR)$(bindir);          \
+        for program in $(ALL_PROGRAMS); do              \
+                install $$program $(DESTDIR)$(bindir);  \
+        done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare
diff --git a/tools/spi/spidev_fdx.c b/tools/spi/spidev_fdx.c
index 0ea3e51292fc..7d2a867cd4ae 100644
--- a/tools/spi/spidev_fdx.c
+++ b/tools/spi/spidev_fdx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <unistd.h>
 #include <stdlib.h>
diff --git a/tools/testing/fault-injection/failcmd.sh b/tools/testing/fault-injection/failcmd.sh
index 78a9ed7fecdb..29a6c63c5a15 100644
--- a/tools/testing/fault-injection/failcmd.sh
+++ b/tools/testing/fault-injection/failcmd.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # NAME
 #       failcmd.sh - run a command with injecting slab/page allocation failures
diff --git a/tools/testing/ktest/compare-ktest-sample.pl b/tools/testing/ktest/compare-ktest-sample.pl
index a373a5bfff68..4118eb4a842d 100755
--- a/tools/testing/ktest/compare-ktest-sample.pl
+++ b/tools/testing/ktest/compare-ktest-sample.pl
@@ -1,4 +1,5 @@
 #!/usr/bin/perl
+# SPDX-License-Identifier: GPL-2.0
 
 open (IN,"ktest.pl");
 while (<IN>) {
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index d870520da68b..db33b28c5ef3 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ldflags-y += --wrap=ioremap_wc
 ldflags-y += --wrap=memremap
 ldflags-y += --wrap=devm_ioremap_nocache
@@ -69,6 +70,7 @@ libnvdimm-y += $(NVDIMM_SRC)/region_devs.o
 libnvdimm-y += $(NVDIMM_SRC)/region.o
 libnvdimm-y += $(NVDIMM_SRC)/namespace_devs.o
 libnvdimm-y += $(NVDIMM_SRC)/label.o
+libnvdimm-y += $(NVDIMM_SRC)/badrange.o
 libnvdimm-$(CONFIG_ND_CLAIM) += $(NVDIMM_SRC)/claim.o
 libnvdimm-$(CONFIG_BTT) += $(NVDIMM_SRC)/btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += $(NVDIMM_SRC)/pfn_devs.o
diff --git a/tools/testing/nvdimm/Makefile b/tools/testing/nvdimm/Makefile
index 3dfe024b4e7e..c37a6a0bde28 100644
--- a/tools/testing/nvdimm/Makefile
+++ b/tools/testing/nvdimm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 KDIR ?= ../../../
 
 default:
diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c
index 7dc5a0af9b54..cac891028cd1 100644
--- a/tools/testing/nvdimm/config_check.c
+++ b/tools/testing/nvdimm/config_check.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/bug.h>
 
 void check(void)
diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild
index d32f25bba42a..fb3c3d7cdb9b 100644
--- a/tools/testing/nvdimm/test/Kbuild
+++ b/tools/testing/nvdimm/test/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ccflags-y := -I$(src)/../../../../drivers/nvdimm/
 ccflags-y += -I$(src)/../../../../drivers/acpi/nfit/
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 4c2fa98ef39d..7217b2b953b5 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -168,8 +168,12 @@ struct nfit_test {
                 spinlock_t lock;
         } ars_state;
         struct device *dimm_dev[NUM_DCR];
+        struct badrange badrange;
+        struct work_struct work;
 };
 
+static struct workqueue_struct *nfit_wq;
+
 static struct nfit_test *to_nfit_test(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
@@ -234,48 +238,68 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd,
         return rc;
 }
 
-#define NFIT_TEST_ARS_RECORDS 4
 #define NFIT_TEST_CLEAR_ERR_UNIT 256
 
 static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd,
                 unsigned int buf_len)
 {
+        int ars_recs;
+
         if (buf_len < sizeof(*nd_cmd))
                 return -EINVAL;
 
+        /* for testing, only store up to n records that fit within 4k */
+        ars_recs = SZ_4K / sizeof(struct nd_ars_record);
+
         nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status)
-                + NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record);
+                + ars_recs * sizeof(struct nd_ars_record);
         nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16;
         nd_cmd->clear_err_unit = NFIT_TEST_CLEAR_ERR_UNIT;
 
         return 0;
 }
 
-/*
- * Initialize the ars_state to return an ars_result 1 second in the future with
- * a 4K error range in the middle of the requested address range.
- */
-static void post_ars_status(struct ars_state *ars_state, u64 addr, u64 len)
+static void post_ars_status(struct ars_state *ars_state,
+                struct badrange *badrange, u64 addr, u64 len)
 {
         struct nd_cmd_ars_status *ars_status;
         struct nd_ars_record *ars_record;
+        struct badrange_entry *be;
+        u64 end = addr + len - 1;
+        int i = 0;
 
         ars_state->deadline = jiffies + 1*HZ;
         ars_status = ars_state->ars_status;
         ars_status->status = 0;
-        ars_status->out_length = sizeof(struct nd_cmd_ars_status)
-                + sizeof(struct nd_ars_record);
         ars_status->address = addr;
         ars_status->length = len;
         ars_status->type = ND_ARS_PERSISTENT;
-        ars_status->num_records = 1;
-        ars_record = &ars_status->records[0];
-        ars_record->handle = 0;
-        ars_record->err_address = addr + len / 2;
-        ars_record->length = SZ_4K;
+
+        spin_lock(&badrange->lock);
+        list_for_each_entry(be, &badrange->list, list) {
+                u64 be_end = be->start + be->length - 1;
+                u64 rstart, rend;
+
+                /* skip entries outside the range */
+                if (be_end < addr || be->start > end)
+                        continue;
+
+                rstart = (be->start < addr) ? addr : be->start;
+                rend = (be_end < end) ? be_end : end;
+                ars_record = &ars_status->records[i];
+                ars_record->handle = 0;
+                ars_record->err_address = rstart;
+                ars_record->length = rend - rstart + 1;
+                i++;
+        }
+        spin_unlock(&badrange->lock);
+        ars_status->num_records = i;
+        ars_status->out_length = sizeof(struct nd_cmd_ars_status)
+                + i * sizeof(struct nd_ars_record);
 }
 
-static int nfit_test_cmd_ars_start(struct ars_state *ars_state,
+static int nfit_test_cmd_ars_start(struct nfit_test *t,
+                struct ars_state *ars_state,
                 struct nd_cmd_ars_start *ars_start, unsigned int buf_len,
                 int *cmd_rc)
 {
@@ -289,7 +313,7 @@ static int nfit_test_cmd_ars_start(struct ars_state *ars_state,
         } else {
                 ars_start->status = 0;
                 ars_start->scrub_time = 1;
-                post_ars_status(ars_state, ars_start->address,
+                post_ars_status(ars_state, &t->badrange, ars_start->address,
                                 ars_start->length);
                 *cmd_rc = 0;
         }
@@ -320,7 +344,8 @@ static int nfit_test_cmd_ars_status(struct ars_state *ars_state,
         return 0;
 }
 
-static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
+static int nfit_test_cmd_clear_error(struct nfit_test *t,
+                struct nd_cmd_clear_error *clear_err,
                 unsigned int buf_len, int *cmd_rc)
 {
         const u64 mask = NFIT_TEST_CLEAR_ERR_UNIT - 1;
@@ -330,18 +355,91 @@ static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
         if ((clear_err->address & mask) || (clear_err->length & mask))
                 return -EINVAL;
 
-        /*
-         * Report 'all clear' success for all commands even though a new
-         * scrub will find errors again.  This is enough to have the
-         * error removed from the 'badblocks' tracking in the pmem
-         * driver.
-         */
+        badrange_forget(&t->badrange, clear_err->address, clear_err->length);
         clear_err->status = 0;
         clear_err->cleared = clear_err->length;
         *cmd_rc = 0;
         return 0;
 }
 
+struct region_search_spa {
+        u64 addr;
+        struct nd_region *region;
+};
+
+static int is_region_device(struct device *dev)
+{
+        return !strncmp(dev->kobj.name, "region", 6);
+}
+
+static int nfit_test_search_region_spa(struct device *dev, void *data)
+{
+        struct region_search_spa *ctx = data;
+        struct nd_region *nd_region;
+        resource_size_t ndr_end;
+
+        if (!is_region_device(dev))
+                return 0;
+
+        nd_region = to_nd_region(dev);
+        ndr_end = nd_region->ndr_start + nd_region->ndr_size;
+
+        if (ctx->addr >= nd_region->ndr_start && ctx->addr < ndr_end) {
+                ctx->region = nd_region;
+                return 1;
+        }
+
+        return 0;
+}
+
+static int nfit_test_search_spa(struct nvdimm_bus *bus,
+                struct nd_cmd_translate_spa *spa)
+{
+        int ret;
+        struct nd_region *nd_region = NULL;
+        struct nvdimm *nvdimm = NULL;
+        struct nd_mapping *nd_mapping = NULL;
+        struct region_search_spa ctx = {
+                .addr = spa->spa,
+                .region = NULL,
+        };
+        u64 dpa;
+
+        ret = device_for_each_child(&bus->dev, &ctx,
+                                nfit_test_search_region_spa);
+
+        if (!ret)
+                return -ENODEV;
+
+        nd_region = ctx.region;
+
+        dpa = ctx.addr - nd_region->ndr_start;
+
+        /*
+         * last dimm is selected for test
+         */
+        nd_mapping = &nd_region->mapping[nd_region->ndr_mappings - 1];
+        nvdimm = nd_mapping->nvdimm;
+
+        spa->devices[0].nfit_device_handle = handle[nvdimm->id];
+        spa->num_nvdimms = 1;
+        spa->devices[0].dpa = dpa;
+
+        return 0;
+}
+
+static int nfit_test_cmd_translate_spa(struct nvdimm_bus *bus,
+                struct nd_cmd_translate_spa *spa, unsigned int buf_len)
+{
+        if (buf_len < spa->translate_length)
+                return -EINVAL;
+
+        if (nfit_test_search_spa(bus, spa) < 0 || !spa->num_nvdimms)
+                spa->status = 2;
+
+        return 0;
+}
+
 static int nfit_test_cmd_smart(struct nd_cmd_smart *smart, unsigned int buf_len)
 {
         static const struct nd_smart_payload smart_data = {
@@ -378,6 +476,93 @@ static int nfit_test_cmd_smart_threshold(struct nd_cmd_smart_threshold *smart_t,
         return 0;
 }
 
+static void uc_error_notify(struct work_struct *work)
+{
+        struct nfit_test *t = container_of(work, typeof(*t), work);
+
+        __acpi_nfit_notify(&t->pdev.dev, t, NFIT_NOTIFY_UC_MEMORY_ERROR);
+}
+
+static int nfit_test_cmd_ars_error_inject(struct nfit_test *t,
+                struct nd_cmd_ars_err_inj *err_inj, unsigned int buf_len)
+{
+        int rc;
+
+        if (buf_len != sizeof(*err_inj)) {
+                rc = -EINVAL;
+                goto err;
+        }
+
+        if (err_inj->err_inj_spa_range_length <= 0) {
+                rc = -EINVAL;
+                goto err;
+        }
+
+        rc =  badrange_add(&t->badrange, err_inj->err_inj_spa_range_base,
+                        err_inj->err_inj_spa_range_length);
+        if (rc < 0)
+                goto err;
+
+        if (err_inj->err_inj_options & (1 << ND_ARS_ERR_INJ_OPT_NOTIFY))
+                queue_work(nfit_wq, &t->work);
+
+        err_inj->status = 0;
+        return 0;
+
+err:
+        err_inj->status = NFIT_ARS_INJECT_INVALID;
+        return rc;
+}
+
+static int nfit_test_cmd_ars_inject_clear(struct nfit_test *t,
+                struct nd_cmd_ars_err_inj_clr *err_clr, unsigned int buf_len)
+{
+        int rc;
+
+        if (buf_len != sizeof(*err_clr)) {
+                rc = -EINVAL;
+                goto err;
+        }
+
+        if (err_clr->err_inj_clr_spa_range_length <= 0) {
+                rc = -EINVAL;
+                goto err;
+        }
+
+        badrange_forget(&t->badrange, err_clr->err_inj_clr_spa_range_base,
+                        err_clr->err_inj_clr_spa_range_length);
+
+        err_clr->status = 0;
+        return 0;
+
+err:
+        err_clr->status = NFIT_ARS_INJECT_INVALID;
+        return rc;
+}
+
+static int nfit_test_cmd_ars_inject_status(struct nfit_test *t,
+                struct nd_cmd_ars_err_inj_stat *err_stat,
+                unsigned int buf_len)
+{
+        struct badrange_entry *be;
+        int max = SZ_4K / sizeof(struct nd_error_stat_query_record);
+        int i = 0;
+
+        err_stat->status = 0;
+        spin_lock(&t->badrange.lock);
+        list_for_each_entry(be, &t->badrange.list, list) {
+                err_stat->record[i].err_inj_stat_spa_range_base = be->start;
+                err_stat->record[i].err_inj_stat_spa_range_length = be->length;
+                i++;
+                if (i > max)
+                        break;
+        }
+        spin_unlock(&t->badrange.lock);
+        err_stat->inj_err_rec_count = i;
+
+        return 0;
+}
+
 static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
                 struct nvdimm *nvdimm, unsigned int cmd, void *buf,
                 unsigned int buf_len, int *cmd_rc)
@@ -449,6 +634,38 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
                 }
         } else {
                 struct ars_state *ars_state = &t->ars_state;
+                struct nd_cmd_pkg *call_pkg = buf;
+
+                if (!nd_desc)
+                        return -ENOTTY;
+
+                if (cmd == ND_CMD_CALL) {
+                        func = call_pkg->nd_command;
+
+                        buf_len = call_pkg->nd_size_in + call_pkg->nd_size_out;
+                        buf = (void *) call_pkg->nd_payload;
+
+                        switch (func) {
+                        case NFIT_CMD_TRANSLATE_SPA:
+                                rc = nfit_test_cmd_translate_spa(
+                                        acpi_desc->nvdimm_bus, buf, buf_len);
+                                return rc;
+                        case NFIT_CMD_ARS_INJECT_SET:
+                                rc = nfit_test_cmd_ars_error_inject(t, buf,
+                                        buf_len);
+                                return rc;
+                        case NFIT_CMD_ARS_INJECT_CLEAR:
+                                rc = nfit_test_cmd_ars_inject_clear(t, buf,
+                                        buf_len);
+                                return rc;
+                        case NFIT_CMD_ARS_INJECT_GET:
+                                rc = nfit_test_cmd_ars_inject_status(t, buf,
+                                        buf_len);
+                                return rc;
+                        default:
+                                return -ENOTTY;
+                        }
+                }
 
                 if (!nd_desc || !test_bit(cmd, &nd_desc->cmd_mask))
                         return -ENOTTY;
@@ -458,15 +675,15 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
                         rc = nfit_test_cmd_ars_cap(buf, buf_len);
                         break;
                 case ND_CMD_ARS_START:
-                        rc = nfit_test_cmd_ars_start(ars_state, buf, buf_len,
-                                        cmd_rc);
+                        rc = nfit_test_cmd_ars_start(t, ars_state, buf,
+                                        buf_len, cmd_rc);
                         break;
                 case ND_CMD_ARS_STATUS:
                         rc = nfit_test_cmd_ars_status(ars_state, buf, buf_len,
                                         cmd_rc);
                         break;
                 case ND_CMD_CLEAR_ERROR:
-                        rc = nfit_test_cmd_clear_error(buf, buf_len, cmd_rc);
+                        rc = nfit_test_cmd_clear_error(t, buf, buf_len, cmd_rc);
                         break;
                 default:
                         return -ENOTTY;
@@ -566,10 +783,9 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 
 static int ars_state_init(struct device *dev, struct ars_state *ars_state)
 {
+        /* for testing, only store up to n records that fit within 4k */
         ars_state->ars_status = devm_kzalloc(dev,
-                        sizeof(struct nd_cmd_ars_status)
-                        + sizeof(struct nd_ars_record) * NFIT_TEST_ARS_RECORDS,
-                        GFP_KERNEL);
+                        sizeof(struct nd_cmd_ars_status) + SZ_4K, GFP_KERNEL);
         if (!ars_state->ars_status)
                 return -ENOMEM;
         spin_lock_init(&ars_state->lock);
@@ -1419,7 +1635,8 @@ static void nfit_test0_setup(struct nfit_test *t)
                                 + i * sizeof(u64);
         }
 
-        post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE);
+        post_ars_status(&t->ars_state, &t->badrange, t->spa_set_dma[0],
+                        SPA0_SIZE);
 
         acpi_desc = &t->acpi_desc;
         set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
@@ -1430,7 +1647,12 @@ static void nfit_test0_setup(struct nfit_test *t)
         set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
         set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
         set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
+        set_bit(ND_CMD_CALL, &acpi_desc->bus_cmd_force_en);
         set_bit(ND_CMD_SMART_THRESHOLD, &acpi_desc->dimm_cmd_force_en);
+        set_bit(NFIT_CMD_TRANSLATE_SPA, &acpi_desc->bus_nfit_cmd_force_en);
+        set_bit(NFIT_CMD_ARS_INJECT_SET, &acpi_desc->bus_nfit_cmd_force_en);
+        set_bit(NFIT_CMD_ARS_INJECT_CLEAR, &acpi_desc->bus_nfit_cmd_force_en);
+        set_bit(NFIT_CMD_ARS_INJECT_GET, &acpi_desc->bus_nfit_cmd_force_en);
 }
 
 static void nfit_test1_setup(struct nfit_test *t)
@@ -1520,16 +1742,14 @@ static void nfit_test1_setup(struct nfit_test *t)
         dcr->code = NFIT_FIC_BYTE;
         dcr->windows = 0;
 
-        post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA2_SIZE);
+        post_ars_status(&t->ars_state, &t->badrange, t->spa_set_dma[0],
+                        SPA2_SIZE);
 
         acpi_desc = &t->acpi_desc;
         set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_cmd_force_en);
         set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
         set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
         set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
-        set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
-        set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
-        set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
@@ -1546,8 +1766,8 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
         else {
                 memcpy(iobuf, mmio->addr.base + dpa, len);
 
-                /* give us some some coverage of the mmio_flush_range() API */
-                mmio_flush_range(mmio->addr.base + dpa, len);
+                /* give us some some coverage of the arch_invalidate_pmem() API */
+                arch_invalidate_pmem(mmio->addr.base + dpa, len);
         }
         nd_region_release_lane(nd_region, lane);
 
@@ -1592,6 +1812,7 @@ static int nfit_ctl_test(struct device *dev)
         unsigned long mask, cmd_size, offset;
         union {
                 struct nd_cmd_get_config_size cfg_size;
+                struct nd_cmd_clear_error clear_err;
                 struct nd_cmd_ars_status ars_stat;
                 struct nd_cmd_ars_cap ars_cap;
                 char buf[sizeof(struct nd_cmd_ars_status)
@@ -1616,10 +1837,15 @@ static int nfit_ctl_test(struct device *dev)
                         .cmd_mask = 1UL << ND_CMD_ARS_CAP
                                 | 1UL << ND_CMD_ARS_START
                                 | 1UL << ND_CMD_ARS_STATUS
-                                | 1UL << ND_CMD_CLEAR_ERROR,
+                                | 1UL << ND_CMD_CLEAR_ERROR
+                                | 1UL << ND_CMD_CALL,
                         .module = THIS_MODULE,
                         .provider_name = "ACPI.NFIT",
                         .ndctl = acpi_nfit_ctl,
+                        .bus_dsm_mask = 1UL << NFIT_CMD_TRANSLATE_SPA
+                                | 1UL << NFIT_CMD_ARS_INJECT_SET
+                                | 1UL << NFIT_CMD_ARS_INJECT_CLEAR
+                                | 1UL << NFIT_CMD_ARS_INJECT_GET,
                 },
                 .dev = &adev->dev,
         };
@@ -1770,6 +1996,23 @@ static int nfit_ctl_test(struct device *dev)
                 return -EIO;
         }
 
+        /* test clear error */
+        cmd_size = sizeof(cmds.clear_err);
+        cmds.clear_err = (struct nd_cmd_clear_error) {
+                .length = 512,
+                .cleared = 512,
+        };
+        rc = setup_result(cmds.buf, cmd_size);
+        if (rc)
+                return rc;
+        rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_CLEAR_ERROR,
+                        cmds.buf, cmd_size, &cmd_rc);
+        if (rc < 0 || cmd_rc) {
+                dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n",
+                                __func__, __LINE__, rc, cmd_rc);
+                return -EIO;
+        }
+
         return 0;
 }
 
@@ -1918,6 +2161,10 @@ static __init int nfit_test_init(void)
 
         nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);
 
+        nfit_wq = create_singlethread_workqueue("nfit");
+        if (!nfit_wq)
+                return -ENOMEM;
+
         nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm");
         if (IS_ERR(nfit_test_dimm)) {
                 rc = PTR_ERR(nfit_test_dimm);
@@ -1934,6 +2181,7 @@ static __init int nfit_test_init(void)
                         goto err_register;
                 }
                 INIT_LIST_HEAD(&nfit_test->resources);
+                badrange_init(&nfit_test->badrange);
                 switch (i) {
                 case 0:
                         nfit_test->num_pm = NUM_PM;
@@ -1969,6 +2217,7 @@ static __init int nfit_test_init(void)
                         goto err_register;
 
                 instances[i] = nfit_test;
+                INIT_WORK(&nfit_test->work, uc_error_notify);
         }
 
         rc = platform_driver_register(&nfit_test_driver);
@@ -1977,6 +2226,7 @@ static __init int nfit_test_init(void)
         return 0;
 
  err_register:
+        destroy_workqueue(nfit_wq);
         for (i = 0; i < NUM_NFITS; i++)
                 if (instances[i])
                         platform_device_unregister(&instances[i]->pdev);
@@ -1992,6 +2242,8 @@ static __exit void nfit_test_exit(void)
 {
         int i;
 
+        flush_workqueue(nfit_wq);
+        destroy_workqueue(nfit_wq);
         for (i = 0; i < NUM_NFITS; i++)
                 platform_device_unregister(&instances[i]->pdev);
         platform_driver_unregister(&nfit_test_driver);
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index d3d63dd5ed38..113b44675a71 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -32,6 +32,58 @@ struct nfit_test_resource {
         void *buf;
 };
 
+#define ND_TRANSLATE_SPA_STATUS_INVALID_SPA  2
+#define NFIT_ARS_INJECT_INVALID 2
+
+enum err_inj_options {
+        ND_ARS_ERR_INJ_OPT_NOTIFY = 0,
+};
+
+/* nfit commands */
+enum nfit_cmd_num {
+        NFIT_CMD_TRANSLATE_SPA = 5,
+        NFIT_CMD_ARS_INJECT_SET = 7,
+        NFIT_CMD_ARS_INJECT_CLEAR = 8,
+        NFIT_CMD_ARS_INJECT_GET = 9,
+};
+
+struct nd_cmd_translate_spa {
+        __u64 spa;
+        __u32 status;
+        __u8  flags;
+        __u8  _reserved[3];
+        __u64 translate_length;
+        __u32 num_nvdimms;
+        struct nd_nvdimm_device {
+                __u32 nfit_device_handle;
+                __u32 _reserved;
+                __u64 dpa;
+        } __packed devices[0];
+
+} __packed;
+
+struct nd_cmd_ars_err_inj {
+        __u64 err_inj_spa_range_base;
+        __u64 err_inj_spa_range_length;
+        __u8  err_inj_options;
+        __u32 status;
+} __packed;
+
+struct nd_cmd_ars_err_inj_clr {
+        __u64 err_inj_clr_spa_range_base;
+        __u64 err_inj_clr_spa_range_length;
+        __u32 status;
+} __packed;
+
+struct nd_cmd_ars_err_inj_stat {
+        __u32 status;
+        __u32 inj_err_rec_count;
+        struct nd_error_stat_query_record {
+                __u64 err_inj_stat_spa_range_base;
+                __u64 err_inj_stat_spa_range_length;
+        } __packed record[0];
+} __packed;
+
 union acpi_object;
 typedef void *acpi_handle;
 
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 6a9480c03cbd..fa7ee369b3c9 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address
 LDFLAGS += -fsanitize=address
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index cf48c8473f48..6903ccf35595 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <string.h>
 #include <malloc.h>
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
index 39a0dcb9475a..e9fff59dfd8a 100644
--- a/tools/testing/radix-tree/linux/gfp.h
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _GFP_H
 #define _GFP_H
 
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index b21a77fddcf7..c3bc3f364f68 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _KERNEL_H
 #define _KERNEL_H
 
diff --git a/tools/testing/radix-tree/linux/percpu.h b/tools/testing/radix-tree/linux/percpu.h
index 3ea01a1a88c2..b2403aa743b2 100644
--- a/tools/testing/radix-tree/linux/percpu.h
+++ b/tools/testing/radix-tree/linux/percpu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #define DECLARE_PER_CPU(type, val) extern type val
 #define DEFINE_PER_CPU(type, val) type val
 
diff --git a/tools/testing/radix-tree/linux/preempt.h b/tools/testing/radix-tree/linux/preempt.h
index 35c5ac81529f..edb10302b903 100644
--- a/tools/testing/radix-tree/linux/preempt.h
+++ b/tools/testing/radix-tree/linux/preempt.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_PREEMPT_H
 #define __LINUX_PREEMPT_H
 
diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h
index bf1bb231f9b5..24f13d27a8da 100644
--- a/tools/testing/radix-tree/linux/radix-tree.h
+++ b/tools/testing/radix-tree/linux/radix-tree.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TEST_RADIX_TREE_H
 #define _TEST_RADIX_TREE_H
 
diff --git a/tools/testing/radix-tree/linux/rcupdate.h b/tools/testing/radix-tree/linux/rcupdate.h
index f7129ea2a899..73ed33658203 100644
--- a/tools/testing/radix-tree/linux/rcupdate.h
+++ b/tools/testing/radix-tree/linux/rcupdate.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _RCUPDATE_H
 #define _RCUPDATE_H
 
diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h
index e40337f41a38..979baeec7e70 100644
--- a/tools/testing/radix-tree/linux/slab.h
+++ b/tools/testing/radix-tree/linux/slab.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef SLAB_H
 #define SLAB_H
 
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index bc9a78449572..257f3f8aacaa 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 06c71178d07d..59245b3d587c 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -618,7 +618,7 @@ static void multiorder_account(void)
         __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
         __radix_tree_lookup(&tree, 1 << 5, &node, &slot);
         assert(node->count == node->exceptional * 2);
-        __radix_tree_replace(&tree, node, slot, NULL, NULL, NULL);
+        __radix_tree_replace(&tree, node, slot, NULL, NULL);
         assert(node->exceptional == 0);
 
         item_kill_tree(&tree);
diff --git a/tools/testing/radix-tree/regression.h b/tools/testing/radix-tree/regression.h
index e018c4816688..3c8a1584e9ee 100644
--- a/tools/testing/radix-tree/regression.h
+++ b/tools/testing/radix-tree/regression.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __REGRESSION_H__
 #define __REGRESSION_H__
 
diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index bf97742fc18c..0aece092f40e 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Regression1
  * Description:
diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c
index 42dd2a33ed24..424b91c77831 100644
--- a/tools/testing/radix-tree/regression2.c
+++ b/tools/testing/radix-tree/regression2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Regression2
  * Description:
diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c
index 670c3d2ae7b1..ace2543c3eda 100644
--- a/tools/testing/radix-tree/regression3.c
+++ b/tools/testing/radix-tree/regression3.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Regression3
  * Description:
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index 36dcf7d6945d..543181e4847b 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <assert.h>
 #include <stdio.h>
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 1a257d738a1e..5978ab1f403d 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <assert.h>
 #include <stdio.h>
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 0f8220cc6166..d9c031dbeb1a 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/gfp.h>
 #include <linux/types.h>
 #include <linux/radix-tree.h>
diff --git a/tools/testing/scatterlist/Makefile b/tools/testing/scatterlist/Makefile
new file mode 100644
index 000000000000..933c3a6e4d77
--- /dev/null
+++ b/tools/testing/scatterlist/Makefile
@@ -0,0 +1,30 @@
+CFLAGS += -I. -I../../include -g -O2 -Wall -fsanitize=address
+LDFLAGS += -fsanitize=address -fsanitize=undefined
+TARGETS = main
+OFILES = main.o scatterlist.o
+
+ifeq ($(BUILD), 32)
+        CFLAGS += -m32
+        LDFLAGS += -m32
+endif
+
+targets: include $(TARGETS)
+
+main: $(OFILES)
+
+clean:
+        $(RM) $(TARGETS) $(OFILES) scatterlist.c linux/scatterlist.h linux/highmem.h linux/kmemleak.h asm/io.h
+        @rmdir asm
+
+scatterlist.c: ../../../lib/scatterlist.c
+        @sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
+
+.PHONY: include
+
+include: ../../../include/linux/scatterlist.h
+        @mkdir -p linux
+        @mkdir -p asm
+        @touch asm/io.h
+        @touch linux/highmem.h
+        @touch linux/kmemleak.h
+        @cp $< linux/scatterlist.h
diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h
new file mode 100644
index 000000000000..6f9ac14aa800
--- /dev/null
+++ b/tools/testing/scatterlist/linux/mm.h
@@ -0,0 +1,125 @@
+#ifndef _LINUX_MM_H
+#define _LINUX_MM_H
+
+#include <assert.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <limits.h>
+#include <stdio.h>
+
+typedef unsigned long dma_addr_t;
+
+#define unlikely
+
+#define BUG_ON(x) assert(!(x))
+
+#define WARN_ON(condition) ({                                           \
+        int __ret_warn_on = !!(condition);                              \
+        unlikely(__ret_warn_on);                                        \
+})
+
+#define WARN_ON_ONCE(condition) ({                              \
+        int __ret_warn_on = !!(condition);                      \
+        if (unlikely(__ret_warn_on))                            \
+                assert(0);                                      \
+        unlikely(__ret_warn_on);                                \
+})
+
+#define PAGE_SIZE       (4096)
+#define PAGE_SHIFT      (12)
+#define PAGE_MASK       (~(PAGE_SIZE-1))
+
+#define __ALIGN_KERNEL(x, a)            __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)    (((x) + (mask)) & ~(mask))
+#define ALIGN(x, a)                     __ALIGN_KERNEL((x), (a))
+
+#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+
+#define offset_in_page(p)       ((unsigned long)(p) & ~PAGE_MASK)
+
+#define virt_to_page(x) ((void *)x)
+#define page_address(x) ((void *)x)
+
+static inline unsigned long page_to_phys(struct page *page)
+{
+        assert(0);
+
+        return 0;
+}
+
+#define page_to_pfn(page) ((unsigned long)(page) / PAGE_SIZE)
+#define pfn_to_page(pfn) (void *)((pfn) * PAGE_SIZE)
+#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
+
+#define __min(t1, t2, min1, min2, x, y) ({              \
+        t1 min1 = (x);                                  \
+        t2 min2 = (y);                                  \
+        (void) (&min1 == &min2);                        \
+        min1 < min2 ? min1 : min2; })
+
+#define ___PASTE(a,b) a##b
+#define __PASTE(a,b) ___PASTE(a,b)
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#define min(x, y)                                       \
+        __min(typeof(x), typeof(y),                     \
+              __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),   \
+              x, y)
+
+#define min_t(type, x, y)                               \
+        __min(type, type,                               \
+              __UNIQUE_ID(min1_), __UNIQUE_ID(min2_),   \
+              x, y)
+
+#define preemptible() (1)
+
+static inline void *kmap(struct page *page)
+{
+        assert(0);
+
+        return NULL;
+}
+
+static inline void *kmap_atomic(struct page *page)
+{
+        assert(0);
+
+        return NULL;
+}
+
+static inline void kunmap(void *addr)
+{
+        assert(0);
+}
+
+static inline void kunmap_atomic(void *addr)
+{
+        assert(0);
+}
+
+static inline unsigned long __get_free_page(unsigned int flags)
+{
+        return (unsigned long)malloc(PAGE_SIZE);
+}
+
+static inline void free_page(unsigned long page)
+{
+        free((void *)page);
+}
+
+static inline void *kmalloc(unsigned int size, unsigned int flags)
+{
+        return malloc(size);
+}
+
+#define kfree(x) free(x)
+
+#define kmemleak_alloc(a, b, c, d)
+#define kmemleak_free(a)
+
+#define PageSlab(p) (0)
+#define flush_kernel_dcache_page(p)
+
+#endif
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
new file mode 100644
index 000000000000..0a1464181226
--- /dev/null
+++ b/tools/testing/scatterlist/main.c
@@ -0,0 +1,79 @@
+#include <stdio.h>
+#include <assert.h>
+
+#include <linux/scatterlist.h>
+
+#define MAX_PAGES (64)
+
+static void set_pages(struct page **pages, const unsigned *array, unsigned num)
+{
+        unsigned int i;
+
+        assert(num < MAX_PAGES);
+        for (i = 0; i < num; i++)
+                pages[i] = (struct page *)(unsigned long)
+                           ((1 + array[i]) * PAGE_SIZE);
+}
+
+#define pfn(...) (unsigned []){ __VA_ARGS__ }
+
+int main(void)
+{
+        const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT;
+        struct test {
+                int alloc_ret;
+                unsigned num_pages;
+                unsigned *pfn;
+                unsigned size;
+                unsigned int max_seg;
+                unsigned int expected_segments;
+        } *test, tests[] = {
+                { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
+                { -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 },
+                { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
+                { 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 },
+                { 0, 1, pfn(0), 1, sgmax, 1 },
+                { 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 },
+                { 0, 2, pfn(1, 0), 2 * PAGE_SIZE, sgmax, 2 },
+                { 0, 3, pfn(0, 1, 2), 3 * PAGE_SIZE, sgmax, 1 },
+                { 0, 3, pfn(0, 2, 1), 3 * PAGE_SIZE, sgmax, 3 },
+                { 0, 3, pfn(0, 1, 3), 3 * PAGE_SIZE, sgmax, 2 },
+                { 0, 3, pfn(1, 2, 4), 3 * PAGE_SIZE, sgmax, 2 },
+                { 0, 3, pfn(1, 3, 4), 3 * PAGE_SIZE, sgmax, 2 },
+                { 0, 4, pfn(0, 1, 3, 4), 4 * PAGE_SIZE, sgmax, 2 },
+                { 0, 5, pfn(0, 1, 3, 4, 5), 5 * PAGE_SIZE, sgmax, 2 },
+                { 0, 5, pfn(0, 1, 3, 4, 6), 5 * PAGE_SIZE, sgmax, 3 },
+                { 0, 5, pfn(0, 1, 2, 3, 4), 5 * PAGE_SIZE, sgmax, 1 },
+                { 0, 5, pfn(0, 1, 2, 3, 4), 5 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
+                { 0, 6, pfn(0, 1, 2, 3, 4, 5), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
+                { 0, 6, pfn(0, 2, 3, 4, 5, 6), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 4 },
+                { 0, 6, pfn(0, 1, 3, 4, 5, 6), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
+                { 0, 0, NULL, 0, 0, 0 },
+        };
+        unsigned int i;
+
+        for (i = 0, test = tests; test->expected_segments; test++, i++) {
+                struct page *pages[MAX_PAGES];
+                struct sg_table st;
+                int ret;
+
+                set_pages(pages, test->pfn, test->num_pages);
+
+                ret = __sg_alloc_table_from_pages(&st, pages, test->num_pages,
+                                                  0, test->size, test->max_seg,
+                                                  GFP_KERNEL);
+                assert(ret == test->alloc_ret);
+
+                if (test->alloc_ret)
+                        continue;
+
+                assert(st.nents == test->expected_segments);
+                assert(st.orig_nents == test->expected_segments);
+
+                sg_free_table(&st);
+        }
+
+        assert(i == (sizeof(tests) / sizeof(tests[0])) - 1);
+
+        return 0;
+}
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 26ce4f7168be..eaf599dc2137 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,4 +1,6 @@
-TARGETS =  bpf
+# SPDX-License-Identifier: GPL-2.0
+TARGETS = android
+TARGETS += bpf
 TARGETS += breakpoints
 TARGETS += capabilities
 TARGETS += cpufreq
@@ -52,6 +54,10 @@ override LDFLAGS =
 override MAKEFLAGS =
 endif
 
+ifneq ($(KBUILD_SRC),)
+override LDFLAGS =
+endif
+
 BUILD := $(O)
 ifndef BUILD
   BUILD := $(KBUILD_OUTPUT)
@@ -62,32 +68,32 @@ endif
 
 export BUILD
 all:
-        for TARGET in $(TARGETS); do            \
+        @for TARGET in $(TARGETS); do           \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
         done;
 
 run_tests: all
-        for TARGET in $(TARGETS); do \
+        @for TARGET in $(TARGETS); do \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
         done;
 
 hotplug:
-        for TARGET in $(TARGETS_HOTPLUG); do \
+        @for TARGET in $(TARGETS_HOTPLUG); do \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
         done;
 
 run_hotplug: hotplug
-        for TARGET in $(TARGETS_HOTPLUG); do \
+        @for TARGET in $(TARGETS_HOTPLUG); do \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\
         done;
 
 clean_hotplug:
-        for TARGET in $(TARGETS_HOTPLUG); do \
+        @for TARGET in $(TARGETS_HOTPLUG); do \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
         done;
@@ -103,7 +109,7 @@ install:
 ifdef INSTALL_PATH
         @# Ask all targets to install their files
         mkdir -p $(INSTALL_PATH)
-        for TARGET in $(TARGETS); do \
+        @for TARGET in $(TARGETS); do \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
         done;
@@ -128,7 +134,7 @@ else
 endif
 
 clean:
-        for TARGET in $(TARGETS); do \
+        @for TARGET in $(TARGETS); do \
                 BUILD_TARGET=$$BUILD/$$TARGET;  \
                 make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
         done;
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
new file mode 100644
index 000000000000..1a7492268993
--- /dev/null
+++ b/tools/testing/selftests/android/Makefile
@@ -0,0 +1,46 @@
+SUBDIRS := ion
+
+TEST_PROGS := run.sh
+
+.PHONY: all clean
+
+include ../lib.mk
+
+all:
+        @for DIR in $(SUBDIRS); do              \
+                BUILD_TARGET=$(OUTPUT)/$$DIR;   \
+                mkdir $$BUILD_TARGET  -p;       \
+                make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+                #SUBDIR test prog name should be in the form: SUBDIR_test.sh
+                TEST=$$DIR"_test.sh"; \
+                if [ -e $$DIR/$$TEST ]; then
+                        rsync -a $$DIR/$$TEST $$BUILD_TARGET/;
+                fi
+        done
+
+override define RUN_TESTS
+        @cd $(OUTPUT); ./run.sh
+endef
+
+override define INSTALL_RULE
+        mkdir -p $(INSTALL_PATH)
+        install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
+
+        @for SUBDIR in $(SUBDIRS); do \
+                BUILD_TARGET=$(OUTPUT)/$$SUBDIR;        \
+                mkdir $$BUILD_TARGET  -p;       \
+                $(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
+        done;
+endef
+
+override define EMIT_TESTS
+        echo "./run.sh"
+endef
+
+override define CLEAN
+        @for DIR in $(SUBDIRS); do              \
+                BUILD_TARGET=$(OUTPUT)/$$DIR;   \
+                mkdir $$BUILD_TARGET  -p;       \
+                make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+        done
+endef
diff --git a/tools/testing/selftests/android/ion/.gitignore b/tools/testing/selftests/android/ion/.gitignore
new file mode 100644
index 000000000000..67e6f391b2a9
--- /dev/null
+++ b/tools/testing/selftests/android/ion/.gitignore
@@ -0,0 +1,2 @@
+ionapp_export
+ionapp_import
diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile
new file mode 100644
index 000000000000..96e0c448b39d
--- /dev/null
+++ b/tools/testing/selftests/android/ion/Makefile
@@ -0,0 +1,16 @@
+
+INCLUDEDIR := -I. -I../../../../../drivers/staging/android/uapi/
+CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
+
+TEST_GEN_FILES := ionapp_export ionapp_import
+
+all: $(TEST_GEN_FILES)
+
+$(TEST_GEN_FILES): ipcsocket.c ionutils.c
+
+TEST_PROGS := ion_test.sh
+
+include ../../lib.mk
+
+$(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
+$(OUTPUT)/ionapp_import: ionapp_import.c ipcsocket.c ionutils.c
diff --git a/tools/testing/selftests/android/ion/README b/tools/testing/selftests/android/ion/README
new file mode 100644
index 000000000000..21783e9c451e
--- /dev/null
+++ b/tools/testing/selftests/android/ion/README
@@ -0,0 +1,101 @@
+ION BUFFER SHARING UTILITY
+==========================
+File: ion_test.sh : Utility to test ION driver buffer sharing mechanism.
+Author: Pintu Kumar <pintu.ping@gmail.com>
+
+Introduction:
+-------------
+This is a test utility to verify ION buffer sharing in user space
+between 2 independent processes.
+It uses unix domain socket (with SCM_RIGHTS) as IPC to transfer an FD to
+another process to share the same buffer.
+This utility demonstrates how ION buffer sharing can be implemented between
+two user space processes, using various heap types.
+The following heap types are supported by ION driver.
+ION_HEAP_TYPE_SYSTEM (0)
+ION_HEAP_TYPE_SYSTEM_CONTIG (1)
+ION_HEAP_TYPE_CARVEOUT (2)
+ION_HEAP_TYPE_CHUNK (3)
+ION_HEAP_TYPE_DMA (4)
+
+By default only the SYSTEM and SYSTEM_CONTIG heaps are supported.
+Each heap is associated with the respective heap id.
+This utility is designed in the form of client/server program.
+The server part (ionapp_export) is the exporter of the buffer.
+It is responsible for creating an ION client, allocating the buffer based on
+the heap id, writing some data to this buffer and then exporting the FD
+(associated with this buffer) to another process using socket IPC.
+This FD is called as buffer FD (which is different than the ION client FD).
+
+The client part (ionapp_import) is the importer of the buffer.
+It retrives the FD from the socket data and installs into its address space.
+This new FD internally points to the same kernel buffer.
+So first it reads the data that is stored in this buffer and prints it.
+Then it writes the different size of data (it could be different data) to the
+same buffer.
+Finally the buffer FD must be closed by both the exporter and importer.
+Thus the same kernel buffer is shared among two user space processes using
+ION driver and only one time allocation.
+
+Prerequisite:
+-------------
+This utility works only if /dev/ion interface is present.
+The following configs needs to be enabled in kernel to include ion driver.
+CONFIG_ANDROID=y
+CONFIG_STAGING=y
+CONFIG_ION=y
+CONFIG_ION_SYSTEM_HEAP=y
+
+This utility requires to be run as root user.
+
+
+Compile and test:
+-----------------
+This utility is made to be run as part of kselftest framework in kernel.
+To compile and run using kselftest you can simply do the following from the
+kernel top directory.
+linux$ make TARGETS=android kselftest
+Or you can also use:
+linux$ make -C tools/testing/selftests TARGETS=android run_tests
+Using the selftest it can directly execute the ion_test.sh script to test the
+buffer sharing using ion system heap.
+Currently the heap size is hard coded as just 10 bytes inside this script.
+You need to be a root user to run under selftest.
+
+You can also compile and test manually using the following steps:
+ion$ make
+These will generate 2 executable: ionapp_export, ionapp_import
+Now you can run the export and import manually by specifying the heap type
+and the heap size.
+You can also directly execute the shell script to run the test automatically.
+Simply use the following command to run the test.
+ion$ sudo ./ion_test.sh
+
+Test Results:
+-------------
+The utility is verified on Ubuntu-32 bit system with Linux Kernel 4.14.
+Here is the snapshot of the test result using kselftest.
+
+linux# make TARGETS=android kselftest
+heap_type: 0, heap_size: 10
+--------------------------------------
+heap type: 0
+  heap id: 1
+heap name: ion_system_heap
+--------------------------------------
+Fill buffer content:
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
+Sharing fd: 6, Client fd: 5
+<ion_close_buffer_fd>: buffer release successfully....
+Received buffer fd: 4
+Read buffer content:
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0x0 0x0 0x0 0x0 0x0 0x0
+0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0
+Fill buffer content:
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
+0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
+0xfd 0xfd
+<ion_close_buffer_fd>: buffer release successfully....
+ion_test.sh: heap_type: 0 - [PASS]
+
+ion_test.sh: done
diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/ion/config
new file mode 100644
index 000000000000..19db6ca9aa2b
--- /dev/null
+++ b/tools/testing/selftests/android/ion/config
@@ -0,0 +1,4 @@
+CONFIG_ANDROID=y
+CONFIG_STAGING=y
+CONFIG_ION=y
+CONFIG_ION_SYSTEM_HEAP=y
diff --git a/tools/testing/selftests/android/ion/ion.h b/tools/testing/selftests/android/ion/ion.h
new file mode 100644
index 000000000000..f7021ac51335
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ion.h
@@ -0,0 +1,143 @@
+/*
+ * ion.h
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* This file is copied from drivers/staging/android/uapi/ion.h
+ * This local copy is required for the selftest to pass, when build
+ * outside the kernel source tree.
+ * Please keep this file in sync with its original file until the
+ * ion driver is moved outside the staging tree.
+ */
+
+#ifndef _UAPI_LINUX_ION_H
+#define _UAPI_LINUX_ION_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * enum ion_heap_types - list of all possible types of heaps
+ * @ION_HEAP_TYPE_SYSTEM:        memory allocated via vmalloc
+ * @ION_HEAP_TYPE_SYSTEM_CONTIG: memory allocated via kmalloc
+ * @ION_HEAP_TYPE_CARVEOUT:      memory allocated from a prereserved
+ *                               carveout heap, allocations are physically
+ *                               contiguous
+ * @ION_HEAP_TYPE_DMA:           memory allocated via DMA API
+ * @ION_NUM_HEAPS:               helper for iterating over heaps, a bit mask
+ *                               is used to identify the heaps, so only 32
+ *                               total heap types are supported
+ */
+enum ion_heap_type {
+        ION_HEAP_TYPE_SYSTEM,
+        ION_HEAP_TYPE_SYSTEM_CONTIG,
+        ION_HEAP_TYPE_CARVEOUT,
+        ION_HEAP_TYPE_CHUNK,
+        ION_HEAP_TYPE_DMA,
+        ION_HEAP_TYPE_CUSTOM, /*
+                               * must be last so device specific heaps always
+                               * are at the end of this enum
+                               */
+};
+
+#define ION_NUM_HEAP_IDS                (sizeof(unsigned int) * 8)
+
+/**
+ * allocation flags - the lower 16 bits are used by core ion, the upper 16
+ * bits are reserved for use by the heaps themselves.
+ */
+
+/*
+ * mappings of this buffer should be cached, ion will do cache maintenance
+ * when the buffer is mapped for dma
+ */
+#define ION_FLAG_CACHED 1
+
+/**
+ * DOC: Ion Userspace API
+ *
+ * create a client by opening /dev/ion
+ * most operations handled via following ioctls
+ *
+ */
+
+/**
+ * struct ion_allocation_data - metadata passed from userspace for allocations
+ * @len:                size of the allocation
+ * @heap_id_mask:       mask of heap ids to allocate from
+ * @flags:              flags passed to heap
+ * @handle:             pointer that will be populated with a cookie to use to
+ *                      refer to this allocation
+ *
+ * Provided by userspace as an argument to the ioctl
+ */
+struct ion_allocation_data {
+        __u64 len;
+        __u32 heap_id_mask;
+        __u32 flags;
+        __u32 fd;
+        __u32 unused;
+};
+
+#define MAX_HEAP_NAME                   32
+
+/**
+ * struct ion_heap_data - data about a heap
+ * @name - first 32 characters of the heap name
+ * @type - heap type
+ * @heap_id - heap id for the heap
+ */
+struct ion_heap_data {
+        char name[MAX_HEAP_NAME];
+        __u32 type;
+        __u32 heap_id;
+        __u32 reserved0;
+        __u32 reserved1;
+        __u32 reserved2;
+};
+
+/**
+ * struct ion_heap_query - collection of data about all heaps
+ * @cnt - total number of heaps to be copied
+ * @heaps - buffer to copy heap data
+ */
+struct ion_heap_query {
+        __u32 cnt; /* Total number of heaps to be copied */
+        __u32 reserved0; /* align to 64bits */
+        __u64 heaps; /* buffer to be populated */
+        __u32 reserved1;
+        __u32 reserved2;
+};
+
+#define ION_IOC_MAGIC           'I'
+
+/**
+ * DOC: ION_IOC_ALLOC - allocate memory
+ *
+ * Takes an ion_allocation_data struct and returns it with the handle field
+ * populated with the opaque handle for the allocation.
+ */
+#define ION_IOC_ALLOC           _IOWR(ION_IOC_MAGIC, 0, \
+                                      struct ion_allocation_data)
+
+/**
+ * DOC: ION_IOC_HEAP_QUERY - information about available heaps
+ *
+ * Takes an ion_heap_query structure and populates information about
+ * available Ion heaps.
+ */
+#define ION_IOC_HEAP_QUERY     _IOWR(ION_IOC_MAGIC, 8, \
+                                        struct ion_heap_query)
+
+#endif /* _UAPI_LINUX_ION_H */
diff --git a/tools/testing/selftests/android/ion/ion_test.sh b/tools/testing/selftests/android/ion/ion_test.sh
new file mode 100755
index 000000000000..a1aff506f5e6
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ion_test.sh
@@ -0,0 +1,55 @@
+#!/bin/bash
+
+heapsize=4096
+TCID="ion_test.sh"
+errcode=0
+
+run_test()
+{
+        heaptype=$1
+        ./ionapp_export -i $heaptype -s $heapsize &
+        sleep 1
+        ./ionapp_import
+        if [ $? -ne 0 ]; then
+                echo "$TCID: heap_type: $heaptype - [FAIL]"
+                errcode=1
+        else
+                echo "$TCID: heap_type: $heaptype - [PASS]"
+        fi
+        sleep 1
+        echo ""
+}
+
+check_root()
+{
+        uid=$(id -u)
+        if [ $uid -ne 0 ]; then
+                echo $TCID: must be run as root >&2
+                exit 0
+        fi
+}
+
+check_device()
+{
+        DEVICE=/dev/ion
+        if [ ! -e $DEVICE ]; then
+                echo $TCID: No $DEVICE device found >&2
+                echo $TCID: May be CONFIG_ION is not set >&2
+                exit 0
+        fi
+}
+
+main_function()
+{
+        check_device
+        check_root
+
+        # ION_SYSTEM_HEAP TEST
+        run_test 0
+        # ION_SYSTEM_CONTIG_HEAP TEST
+        run_test 1
+}
+
+main_function
+echo "$TCID: done"
+exit $errcode
diff --git a/tools/testing/selftests/android/ion/ionapp_export.c b/tools/testing/selftests/android/ion/ionapp_export.c
new file mode 100644
index 000000000000..a944e72621a9
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionapp_export.c
@@ -0,0 +1,135 @@
+/*
+ * ionapp_export.c
+ *
+ * It is a user space utility to create and export android
+ * ion memory buffer fd to another process using unix domain socket as IPC.
+ * This acts like a server for ionapp_import(client).
+ * So, this server has to be started first before the client.
+ *
+ * Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/time.h>
+#include "ionutils.h"
+#include "ipcsocket.h"
+
+
+void print_usage(int argc, char *argv[])
+{
+        printf("Usage: %s [-h <help>] [-i <heap id>] [-s <size in bytes>]\n",
+                argv[0]);
+}
+
+int main(int argc, char *argv[])
+{
+        int opt, ret, status, heapid;
+        int sockfd, client_fd, shared_fd;
+        unsigned char *map_buf;
+        unsigned long map_len, heap_type, heap_size, flags;
+        struct ion_buffer_info info;
+        struct socket_info skinfo;
+
+        if (argc < 2) {
+                print_usage(argc, argv);
+                return -1;
+        }
+
+        heap_size = 0;
+        flags = 0;
+
+        while ((opt = getopt(argc, argv, "hi:s:")) != -1) {
+                switch (opt) {
+                case 'h':
+                        print_usage(argc, argv);
+                        exit(0);
+                        break;
+                case 'i':
+                        heapid = atoi(optarg);
+                        switch (heapid) {
+                        case 0:
+                                heap_type = ION_HEAP_TYPE_SYSTEM;
+                                break;
+                        case 1:
+                                heap_type = ION_HEAP_TYPE_SYSTEM_CONTIG;
+                                break;
+                        default:
+                                printf("ERROR: heap type not supported\n");
+                                exit(1);
+                        }
+                        break;
+                case 's':
+                        heap_size = atoi(optarg);
+                        break;
+                default:
+                        print_usage(argc, argv);
+                        exit(1);
+                        break;
+                }
+        }
+
+        if (heap_size <= 0) {
+                printf("heap_size cannot be 0\n");
+                print_usage(argc, argv);
+                exit(1);
+        }
+
+        printf("heap_type: %ld, heap_size: %ld\n", heap_type, heap_size);
+        info.heap_type = heap_type;
+        info.heap_size = heap_size;
+        info.flag_type = flags;
+
+        /* This is server: open the socket connection first */
+        /* Here; 1 indicates server or exporter */
+        status = opensocket(&sockfd, SOCKET_NAME, 1);
+        if (status < 0) {
+                fprintf(stderr, "<%s>: Failed opensocket.\n", __func__);
+                goto err_socket;
+        }
+        skinfo.sockfd = sockfd;
+
+        ret = ion_export_buffer_fd(&info);
+        if (ret < 0) {
+                fprintf(stderr, "FAILED: ion_get_buffer_fd\n");
+                goto err_export;
+        }
+        client_fd = info.ionfd;
+        shared_fd = info.buffd;
+        map_buf = info.buffer;
+        map_len = info.buflen;
+        write_buffer(map_buf, map_len);
+
+        /* share ion buf fd with other user process */
+        printf("Sharing fd: %d, Client fd: %d\n", shared_fd, client_fd);
+        skinfo.datafd = shared_fd;
+        skinfo.buflen = map_len;
+
+        ret = socket_send_fd(&skinfo);
+        if (ret < 0) {
+                fprintf(stderr, "FAILED: socket_send_fd\n");
+                goto err_send;
+        }
+
+err_send:
+err_export:
+        ion_close_buffer_fd(&info);
+
+err_socket:
+        closesocket(sockfd, SOCKET_NAME);
+
+        return 0;
+}
diff --git a/tools/testing/selftests/android/ion/ionapp_import.c b/tools/testing/selftests/android/ion/ionapp_import.c
new file mode 100644
index 000000000000..ae2d704cfa46
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionapp_import.c
@@ -0,0 +1,88 @@
+/*
+ * ionapp_import.c
+ *
+ * It is a user space utility to receive android ion memory buffer fd
+ * over unix domain socket IPC that can be exported by ionapp_export.
+ * This acts like a client for ionapp_export.
+ *
+ * Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include "ionutils.h"
+#include "ipcsocket.h"
+
+
+int main(void)
+{
+        int ret, status;
+        int sockfd, shared_fd;
+        unsigned char *map_buf;
+        unsigned long map_len;
+        struct ion_buffer_info info;
+        struct socket_info skinfo;
+
+        /* This is the client part. Here 0 means client or importer */
+        status = opensocket(&sockfd, SOCKET_NAME, 0);
+        if (status < 0) {
+                fprintf(stderr, "No exporter exists...\n");
+                ret = status;
+                goto err_socket;
+        }
+
+        skinfo.sockfd = sockfd;
+
+        ret = socket_receive_fd(&skinfo);
+        if (ret < 0) {
+                fprintf(stderr, "Failed: socket_receive_fd\n");
+                goto err_recv;
+        }
+
+        shared_fd = skinfo.datafd;
+        printf("Received buffer fd: %d\n", shared_fd);
+        if (shared_fd <= 0) {
+                fprintf(stderr, "ERROR: improper buf fd\n");
+                ret = -1;
+                goto err_fd;
+        }
+
+        memset(&info, 0, sizeof(info));
+        info.buffd = shared_fd;
+        info.buflen = ION_BUFFER_LEN;
+
+        ret = ion_import_buffer_fd(&info);
+        if (ret < 0) {
+                fprintf(stderr, "Failed: ion_use_buffer_fd\n");
+                goto err_import;
+        }
+
+        map_buf = info.buffer;
+        map_len = info.buflen;
+        read_buffer(map_buf, map_len);
+
+        /* Write probably new data to the same buffer again */
+        map_len = ION_BUFFER_LEN;
+        write_buffer(map_buf, map_len);
+
+err_import:
+        ion_close_buffer_fd(&info);
+err_fd:
+err_recv:
+err_socket:
+        closesocket(sockfd, SOCKET_NAME);
+
+        return ret;
+}
diff --git a/tools/testing/selftests/android/ion/ionutils.c b/tools/testing/selftests/android/ion/ionutils.c
new file mode 100644
index 000000000000..ce69c14f51fa
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionutils.c
@@ -0,0 +1,259 @@
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <errno.h>
+//#include <stdint.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include "ionutils.h"
+#include "ipcsocket.h"
+
+
+void write_buffer(void *buffer, unsigned long len)
+{
+        int i;
+        unsigned char *ptr = (unsigned char *)buffer;
+
+        if (!ptr) {
+                fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
+                return;
+        }
+
+        printf("Fill buffer content:\n");
+        memset(ptr, 0xfd, len);
+        for (i = 0; i < len; i++)
+                printf("0x%x ", ptr[i]);
+        printf("\n");
+}
+
+void read_buffer(void *buffer, unsigned long len)
+{
+        int i;
+        unsigned char *ptr = (unsigned char *)buffer;
+
+        if (!ptr) {
+                fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
+                return;
+        }
+
+        printf("Read buffer content:\n");
+        for (i = 0; i < len; i++)
+                printf("0x%x ", ptr[i]);
+        printf("\n");
+}
+
+int ion_export_buffer_fd(struct ion_buffer_info *ion_info)
+{
+        int i, ret, ionfd, buffer_fd;
+        unsigned int heap_id;
+        unsigned long maplen;
+        unsigned char *map_buffer;
+        struct ion_allocation_data alloc_data;
+        struct ion_heap_query query;
+        struct ion_heap_data heap_data[MAX_HEAP_COUNT];
+
+        if (!ion_info) {
+                fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
+                return -1;
+        }
+
+        /* Create an ION client */
+        ionfd = open(ION_DEVICE, O_RDWR);
+        if (ionfd < 0) {
+                fprintf(stderr, "<%s>: Failed to open ion client: %s\n",
+                        __func__, strerror(errno));
+                return -1;
+        }
+
+        memset(&query, 0, sizeof(query));
+        query.cnt = MAX_HEAP_COUNT;
+        query.heaps = (unsigned long int)&heap_data[0];
+        /* Query ION heap_id_mask from ION heap */
+        ret = ioctl(ionfd, ION_IOC_HEAP_QUERY, &query);
+        if (ret < 0) {
+                fprintf(stderr, "<%s>: Failed: ION_IOC_HEAP_QUERY: %s\n",
+                        __func__, strerror(errno));
+                goto err_query;
+        }
+
+        heap_id = MAX_HEAP_COUNT + 1;
+        for (i = 0; i < query.cnt; i++) {
+                if (heap_data[i].type == ion_info->heap_type) {
+                        printf("--------------------------------------\n");
+                        printf("heap type: %d\n", heap_data[i].type);
+                        printf("  heap id: %d\n", heap_data[i].heap_id);
+                        printf("heap name: %s\n", heap_data[i].name);
+                        printf("--------------------------------------\n");
+                        heap_id = heap_data[i].heap_id;
+                        break;
+                }
+        }
+
+        if (heap_id > MAX_HEAP_COUNT) {
+                fprintf(stderr, "<%s>: ERROR: heap type does not exists\n",
+                        __func__);
+                goto err_heap;
+        }
+
+        alloc_data.len = ion_info->heap_size;
+        alloc_data.heap_id_mask = 1 << heap_id;
+        alloc_data.flags = ion_info->flag_type;
+
+        /* Allocate memory for this ION client as per heap_type */
+        ret = ioctl(ionfd, ION_IOC_ALLOC, &alloc_data);
+        if (ret < 0) {
+                fprintf(stderr, "<%s>: Failed: ION_IOC_ALLOC: %s\n",
+                        __func__, strerror(errno));
+                goto err_alloc;
+        }
+
+        /* This will return a valid buffer fd */
+        buffer_fd = alloc_data.fd;
+        maplen = alloc_data.len;
+
+        if (buffer_fd < 0 || maplen <= 0) {
+                fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
+                        __func__, buffer_fd, maplen);
+                goto err_fd_data;
+        }
+
+        /* Create memory mapped buffer for the buffer fd */
+        map_buffer = (unsigned char *)mmap(NULL, maplen, PROT_READ|PROT_WRITE,
+                        MAP_SHARED, buffer_fd, 0);
+        if (map_buffer == MAP_FAILED) {
+                fprintf(stderr, "<%s>: Failed: mmap: %s\n",
+                        __func__, strerror(errno));
+                goto err_mmap;
+        }
+
+        ion_info->ionfd = ionfd;
+        ion_info->buffd = buffer_fd;
+        ion_info->buffer = map_buffer;
+        ion_info->buflen = maplen;
+
+        return 0;
+
+        munmap(map_buffer, maplen);
+
+err_fd_data:
+err_mmap:
+        /* in case of error: close the buffer fd */
+        if (buffer_fd)
+                close(buffer_fd);
+
+err_query:
+err_heap:
+err_alloc:
+        /* In case of error: close the ion client fd */
+        if (ionfd)
+                close(ionfd);
+
+        return -1;
+}
+
+int ion_import_buffer_fd(struct ion_buffer_info *ion_info)
+{
+        int buffd;
+        unsigned char *map_buf;
+        unsigned long map_len;
+
+        if (!ion_info) {
+                fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
+                return -1;
+        }
+
+        map_len = ion_info->buflen;
+        buffd = ion_info->buffd;
+
+        if (buffd < 0 || map_len <= 0) {
+                fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
+                        __func__, buffd, map_len);
+                goto err_buffd;
+        }
+
+        map_buf = (unsigned char *)mmap(NULL, map_len, PROT_READ|PROT_WRITE,
+                        MAP_SHARED, buffd, 0);
+        if (map_buf == MAP_FAILED) {
+                printf("<%s>: Failed - mmap: %s\n",
+                        __func__, strerror(errno));
+                goto err_mmap;
+        }
+
+        ion_info->buffer = map_buf;
+        ion_info->buflen = map_len;
+
+        return 0;
+
+err_mmap:
+        if (buffd)
+                close(buffd);
+
+err_buffd:
+        return -1;
+}
+
+void ion_close_buffer_fd(struct ion_buffer_info *ion_info)
+{
+        if (ion_info) {
+                /* unmap the buffer properly in the end */
+                munmap(ion_info->buffer, ion_info->buflen);
+                /* close the buffer fd */
+                if (ion_info->buffd > 0)
+                        close(ion_info->buffd);
+                /* Finally, close the client fd */
+                if (ion_info->ionfd > 0)
+                        close(ion_info->ionfd);
+                printf("<%s>: buffer release successfully....\n", __func__);
+        }
+}
+
+int socket_send_fd(struct socket_info *info)
+{
+        int status;
+        int fd, sockfd;
+        struct socketdata skdata;
+
+        if (!info) {
+                fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
+                return -1;
+        }
+
+        sockfd = info->sockfd;
+        fd = info->datafd;
+        memset(&skdata, 0, sizeof(skdata));
+        skdata.data = fd;
+        skdata.len = sizeof(skdata.data);
+        status = sendtosocket(sockfd, &skdata);
+        if (status < 0) {
+                fprintf(stderr, "<%s>: Failed: sendtosocket\n", __func__);
+                return -1;
+        }
+
+        return 0;
+}
+
+int socket_receive_fd(struct socket_info *info)
+{
+        int status;
+        int fd, sockfd;
+        struct socketdata skdata;
+
+        if (!info) {
+                fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
+                return -1;
+        }
+
+        sockfd = info->sockfd;
+        memset(&skdata, 0, sizeof(skdata));
+        status = receivefromsocket(sockfd, &skdata);
+        if (status < 0) {
+                fprintf(stderr, "<%s>: Failed: receivefromsocket\n", __func__);
+                return -1;
+        }
+
+        fd = (int)skdata.data;
+        info->datafd = fd;
+
+        return status;
+}
diff --git a/tools/testing/selftests/android/ion/ionutils.h b/tools/testing/selftests/android/ion/ionutils.h
new file mode 100644
index 000000000000..9941eb858576
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ionutils.h
@@ -0,0 +1,55 @@
+#ifndef __ION_UTILS_H
+#define __ION_UTILS_H
+
+#include "ion.h"
+
+#define SOCKET_NAME "ion_socket"
+#define ION_DEVICE "/dev/ion"
+
+#define ION_BUFFER_LEN  4096
+#define MAX_HEAP_COUNT  ION_HEAP_TYPE_CUSTOM
+
+struct socket_info {
+        int sockfd;
+        int datafd;
+        unsigned long buflen;
+};
+
+struct ion_buffer_info {
+        int ionfd;
+        int buffd;
+        unsigned int heap_type;
+        unsigned int flag_type;
+        unsigned long heap_size;
+        unsigned long buflen;
+        unsigned char *buffer;
+};
+
+
+/* This is used to fill the data into the mapped buffer */
+void write_buffer(void *buffer, unsigned long len);
+
+/* This is used to read the data from the exported buffer */
+void read_buffer(void *buffer, unsigned long len);
+
+/* This is used to create an ION buffer FD for the kernel buffer
+ * So you can export this same buffer to others in the form of FD
+ */
+int ion_export_buffer_fd(struct ion_buffer_info *ion_info);
+
+/* This is used to import or map an exported FD.
+ * So we point to same buffer without making a copy. Hence zero-copy.
+ */
+int ion_import_buffer_fd(struct ion_buffer_info *ion_info);
+
+/* This is used to close all references for the ION client */
+void ion_close_buffer_fd(struct ion_buffer_info *ion_info);
+
+/* This is used to send FD to another process using socket IPC */
+int socket_send_fd(struct socket_info *skinfo);
+
+/* This is used to receive FD from another process using socket IPC */
+int socket_receive_fd(struct socket_info *skinfo);
+
+
+#endif
diff --git a/tools/testing/selftests/android/ion/ipcsocket.c b/tools/testing/selftests/android/ion/ipcsocket.c
new file mode 100644
index 000000000000..7dc521002095
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ipcsocket.c
@@ -0,0 +1,227 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/un.h>
+#include <errno.h>
+
+#include "ipcsocket.h"
+
+
+int opensocket(int *sockfd, const char *name, int connecttype)
+{
+        int ret, temp = 1;
+
+        if (!name || strlen(name) > MAX_SOCK_NAME_LEN) {
+                fprintf(stderr, "<%s>: Invalid socket name.\n", __func__);
+                return -1;
+        }
+
+        ret = socket(PF_LOCAL, SOCK_STREAM, 0);
+        if (ret < 0) {
+                fprintf(stderr, "<%s>: Failed socket: <%s>\n",
+                        __func__, strerror(errno));
+                return ret;
+        }
+
+        *sockfd = ret;
+        if (setsockopt(*sockfd, SOL_SOCKET, SO_REUSEADDR,
+                (char *)&temp, sizeof(int)) < 0) {
+                fprintf(stderr, "<%s>: Failed setsockopt: <%s>\n",
+                __func__, strerror(errno));
+                goto err;
+        }
+
+        sprintf(sock_name, "/tmp/%s", name);
+
+        if (connecttype == 1) {
+                /* This is for Server connection */
+                struct sockaddr_un skaddr;
+                int clientfd;
+                socklen_t sklen;
+
+                unlink(sock_name);
+                memset(&skaddr, 0, sizeof(skaddr));
+                skaddr.sun_family = AF_LOCAL;
+                strcpy(skaddr.sun_path, sock_name);
+
+                ret = bind(*sockfd, (struct sockaddr *)&skaddr,
+                        SUN_LEN(&skaddr));
+                if (ret < 0) {
+                        fprintf(stderr, "<%s>: Failed bind: <%s>\n",
+                        __func__, strerror(errno));
+                        goto err;
+                }
+
+                ret = listen(*sockfd, 5);
+                if (ret < 0) {
+                        fprintf(stderr, "<%s>: Failed listen: <%s>\n",
+                        __func__, strerror(errno));
+                        goto err;
+                }
+
+                memset(&skaddr, 0, sizeof(skaddr));
+                sklen = sizeof(skaddr);
+
+                ret = accept(*sockfd, (struct sockaddr *)&skaddr,
+                        (socklen_t *)&sklen);
+                if (ret < 0) {
+                        fprintf(stderr, "<%s>: Failed accept: <%s>\n",
+                        __func__, strerror(errno));
+                        goto err;
+                }
+
+                clientfd = ret;
+                *sockfd = clientfd;
+        } else {
+                /* This is for client connection */
+                struct sockaddr_un skaddr;
+
+                memset(&skaddr, 0, sizeof(skaddr));
+                skaddr.sun_family = AF_LOCAL;
+                strcpy(skaddr.sun_path, sock_name);
+
+                ret = connect(*sockfd, (struct sockaddr *)&skaddr,
+                        SUN_LEN(&skaddr));
+                if (ret < 0) {
+                        fprintf(stderr, "<%s>: Failed connect: <%s>\n",
+                        __func__, strerror(errno));
+                        goto err;
+                }
+        }
+
+        return 0;
+
+err:
+        if (*sockfd)
+                close(*sockfd);
+
+        return ret;
+}
+
+int sendtosocket(int sockfd, struct socketdata *skdata)
+{
+        int ret, buffd;
+        unsigned int len;
+        char cmsg_b[CMSG_SPACE(sizeof(int))];
+        struct cmsghdr *cmsg;
+        struct msghdr msgh;
+        struct iovec iov;
+        struct timeval timeout;
+        fd_set selFDs;
+
+        if (!skdata) {
+                fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
+                return -1;
+        }
+
+        FD_ZERO(&selFDs);
+        FD_SET(0, &selFDs);
+        FD_SET(sockfd, &selFDs);
+        timeout.tv_sec = 20;
+        timeout.tv_usec = 0;
+
+        ret = select(sockfd+1, NULL, &selFDs, NULL, &timeout);
+        if (ret < 0) {
+                fprintf(stderr, "<%s>: Failed select: <%s>\n",
+                __func__, strerror(errno));
+                return -1;
+        }
+
+        if (FD_ISSET(sockfd, &selFDs)) {
+                buffd = skdata->data;
+                len = skdata->len;
+                memset(&msgh, 0, sizeof(msgh));
+                msgh.msg_control = &cmsg_b;
+                msgh.msg_controllen = CMSG_LEN(len);
+                iov.iov_base = "OK";
+                iov.iov_len = 2;
+                msgh.msg_iov = &iov;
+                msgh.msg_iovlen = 1;
+                cmsg = CMSG_FIRSTHDR(&msgh);
+                cmsg->cmsg_level = SOL_SOCKET;
+                cmsg->cmsg_type = SCM_RIGHTS;
+                cmsg->cmsg_len = CMSG_LEN(len);
+                memcpy(CMSG_DATA(cmsg), &buffd, len);
+
+                ret = sendmsg(sockfd, &msgh, MSG_DONTWAIT);
+                if (ret < 0) {
+                        fprintf(stderr, "<%s>: Failed sendmsg: <%s>\n",
+                        __func__, strerror(errno));
+                        return -1;
+                }
+        }
+
+        return 0;
+}
+
+int receivefromsocket(int sockfd, struct socketdata *skdata)
+{
+        int ret, buffd;
+        unsigned int len = 0;
+        char cmsg_b[CMSG_SPACE(sizeof(int))];
+        struct cmsghdr *cmsg;
+        struct msghdr msgh;
+        struct iovec iov;
+        fd_set recvFDs;
+        char data[32];
+
+        if (!skdata) {
+                fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
+                return -1;
+        }
+
+        FD_ZERO(&recvFDs);
+        FD_SET(0, &recvFDs);
+        FD_SET(sockfd, &recvFDs);
+
+        ret = select(sockfd+1, &recvFDs, NULL, NULL, NULL);
+        if (ret < 0) {
+                fprintf(stderr, "<%s>: Failed select: <%s>\n",
+                __func__, strerror(errno));
+                return -1;
+        }
+
+        if (FD_ISSET(sockfd, &recvFDs)) {
+                len = sizeof(buffd);
+                memset(&msgh, 0, sizeof(msgh));
+                msgh.msg_control = &cmsg_b;
+                msgh.msg_controllen = CMSG_LEN(len);
+                iov.iov_base = data;
+                iov.iov_len = sizeof(data)-1;
+                msgh.msg_iov = &iov;
+                msgh.msg_iovlen = 1;
+                cmsg = CMSG_FIRSTHDR(&msgh);
+                cmsg->cmsg_level = SOL_SOCKET;
+                cmsg->cmsg_type = SCM_RIGHTS;
+                cmsg->cmsg_len = CMSG_LEN(len);
+
+                ret = recvmsg(sockfd, &msgh, MSG_DONTWAIT);
+                if (ret < 0) {
+                        fprintf(stderr, "<%s>: Failed recvmsg: <%s>\n",
+                        __func__, strerror(errno));
+                        return -1;
+                }
+
+                memcpy(&buffd, CMSG_DATA(cmsg), len);
+                skdata->data = buffd;
+                skdata->len = len;
+        }
+        return 0;
+}
+
+int closesocket(int sockfd, char *name)
+{
+        char sockname[MAX_SOCK_NAME_LEN];
+
+        if (sockfd)
+                close(sockfd);
+        sprintf(sockname, "/tmp/%s", name);
+        unlink(sockname);
+        shutdown(sockfd, 2);
+
+        return 0;
+}
diff --git a/tools/testing/selftests/android/ion/ipcsocket.h b/tools/testing/selftests/android/ion/ipcsocket.h
new file mode 100644
index 000000000000..b3e84498a8a1
--- /dev/null
+++ b/tools/testing/selftests/android/ion/ipcsocket.h
@@ -0,0 +1,35 @@
+
+#ifndef _IPCSOCKET_H
+#define _IPCSOCKET_H
+
+
+#define MAX_SOCK_NAME_LEN       64
+
+char sock_name[MAX_SOCK_NAME_LEN];
+
+/* This structure is responsible for holding the IPC data
+ * data: hold the buffer fd
+ * len: just the length of 32-bit integer fd
+ */
+struct socketdata {
+        int data;
+        unsigned int len;
+};
+
+/* This API is used to open the IPC socket connection
+ * name: implies a unique socket name in the system
+ * connecttype: implies server(0) or client(1)
+ */
+int opensocket(int *sockfd, const char *name, int connecttype);
+
+/* This is the API to send socket data over IPC socket */
+int sendtosocket(int sockfd, struct socketdata *data);
+
+/* This is the API to receive socket data over IPC socket */
+int receivefromsocket(int sockfd, struct socketdata *data);
+
+/* This is the API to close the socket connection */
+int closesocket(int sockfd, char *name);
+
+
+#endif
diff --git a/tools/testing/selftests/android/run.sh b/tools/testing/selftests/android/run.sh
new file mode 100755
index 000000000000..dd8edf291454
--- /dev/null
+++ b/tools/testing/selftests/android/run.sh
@@ -0,0 +1,3 @@
+#!/bin/sh
+
+(cd ion; ./ion_test.sh)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 153c3a181a4c..333a48655ee0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
 APIDIR := ../../../include/uapi
@@ -12,16 +13,17 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i
 LDLIBS += -lcap -lelf
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-        test_align
+        test_align test_verifier_log test_dev_cgroup
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
-        test_pkt_md_access.o
+        test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
+        sockmap_verdict_prog.o dev_cgroup.o
 
-TEST_PROGS := test_kmod.sh
+TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
 
 include ../lib.mk
 
-BPFOBJ := $(OUTPUT)/libbpf.a
+BPFOBJ := $(OUTPUT)/libbpf.a $(OUTPUT)/cgroup_helpers.c
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
 
@@ -34,8 +36,20 @@ $(BPFOBJ): force
         $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
 CLANG ?= clang
+LLC   ?= llc
+
+PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+
+# Let newer LLVM versions transparently probe the kernel for availability
+# of full BPF instruction set.
+ifeq ($(PROBE),)
+  CPU ?= probe
+else
+  CPU ?= generic
+endif
 
 %.o: %.c
         $(CLANG) -I. -I./include/uapi -I../../../include/uapi \
-                -Wno-compare-distinct-pointer-types \
-                -O2 -target bpf -c $< -o $@
+                 -Wno-compare-distinct-pointer-types          \
+                 -O2 -target bpf -emit-llvm -c $< -o - |      \
+        $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@
diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h
index 74af266aa512..b25595ea4a78 100644
--- a/tools/testing/selftests/bpf/bpf_endian.h
+++ b/tools/testing/selftests/bpf/bpf_endian.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __BPF_ENDIAN__
 #define __BPF_ENDIAN__
 
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index d50ac342dc92..fd9a17fa8a8b 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __BPF_HELPERS_H
 #define __BPF_HELPERS_H
 
@@ -38,6 +39,8 @@ static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) =
         (void *) BPF_FUNC_clone_redirect;
 static int (*bpf_redirect)(int ifindex, int flags) =
         (void *) BPF_FUNC_redirect;
+static int (*bpf_redirect_map)(void *map, int key, int flags) =
+        (void *) BPF_FUNC_redirect_map;
 static int (*bpf_perf_event_output)(void *ctx, void *map,
                                     unsigned long long flags, void *data,
                                     int size) =
@@ -60,9 +63,26 @@ static unsigned long long (*bpf_get_prandom_u32)(void) =
         (void *) BPF_FUNC_get_prandom_u32;
 static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
         (void *) BPF_FUNC_xdp_adjust_head;
+static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
+        (void *) BPF_FUNC_xdp_adjust_meta;
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
                              int optlen) =
         (void *) BPF_FUNC_setsockopt;
+static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval,
+                             int optlen) =
+        (void *) BPF_FUNC_getsockopt;
+static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
+        (void *) BPF_FUNC_sk_redirect_map;
+static int (*bpf_sock_map_update)(void *map, void *key, void *value,
+                                  unsigned long long flags) =
+        (void *) BPF_FUNC_sock_map_update;
+static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
+                                        void *buf, unsigned int buf_size) =
+        (void *) BPF_FUNC_perf_event_read_value;
+static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
+                                       unsigned int buf_size) =
+        (void *) BPF_FUNC_perf_prog_read_value;
+
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
@@ -85,6 +105,7 @@ struct bpf_map_def {
         unsigned int max_entries;
         unsigned int map_flags;
         unsigned int inner_map_idx;
+        unsigned int numa_node;
 };
 
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
@@ -100,7 +121,47 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
 static int (*bpf_skb_change_head)(void *, int len, int flags) =
         (void *) BPF_FUNC_skb_change_head;
 
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+        #define bpf_target_x86
+        #define bpf_target_defined
+#elif defined(__TARGET_ARCH_s930x)
+        #define bpf_target_s930x
+        #define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+        #define bpf_target_arm64
+        #define bpf_target_defined
+#elif defined(__TARGET_ARCH_mips)
+        #define bpf_target_mips
+        #define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+        #define bpf_target_powerpc
+        #define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+        #define bpf_target_sparc
+        #define bpf_target_defined
+#else
+        #undef bpf_target_defined
+#endif
+
+/* Fall back to what the compiler says */
+#ifndef bpf_target_defined
 #if defined(__x86_64__)
+        #define bpf_target_x86
+#elif defined(__s390x__)
+        #define bpf_target_s930x
+#elif defined(__aarch64__)
+        #define bpf_target_arm64
+#elif defined(__mips__)
+        #define bpf_target_mips
+#elif defined(__powerpc__)
+        #define bpf_target_powerpc
+#elif defined(__sparc__)
+        #define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
 
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
@@ -113,7 +174,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
 
-#elif defined(__s390x__)
+#elif defined(bpf_target_s390x)
 
 #define PT_REGS_PARM1(x) ((x)->gprs[2])
 #define PT_REGS_PARM2(x) ((x)->gprs[3])
@@ -126,7 +187,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->gprs[15])
 #define PT_REGS_IP(x) ((x)->psw.addr)
 
-#elif defined(__aarch64__)
+#elif defined(bpf_target_arm64)
 
 #define PT_REGS_PARM1(x) ((x)->regs[0])
 #define PT_REGS_PARM2(x) ((x)->regs[1])
@@ -139,7 +200,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->pc)
 
-#elif defined(__mips__)
+#elif defined(bpf_target_mips)
 
 #define PT_REGS_PARM1(x) ((x)->regs[4])
 #define PT_REGS_PARM2(x) ((x)->regs[5])
@@ -152,7 +213,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->regs[29])
 #define PT_REGS_IP(x) ((x)->cp0_epc)
 
-#elif defined(__powerpc__)
+#elif defined(bpf_target_powerpc)
 
 #define PT_REGS_PARM1(x) ((x)->gpr[3])
 #define PT_REGS_PARM2(x) ((x)->gpr[4])
@@ -163,7 +224,7 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
-#elif defined(__sparc__)
+#elif defined(bpf_target_sparc)
 
 #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
@@ -173,6 +234,8 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
 #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+
+/* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
 #define PT_REGS_IP(x) ((x)->tpc)
 #else
@@ -181,10 +244,10 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 
 #endif
 
-#ifdef __powerpc__
+#ifdef bpf_target_powerpc
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)         ({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP               BPF_KPROBE_READ_RET_IP
-#elif defined(__sparc__)
+#elif bpf_target_sparc
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)         ({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP               BPF_KPROBE_READ_RET_IP
 #else
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 20ecbaa0d85d..d0811b3d6a6f 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __BPF_UTIL__
 #define __BPF_UTIL__
 
@@ -12,6 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void)
         unsigned int start, end, possible_cpus = 0;
         char buff[128];
         FILE *fp;
+        int n;
 
         fp = fopen(fcpu, "r");
         if (!fp) {
@@ -20,17 +22,17 @@ static inline unsigned int bpf_num_possible_cpus(void)
         }
 
         while (fgets(buff, sizeof(buff), fp)) {
-                if (sscanf(buff, "%u-%u", &start, &end) == 2) {
-                        possible_cpus = start == 0 ? end + 1 : 0;
-                        break;
+                n = sscanf(buff, "%u-%u", &start, &end);
+                if (n == 0) {
+                        printf("Failed to retrieve # possible CPUs!\n");
+                        exit(1);
+                } else if (n == 1) {
+                        end = start;
                 }
+                possible_cpus = start == 0 ? end + 1 : 0;
+                break;
         }
-
         fclose(fp);
-        if (!possible_cpus) {
-                printf("Failed to retrieve # possible CPUs!\n");
-                exit(1);
-        }
 
         return possible_cpus;
 }
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
new file mode 100644
index 000000000000..f3bca3ade0f3
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <linux/limits.h>
+#include <stdio.h>
+#include <linux/sched.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <ftw.h>
+
+
+#include "cgroup_helpers.h"
+
+/*
+ * To avoid relying on the system setup, when setup_cgroup_env is called
+ * we create a new mount namespace, and cgroup namespace. The cgroup2
+ * root is mounted at CGROUP_MOUNT_PATH
+ *
+ * Unfortunately, most people don't have cgroupv2 enabled at this point in time.
+ * It's easier to create our own mount namespace and manage it ourselves.
+ *
+ * We assume /mnt exists.
+ */
+
+#define WALK_FD_LIMIT                   16
+#define CGROUP_MOUNT_PATH               "/mnt"
+#define CGROUP_WORK_DIR                 "/cgroup-test-work-dir"
+#define format_cgroup_path(buf, path) \
+        snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
+                 CGROUP_WORK_DIR, path)
+
+/**
+ * setup_cgroup_environment() - Setup the cgroup environment
+ *
+ * After calling this function, cleanup_cgroup_environment should be called
+ * once testing is complete.
+ *
+ * This function will print an error to stderr and return 1 if it is unable
+ * to setup the cgroup environment. If setup is successful, 0 is returned.
+ */
+int setup_cgroup_environment(void)
+{
+        char cgroup_workdir[PATH_MAX + 1];
+
+        format_cgroup_path(cgroup_workdir, "");
+
+        if (unshare(CLONE_NEWNS)) {
+                log_err("unshare");
+                return 1;
+        }
+
+        if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
+                log_err("mount fakeroot");
+                return 1;
+        }
+
+        if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
+                log_err("mount cgroup2");
+                return 1;
+        }
+
+        /* Cleanup existing failed runs, now that the environment is setup */
+        cleanup_cgroup_environment();
+
+        if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
+                log_err("mkdir cgroup work dir");
+                return 1;
+        }
+
+        return 0;
+}
+
+static int nftwfunc(const char *filename, const struct stat *statptr,
+                    int fileflags, struct FTW *pfwt)
+{
+        if ((fileflags & FTW_D) && rmdir(filename))
+                log_err("Removing cgroup: %s", filename);
+        return 0;
+}
+
+
+static int join_cgroup_from_top(char *cgroup_path)
+{
+        char cgroup_procs_path[PATH_MAX + 1];
+        pid_t pid = getpid();
+        int fd, rc = 0;
+
+        snprintf(cgroup_procs_path, sizeof(cgroup_procs_path),
+                 "%s/cgroup.procs", cgroup_path);
+
+        fd = open(cgroup_procs_path, O_WRONLY);
+        if (fd < 0) {
+                log_err("Opening Cgroup Procs: %s", cgroup_procs_path);
+                return 1;
+        }
+
+        if (dprintf(fd, "%d\n", pid) < 0) {
+                log_err("Joining Cgroup");
+                rc = 1;
+        }
+
+        close(fd);
+        return rc;
+}
+
+/**
+ * join_cgroup() - Join a cgroup
+ * @path: The cgroup path, relative to the workdir, to join
+ *
+ * This function expects a cgroup to already be created, relative to the cgroup
+ * work dir, and it joins it. For example, passing "/my-cgroup" as the path
+ * would actually put the calling process into the cgroup
+ * "/cgroup-test-work-dir/my-cgroup"
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_cgroup(char *path)
+{
+        char cgroup_path[PATH_MAX + 1];
+
+        format_cgroup_path(cgroup_path, path);
+        return join_cgroup_from_top(cgroup_path);
+}
+
+/**
+ * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
+ *
+ * This is an idempotent function to delete all temporary cgroups that
+ * have been created during the test, including the cgroup testing work
+ * directory.
+ *
+ * At call time, it moves the calling process to the root cgroup, and then
+ * runs the deletion process. It is idempotent, and should not fail, unless
+ * a process is lingering.
+ *
+ * On failure, it will print an error to stderr, and try to continue.
+ */
+void cleanup_cgroup_environment(void)
+{
+        char cgroup_workdir[PATH_MAX + 1];
+
+        format_cgroup_path(cgroup_workdir, "");
+        join_cgroup_from_top(CGROUP_MOUNT_PATH);
+        nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
+
+/**
+ * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
+ * @path: The cgroup path, relative to the workdir, to join
+ *
+ * This function creates a cgroup under the top level workdir and returns the
+ * file descriptor. It is idempotent.
+ *
+ * On success, it returns the file descriptor. On failure it returns 0.
+ * If there is a failure, it prints the error to stderr.
+ */
+int create_and_get_cgroup(char *path)
+{
+        char cgroup_path[PATH_MAX + 1];
+        int fd;
+
+        format_cgroup_path(cgroup_path, path);
+        if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
+                log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
+                return 0;
+        }
+
+        fd = open(cgroup_path, O_RDONLY);
+        if (fd < 0) {
+                log_err("Opening Cgroup");
+                return 0;
+        }
+
+        return fd;
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
new file mode 100644
index 000000000000..06485e0002b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __CGROUP_HELPERS_H
+#define __CGROUP_HELPERS_H
+#include <errno.h>
+#include <string.h>
+
+#define clean_errno() (errno == 0 ? "None" : strerror(errno))
+#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+        __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
+
+
+int create_and_get_cgroup(char *path);
+int join_cgroup(char *path);
+int setup_cgroup_environment(void);
+void cleanup_cgroup_environment(void);
+
+#endif
diff --git a/tools/testing/selftests/bpf/dev_cgroup.c b/tools/testing/selftests/bpf/dev_cgroup.c
new file mode 100644
index 000000000000..ce41a3475f27
--- /dev/null
+++ b/tools/testing/selftests/bpf/dev_cgroup.c
@@ -0,0 +1,60 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+SEC("cgroup/dev")
+int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
+{
+        short type = ctx->access_type & 0xFFFF;
+#ifdef DEBUG
+        short access = ctx->access_type >> 16;
+        char fmt[] = "  %d:%d    \n";
+
+        switch (type) {
+        case BPF_DEVCG_DEV_BLOCK:
+                fmt[0] = 'b';
+                break;
+        case BPF_DEVCG_DEV_CHAR:
+                fmt[0] = 'c';
+                break;
+        default:
+                fmt[0] = '?';
+                break;
+        }
+
+        if (access & BPF_DEVCG_ACC_READ)
+                fmt[8] = 'r';
+
+        if (access & BPF_DEVCG_ACC_WRITE)
+                fmt[9] = 'w';
+
+        if (access & BPF_DEVCG_ACC_MKNOD)
+                fmt[10] = 'm';
+
+        bpf_trace_printk(fmt, sizeof(fmt), ctx->major, ctx->minor);
+#endif
+
+        /* Allow access to /dev/zero and /dev/random.
+         * Forbid everything else.
+         */
+        if (ctx->major != 1 || type != BPF_DEVCG_DEV_CHAR)
+                return 0;
+
+        switch (ctx->minor) {
+        case 5: /* 1:5 /dev/zero */
+        case 9: /* 1:9 /dev/urandom */
+                return 1;
+        }
+
+        return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/testing/selftests/bpf/include/uapi/linux/types.h
index 51841848fbfe..91fa51a9c31d 100644
--- a/tools/testing/selftests/bpf/include/uapi/linux/types.h
+++ b/tools/testing/selftests/bpf/include/uapi/linux/types.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _UAPI_LINUX_TYPES_H
 #define _UAPI_LINUX_TYPES_H
 
diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c
new file mode 100644
index 000000000000..a1dec2b6d9c5
--- /dev/null
+++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c
@@ -0,0 +1,35 @@
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#include "bpf_util.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+
+#define bpf_printk(fmt, ...)                                    \
+({                                                              \
+               char ____fmt[] = fmt;                            \
+               bpf_trace_printk(____fmt, sizeof(____fmt),       \
+                                ##__VA_ARGS__);                 \
+})
+
+SEC("sk_skb1")
+int bpf_prog1(struct __sk_buff *skb)
+{
+        void *data_end = (void *)(long) skb->data_end;
+        void *data = (void *)(long) skb->data;
+        __u32 lport = skb->local_port;
+        __u32 rport = skb->remote_port;
+        __u8 *d = data;
+
+        if (data + 10 > data_end)
+                return skb->len;
+
+        /* This write/read is a bit pointless but tests the verifier and
+         * strparser handler for read/write pkt data and access into sk
+         * fields.
+         */
+        d[7] = 1;
+        return skb->len;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
new file mode 100644
index 000000000000..d7bea972cb21
--- /dev/null
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -0,0 +1,66 @@
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#include "bpf_util.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+
+#define bpf_printk(fmt, ...)                                    \
+({                                                              \
+               char ____fmt[] = fmt;                            \
+               bpf_trace_printk(____fmt, sizeof(____fmt),       \
+                                ##__VA_ARGS__);                 \
+})
+
+struct bpf_map_def SEC("maps") sock_map_rx = {
+        .type = BPF_MAP_TYPE_SOCKMAP,
+        .key_size = sizeof(int),
+        .value_size = sizeof(int),
+        .max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_tx = {
+        .type = BPF_MAP_TYPE_SOCKMAP,
+        .key_size = sizeof(int),
+        .value_size = sizeof(int),
+        .max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_break = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(int),
+        .value_size = sizeof(int),
+        .max_entries = 20,
+};
+
+SEC("sk_skb2")
+int bpf_prog2(struct __sk_buff *skb)
+{
+        void *data_end = (void *)(long) skb->data_end;
+        void *data = (void *)(long) skb->data;
+        __u32 lport = skb->local_port;
+        __u32 rport = skb->remote_port;
+        __u8 *d = data;
+        __u8 sk, map;
+
+        if (data + 8 > data_end)
+                return SK_DROP;
+
+        map = d[0];
+        sk = d[1];
+
+        d[0] = 0xd;
+        d[1] = 0xe;
+        d[2] = 0xa;
+        d[3] = 0xd;
+        d[4] = 0xb;
+        d[5] = 0xe;
+        d[6] = 0xe;
+        d[7] = 0xf;
+
+        if (!map)
+                return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
+        return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
index 29793694cbc7..8591c89c0828 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -27,6 +27,11 @@
 #define MAX_INSNS       512
 #define MAX_MATCHES     16
 
+struct bpf_reg_match {
+        unsigned int line;
+        const char *match;
+};
+
 struct bpf_align_test {
         const char *descr;
         struct bpf_insn insns[MAX_INSNS];
@@ -36,10 +41,14 @@ struct bpf_align_test {
                 REJECT
         } result;
         enum bpf_prog_type prog_type;
-        const char *matches[MAX_MATCHES];
+        /* Matches must be in order of increasing line */
+        struct bpf_reg_match matches[MAX_MATCHES];
 };
 
 static struct bpf_align_test tests[] = {
+        /* Four tests of known constants.  These aren't staggeringly
+         * interesting since we track exact values now.
+         */
         {
                 .descr = "mov",
                 .insns = {
@@ -53,11 +62,13 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
-                        "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
-                        "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
-                        "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
-                        "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+                        {1, "R1=ctx(id=0,off=0,imm=0)"},
+                        {1, "R10=fp0"},
+                        {1, "R3=inv2"},
+                        {2, "R3=inv4"},
+                        {3, "R3=inv8"},
+                        {4, "R3=inv16"},
+                        {5, "R3=inv32"},
                 },
         },
         {
@@ -79,17 +90,19 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
-                        "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
-                        "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
-                        "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
-                        "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
-                        "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
-                        "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
-                        "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
-                        "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
-                        "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
-                        "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+                        {1, "R1=ctx(id=0,off=0,imm=0)"},
+                        {1, "R10=fp0"},
+                        {1, "R3=inv1"},
+                        {2, "R3=inv2"},
+                        {3, "R3=inv4"},
+                        {4, "R3=inv8"},
+                        {5, "R3=inv16"},
+                        {6, "R3=inv1"},
+                        {7, "R4=inv32"},
+                        {8, "R4=inv16"},
+                        {9, "R4=inv8"},
+                        {10, "R4=inv4"},
+                        {11, "R4=inv2"},
                 },
         },
         {
@@ -106,12 +119,14 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
-                        "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp",
-                        "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp",
-                        "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
-                        "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp",
-                        "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+                        {1, "R1=ctx(id=0,off=0,imm=0)"},
+                        {1, "R10=fp0"},
+                        {1, "R3=inv4"},
+                        {2, "R3=inv8"},
+                        {3, "R3=inv10"},
+                        {4, "R4=inv8"},
+                        {5, "R4=inv12"},
+                        {6, "R4=inv14"},
                 },
         },
         {
@@ -126,13 +141,16 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
-                        "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
-                        "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
-                        "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp",
+                        {1, "R1=ctx(id=0,off=0,imm=0)"},
+                        {1, "R10=fp0"},
+                        {1, "R3=inv7"},
+                        {2, "R3=inv7"},
+                        {3, "R3=inv14"},
+                        {4, "R3=inv56"},
                 },
         },
 
+        /* Tests using unknown values */
 #define PREP_PKT_POINTERS \
         BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \
                     offsetof(struct __sk_buff, data)), \
@@ -166,17 +184,19 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
-                        "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp",
-                        "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp",
-                        "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp",
-                        "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp",
-                        "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp",
-                        "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp",
-                        "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp",
-                        "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp",
-                        "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp",
-                        "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp",
+                        {7, "R0=pkt(id=0,off=8,r=8,imm=0)"},
+                        {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {8, "R3=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+                        {9, "R3=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        {10, "R3=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+                        {11, "R3=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+                        {18, "R3=pkt_end(id=0,off=0,imm=0)"},
+                        {18, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {19, "R4=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
+                        {20, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+                        {21, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+                        {22, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        {23, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
                 },
         },
         {
@@ -197,16 +217,16 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
-                        "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
-                        "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp",
-                        "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
-                        "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp",
-                        "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
-                        "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp",
-                        "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
-                        "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp",
-                        "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp"
+                        {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {8, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {9, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {11, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+                        {12, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {13, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        {14, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {15, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+                        {16, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
                 },
         },
         {
@@ -237,12 +257,14 @@ static struct bpf_align_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .matches = {
-                        "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp",
-                        "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp",
-                        "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp",
-                        "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp",
-                        "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
-                        "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+                        {4, "R5=pkt(id=0,off=0,r=0,imm=0)"},
+                        {5, "R5=pkt(id=0,off=14,r=0,imm=0)"},
+                        {6, "R4=pkt(id=0,off=14,r=0,imm=0)"},
+                        {10, "R2=pkt(id=0,off=0,r=18,imm=0)"},
+                        {10, "R5=pkt(id=0,off=14,r=18,imm=0)"},
+                        {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+                        {14, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
+                        {15, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
                 },
         },
         {
@@ -297,62 +319,286 @@ static struct bpf_align_test tests[] = {
                         /* Calculated offset in R6 has unknown value, but known
                          * alignment of 4.
                          */
-                        "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp",
-
-                        /* Offset is added to packet pointer R5, resulting in known
-                         * auxiliary alignment and offset.
+                        {8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+                        {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* Offset is added to packet pointer R5, resulting in
+                         * known fixed offset, and variable offset from R6.
                          */
-                        "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-
+                        {11, "R5=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
                         /* At the time the word size load is performed from R5,
                          * it's total offset is NET_IP_ALIGN + reg->off (0) +
                          * reg->aux_off (14) which is 16.  Then the variable
                          * offset is considered using reg->aux_off_align which
                          * is 4 and meets the load's requirements.
                          */
-                        "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-
-
+                        {15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        {15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
                         /* Variable offset is added to R5 packet pointer,
                          * resulting in auxiliary alignment of 4.
                          */
-                        "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-
+                        {18, "R5=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
                         /* Constant offset is added to R5, resulting in
                          * reg->off of 14.
                          */
-                        "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-
+                        {19, "R5=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
                         /* At the time the word size load is performed from R5,
-                         * it's total offset is NET_IP_ALIGN + reg->off (14) which
-                         * is 16.  Then the variable offset is considered using
-                         * reg->aux_off_align which is 4 and meets the load's
-                         * requirements.
+                         * its total fixed offset is NET_IP_ALIGN + reg->off
+                         * (14) which is 16.  Then the variable offset is 4-byte
+                         * aligned, so the total offset is 4-byte aligned and
+                         * meets the load's requirements.
                          */
-                        "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-
+                        {23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        {23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
                         /* Constant offset is added to R5 packet pointer,
                          * resulting in reg->off value of 14.
                          */
-                        "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp",
-                        /* Variable offset is added to R5, resulting in an
-                         * auxiliary offset of 14, and an auxiliary alignment of 4.
+                        {26, "R5=pkt(id=0,off=14,r=8"},
+                        /* Variable offset is added to R5, resulting in a
+                         * variable offset of (4n).
                          */
-                        "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-                        /* Constant is added to R5 again, setting reg->off to 4. */
-                        "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
-                        /* And once more we add a variable, which causes an accumulation
-                         * of reg->off into reg->aux_off_align, with resulting value of
-                         * 18.  The auxiliary alignment stays at 4.
+                        {27, "R5=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* Constant is added to R5 again, setting reg->off to 18. */
+                        {28, "R5=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* And once more we add a variable; resulting var_off
+                         * is still (4n), fixed offset is not changed.
+                         * Also, we create a new reg->id.
                          */
-                        "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+                        {29, "R5=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"},
                         /* At the time the word size load is performed from R5,
-                         * it's total offset is NET_IP_ALIGN + reg->off (0) +
-                         * reg->aux_off (18) which is 20.  Then the variable offset
-                         * is considered using reg->aux_off_align which is 4 and meets
-                         * the load's requirements.
+                         * its total fixed offset is NET_IP_ALIGN + reg->off (18)
+                         * which is 20.  Then the variable offset is (4n), so
+                         * the total offset is 4-byte aligned and meets the
+                         * load's requirements.
+                         */
+                        {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
+                        {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
+                },
+        },
+        {
+                .descr = "packet variable offset 2",
+                .insns = {
+                        /* Create an unknown offset, (4n+2)-aligned */
+                        LOAD_UNKNOWN(BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14),
+                        /* Add it to the packet pointer */
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+                        /* Check bounds and perform a read */
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
+                        /* Make a (4n) offset from the value we just read */
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xff),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+                        /* Add it to the packet pointer */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+                        /* Check bounds and perform a read */
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .matches = {
+                        /* Calculated offset in R6 has unknown value, but known
+                         * alignment of 4.
+                         */
+                        {8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+                        {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* Adding 14 makes R6 be (4n+2) */
+                        {9, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                        /* Packet pointer has (4n+2) offset */
+                        {11, "R5=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                        {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                        /* At the time the word size load is performed from R5,
+                         * its total fixed offset is NET_IP_ALIGN + reg->off (0)
+                         * which is 2.  Then the variable offset is (4n+2), so
+                         * the total offset is 4-byte aligned and meets the
+                         * load's requirements.
+                         */
+                        {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                        /* Newly read value in R6 was shifted left by 2, so has
+                         * known alignment of 4.
+                         */
+                        {18, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* Added (4n) to packet pointer's (4n+2) var_off, giving
+                         * another (4n+2).
+                         */
+                        {19, "R5=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+                        {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+                        /* At the time the word size load is performed from R5,
+                         * its total fixed offset is NET_IP_ALIGN + reg->off (0)
+                         * which is 2.  Then the variable offset is (4n+2), so
+                         * the total offset is 4-byte aligned and meets the
+                         * load's requirements.
+                         */
+                        {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+                },
+        },
+        {
+                .descr = "dubious pointer arithmetic",
+                .insns = {
+                        PREP_PKT_POINTERS,
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        /* ptr & const => unknown & const */
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 0x40),
+                        /* ptr << const => unknown << const */
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_5, 2),
+                        /* We have a (4n) value.  Let's make a packet offset
+                         * out of it.  First add 14, to make it a (4n+2)
+                         */
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+                        /* Then make sure it's nonnegative */
+                        BPF_JMP_IMM(BPF_JSGE, BPF_REG_5, 0, 1),
+                        BPF_EXIT_INSN(),
+                        /* Add it to packet pointer */
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
+                        /* Check bounds and perform a read */
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_6, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .result = REJECT,
+                .matches = {
+                        {4, "R5=pkt(id=0,off=0,r=0,imm=0)"},
+                        /* ptr & 0x40 == either 0 or 0x40 */
+                        {5, "R5=inv(id=0,umax_value=64,var_off=(0x0; 0x40))"},
+                        /* ptr << 2 == unknown, (4n) */
+                        {7, "R5=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"},
+                        /* (4n) + 14 == (4n+2).  We blow our bounds, because
+                         * the add could overflow.
+                         */
+                        {8, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
+                        /* Checked s>=0 */
+                        {10, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+                        /* packet pointer + nonnegative (4n+2) */
+                        {12, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+                        {14, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+                        /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
+                         * We checked the bounds, but it might have been able
+                         * to overflow if the packet pointer started in the
+                         * upper half of the address space.
+                         * So we did not get a 'range' on R6, and the access
+                         * attempt will fail.
+                         */
+                        {16, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+                }
+        },
+        {
+                .descr = "variable subtraction",
+                .insns = {
+                        /* Create an unknown offset, (4n+2)-aligned */
+                        LOAD_UNKNOWN(BPF_REG_6),
+                        BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14),
+                        /* Create another unknown, (4n)-aligned, and subtract
+                         * it from the first one
+                         */
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2),
+                        BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_7),
+                        /* Bounds-check the result */
+                        BPF_JMP_IMM(BPF_JSGE, BPF_REG_6, 0, 1),
+                        BPF_EXIT_INSN(),
+                        /* Add it to the packet pointer */
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+                        /* Check bounds and perform a read */
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .matches = {
+                        /* Calculated offset in R6 has unknown value, but known
+                         * alignment of 4.
+                         */
+                        {7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+                        {9, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* Adding 14 makes R6 be (4n+2) */
+                        {10, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                        /* New unknown value in R7 is (4n) */
+                        {11, "R7=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+                        /* Subtracting it from R6 blows our unsigned bounds */
+                        {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"},
+                        /* Checked s>= 0 */
+                        {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                        /* At the time the word size load is performed from R5,
+                         * its total fixed offset is NET_IP_ALIGN + reg->off (0)
+                         * which is 2.  Then the variable offset is (4n+2), so
+                         * the total offset is 4-byte aligned and meets the
+                         * load's requirements.
+                         */
+                        {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
+                },
+        },
+        {
+                .descr = "pointer variable subtraction",
+                .insns = {
+                        /* Create an unknown offset, (4n+2)-aligned and bounded
+                         * to [14,74]
+                         */
+                        LOAD_UNKNOWN(BPF_REG_6),
+                        BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xf),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14),
+                        /* Subtract it from the packet pointer */
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_ALU64_REG(BPF_SUB, BPF_REG_5, BPF_REG_6),
+                        /* Create another unknown, (4n)-aligned and >= 74.
+                         * That in fact means >= 76, since 74 % 4 == 2
                          */
-                        "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 76),
+                        /* Add it to the packet pointer */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_7),
+                        /* Check bounds and perform a read */
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .matches = {
+                        /* Calculated offset in R6 has unknown value, but known
+                         * alignment of 4.
+                         */
+                        {7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+                        {10, "R6=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
+                        /* Adding 14 makes R6 be (4n+2) */
+                        {11, "R6=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
+                        /* Subtracting from packet pointer overflows ubounds */
+                        {13, "R5=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"},
+                        /* New unknown value in R7 is (4n), >= 76 */
+                        {15, "R7=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
+                        /* Adding it to packet pointer gives nice bounds again */
+                        {16, "R5=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
+                        /* At the time the word size load is performed from R5,
+                         * its total fixed offset is NET_IP_ALIGN + reg->off (0)
+                         * which is 2.  Then the variable offset is (4n+2), so
+                         * the total offset is 4-byte aligned and meets the
+                         * load's requirements.
+                         */
+                        {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
                 },
         },
 };
@@ -373,6 +619,9 @@ static int do_test_single(struct bpf_align_test *test)
 {
         struct bpf_insn *prog = test->insns;
         int prog_type = test->prog_type;
+        char bpf_vlog_copy[32768];
+        const char *line_ptr;
+        int cur_line = -1;
         int prog_len, i;
         int fd_prog;
         int ret;
@@ -381,26 +630,49 @@ static int do_test_single(struct bpf_align_test *test)
         fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
                                      prog, prog_len, 1, "GPL", 0,
                                      bpf_vlog, sizeof(bpf_vlog), 2);
-        if (fd_prog < 0) {
+        if (fd_prog < 0 && test->result != REJECT) {
                 printf("Failed to load program.\n");
                 printf("%s", bpf_vlog);
                 ret = 1;
+        } else if (fd_prog >= 0 && test->result == REJECT) {
+                printf("Unexpected success to load!\n");
+                printf("%s", bpf_vlog);
+                ret = 1;
+                close(fd_prog);
         } else {
                 ret = 0;
+                /* We make a local copy so that we can strtok() it */
+                strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy));
+                line_ptr = strtok(bpf_vlog_copy, "\n");
                 for (i = 0; i < MAX_MATCHES; i++) {
-                        const char *t, *m = test->matches[i];
+                        struct bpf_reg_match m = test->matches[i];
 
-                        if (!m)
+                        if (!m.match)
                                 break;
-                        t = strstr(bpf_vlog, m);
-                        if (!t) {
-                                printf("Failed to find match: %s\n", m);
+                        while (line_ptr) {
+                                cur_line = -1;
+                                sscanf(line_ptr, "%u: ", &cur_line);
+                                if (cur_line == m.line)
+                                        break;
+                                line_ptr = strtok(NULL, "\n");
+                        }
+                        if (!line_ptr) {
+                                printf("Failed to find line %u for match: %s\n",
+                                       m.line, m.match);
+                                ret = 1;
+                                printf("%s", bpf_vlog);
+                                break;
+                        }
+                        if (!strstr(line_ptr, m.match)) {
+                                printf("Failed to find match %u: %s\n",
+                                       m.line, m.match);
                                 ret = 1;
                                 printf("%s", bpf_vlog);
                                 break;
                         }
                 }
-                close(fd_prog);
+                if (fd_prog >= 0)
+                        close(fd_prog);
         }
         return ret;
 }
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
new file mode 100644
index 000000000000..02c85d6c89b0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_dev_cgroup.c
@@ -0,0 +1,93 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+
+#define DEV_CGROUP_PROG "./dev_cgroup.o"
+
+#define TEST_CGROUP "test-bpf-based-device-cgroup/"
+
+int main(int argc, char **argv)
+{
+        struct bpf_object *obj;
+        int error = EXIT_FAILURE;
+        int prog_fd, cgroup_fd;
+        __u32 prog_cnt;
+
+        if (bpf_prog_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE,
+                          &obj, &prog_fd)) {
+                printf("Failed to load DEV_CGROUP program\n");
+                goto err;
+        }
+
+        if (setup_cgroup_environment()) {
+                printf("Failed to load DEV_CGROUP program\n");
+                goto err;
+        }
+
+        /* Create a cgroup, get fd, and join it */
+        cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+        if (!cgroup_fd) {
+                printf("Failed to create test cgroup\n");
+                goto err;
+        }
+
+        if (join_cgroup(TEST_CGROUP)) {
+                printf("Failed to join cgroup\n");
+                goto err;
+        }
+
+        /* Attach bpf program */
+        if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_DEVICE, 0)) {
+                printf("Failed to attach DEV_CGROUP program");
+                goto err;
+        }
+
+        if (bpf_prog_query(cgroup_fd, BPF_CGROUP_DEVICE, 0, NULL, NULL,
+                           &prog_cnt)) {
+                printf("Failed to query attached programs");
+                goto err;
+        }
+
+        /* All operations with /dev/zero and and /dev/urandom are allowed,
+         * everything else is forbidden.
+         */
+        assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
+        assert(system("mknod /tmp/test_dev_cgroup_null c 1 3"));
+        assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
+
+        /* /dev/zero is whitelisted */
+        assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
+        assert(system("mknod /tmp/test_dev_cgroup_zero c 1 5") == 0);
+        assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
+
+        assert(system("dd if=/dev/urandom of=/dev/zero count=64") == 0);
+
+        /* src is allowed, target is forbidden */
+        assert(system("dd if=/dev/urandom of=/dev/full count=64"));
+
+        /* src is forbidden, target is allowed */
+        assert(system("dd if=/dev/random of=/dev/zero count=64"));
+
+        error = 0;
+        printf("test_dev_cgroup:PASS\n");
+
+err:
+        cleanup_cgroup_environment();
+
+        return error;
+}
diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh
index 6d58cca8e235..ed4774d8d6ed 100755
--- a/tools/testing/selftests/bpf/test_kmod.sh
+++ b/tools/testing/selftests/bpf/test_kmod.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 SRC_TREE=../../../../
 
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index e97565243d59..f61480641b6e 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Randomized tests for eBPF longest-prefix-match maps
  *
@@ -31,6 +32,10 @@ struct tlpm_node {
         uint8_t key[];
 };
 
+static struct tlpm_node *tlpm_match(struct tlpm_node *list,
+                                    const uint8_t *key,
+                                    size_t n_bits);
+
 static struct tlpm_node *tlpm_add(struct tlpm_node *list,
                                   const uint8_t *key,
                                   size_t n_bits)
@@ -38,9 +43,17 @@ static struct tlpm_node *tlpm_add(struct tlpm_node *list,
         struct tlpm_node *node;
         size_t n;
 
+        n = (n_bits + 7) / 8;
+
+        /* 'overwrite' an equivalent entry if one already exists */
+        node = tlpm_match(list, key, n_bits);
+        if (node && node->n_bits == n_bits) {
+                memcpy(node->key, key, n);
+                return list;
+        }
+
         /* add new entry with @key/@n_bits to @list and return new head */
 
-        n = (n_bits + 7) / 8;
         node = malloc(sizeof(*node) + n);
         assert(node);
 
@@ -92,6 +105,34 @@ static struct tlpm_node *tlpm_match(struct tlpm_node *list,
         return best;
 }
 
+static struct tlpm_node *tlpm_delete(struct tlpm_node *list,
+                                     const uint8_t *key,
+                                     size_t n_bits)
+{
+        struct tlpm_node *best = tlpm_match(list, key, n_bits);
+        struct tlpm_node *node;
+
+        if (!best || best->n_bits != n_bits)
+                return list;
+
+        if (best == list) {
+                node = best->next;
+                free(best);
+                return node;
+        }
+
+        for (node = list; node; node = node->next) {
+                if (node->next == best) {
+                        node->next = best->next;
+                        free(best);
+                        return list;
+                }
+        }
+        /* should never get here */
+        assert(0);
+        return list;
+}
+
 static void test_lpm_basic(void)
 {
         struct tlpm_node *list = NULL, *t1, *t2;
@@ -114,6 +155,13 @@ static void test_lpm_basic(void)
         assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15));
         assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16));
 
+        list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16);
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+        assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
+
+        list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8);
+        assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
+
         tlpm_clear(list);
 }
 
@@ -158,7 +206,7 @@ static void test_lpm_order(void)
 
 static void test_lpm_map(int keysize)
 {
-        size_t i, j, n_matches, n_nodes, n_lookups;
+        size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
         struct tlpm_node *t, *list = NULL;
         struct bpf_lpm_trie_key *key;
         uint8_t *data, *value;
@@ -170,6 +218,7 @@ static void test_lpm_map(int keysize)
          */
 
         n_matches = 0;
+        n_matches_after_delete = 0;
         n_nodes = 1 << 8;
         n_lookups = 1 << 16;
 
@@ -223,15 +272,54 @@ static void test_lpm_map(int keysize)
                 }
         }
 
+        /* Remove the first half of the elements in the tlpm and the
+         * corresponding nodes from the bpf-lpm.  Then run the same
+         * large number of random lookups in both and make sure they match.
+         * Note: we need to count the number of nodes actually inserted
+         * since there may have been duplicates.
+         */
+        for (i = 0, t = list; t; i++, t = t->next)
+                ;
+        for (j = 0; j < i / 2; ++j) {
+                key->prefixlen = list->n_bits;
+                memcpy(key->data, list->key, keysize);
+                r = bpf_map_delete_elem(map, key);
+                assert(!r);
+                list = tlpm_delete(list, list->key, list->n_bits);
+                assert(list);
+        }
+        for (i = 0; i < n_lookups; ++i) {
+                for (j = 0; j < keysize; ++j)
+                        data[j] = rand() & 0xff;
+
+                t = tlpm_match(list, data, 8 * keysize);
+
+                key->prefixlen = 8 * keysize;
+                memcpy(key->data, data, keysize);
+                r = bpf_map_lookup_elem(map, key, value);
+                assert(!r || errno == ENOENT);
+                assert(!t == !!r);
+
+                if (t) {
+                        ++n_matches_after_delete;
+                        assert(t->n_bits == value[keysize]);
+                        for (j = 0; j < t->n_bits; ++j)
+                                assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
+                                       (value[j / 8] & (1 << (7 - j % 8))));
+                }
+        }
+
         close(map);
         tlpm_clear(list);
 
         /* With 255 random nodes in the map, we are pretty likely to match
          * something on every lookup. For statistics, use this:
          *
-         *     printf("  nodes: %zu\n"
-         *            "lookups: %zu\n"
-         *            "matches: %zu\n", n_nodes, n_lookups, n_matches);
+         *     printf("          nodes: %zu\n"
+         *            "        lookups: %zu\n"
+         *            "        matches: %zu\n"
+         *            "matches(delete): %zu\n",
+         *            n_nodes, n_lookups, n_matches, n_matches_after_delete);
          */
 }
 
@@ -331,6 +419,108 @@ static void test_lpm_ipaddr(void)
         close(map_fd_ipv6);
 }
 
+static void test_lpm_delete(void)
+{
+        struct bpf_lpm_trie_key *key;
+        size_t key_size;
+        int map_fd;
+        __u64 value;
+
+        key_size = sizeof(*key) + sizeof(__u32);
+        key = alloca(key_size);
+
+        map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+                                key_size, sizeof(value),
+                                100, BPF_F_NO_PREALLOC);
+        assert(map_fd >= 0);
+
+        /* Add nodes:
+         * 192.168.0.0/16   (1)
+         * 192.168.0.0/24   (2)
+         * 192.168.128.0/24 (3)
+         * 192.168.1.0/24   (4)
+         *
+         *         (1)
+         *        /   \
+         *     (IM)    (3)
+         *    /   \
+         *   (2)  (4)
+         */
+        value = 1;
+        key->prefixlen = 16;
+        inet_pton(AF_INET, "192.168.0.0", key->data);
+        assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+        value = 2;
+        key->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.0.0", key->data);
+        assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+        value = 3;
+        key->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.128.0", key->data);
+        assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+        value = 4;
+        key->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.1.0", key->data);
+        assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
+
+        /* remove non-existent node */
+        key->prefixlen = 32;
+        inet_pton(AF_INET, "10.0.0.1", key->data);
+        assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
+                errno == ENOENT);
+
+        /* assert initial lookup */
+        key->prefixlen = 32;
+        inet_pton(AF_INET, "192.168.0.1", key->data);
+        assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+        assert(value == 2);
+
+        /* remove leaf node */
+        key->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.0.0", key->data);
+        assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+        key->prefixlen = 32;
+        inet_pton(AF_INET, "192.168.0.1", key->data);
+        assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+        assert(value == 1);
+
+        /* remove leaf (and intermediary) node */
+        key->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.1.0", key->data);
+        assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+        key->prefixlen = 32;
+        inet_pton(AF_INET, "192.168.1.1", key->data);
+        assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+        assert(value == 1);
+
+        /* remove root node */
+        key->prefixlen = 16;
+        inet_pton(AF_INET, "192.168.0.0", key->data);
+        assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+        key->prefixlen = 32;
+        inet_pton(AF_INET, "192.168.128.1", key->data);
+        assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
+        assert(value == 3);
+
+        /* remove last node */
+        key->prefixlen = 24;
+        inet_pton(AF_INET, "192.168.128.0", key->data);
+        assert(bpf_map_delete_elem(map_fd, key) == 0);
+
+        key->prefixlen = 32;
+        inet_pton(AF_INET, "192.168.128.1", key->data);
+        assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
+                errno == ENOENT);
+
+        close(map_fd);
+}
+
 int main(void)
 {
         struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
@@ -353,6 +543,8 @@ int main(void)
 
         test_lpm_ipaddr();
 
+        test_lpm_delete();
+
         printf("test_lpm: OK\n");
         return 0;
 }
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 79601c81e169..040356ecc862 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -22,6 +22,7 @@
 #include <linux/bpf.h>
 
 #include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include "bpf_util.h"
 
 static int map_flags;
@@ -438,6 +439,454 @@ static void test_arraymap_percpu_many_keys(void)
         close(fd);
 }
 
+static void test_devmap(int task, void *data)
+{
+        int fd;
+        __u32 key, value;
+
+        fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value),
+                            2, 0);
+        if (fd < 0) {
+                printf("Failed to create arraymap '%s'!\n", strerror(errno));
+                exit(1);
+        }
+
+        close(fd);
+}
+
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <arpa/inet.h>
+#include <sys/select.h>
+#include <linux/err.h>
+#define SOCKMAP_PARSE_PROG "./sockmap_parse_prog.o"
+#define SOCKMAP_VERDICT_PROG "./sockmap_verdict_prog.o"
+static void test_sockmap(int tasks, void *data)
+{
+        int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc;
+        struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break;
+        int ports[] = {50200, 50201, 50202, 50204};
+        int err, i, fd, udp, sfd[6] = {0xdeadbeef};
+        u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0};
+        int parse_prog, verdict_prog;
+        struct sockaddr_in addr;
+        struct bpf_object *obj;
+        struct timeval to;
+        __u32 key, value;
+        pid_t pid[tasks];
+        fd_set w;
+
+        /* Create some sockets to use with sockmap */
+        for (i = 0; i < 2; i++) {
+                sfd[i] = socket(AF_INET, SOCK_STREAM, 0);
+                if (sfd[i] < 0)
+                        goto out;
+                err = setsockopt(sfd[i], SOL_SOCKET, SO_REUSEADDR,
+                                 (char *)&one, sizeof(one));
+                if (err) {
+                        printf("failed to setsockopt\n");
+                        goto out;
+                }
+                err = ioctl(sfd[i], FIONBIO, (char *)&one);
+                if (err < 0) {
+                        printf("failed to ioctl\n");
+                        goto out;
+                }
+                memset(&addr, 0, sizeof(struct sockaddr_in));
+                addr.sin_family = AF_INET;
+                addr.sin_addr.s_addr = inet_addr("127.0.0.1");
+                addr.sin_port = htons(ports[i]);
+                err = bind(sfd[i], (struct sockaddr *)&addr, sizeof(addr));
+                if (err < 0) {
+                        printf("failed to bind: err %i: %i:%i\n",
+                               err, i, sfd[i]);
+                        goto out;
+                }
+                err = listen(sfd[i], 32);
+                if (err < 0) {
+                        printf("failed to listen\n");
+                        goto out;
+                }
+        }
+
+        for (i = 2; i < 4; i++) {
+                sfd[i] = socket(AF_INET, SOCK_STREAM, 0);
+                if (sfd[i] < 0)
+                        goto out;
+                err = setsockopt(sfd[i], SOL_SOCKET, SO_REUSEADDR,
+                                 (char *)&one, sizeof(one));
+                if (err) {
+                        printf("set sock opt\n");
+                        goto out;
+                }
+                memset(&addr, 0, sizeof(struct sockaddr_in));
+                addr.sin_family = AF_INET;
+                addr.sin_addr.s_addr = inet_addr("127.0.0.1");
+                addr.sin_port = htons(ports[i - 2]);
+                err = connect(sfd[i], (struct sockaddr *)&addr, sizeof(addr));
+                if (err) {
+                        printf("failed to connect\n");
+                        goto out;
+                }
+        }
+
+
+        for (i = 4; i < 6; i++) {
+                sfd[i] = accept(sfd[i - 4], NULL, NULL);
+                if (sfd[i] < 0) {
+                        printf("accept failed\n");
+                        goto out;
+                }
+        }
+
+        /* Test sockmap with connected sockets */
+        fd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP,
+                            sizeof(key), sizeof(value),
+                            6, 0);
+        if (fd < 0) {
+                printf("Failed to create sockmap %i\n", fd);
+                goto out_sockmap;
+        }
+
+        /* Test update with unsupported UDP socket */
+        udp = socket(AF_INET, SOCK_DGRAM, 0);
+        i = 0;
+        err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY);
+        if (!err) {
+                printf("Failed socket SOCK_DGRAM allowed '%i:%i'\n",
+                       i, udp);
+                goto out_sockmap;
+        }
+
+        /* Test update without programs */
+        for (i = 0; i < 6; i++) {
+                err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
+                if (err) {
+                        printf("Failed noprog update sockmap '%i:%i'\n",
+                               i, sfd[i]);
+                        goto out_sockmap;
+                }
+        }
+
+        /* Test attaching/detaching bad fds */
+        err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_PARSER, 0);
+        if (!err) {
+                printf("Failed invalid parser prog attach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_VERDICT, 0);
+        if (!err) {
+                printf("Failed invalid verdict prog attach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_attach(-1, fd, __MAX_BPF_ATTACH_TYPE, 0);
+        if (!err) {
+                printf("Failed unknown prog attach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER);
+        if (err) {
+                printf("Failed empty parser prog detach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT);
+        if (err) {
+                printf("Failed empty verdict prog detach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_detach(fd, __MAX_BPF_ATTACH_TYPE);
+        if (!err) {
+                printf("Detach invalid prog successful\n");
+                goto out_sockmap;
+        }
+
+        /* Load SK_SKB program and Attach */
+        err = bpf_prog_load(SOCKMAP_PARSE_PROG,
+                            BPF_PROG_TYPE_SK_SKB, &obj, &parse_prog);
+        if (err) {
+                printf("Failed to load SK_SKB parse prog\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_load(SOCKMAP_VERDICT_PROG,
+                            BPF_PROG_TYPE_SK_SKB, &obj, &verdict_prog);
+        if (err) {
+                printf("Failed to load SK_SKB verdict prog\n");
+                goto out_sockmap;
+        }
+
+        bpf_map_rx = bpf_object__find_map_by_name(obj, "sock_map_rx");
+        if (IS_ERR(bpf_map_rx)) {
+                printf("Failed to load map rx from verdict prog\n");
+                goto out_sockmap;
+        }
+
+        map_fd_rx = bpf_map__fd(bpf_map_rx);
+        if (map_fd_rx < 0) {
+                printf("Failed to get map fd\n");
+                goto out_sockmap;
+        }
+
+        bpf_map_tx = bpf_object__find_map_by_name(obj, "sock_map_tx");
+        if (IS_ERR(bpf_map_tx)) {
+                printf("Failed to load map tx from verdict prog\n");
+                goto out_sockmap;
+        }
+
+        map_fd_tx = bpf_map__fd(bpf_map_tx);
+        if (map_fd_tx < 0) {
+                printf("Failed to get map tx fd\n");
+                goto out_sockmap;
+        }
+
+        bpf_map_break = bpf_object__find_map_by_name(obj, "sock_map_break");
+        if (IS_ERR(bpf_map_break)) {
+                printf("Failed to load map tx from verdict prog\n");
+                goto out_sockmap;
+        }
+
+        map_fd_break = bpf_map__fd(bpf_map_break);
+        if (map_fd_break < 0) {
+                printf("Failed to get map tx fd\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_attach(parse_prog, map_fd_break,
+                              BPF_SK_SKB_STREAM_PARSER, 0);
+        if (!err) {
+                printf("Allowed attaching SK_SKB program to invalid map\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_attach(parse_prog, map_fd_rx,
+                      BPF_SK_SKB_STREAM_PARSER, 0);
+        if (err) {
+                printf("Failed stream parser bpf prog attach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_attach(verdict_prog, map_fd_rx,
+                              BPF_SK_SKB_STREAM_VERDICT, 0);
+        if (err) {
+                printf("Failed stream verdict bpf prog attach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_attach(verdict_prog, map_fd_rx,
+                              __MAX_BPF_ATTACH_TYPE, 0);
+        if (!err) {
+                printf("Attached unknown bpf prog\n");
+                goto out_sockmap;
+        }
+
+        /* Test map update elem afterwards fd lives in fd and map_fd */
+        for (i = 0; i < 6; i++) {
+                err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY);
+                if (err) {
+                        printf("Failed map_fd_rx update sockmap %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+                err = bpf_map_update_elem(map_fd_tx, &i, &sfd[i], BPF_ANY);
+                if (err) {
+                        printf("Failed map_fd_tx update sockmap %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+        }
+
+        /* Test map delete elem and remove send/recv sockets */
+        for (i = 2; i < 4; i++) {
+                err = bpf_map_delete_elem(map_fd_rx, &i);
+                if (err) {
+                        printf("Failed delete sockmap rx %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+                err = bpf_map_delete_elem(map_fd_tx, &i);
+                if (err) {
+                        printf("Failed delete sockmap tx %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+        }
+
+        /* Test map send/recv */
+        for (i = 0; i < 2; i++) {
+                buf[0] = i;
+                buf[1] = 0x5;
+                sc = send(sfd[2], buf, 20, 0);
+                if (sc < 0) {
+                        printf("Failed sockmap send\n");
+                        goto out_sockmap;
+                }
+
+                FD_ZERO(&w);
+                FD_SET(sfd[3], &w);
+                to.tv_sec = 1;
+                to.tv_usec = 0;
+                s = select(sfd[3] + 1, &w, NULL, NULL, &to);
+                if (s == -1) {
+                        perror("Failed sockmap select()");
+                        goto out_sockmap;
+                } else if (!s) {
+                        printf("Failed sockmap unexpected timeout\n");
+                        goto out_sockmap;
+                }
+
+                if (!FD_ISSET(sfd[3], &w)) {
+                        printf("Failed sockmap select/recv\n");
+                        goto out_sockmap;
+                }
+
+                rc = recv(sfd[3], buf, sizeof(buf), 0);
+                if (rc < 0) {
+                        printf("Failed sockmap recv\n");
+                        goto out_sockmap;
+                }
+        }
+
+        /* Negative null entry lookup from datapath should be dropped */
+        buf[0] = 1;
+        buf[1] = 12;
+        sc = send(sfd[2], buf, 20, 0);
+        if (sc < 0) {
+                printf("Failed sockmap send\n");
+                goto out_sockmap;
+        }
+
+        /* Push fd into same slot */
+        i = 2;
+        err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST);
+        if (!err) {
+                printf("Failed allowed sockmap dup slot BPF_NOEXIST\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
+        if (err) {
+                printf("Failed sockmap update new slot BPF_ANY\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST);
+        if (err) {
+                printf("Failed sockmap update new slot BPF_EXIST\n");
+                goto out_sockmap;
+        }
+
+        /* Delete the elems without programs */
+        for (i = 0; i < 6; i++) {
+                err = bpf_map_delete_elem(fd, &i);
+                if (err) {
+                        printf("Failed delete sockmap %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                }
+        }
+
+        /* Test having multiple maps open and set with programs on same fds */
+        err = bpf_prog_attach(parse_prog, fd,
+                              BPF_SK_SKB_STREAM_PARSER, 0);
+        if (err) {
+                printf("Failed fd bpf parse prog attach\n");
+                goto out_sockmap;
+        }
+        err = bpf_prog_attach(verdict_prog, fd,
+                              BPF_SK_SKB_STREAM_VERDICT, 0);
+        if (err) {
+                printf("Failed fd bpf verdict prog attach\n");
+                goto out_sockmap;
+        }
+
+        for (i = 4; i < 6; i++) {
+                err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
+                if (!err) {
+                        printf("Failed allowed duplicate programs in update ANY sockmap %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+                err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST);
+                if (!err) {
+                        printf("Failed allowed duplicate program in update NOEXIST sockmap  %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+                err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST);
+                if (!err) {
+                        printf("Failed allowed duplicate program in update EXIST sockmap  %i '%i:%i'\n",
+                               err, i, sfd[i]);
+                        goto out_sockmap;
+                }
+        }
+
+        /* Test tasks number of forked operations */
+        for (i = 0; i < tasks; i++) {
+                pid[i] = fork();
+                if (pid[i] == 0) {
+                        for (i = 0; i < 6; i++) {
+                                bpf_map_delete_elem(map_fd_tx, &i);
+                                bpf_map_delete_elem(map_fd_rx, &i);
+                                bpf_map_update_elem(map_fd_tx, &i,
+                                                    &sfd[i], BPF_ANY);
+                                bpf_map_update_elem(map_fd_rx, &i,
+                                                    &sfd[i], BPF_ANY);
+                        }
+                        exit(0);
+                } else if (pid[i] == -1) {
+                        printf("Couldn't spawn #%d process!\n", i);
+                        exit(1);
+                }
+        }
+
+        for (i = 0; i < tasks; i++) {
+                int status;
+
+                assert(waitpid(pid[i], &status, 0) == pid[i]);
+                assert(status == 0);
+        }
+
+        err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE);
+        if (!err) {
+                printf("Detached an invalid prog type.\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER);
+        if (err) {
+                printf("Failed parser prog detach\n");
+                goto out_sockmap;
+        }
+
+        err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT);
+        if (err) {
+                printf("Failed parser prog detach\n");
+                goto out_sockmap;
+        }
+
+        /* Test map close sockets */
+        for (i = 0; i < 6; i++)
+                close(sfd[i]);
+        close(fd);
+        close(map_fd_rx);
+        bpf_object__close(obj);
+        return;
+out:
+        for (i = 0; i < 6; i++)
+                close(sfd[i]);
+        printf("Failed to create sockmap '%i:%s'!\n", i, strerror(errno));
+        exit(1);
+out_sockmap:
+        for (i = 0; i < 6; i++)
+                close(sfd[i]);
+        close(fd);
+        exit(1);
+}
+
 #define MAP_SIZE (32 * 1024)
 
 static void test_map_large(void)
@@ -594,6 +1043,51 @@ static void test_map_parallel(void)
         assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
 }
 
+static void test_map_rdonly(void)
+{
+        int fd, key = 0, value = 0;
+
+        fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+                            MAP_SIZE, map_flags | BPF_F_RDONLY);
+        if (fd < 0) {
+                printf("Failed to create map for read only test '%s'!\n",
+                       strerror(errno));
+                exit(1);
+        }
+
+        key = 1;
+        value = 1234;
+        /* Insert key=1 element. */
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 &&
+               errno == EPERM);
+
+        /* Check that key=2 is not found. */
+        assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
+        assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT);
+}
+
+static void test_map_wronly(void)
+{
+        int fd, key = 0, value = 0;
+
+        fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+                            MAP_SIZE, map_flags | BPF_F_WRONLY);
+        if (fd < 0) {
+                printf("Failed to create map for read only test '%s'!\n",
+                       strerror(errno));
+                exit(1);
+        }
+
+        key = 1;
+        value = 1234;
+        /* Insert key=1 element. */
+        assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
+
+        /* Check that key=2 is not found. */
+        assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
+        assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
+}
+
 static void run_all_tests(void)
 {
         test_hashmap(0, NULL);
@@ -605,9 +1099,15 @@ static void run_all_tests(void)
 
         test_arraymap_percpu_many_keys();
 
+        test_devmap(0, NULL);
+        test_sockmap(0, NULL);
+
         test_map_large();
         test_map_parallel();
         test_map_stress();
+
+        test_map_rdonly();
+        test_map_wronly();
 }
 
 int main(void)
diff --git a/tools/testing/selftests/bpf/test_pkt_md_access.c b/tools/testing/selftests/bpf/test_pkt_md_access.c
index 71729d47eb85..7956302ecdf2 100644
--- a/tools/testing/selftests/bpf/test_pkt_md_access.c
+++ b/tools/testing/selftests/bpf/test_pkt_md_access.c
@@ -12,12 +12,23 @@
 
 int _version SEC("version") = 1;
 
+#if  __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define TEST_FIELD(TYPE, FIELD, MASK)                                   \
         {                                                               \
                 TYPE tmp = *(volatile TYPE *)&skb->FIELD;               \
                 if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK))   \
                         return TC_ACT_SHOT;                             \
         }
+#else
+#define TEST_FIELD_OFFSET(a, b) ((sizeof(a) - sizeof(b)) / sizeof(b))
+#define TEST_FIELD(TYPE, FIELD, MASK)                                   \
+        {                                                               \
+                TYPE tmp = *((volatile TYPE *)&skb->FIELD +             \
+                              TEST_FIELD_OFFSET(skb->FIELD, TYPE));     \
+                if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK))   \
+                        return TC_ACT_SHOT;                             \
+        }
+#endif
 
 SEC("test1")
 int process(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 5855cd3d3d45..69427531408d 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <time.h>
 
 #include <linux/types.h>
 typedef __u16 __sum16;
@@ -19,6 +20,8 @@ typedef __u16 __sum16;
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
 
 #include <sys/wait.h>
 #include <sys/resource.h>
@@ -75,39 +78,6 @@ static struct {
         __ret;                                                          \
 })
 
-static int bpf_prog_load(const char *file, enum bpf_prog_type type,
-                         struct bpf_object **pobj, int *prog_fd)
-{
-        struct bpf_program *prog;
-        struct bpf_object *obj;
-        int err;
-
-        obj = bpf_object__open(file);
-        if (IS_ERR(obj)) {
-                error_cnt++;
-                return -ENOENT;
-        }
-
-        prog = bpf_program__next(NULL, obj);
-        if (!prog) {
-                bpf_object__close(obj);
-                error_cnt++;
-                return -ENOENT;
-        }
-
-        bpf_program__set_type(prog, type);
-        err = bpf_object__load(obj);
-        if (err) {
-                bpf_object__close(obj);
-                error_cnt++;
-                return -EINVAL;
-        }
-
-        *pobj = obj;
-        *prog_fd = bpf_program__fd(prog);
-        return 0;
-}
-
 static int bpf_find_map(const char *test, struct bpf_object *obj,
                         const char *name)
 {
@@ -130,8 +100,10 @@ static void test_pkt_access(void)
         int err, prog_fd;
 
         err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
-        if (err)
+        if (err) {
+                error_cnt++;
                 return;
+        }
 
         err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
                                 NULL, NULL, &retval, &duration);
@@ -162,8 +134,10 @@ static void test_xdp(void)
         int err, prog_fd, map_fd;
 
         err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
-        if (err)
+        if (err) {
+                error_cnt++;
                 return;
+        }
 
         map_fd = bpf_find_map(__func__, obj, "vip2tnl");
         if (map_fd < 0)
@@ -223,8 +197,10 @@ static void test_l4lb(void)
         u32 *magic = (u32 *)buf;
 
         err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
-        if (err)
+        if (err) {
+                error_cnt++;
                 return;
+        }
 
         map_fd = bpf_find_map(__func__, obj, "vip_map");
         if (map_fd < 0)
@@ -280,8 +256,10 @@ static void test_tcp_estats(void)
 
         err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
         CHECK(err, "", "err %d errno %d\n", err, errno);
-        if (err)
+        if (err) {
+                error_cnt++;
                 return;
+        }
 
         bpf_object__close(obj);
 }
@@ -298,16 +276,26 @@ static void test_bpf_obj_id(void)
         const int nr_iters = 2;
         const char *file = "./test_obj_id.o";
         const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+        const char *expected_prog_name = "test_obj_id";
+        const char *expected_map_name = "test_map_id";
+        const __u64 nsec_per_sec = 1000000000;
 
         struct bpf_object *objs[nr_iters];
         int prog_fds[nr_iters], map_fds[nr_iters];
         /* +1 to test for the info_len returned by kernel */
         struct bpf_prog_info prog_infos[nr_iters + 1];
         struct bpf_map_info map_infos[nr_iters + 1];
-        char jited_insns[128], xlated_insns[128];
+        /* Each prog only uses one map. +1 to test nr_map_ids
+         * returned by kernel.
+         */
+        __u32 map_ids[nr_iters + 1];
+        char jited_insns[128], xlated_insns[128], zeros[128];
         __u32 i, next_id, info_len, nr_id_found, duration = 0;
+        struct timespec real_time_ts, boot_time_ts;
         int sysctl_fd, jit_enabled = 0, err = 0;
         __u64 array_value;
+        uid_t my_uid = getuid();
+        time_t now, load_time;
 
         sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
         if (sysctl_fd != -1) {
@@ -330,37 +318,19 @@ static void test_bpf_obj_id(void)
                 objs[i] = NULL;
 
         /* Check bpf_obj_get_info_by_fd() */
+        bzero(zeros, sizeof(zeros));
         for (i = 0; i < nr_iters; i++) {
+                now = time(NULL);
                 err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER,
                                     &objs[i], &prog_fds[i]);
                 /* test_obj_id.o is a dumb prog. It should never fail
                  * to load.
                  */
+                if (err)
+                        error_cnt++;
                 assert(!err);
 
-                /* Check getting prog info */
-                info_len = sizeof(struct bpf_prog_info) * 2;
-                prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns);
-                prog_infos[i].jited_prog_len = sizeof(jited_insns);
-                prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
-                prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
-                err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
-                                             &info_len);
-                if (CHECK(err ||
-                          prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
-                          info_len != sizeof(struct bpf_prog_info) ||
-                          (jit_enabled && !prog_infos[i].jited_prog_len) ||
-                          !prog_infos[i].xlated_prog_len,
-                          "get-prog-info(fd)",
-                          "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u\n",
-                          err, errno, i,
-                          prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
-                          info_len, sizeof(struct bpf_prog_info),
-                          jit_enabled,
-                          prog_infos[i].jited_prog_len,
-                          prog_infos[i].xlated_prog_len))
-                        goto done;
-
+                /* Insert a magic value to the map */
                 map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
                 assert(map_fds[i] >= 0);
                 err = bpf_map_update_elem(map_fds[i], &array_key,
@@ -369,6 +339,7 @@ static void test_bpf_obj_id(void)
 
                 /* Check getting map info */
                 info_len = sizeof(struct bpf_map_info) * 2;
+                bzero(&map_infos[i], info_len);
                 err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
                                              &info_len);
                 if (CHECK(err ||
@@ -377,16 +348,67 @@ static void test_bpf_obj_id(void)
                           map_infos[i].value_size != sizeof(__u64) ||
                           map_infos[i].max_entries != 1 ||
                           map_infos[i].map_flags != 0 ||
-                          info_len != sizeof(struct bpf_map_info),
+                          info_len != sizeof(struct bpf_map_info) ||
+                          strcmp((char *)map_infos[i].name, expected_map_name),
                           "get-map-info(fd)",
-                          "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n",
+                          "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
                           err, errno,
                           map_infos[i].type, BPF_MAP_TYPE_ARRAY,
                           info_len, sizeof(struct bpf_map_info),
                           map_infos[i].key_size,
                           map_infos[i].value_size,
                           map_infos[i].max_entries,
-                          map_infos[i].map_flags))
+                          map_infos[i].map_flags,
+                          map_infos[i].name, expected_map_name))
+                        goto done;
+
+                /* Check getting prog info */
+                info_len = sizeof(struct bpf_prog_info) * 2;
+                bzero(&prog_infos[i], info_len);
+                bzero(jited_insns, sizeof(jited_insns));
+                bzero(xlated_insns, sizeof(xlated_insns));
+                prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns);
+                prog_infos[i].jited_prog_len = sizeof(jited_insns);
+                prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns);
+                prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
+                prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
+                prog_infos[i].nr_map_ids = 2;
+                err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
+                assert(!err);
+                err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
+                assert(!err);
+                err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
+                                             &info_len);
+                load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
+                        + (prog_infos[i].load_time / nsec_per_sec);
+                if (CHECK(err ||
+                          prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER ||
+                          info_len != sizeof(struct bpf_prog_info) ||
+                          (jit_enabled && !prog_infos[i].jited_prog_len) ||
+                          (jit_enabled &&
+                           !memcmp(jited_insns, zeros, sizeof(zeros))) ||
+                          !prog_infos[i].xlated_prog_len ||
+                          !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
+                          load_time < now - 60 || load_time > now + 60 ||
+                          prog_infos[i].created_by_uid != my_uid ||
+                          prog_infos[i].nr_map_ids != 1 ||
+                          *(int *)prog_infos[i].map_ids != map_infos[i].id ||
+                          strcmp((char *)prog_infos[i].name, expected_prog_name),
+                          "get-prog-info(fd)",
+                          "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
+                          err, errno, i,
+                          prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
+                          info_len, sizeof(struct bpf_prog_info),
+                          jit_enabled,
+                          prog_infos[i].jited_prog_len,
+                          prog_infos[i].xlated_prog_len,
+                          !!memcmp(jited_insns, zeros, sizeof(zeros)),
+                          !!memcmp(xlated_insns, zeros, sizeof(zeros)),
+                          load_time, now,
+                          prog_infos[i].created_by_uid, my_uid,
+                          prog_infos[i].nr_map_ids, 1,
+                          *(int *)prog_infos[i].map_ids, map_infos[i].id,
+                          prog_infos[i].name, expected_prog_name))
                         goto done;
         }
 
@@ -394,7 +416,8 @@ static void test_bpf_obj_id(void)
         nr_id_found = 0;
         next_id = 0;
         while (!bpf_prog_get_next_id(next_id, &next_id)) {
-                struct bpf_prog_info prog_info;
+                struct bpf_prog_info prog_info = {};
+                __u32 saved_map_id;
                 int prog_fd;
 
                 info_len = sizeof(prog_info);
@@ -417,14 +440,33 @@ static void test_bpf_obj_id(void)
 
                 nr_id_found++;
 
+                /* Negative test:
+                 * prog_info.nr_map_ids = 1
+                 * prog_info.map_ids = NULL
+                 */
+                prog_info.nr_map_ids = 1;
                 err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+                if (CHECK(!err || errno != EFAULT,
+                          "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
+                          err, errno, EFAULT))
+                        break;
+                bzero(&prog_info, sizeof(prog_info));
+                info_len = sizeof(prog_info);
+
+                saved_map_id = *(int *)(prog_infos[i].map_ids);
+                prog_info.map_ids = prog_infos[i].map_ids;
+                prog_info.nr_map_ids = 2;
+                err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+                prog_infos[i].jited_prog_insns = 0;
+                prog_infos[i].xlated_prog_insns = 0;
                 CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
-                      memcmp(&prog_info, &prog_infos[i], info_len),
+                      memcmp(&prog_info, &prog_infos[i], info_len) ||
+                      *(int *)prog_info.map_ids != saved_map_id,
                       "get-prog-info(next_id->fd)",
-                      "err %d errno %d info_len %u(%lu) memcmp %d\n",
+                      "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n",
                       err, errno, info_len, sizeof(struct bpf_prog_info),
-                      memcmp(&prog_info, &prog_infos[i], info_len));
-
+                      memcmp(&prog_info, &prog_infos[i], info_len),
+                      *(int *)prog_info.map_ids, saved_map_id);
                 close(prog_fd);
         }
         CHECK(nr_id_found != nr_iters,
@@ -436,7 +478,7 @@ static void test_bpf_obj_id(void)
         nr_id_found = 0;
         next_id = 0;
         while (!bpf_map_get_next_id(next_id, &next_id)) {
-                struct bpf_map_info map_info;
+                struct bpf_map_info map_info = {};
                 int map_fd;
 
                 info_len = sizeof(map_info);
@@ -492,8 +534,10 @@ static void test_pkt_md_access(void)
         int err, prog_fd;
 
         err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
-        if (err)
+        if (err) {
+                error_cnt++;
                 return;
+        }
 
         err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4),
                                 NULL, NULL, &retval, &duration);
@@ -504,6 +548,75 @@ static void test_pkt_md_access(void)
         bpf_object__close(obj);
 }
 
+static void test_obj_name(void)
+{
+        struct {
+                const char *name;
+                int success;
+                int expected_errno;
+        } tests[] = {
+                { "", 1, 0 },
+                { "_123456789ABCDE", 1, 0 },
+                { "_123456789ABCDEF", 0, EINVAL },
+                { "_123456789ABCD\n", 0, EINVAL },
+        };
+        struct bpf_insn prog[] = {
+                BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0),
+                BPF_EXIT_INSN(),
+        };
+        __u32 duration = 0;
+        int i;
+
+        for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+                size_t name_len = strlen(tests[i].name) + 1;
+                union bpf_attr attr;
+                size_t ncopy;
+                int fd;
+
+                /* test different attr.prog_name during BPF_PROG_LOAD */
+                ncopy = name_len < sizeof(attr.prog_name) ?
+                        name_len : sizeof(attr.prog_name);
+                bzero(&attr, sizeof(attr));
+                attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+                attr.insn_cnt = 2;
+                attr.insns = ptr_to_u64(prog);
+                attr.license = ptr_to_u64("");
+                memcpy(attr.prog_name, tests[i].name, ncopy);
+
+                fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+                CHECK((tests[i].success && fd < 0) ||
+                      (!tests[i].success && fd != -1) ||
+                      (!tests[i].success && errno != tests[i].expected_errno),
+                      "check-bpf-prog-name",
+                      "fd %d(%d) errno %d(%d)\n",
+                       fd, tests[i].success, errno, tests[i].expected_errno);
+
+                if (fd != -1)
+                        close(fd);
+
+                /* test different attr.map_name during BPF_MAP_CREATE */
+                ncopy = name_len < sizeof(attr.map_name) ?
+                        name_len : sizeof(attr.map_name);
+                bzero(&attr, sizeof(attr));
+                attr.map_type = BPF_MAP_TYPE_ARRAY;
+                attr.key_size = 4;
+                attr.value_size = 4;
+                attr.max_entries = 1;
+                attr.map_flags = 0;
+                memcpy(attr.map_name, tests[i].name, ncopy);
+                fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
+                CHECK((tests[i].success && fd < 0) ||
+                      (!tests[i].success && fd != -1) ||
+                      (!tests[i].success && errno != tests[i].expected_errno),
+                      "check-bpf-map-name",
+                      "fd %d(%d) errno %d(%d)\n",
+                      fd, tests[i].success, errno, tests[i].expected_errno);
+
+                if (fd != -1)
+                        close(fd);
+        }
+}
+
 int main(void)
 {
         struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
@@ -516,6 +629,7 @@ int main(void)
         test_tcp_estats();
         test_bpf_obj_id();
         test_pkt_md_access();
+        test_obj_name();
 
         printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
         return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c
index de409fc50c35..8b201895c569 100644
--- a/tools/testing/selftests/bpf/test_tag.c
+++ b/tools/testing/selftests/bpf/test_tag.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index af7d173910f4..3c64f30cf63c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -8,6 +8,7 @@
  * License as published by the Free Software Foundation.
  */
 
+#include <endian.h>
 #include <asm/types.h>
 #include <linux/types.h>
 #include <stdint.h>
@@ -421,7 +422,7 @@ static struct bpf_test tests[] = {
                         BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr_unpriv = "R1 pointer arithmetic",
+                .errstr_unpriv = "R1 subtraction from stack pointer",
                 .result_unpriv = REJECT,
                 .errstr = "R1 invalid mem access",
                 .result = REJECT,
@@ -603,8 +604,9 @@ static struct bpf_test tests[] = {
                         BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -4),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned stack access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "invalid map_fd for function call",
@@ -650,8 +652,9 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned value access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "sometimes access memory with incorrect alignment",
@@ -672,6 +675,7 @@ static struct bpf_test tests[] = {
                 .errstr = "R0 invalid mem access",
                 .errstr_unpriv = "R0 leaks addr",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "jump test 1",
@@ -963,6 +967,268 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
         },
         {
+                "invalid access __sk_buff family",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, family)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "invalid access __sk_buff remote_ip4",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip4)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "invalid access __sk_buff local_ip4",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip4)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "invalid access __sk_buff remote_ip6",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip6)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "invalid access __sk_buff local_ip6",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip6)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "invalid access __sk_buff remote_port",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_port)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "invalid access __sk_buff remote_port",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_port)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "invalid bpf_context access",
+                .result = REJECT,
+        },
+        {
+                "valid access __sk_buff family",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, family)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "valid access __sk_buff remote_ip4",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip4)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "valid access __sk_buff local_ip4",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip4)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "valid access __sk_buff remote_ip6",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip6[0])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip6[1])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip6[2])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_ip6[3])),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "valid access __sk_buff local_ip6",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip6[0])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip6[1])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip6[2])),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_ip6[3])),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "valid access __sk_buff remote_port",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, remote_port)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "valid access __sk_buff remote_port",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, local_port)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "invalid access of tc_classid for SK_SKB",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, tc_classid)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+                .errstr = "invalid bpf_context access",
+        },
+        {
+                "invalid access of skb->mark for SK_SKB",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, mark)),
+                        BPF_EXIT_INSN(),
+                },
+                .result =  REJECT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+                .errstr = "invalid bpf_context access",
+        },
+        {
+                "check skb->mark is not writeable by SK_SKB",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, mark)),
+                        BPF_EXIT_INSN(),
+                },
+                .result =  REJECT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+                .errstr = "invalid bpf_context access",
+        },
+        {
+                "check skb->tc_index is writeable by SK_SKB",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, tc_index)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "check skb->priority is writeable by SK_SKB",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+                                    offsetof(struct __sk_buff, priority)),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "direct packet read for SK_SKB",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "direct packet write for SK_SKB",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+                        BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
+                "overlapping checks for direct packet access SK_SKB",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SK_SKB,
+        },
+        {
                 "check skb->mark is not writeable by sockets",
                 .insns = {
                         BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
@@ -1098,7 +1364,7 @@ static struct bpf_test tests[] = {
                 "check skb->hash byte load permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, hash)),
 #else
@@ -1135,7 +1401,7 @@ static struct bpf_test tests[] = {
                 "check skb->hash byte load not permitted 3",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, hash) + 3),
 #else
@@ -1215,8 +1481,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[0]) + 1),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check __sk_buff->hash, offset 0, half store not permitted",
@@ -1244,7 +1511,7 @@ static struct bpf_test tests[] = {
                 "check skb->hash half load permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, hash)),
 #else
@@ -1259,7 +1526,7 @@ static struct bpf_test tests[] = {
                 "check skb->hash half load not permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, hash) + 2),
 #else
@@ -1319,8 +1586,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[0]) + 2),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check cb access: word, unaligned 2",
@@ -1330,8 +1598,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[4]) + 1),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check cb access: word, unaligned 3",
@@ -1341,8 +1610,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[4]) + 2),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check cb access: word, unaligned 4",
@@ -1352,8 +1622,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[4]) + 3),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check cb access: double",
@@ -1379,8 +1650,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[1])),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check cb access: double, unaligned 2",
@@ -1390,8 +1662,9 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, cb[3])),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "misaligned access",
+                .errstr = "misaligned context access",
                 .result = REJECT,
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "check cb access: double, oob 1",
@@ -1523,7 +1796,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "misaligned access off -6 size 8",
+                .errstr = "misaligned stack access off (0x0; 0x0)+-8+2 size 8",
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "PTR_TO_STACK store/load - bad alignment on reg",
@@ -1535,7 +1809,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "misaligned access off -2 size 8",
+                .errstr = "misaligned stack access off (0x0; 0x0)+-10+8 size 8",
+                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "PTR_TO_STACK store/load - out of bounds low",
@@ -1579,8 +1854,6 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = ACCEPT,
-                .result_unpriv = REJECT,
-                .errstr_unpriv = "R1 pointer arithmetic",
         },
         {
                 "unpriv: add pointer to pointer",
@@ -1591,7 +1864,7 @@ static struct bpf_test tests[] = {
                 },
                 .result = ACCEPT,
                 .result_unpriv = REJECT,
-                .errstr_unpriv = "R1 pointer arithmetic",
+                .errstr_unpriv = "R1 pointer += pointer",
         },
         {
                 "unpriv: neg pointer",
@@ -1932,10 +2205,7 @@ static struct bpf_test tests[] = {
                         BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
                         BPF_EXIT_INSN(),
                 },
-                .errstr_unpriv = "pointer arithmetic prohibited",
-                .result_unpriv = REJECT,
-                .errstr = "R1 invalid mem access",
-                .result = REJECT,
+                .result = ACCEPT,
         },
         {
                 "unpriv: cmp of stack pointer",
@@ -1999,7 +2269,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid stack type R3",
+                .errstr = "R4 min value is negative",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
@@ -2016,7 +2286,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid stack type R3",
+                .errstr = "R4 min value is negative",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
@@ -2218,7 +2488,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid stack type R3 off=-1 access_size=-1",
+                .errstr = "R4 min value is negative",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
@@ -2235,7 +2505,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid stack type R3 off=-1 access_size=2147483647",
+                .errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
@@ -2252,7 +2522,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid stack type R3 off=-512 access_size=2147483647",
+                .errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
@@ -2323,8 +2593,8 @@ static struct bpf_test tests[] = {
                                     offsetof(struct __sk_buff, data)),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 48),
-                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 48),
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 49),
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 49),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_3),
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
@@ -2652,7 +2922,7 @@ static struct bpf_test tests[] = {
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
                         BPF_JMP_A(-6),
                 },
-                .errstr = "misaligned packet access off 2+15+-4 size 4",
+                .errstr = "misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
@@ -2703,11 +2973,11 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0xffffffff),
                         BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
                         BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0x7fff),
                         BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
                         BPF_MOV64_REG(BPF_REG_5, BPF_REG_4),
-                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xffff - 1),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1),
                         BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
                         BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
                         BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -2729,10 +2999,10 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_4, 0xffffffff),
                         BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -8),
                         BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
-                        BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 0xffff),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 0x7fff),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
                         BPF_MOV64_REG(BPF_REG_5, BPF_REG_4),
-                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xffff - 1),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1),
                         BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
                         BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
                         BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -2758,7 +3028,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_4, 0xffffffff),
                         BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_4, -8),
                         BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
-                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 48),
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 49),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
                         BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
@@ -2795,7 +3065,7 @@ static struct bpf_test tests[] = {
                 },
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
                 .result = REJECT,
-                .errstr = "cannot add integer value with 47 upper zero bits to ptr_to_packet",
+                .errstr = "invalid access to packet, off=0 size=8, R5(id=1,off=0,r=0)",
         },
         {
                 "direct packet access: test24 (x += pkt_ptr, 5)",
@@ -2813,7 +3083,7 @@ static struct bpf_test tests[] = {
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
                         BPF_MOV64_REG(BPF_REG_5, BPF_REG_0),
-                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0xffff - 1),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7fff - 1),
                         BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
                         BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_0, 0),
                         BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -2823,6 +3093,79 @@ static struct bpf_test tests[] = {
                 .result = ACCEPT,
         },
         {
+                "direct packet access: test25 (marking on <, good access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, -4),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "direct packet access: test26 (marking on <, bad access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 3),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, -3),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "direct packet access: test27 (marking on <=, good access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "direct packet access: test28 (marking on <=, bad access)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, -4),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
                 "helper access to packet: test1, valid packet_ptr range",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -3112,7 +3455,7 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test14, cls helper fail sub",
+                "helper access to packet: test14, cls helper ok sub",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3132,12 +3475,36 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to packet: test15, cls helper fail sub",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 12),
+                        BPF_MOV64_IMM(BPF_REG_2, 4),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_csum_diff),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
                 .result = REJECT,
-                .errstr = "type=inv expected=fp",
+                .errstr = "invalid access to packet",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test15, cls helper fail range 1",
+                "helper access to packet: test16, cls helper fail range 1",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3162,7 +3529,7 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test16, cls helper fail range 2",
+                "helper access to packet: test17, cls helper fail range 2",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3183,11 +3550,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid access to packet",
+                .errstr = "R2 min value is negative",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test17, cls helper fail range 3",
+                "helper access to packet: test18, cls helper fail range 3",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3208,11 +3575,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .result = REJECT,
-                .errstr = "invalid access to packet",
+                .errstr = "R2 min value is negative",
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test18, cls helper fail range zero",
+                "helper access to packet: test19, cls helper range zero",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3232,12 +3599,11 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .result = REJECT,
-                .errstr = "invalid access to packet",
+                .result = ACCEPT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test19, pkt end as input",
+                "helper access to packet: test20, pkt end as input",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3262,7 +3628,7 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test20, wrong reg",
+                "helper access to packet: test21, wrong reg",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
@@ -3322,7 +3688,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result_unpriv = REJECT,
                 .result = ACCEPT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -3346,7 +3712,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result_unpriv = REJECT,
                 .result = ACCEPT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -3374,7 +3740,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result_unpriv = REJECT,
                 .result = ACCEPT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -3415,9 +3781,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is outside of the array range",
-                .result_unpriv = REJECT,
                 .result = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
@@ -3439,9 +3803,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
-                .result_unpriv = REJECT,
+                .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map",
                 .result = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
@@ -3455,7 +3817,7 @@ static struct bpf_test tests[] = {
                         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                      BPF_FUNC_map_lookup_elem),
                         BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-                        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
                         BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
                         BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
                         BPF_MOV32_IMM(BPF_REG_1, 0),
@@ -3466,8 +3828,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .errstr_unpriv = "R0 leaks addr",
+                .errstr = "R0 unbounded memory access",
                 .result_unpriv = REJECT,
                 .result = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -3493,7 +3855,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .errstr = "invalid access to map value, value_size=48 off=44 size=8",
                 .result_unpriv = REJECT,
                 .result = REJECT,
@@ -3523,8 +3885,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3, 11 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .errstr_unpriv = "R0 pointer += pointer",
+                .errstr = "R0 invalid mem access 'inv'",
                 .result_unpriv = REJECT,
                 .result = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -3666,34 +4028,6 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS
         },
         {
-                "multiple registers share map_lookup_elem bad reg type",
-                .insns = {
-                        BPF_MOV64_IMM(BPF_REG_1, 10),
-                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-                        BPF_LD_MAP_FD(BPF_REG_1, 0),
-                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-                                     BPF_FUNC_map_lookup_elem),
-                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-                        BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_0),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-                        BPF_MOV64_IMM(BPF_REG_1, 1),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-                        BPF_MOV64_IMM(BPF_REG_1, 2),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 1),
-                        BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 0),
-                        BPF_MOV64_IMM(BPF_REG_1, 3),
-                        BPF_EXIT_INSN(),
-                },
-                .fixup_map1 = { 4 },
-                .result = REJECT,
-                .errstr = "R3 invalid mem access 'inv'",
-                .prog_type = BPF_PROG_TYPE_SCHED_CLS
-        },
-        {
                 "invalid map access from else condition",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
@@ -3711,9 +4045,9 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map",
+                .errstr = "R0 unbounded memory access",
                 .result = REJECT,
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result_unpriv = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
@@ -4043,11 +4377,10 @@ static struct bpf_test tests[] = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
                         BPF_LD_MAP_FD(BPF_REG_1, 0),
                         BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_MOV64_IMM(BPF_REG_2, 0),
-                        BPF_MOV64_IMM(BPF_REG_3, 0),
-                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EMIT_CALL(BPF_FUNC_trace_printk),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
@@ -4091,7 +4424,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "invalid access to map value, value_size=48 off=0 size=-8",
+                .errstr = "R2 min value is negative",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4147,17 +4480,16 @@ static struct bpf_test tests[] = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
                         BPF_LD_MAP_FD(BPF_REG_1, 0),
                         BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
                                 offsetof(struct test_val, foo)),
                         BPF_MOV64_IMM(BPF_REG_2, 0),
-                        BPF_MOV64_IMM(BPF_REG_3, 0),
-                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EMIT_CALL(BPF_FUNC_trace_printk),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "R1 min value is outside of the array range",
+                .errstr = "invalid access to map value, value_size=48 off=4 size=0",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4203,7 +4535,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "invalid access to map value, value_size=48 off=4 size=-8",
+                .errstr = "R2 min value is negative",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4225,7 +4557,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "R1 min value is outside of the array range",
+                .errstr = "R2 min value is negative",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4283,13 +4615,12 @@ static struct bpf_test tests[] = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
                         BPF_LD_MAP_FD(BPF_REG_1, 0),
                         BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_MOV64_IMM(BPF_REG_3, 0),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
                         BPF_MOV64_IMM(BPF_REG_2, 0),
-                        BPF_MOV64_IMM(BPF_REG_3, 0),
-                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EMIT_CALL(BPF_FUNC_trace_printk),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
@@ -4341,7 +4672,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "invalid access to map value, value_size=48 off=4 size=-8",
+                .errstr = "R2 min value is negative",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4364,7 +4695,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "R1 min value is outside of the array range",
+                .errstr = "R2 min value is negative",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4424,15 +4755,14 @@ static struct bpf_test tests[] = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
                         BPF_LD_MAP_FD(BPF_REG_1, 0),
                         BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
                         BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
-                                offsetof(struct test_val, foo), 4),
+                                offsetof(struct test_val, foo), 3),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
                         BPF_MOV64_IMM(BPF_REG_2, 0),
-                        BPF_MOV64_IMM(BPF_REG_3, 0),
-                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EMIT_CALL(BPF_FUNC_trace_printk),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
@@ -4452,13 +4782,13 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
                         BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_2, 1),
                         BPF_MOV64_IMM(BPF_REG_3, 0),
                         BPF_EMIT_CALL(BPF_FUNC_probe_read),
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr = "R1 min value is negative, either use unsigned index or do a if (index >=0) check",
+                .errstr = "R1 unbounded memory access",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4489,6 +4819,246 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
         {
+                "helper access to map: bounds check using <, good access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using <, bad access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 4),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = REJECT,
+                .errstr = "R1 unbounded memory access",
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using <=, good access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using <=, bad access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 4),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = REJECT,
+                .errstr = "R1 unbounded memory access",
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using s<, good access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 0, -3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using s<, good access 2",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using s<, bad access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = REJECT,
+                .errstr = "R1 min value is negative",
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using s<=, good access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 0, -3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using s<=, good access 2",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to map: bounds check using s<=, bad access",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
+                        BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .result = REJECT,
+                .errstr = "R1 min value is negative",
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
                 "map element value is preserved across register spilling",
                 .insns = {
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -4578,7 +5148,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result = ACCEPT,
                 .result_unpriv = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4606,7 +5176,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result = ACCEPT,
                 .result_unpriv = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4625,7 +5195,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 bitwise operator &= on pointer",
                 .errstr = "invalid mem access 'inv'",
                 .result = REJECT,
                 .result_unpriv = REJECT,
@@ -4644,7 +5214,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 32-bit pointer arithmetic prohibited",
                 .errstr = "invalid mem access 'inv'",
                 .result = REJECT,
                 .result_unpriv = REJECT,
@@ -4663,7 +5233,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 pointer arithmetic with /= operator",
                 .errstr = "invalid mem access 'inv'",
                 .result = REJECT,
                 .result_unpriv = REJECT,
@@ -4706,10 +5276,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 invalid mem access 'inv'",
                 .errstr = "R0 invalid mem access 'inv'",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "map element value is preserved across register spilling",
@@ -4731,7 +5299,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 leaks addr",
                 .result = ACCEPT,
                 .result_unpriv = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4777,7 +5345,7 @@ static struct bpf_test tests[] = {
                         BPF_EMIT_CALL(BPF_FUNC_probe_read),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "invalid stack type R1 off=-64 access_size=0",
+                .errstr = "invalid indirect read from stack off -64+0 size 64",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4913,7 +5481,8 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "R2 unbounded memory access",
+                /* because max wasn't checked, signed min is negative */
+                .errstr = "R2 min value is negative, either use unsigned or 'var &= const'",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -4931,7 +5500,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "invalid stack type R1 off=-64 access_size=0",
+                .errstr = "invalid indirect read from stack off -64+0 size 64",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
@@ -5062,7 +5631,21 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
         {
-                "helper access to variable memory: size > 0 not allowed on NULL",
+                "helper access to variable memory: size = 0 allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_1, 0),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_1, 0),
                         BPF_MOV64_IMM(BPF_REG_2, 0),
@@ -5075,12 +5658,12 @@ static struct bpf_test tests[] = {
                         BPF_EMIT_CALL(BPF_FUNC_csum_diff),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "R1 type=imm expected=fp",
+                .errstr = "R1 type=inv expected=fp",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to variable memory: size = 0 not allowed on != NULL",
+                "helper access to variable memory: size = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)",
                 .insns = {
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
                         BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
@@ -5093,11 +5676,201 @@ static struct bpf_test tests[] = {
                         BPF_EMIT_CALL(BPF_FUNC_csum_diff),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "invalid stack type R1 off=-8 access_size=0",
-                .result = REJECT,
+                .result = ACCEPT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
+                "helper access to variable memory: size = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: size possible = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: size possible = 0 allowed on != NULL packet pointer (ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_4, 0),
+                        BPF_MOV64_IMM(BPF_REG_5, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_1, 0),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 type=inv expected=fp",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: size > 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_1, 0),
+                        BPF_MOV64_IMM(BPF_REG_2, 1),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 type=inv expected=fp",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: size = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: size = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_MOV64_IMM(BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
+                "helper access to variable memory: size possible = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 2),
+                        BPF_MOV64_IMM(BPF_REG_3, 0),
+                        BPF_EMIT_CALL(BPF_FUNC_probe_read),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+        },
+        {
                 "helper access to variable memory: 8 bytes leak",
                 .insns = {
                         BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
@@ -5160,7 +5933,7 @@ static struct bpf_test tests[] = {
                         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                      BPF_FUNC_map_lookup_elem),
                         BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-                        BPF_MOV64_IMM(BPF_REG_1, 6),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
                         BPF_ALU64_IMM(BPF_AND, BPF_REG_1, -4),
                         BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
                         BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
@@ -5169,10 +5942,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .errstr = "R0 max value is outside of the array range",
                 .result = REJECT,
-                .result_unpriv = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
@@ -5201,10 +5972,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .errstr = "R0 max value is outside of the array range",
                 .result = REJECT,
-                .result_unpriv = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
         {
@@ -5251,7 +6020,7 @@ static struct bpf_test tests[] = {
                 },
                 .fixup_map_in_map = { 3 },
                 .errstr = "R1 type=inv expected=map_ptr",
-                .errstr_unpriv = "R1 pointer arithmetic prohibited",
+                .errstr_unpriv = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited",
                 .result = REJECT,
         },
         {
@@ -5422,7 +6191,7 @@ static struct bpf_test tests[] = {
                 "check bpf_perf_event_data->sample_period byte load permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct bpf_perf_event_data, sample_period)),
 #else
@@ -5438,7 +6207,7 @@ static struct bpf_test tests[] = {
                 "check bpf_perf_event_data->sample_period half load permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct bpf_perf_event_data, sample_period)),
 #else
@@ -5454,7 +6223,7 @@ static struct bpf_test tests[] = {
                 "check bpf_perf_event_data->sample_period word load permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct bpf_perf_event_data, sample_period)),
 #else
@@ -5481,7 +6250,7 @@ static struct bpf_test tests[] = {
                 "check skb->data half load not permitted",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, data)),
 #else
@@ -5497,7 +6266,7 @@ static struct bpf_test tests[] = {
                 "check skb->tc_classid half load not permitted for lwt prog",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
-#ifdef __LITTLE_ENDIAN
+#if __BYTE_ORDER == __LITTLE_ENDIAN
                         BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
                                     offsetof(struct __sk_buff, tc_classid)),
 #else
@@ -5531,10 +6300,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "bounds checks mixing signed and unsigned",
@@ -5557,10 +6324,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 2",
@@ -5585,10 +6350,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R8 invalid mem access 'inv'",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 3",
@@ -5612,10 +6375,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R8 invalid mem access 'inv'",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 4",
@@ -5638,10 +6399,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative",
-                .result = REJECT,
-                .result_unpriv = REJECT,
+                .result = ACCEPT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 5",
@@ -5665,10 +6423,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 invalid mem access",
+                .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 6",
@@ -5689,10 +6445,8 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr_unpriv = "R4 min value is negative, either use unsigned",
                 .errstr = "R4 min value is negative, either use unsigned",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 7",
@@ -5715,10 +6469,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative",
-                .result = REJECT,
-                .result_unpriv = REJECT,
+                .result = ACCEPT,
         },
         {
                 "bounds checks mixing signed and unsigned, variant 8",
@@ -5729,32 +6480,6 @@ static struct bpf_test tests[] = {
                         BPF_LD_MAP_FD(BPF_REG_1, 0),
                         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                      BPF_FUNC_map_lookup_elem),
-                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-                        BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-                        BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024 + 1),
-                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3),
-                        BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-                        BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-                        BPF_MOV64_IMM(BPF_REG_0, 0),
-                        BPF_EXIT_INSN(),
-                },
-                .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative",
-                .result = REJECT,
-                .result_unpriv = REJECT,
-        },
-        {
-                "bounds checks mixing signed and unsigned, variant 9",
-                .insns = {
-                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-                        BPF_LD_MAP_FD(BPF_REG_1, 0),
-                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-                                     BPF_FUNC_map_lookup_elem),
                         BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
                         BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
@@ -5769,13 +6494,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 10",
+                "bounds checks mixing signed and unsigned, variant 9",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5797,13 +6520,10 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
-                .errstr = "R0 min value is negative",
-                .result = REJECT,
-                .result_unpriv = REJECT,
+                .result = ACCEPT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 11",
+                "bounds checks mixing signed and unsigned, variant 10",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5825,13 +6545,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 12",
+                "bounds checks mixing signed and unsigned, variant 11",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5854,13 +6572,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 13",
+                "bounds checks mixing signed and unsigned, variant 12",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5882,13 +6598,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 14",
+                "bounds checks mixing signed and unsigned, variant 13",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5913,13 +6627,11 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 15",
+                "bounds checks mixing signed and unsigned, variant 14",
                 .insns = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
                                     offsetof(struct __sk_buff, mark)),
@@ -5945,13 +6657,11 @@ static struct bpf_test tests[] = {
                         BPF_JMP_IMM(BPF_JA, 0, 0, -7),
                 },
                 .fixup_map1 = { 4 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
-                "bounds checks mixing signed and unsigned, variant 16",
+                "bounds checks mixing signed and unsigned, variant 15",
                 .insns = {
                         BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
                         BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -5975,11 +6685,1418 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic prohibited",
+                .errstr_unpriv = "R0 pointer comparison prohibited",
                 .errstr = "R0 min value is negative",
                 .result = REJECT,
                 .result_unpriv = REJECT,
         },
+        {
+                "subtraction bounds (map value) variant 1",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 7),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 5),
+                        BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 56),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "R0 max value is outside of the array range",
+                .result = REJECT,
+        },
+        {
+                "subtraction bounds (map value) variant 2",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 6),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 4),
+                        BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
+                .result = REJECT,
+        },
+        {
+                "variable-offset ctx access",
+                .insns = {
+                        /* Get an unknown value */
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+                        /* Make it small and 4-byte aligned */
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+                        /* add it to skb.  We now have either &skb->len or
+                         * &skb->pkt_type, but we don't know which
+                         */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
+                        /* dereference it */
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "variable ctx access var_off=(0x0; 0x4)",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_LWT_IN,
+        },
+        {
+                "variable-offset stack access",
+                .insns = {
+                        /* Fill the top 8 bytes of the stack */
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        /* Get an unknown value */
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+                        /* Make it small and 4-byte aligned */
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8),
+                        /* add it to fp.  We now have either fp-4 or fp-8, but
+                         * we don't know which
+                         */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+                        /* dereference it */
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "variable stack access var_off=(0xfffffffffffffff8; 0x4)",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_LWT_IN,
+        },
+        {
+                "liveness pruning and write screening",
+                .insns = {
+                        /* Get an unknown value */
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+                        /* branch conditions teach us nothing about R2 */
+                        BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R0 !read_ok",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_LWT_IN,
+        },
+        {
+                "varlen_map_value_access pruning",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
+                        BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
+                        BPF_MOV32_IMM(BPF_REG_1, 0),
+                        BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+                        BPF_ST_MEM(BPF_DW, BPF_REG_0, 0,
+                                   offsetof(struct test_val, foo)),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map2 = { 3 },
+                .errstr_unpriv = "R0 leaks addr",
+                .errstr = "R0 unbounded memory access",
+                .result_unpriv = REJECT,
+                .result = REJECT,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "invalid 64-bit BPF_END",
+                .insns = {
+                        BPF_MOV32_IMM(BPF_REG_0, 0),
+                        {
+                                .code  = BPF_ALU64 | BPF_END | BPF_TO_LE,
+                                .dst_reg = BPF_REG_0,
+                                .src_reg = 0,
+                                .off   = 0,
+                                .imm   = 32,
+                        },
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "BPF_END uses reserved fields",
+                .result = REJECT,
+        },
+        {
+                "meta access, test1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 8),
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet, off=-8",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test3",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test4",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test5",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_4, 3),
+                        BPF_MOV64_IMM(BPF_REG_2, -8),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_xdp_adjust_meta),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "R3 !read_ok",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test6",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test7",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test8",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test9",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test10",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_IMM(BPF_REG_5, 42),
+                        BPF_MOV64_IMM(BPF_REG_6, 24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
+                        BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_5, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "invalid access to packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test11",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_IMM(BPF_REG_5, 42),
+                        BPF_MOV64_IMM(BPF_REG_6, 24),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
+                        BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
+                        BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_5, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "meta access, test12",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 5),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
+                        BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "arithmetic ops make PTR_TO_CTX unusable",
+                .insns = {
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+                                      offsetof(struct __sk_buff, data) -
+                                      offsetof(struct __sk_buff, mark)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, mark)),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "dereference of modified ctx ptr R1 off=68+8, ctx+const is allowed, ctx+const+const is not",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "XDP pkt read, pkt_end mangling, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end mangling, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_3, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' > pkt_end, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' > pkt_end, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data' > pkt_end, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end > pkt_data', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_end > pkt_data', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end > pkt_data', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' < pkt_end, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data' < pkt_end, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' < pkt_end, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end < pkt_data', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end < pkt_data', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_end < pkt_data', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' >= pkt_end, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data' >= pkt_end, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' >= pkt_end, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_end >= pkt_data', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end >= pkt_data', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_end >= pkt_data', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' <= pkt_end, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data' <= pkt_end, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data' <= pkt_end, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end <= pkt_data', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_end <= pkt_data', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_end <= pkt_data', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_meta' > pkt_data, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' > pkt_data, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_meta' > pkt_data, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data > pkt_meta', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data > pkt_meta', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data > pkt_meta', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' < pkt_data, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_meta' < pkt_data, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' < pkt_data, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data < pkt_meta', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data < pkt_meta', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data < pkt_meta', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' >= pkt_data, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_meta' >= pkt_data, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' >= pkt_data, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data >= pkt_meta', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data >= pkt_meta', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data >= pkt_meta', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' <= pkt_data, good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_meta' <= pkt_data, bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_meta' <= pkt_data, bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data <= pkt_meta', good access",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "XDP pkt read, pkt_data <= pkt_meta', bad access 1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
+        {
+                "XDP pkt read, pkt_data <= pkt_meta', bad access 2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_meta)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R1 offset is outside of the packet",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_XDP,
+                .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+        },
+        {
+                "bpf_exit with invalid return code. test1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R0 has value (0x0; 0xffffffff)",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "bpf_exit with invalid return code. test2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "bpf_exit with invalid return code. test3",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R0 has value (0x0; 0x3)",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "bpf_exit with invalid return code. test4",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "bpf_exit with invalid return code. test5",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 2),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R0 has value (0x2; 0x0)",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "bpf_exit with invalid return code. test6",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R0 is not a known value (ctx)",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
+        {
+                "bpf_exit with invalid return code. test7",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4),
+                        BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2),
+                        BPF_EXIT_INSN(),
+                },
+                .errstr = "R0 has unknown scalar value",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+        },
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -6027,7 +8144,7 @@ static int create_map_in_map(void)
                 return inner_map_fd;
         }
 
-        outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS,
+        outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
                                              sizeof(int), inner_map_fd, 1, 0);
         if (outer_map_fd < 0)
                 printf("Failed to create array of maps '%s'!\n",
diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c
new file mode 100644
index 000000000000..3cc0b561489e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_verifier_log.c
@@ -0,0 +1,171 @@
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+
+#include <bpf/bpf.h>
+
+#define LOG_SIZE (1 << 20)
+
+#define err(str...)     printf("ERROR: " str)
+
+static const struct bpf_insn code_sample[] = {
+        /* We need a few instructions to pass the min log length */
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_MOV64_IMM(BPF_REG_0, 0),
+        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                     BPF_FUNC_map_lookup_elem),
+        BPF_EXIT_INSN(),
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+        return (__u64) (unsigned long) ptr;
+}
+
+static int load(char *log, size_t log_len, int log_level)
+{
+        union bpf_attr attr;
+
+        bzero(&attr, sizeof(attr));
+        attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+        attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn));
+        attr.insns = ptr_to_u64(code_sample);
+        attr.license = ptr_to_u64("GPL");
+        attr.log_buf = ptr_to_u64(log);
+        attr.log_size = log_len;
+        attr.log_level = log_level;
+
+        return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
+static void check_ret(int ret, int exp_errno)
+{
+        if (ret > 0) {
+                close(ret);
+                err("broken sample loaded successfully!?\n");
+                exit(1);
+        }
+
+        if (!ret || errno != exp_errno) {
+                err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n",
+                    ret, errno, -1, exp_errno);
+                exit(1);
+        }
+}
+
+static void check_ones(const char *buf, size_t len, const char *msg)
+{
+        while (len--)
+                if (buf[len] != 1) {
+                        err("%s", msg);
+                        exit(1);
+                }
+}
+
+static void test_log_good(char *log, size_t buf_len, size_t log_len,
+                          size_t exp_len, int exp_errno, const char *full_log)
+{
+        size_t len;
+        int ret;
+
+        memset(log, 1, buf_len);
+
+        ret = load(log, log_len, 1);
+        check_ret(ret, exp_errno);
+
+        len = strnlen(log, buf_len);
+        if (len == buf_len) {
+                err("verifier did not NULL terminate the log\n");
+                exit(1);
+        }
+        if (exp_len && len != exp_len) {
+                err("incorrect log length expected:%zd have:%zd\n",
+                    exp_len, len);
+                exit(1);
+        }
+
+        if (strchr(log, 1)) {
+                err("verifier leaked a byte through\n");
+                exit(1);
+        }
+
+        check_ones(log + len + 1, buf_len - len - 1,
+                   "verifier wrote bytes past NULL termination\n");
+
+        if (memcmp(full_log, log, LOG_SIZE)) {
+                err("log did not match expected output\n");
+                exit(1);
+        }
+}
+
+static void test_log_bad(char *log, size_t log_len, int log_level)
+{
+        int ret;
+
+        ret = load(log, log_len, log_level);
+        check_ret(ret, EINVAL);
+        if (log)
+                check_ones(log, LOG_SIZE,
+                           "verifier touched log with bad parameters\n");
+}
+
+int main(int argc, char **argv)
+{
+        char full_log[LOG_SIZE];
+        char log[LOG_SIZE];
+        size_t want_len;
+        int i;
+
+        memset(log, 1, LOG_SIZE);
+
+        /* Test incorrect attr */
+        printf("Test log_level 0...\n");
+        test_log_bad(log, LOG_SIZE, 0);
+
+        printf("Test log_size < 128...\n");
+        test_log_bad(log, 15, 1);
+
+        printf("Test log_buff = NULL...\n");
+        test_log_bad(NULL, LOG_SIZE, 1);
+
+        /* Test with log big enough */
+        printf("Test oversized buffer...\n");
+        test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log);
+
+        want_len = strlen(full_log);
+
+        printf("Test exact buffer...\n");
+        test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log);
+
+        printf("Test undersized buffers...\n");
+        for (i = 0; i < 64; i++) {
+                full_log[want_len - i + 1] = 1;
+                full_log[want_len - i] = 0;
+
+                test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i,
+                              ENOSPC, full_log);
+        }
+
+        printf("test_verifier_log: OK\n");
+        return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c
new file mode 100644
index 000000000000..8d0182650653
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_meta.c
@@ -0,0 +1,53 @@
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
+
+#include "bpf_helpers.h"
+
+#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
+#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
+#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
+
+SEC("t")
+int ing_cls(struct __sk_buff *ctx)
+{
+        __u8 *data, *data_meta, *data_end;
+        __u32 diff = 0;
+
+        data_meta = ctx_ptr(ctx, data_meta);
+        data_end  = ctx_ptr(ctx, data_end);
+        data      = ctx_ptr(ctx, data);
+
+        if (data + ETH_ALEN > data_end ||
+            data_meta + round_up(ETH_ALEN, 4) > data)
+                return TC_ACT_SHOT;
+
+        diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0];
+        diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2];
+
+        return diff ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+SEC("x")
+int ing_xdp(struct xdp_md *ctx)
+{
+        __u8 *data, *data_meta, *data_end;
+        int ret;
+
+        ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4));
+        if (ret < 0)
+                return XDP_DROP;
+
+        data_meta = ctx_ptr(ctx, data_meta);
+        data_end  = ctx_ptr(ctx, data_end);
+        data      = ctx_ptr(ctx, data);
+
+        if (data + ETH_ALEN > data_end ||
+            data_meta + round_up(ETH_ALEN, 4) > data)
+                return XDP_DROP;
+
+        __builtin_memcpy(data_meta, data, ETH_ALEN);
+        return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh
new file mode 100755
index 000000000000..307aa856cee3
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_meta.sh
@@ -0,0 +1,51 @@
+#!/bin/sh
+
+cleanup()
+{
+        if [ "$?" = "0" ]; then
+                echo "selftests: test_xdp_meta [PASS]";
+        else
+                echo "selftests: test_xdp_meta [FAILED]";
+        fi
+
+        set +e
+        ip netns del ns1 2> /dev/null
+        ip netns del ns2 2> /dev/null
+}
+
+ip link set dev lo xdp off 2>/dev/null > /dev/null
+if [ $? -ne 0 ];then
+        echo "selftests: [SKIP] Could not run test without the ip xdp support"
+        exit 0
+fi
+set -e
+
+ip netns add ns1
+ip netns add ns2
+
+trap cleanup 0 2 3 6 9
+
+ip link add veth1 type veth peer name veth2
+
+ip link set veth1 netns ns1
+ip link set veth2 netns ns2
+
+ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1
+ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2
+
+ip netns exec ns1 tc qdisc add dev veth1 clsact
+ip netns exec ns2 tc qdisc add dev veth2 clsact
+
+ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t
+ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t
+
+ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x
+ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x
+
+ip netns exec ns1 ip link set dev veth1 up
+ip netns exec ns2 ip link set dev veth2 up
+
+ip netns exec ns1 ping -c 1 10.1.1.22
+ip netns exec ns2 ping -c 1 10.1.1.11
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.c b/tools/testing/selftests/bpf/test_xdp_redirect.c
new file mode 100644
index 000000000000..ef9e704be140
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_redirect.c
@@ -0,0 +1,28 @@
+/* Copyright (c) 2017 VMware
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+SEC("redirect_to_111")
+int xdp_redirect_to_111(struct xdp_md *xdp)
+{
+        return bpf_redirect(111, 0);
+}
+SEC("redirect_to_222")
+int xdp_redirect_to_222(struct xdp_md *xdp)
+{
+        return bpf_redirect(222, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh
new file mode 100755
index 000000000000..344a3656dea6
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh
@@ -0,0 +1,59 @@
+#!/bin/sh
+# Create 2 namespaces with two veth peers, and
+# forward packets in-between using generic XDP
+#
+# NS1(veth11)     NS2(veth22)
+#     |               |
+#     |               |
+#   (veth1, ------ (veth2,
+#   id:111)         id:222)
+#     | xdp forwarding |
+#     ------------------
+
+cleanup()
+{
+        if [ "$?" = "0" ]; then
+                echo "selftests: test_xdp_redirect [PASS]";
+        else
+                echo "selftests: test_xdp_redirect [FAILED]";
+        fi
+
+        set +e
+        ip netns del ns1 2> /dev/null
+        ip netns del ns2 2> /dev/null
+}
+
+ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
+if [ $? -ne 0 ];then
+        echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
+        exit 0
+fi
+set -e
+
+ip netns add ns1
+ip netns add ns2
+
+trap cleanup 0 2 3 6 9
+
+ip link add veth1 index 111 type veth peer name veth11
+ip link add veth2 index 222 type veth peer name veth22
+
+ip link set veth11 netns ns1
+ip link set veth22 netns ns2
+
+ip link set veth1 up
+ip link set veth2 up
+
+ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth11
+ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth22
+
+ip netns exec ns1 ip link set dev veth11 up
+ip netns exec ns2 ip link set dev veth22 up
+
+ip link set dev veth1 xdpgeneric obj test_xdp_redirect.o sec redirect_to_222
+ip link set dev veth2 xdpgeneric obj test_xdp_redirect.o sec redirect_to_111
+
+ip netns exec ns1 ping -c 1 10.1.1.22
+ip netns exec ns2 ping -c 1 10.1.1.11
+
+exit 0
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index 6b214b7b10fb..9ec2c78de8ca 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -1,15 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
 # Taken from perf makefile
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
+TEST_GEN_PROGS := step_after_suspend_test
+
 ifeq ($(ARCH),x86)
-TEST_GEN_PROGS := breakpoint_test
+TEST_GEN_PROGS += breakpoint_test
 endif
 ifneq (,$(filter $(ARCH),aarch64 arm64))
-TEST_GEN_PROGS := breakpoint_test_arm64
+TEST_GEN_PROGS += breakpoint_test_arm64
 endif
 
-TEST_GEN_PROGS += step_after_suspend_test
-
 include ../lib.mk
 
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c
index f63356151ad4..901b85ea6a59 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test.c
@@ -367,11 +367,11 @@ static void launch_tests(void)
 
         /* Icebp traps */
         ptrace(PTRACE_CONT, child_pid, NULL, 0);
-        check_success("Test icebp");
+        check_success("Test icebp\n");
 
         /* Int 3 traps */
         ptrace(PTRACE_CONT, child_pid, NULL, 0);
-        check_success("Test int 3 trap");
+        check_success("Test int 3 trap\n");
 
         ptrace(PTRACE_CONT, child_pid, NULL, 0);
 }
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
index 960d02100c26..2d95e5adde72 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
@@ -19,6 +19,7 @@
 
 #define _GNU_SOURCE
 
+#include <asm/ptrace.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <sys/ptrace.h>
diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile
index 29b8adfdac71..6e9d98d457d5 100644
--- a/tools/testing/selftests/capabilities/Makefile
+++ b/tools/testing/selftests/capabilities/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_GEN_FILES := validate_cap
 TEST_GEN_PROGS := test_execve
 
diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c
index 763f37fecfb8..3ab39a61b95b 100644
--- a/tools/testing/selftests/capabilities/test_execve.c
+++ b/tools/testing/selftests/capabilities/test_execve.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 
 #include <cap-ng.h>
-#include <err.h>
 #include <linux/capability.h>
 #include <stdbool.h>
 #include <string.h>
@@ -18,6 +18,8 @@
 #include <sys/prctl.h>
 #include <sys/stat.h>
 
+#include "../kselftest.h"
+
 #ifndef PR_CAP_AMBIENT
 #define PR_CAP_AMBIENT                  47
 # define PR_CAP_AMBIENT_IS_SET          1
@@ -27,6 +29,7 @@
 #endif
 
 static int nerrs;
+static pid_t mpid;      /*  main() pid is used to avoid duplicate test counts */
 
 static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
 {
@@ -36,29 +39,32 @@ static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list
         int buf_len;
 
         buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
-        if (buf_len < 0) {
-                err(1, "vsnprintf failed");
-        }
-        if (buf_len >= sizeof(buf)) {
-                errx(1, "vsnprintf output truncated");
-        }
+        if (buf_len < 0)
+                ksft_exit_fail_msg("vsnprintf failed - %s\n", strerror(errno));
+
+        if (buf_len >= sizeof(buf))
+                ksft_exit_fail_msg("vsnprintf output truncated\n");
+
 
         fd = open(filename, O_WRONLY);
         if (fd < 0) {
                 if ((errno == ENOENT) && enoent_ok)
                         return;
-                err(1, "open of %s failed", filename);
+                ksft_exit_fail_msg("open of %s failed - %s\n",
+                                        filename, strerror(errno));
         }
         written = write(fd, buf, buf_len);
         if (written != buf_len) {
                 if (written >= 0) {
-                        errx(1, "short write to %s", filename);
+                        ksft_exit_fail_msg("short write to %s\n", filename);
                 } else {
-                        err(1, "write to %s failed", filename);
+                        ksft_exit_fail_msg("write to %s failed - %s\n",
+                                                filename, strerror(errno));
                 }
         }
         if (close(fd) != 0) {
-                err(1, "close of %s failed", filename);
+                ksft_exit_fail_msg("close of %s failed - %s\n",
+                                        filename, strerror(errno));
         }
 }
 
@@ -95,11 +101,12 @@ static bool create_and_enter_ns(uid_t inner_uid)
          */
 
         if (unshare(CLONE_NEWNS) == 0) {
-                printf("[NOTE]\tUsing global UIDs for tests\n");
+                ksft_print_msg("[NOTE]\tUsing global UIDs for tests\n");
                 if (prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0) != 0)
-                        err(1, "PR_SET_KEEPCAPS");
+                        ksft_exit_fail_msg("PR_SET_KEEPCAPS - %s\n",
+                                                strerror(errno));
                 if (setresuid(inner_uid, inner_uid, -1) != 0)
-                        err(1, "setresuid");
+                        ksft_exit_fail_msg("setresuid - %s\n", strerror(errno));
 
                 // Re-enable effective caps
                 capng_get_caps_process();
@@ -107,22 +114,24 @@ static bool create_and_enter_ns(uid_t inner_uid)
                         if (capng_have_capability(CAPNG_PERMITTED, i))
                                 capng_update(CAPNG_ADD, CAPNG_EFFECTIVE, i);
                 if (capng_apply(CAPNG_SELECT_CAPS) != 0)
-                        err(1, "capng_apply");
+                        ksft_exit_fail_msg(
+                                        "capng_apply - %s\n", strerror(errno));
 
                 have_outer_privilege = true;
         } else if (unshare(CLONE_NEWUSER | CLONE_NEWNS) == 0) {
-                printf("[NOTE]\tUsing a user namespace for tests\n");
+                ksft_print_msg("[NOTE]\tUsing a user namespace for tests\n");
                 maybe_write_file("/proc/self/setgroups", "deny");
                 write_file("/proc/self/uid_map", "%d %d 1", inner_uid, outer_uid);
                 write_file("/proc/self/gid_map", "0 %d 1", outer_gid);
 
                 have_outer_privilege = false;
         } else {
-                errx(1, "must be root or be able to create a userns");
+                ksft_exit_skip("must be root or be able to create a userns\n");
         }
 
         if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL) != 0)
-                err(1, "remount everything private");
+                ksft_exit_fail_msg("remount everything private - %s\n",
+                                        strerror(errno));
 
         return have_outer_privilege;
 }
@@ -131,20 +140,22 @@ static void chdir_to_tmpfs(void)
 {
         char cwd[PATH_MAX];
         if (getcwd(cwd, sizeof(cwd)) != cwd)
-                err(1, "getcwd");
+                ksft_exit_fail_msg("getcwd - %s\n", strerror(errno));
 
         if (mount("private_tmp", ".", "tmpfs", 0, "mode=0777") != 0)
-                err(1, "mount private tmpfs");
+                ksft_exit_fail_msg("mount private tmpfs - %s\n",
+                                        strerror(errno));
 
         if (chdir(cwd) != 0)
-                err(1, "chdir to private tmpfs");
+                ksft_exit_fail_msg("chdir to private tmpfs - %s\n",
+                                        strerror(errno));
 }
 
 static void copy_fromat_to(int fromfd, const char *fromname, const char *toname)
 {
         int from = openat(fromfd, fromname, O_RDONLY);
         if (from == -1)
-                err(1, "open copy source");
+                ksft_exit_fail_msg("open copy source - %s\n", strerror(errno));
 
         int to = open(toname, O_CREAT | O_WRONLY | O_EXCL, 0700);
 
@@ -154,10 +165,11 @@ static void copy_fromat_to(int fromfd, const char *fromname, const char *toname)
                 if (sz == 0)
                         break;
                 if (sz < 0)
-                        err(1, "read");
+                        ksft_exit_fail_msg("read - %s\n", strerror(errno));
 
                 if (write(to, buf, sz) != sz)
-                        err(1, "write");        /* no short writes on tmpfs */
+                        /* no short writes on tmpfs */
+                        ksft_exit_fail_msg("write - %s\n", strerror(errno));
         }
 
         close(from);
@@ -174,18 +186,20 @@ static bool fork_wait(void)
                 int status;
                 if (waitpid(child, &status, 0) != child ||
                     !WIFEXITED(status)) {
-                        printf("[FAIL]\tChild died\n");
+                        ksft_print_msg("Child died\n");
                         nerrs++;
                 } else if (WEXITSTATUS(status) != 0) {
-                        printf("[FAIL]\tChild failed\n");
+                        ksft_print_msg("Child failed\n");
                         nerrs++;
                 } else {
-                        printf("[OK]\tChild succeeded\n");
+                        /* don't print this message for mpid */
+                        if (getpid() != mpid)
+                                ksft_test_result_pass("Passed\n");
                 }
-
                 return false;
         } else {
-                err(1, "fork");
+                ksft_exit_fail_msg("fork - %s\n", strerror(errno));
+                return false;
         }
 }
 
@@ -195,7 +209,7 @@ static void exec_other_validate_cap(const char *name,
         execl(name, name, (eff ? "1" : "0"),
               (perm ? "1" : "0"), (inh ? "1" : "0"), (ambient ? "1" : "0"),
               NULL);
-        err(1, "execl");
+        ksft_exit_fail_msg("execl - %s\n", strerror(errno));
 }
 
 static void exec_validate_cap(bool eff, bool perm, bool inh, bool ambient)
@@ -209,7 +223,8 @@ static int do_tests(int uid, const char *our_path)
 
         int ourpath_fd = open(our_path, O_RDONLY | O_DIRECTORY);
         if (ourpath_fd == -1)
-                err(1, "open '%s'", our_path);
+                ksft_exit_fail_msg("open '%s' - %s\n",
+                                        our_path, strerror(errno));
 
         chdir_to_tmpfs();
 
@@ -221,30 +236,30 @@ static int do_tests(int uid, const char *our_path)
                 copy_fromat_to(ourpath_fd, "validate_cap",
                                "validate_cap_suidroot");
                 if (chown("validate_cap_suidroot", 0, -1) != 0)
-                        err(1, "chown");
+                        ksft_exit_fail_msg("chown - %s\n", strerror(errno));
                 if (chmod("validate_cap_suidroot", S_ISUID | 0700) != 0)
-                        err(1, "chmod");
+                        ksft_exit_fail_msg("chmod - %s\n", strerror(errno));
 
                 copy_fromat_to(ourpath_fd, "validate_cap",
                                "validate_cap_suidnonroot");
                 if (chown("validate_cap_suidnonroot", uid + 1, -1) != 0)
-                        err(1, "chown");
+                        ksft_exit_fail_msg("chown - %s\n", strerror(errno));
                 if (chmod("validate_cap_suidnonroot", S_ISUID | 0700) != 0)
-                        err(1, "chmod");
+                        ksft_exit_fail_msg("chmod - %s\n", strerror(errno));
 
                 copy_fromat_to(ourpath_fd, "validate_cap",
                                "validate_cap_sgidroot");
                 if (chown("validate_cap_sgidroot", -1, 0) != 0)
-                        err(1, "chown");
+                        ksft_exit_fail_msg("chown - %s\n", strerror(errno));
                 if (chmod("validate_cap_sgidroot", S_ISGID | 0710) != 0)
-                        err(1, "chmod");
+                        ksft_exit_fail_msg("chmod - %s\n", strerror(errno));
 
                 copy_fromat_to(ourpath_fd, "validate_cap",
                                "validate_cap_sgidnonroot");
                 if (chown("validate_cap_sgidnonroot", -1, gid + 1) != 0)
-                        err(1, "chown");
+                        ksft_exit_fail_msg("chown - %s\n", strerror(errno));
                 if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0)
-                        err(1, "chmod");
+                        ksft_exit_fail_msg("chmod - %s\n", strerror(errno));
         }
 
         capng_get_caps_process();
@@ -252,147 +267,162 @@ static int do_tests(int uid, const char *our_path)
         /* Make sure that i starts out clear */
         capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE);
         if (capng_apply(CAPNG_SELECT_CAPS) != 0)
-                err(1, "capng_apply");
+                ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno));
 
         if (uid == 0) {
-                printf("[RUN]\tRoot => ep\n");
+                ksft_print_msg("[RUN]\tRoot => ep\n");
                 if (fork_wait())
                         exec_validate_cap(true, true, false, false);
         } else {
-                printf("[RUN]\tNon-root => no caps\n");
+                ksft_print_msg("[RUN]\tNon-root => no caps\n");
                 if (fork_wait())
                         exec_validate_cap(false, false, false, false);
         }
 
-        printf("[OK]\tCheck cap_ambient manipulation rules\n");
+        ksft_print_msg("Check cap_ambient manipulation rules\n");
 
         /* We should not be able to add ambient caps yet. */
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != -1 || errno != EPERM) {
                 if (errno == EINVAL)
-                        printf("[FAIL]\tPR_CAP_AMBIENT_RAISE isn't supported\n");
+                        ksft_test_result_fail(
+                                "PR_CAP_AMBIENT_RAISE isn't supported\n");
                 else
-                        printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed eith EPERM on a non-inheritable cap\n");
+                        ksft_test_result_fail(
+                                "PR_CAP_AMBIENT_RAISE should have failed eith EPERM on a non-inheritable cap\n");
                 return 1;
         }
-        printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-inheritable cap\n");
+        ksft_test_result_pass(
+                "PR_CAP_AMBIENT_RAISE failed on non-inheritable cap\n");
 
         capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_RAW);
         capng_update(CAPNG_DROP, CAPNG_PERMITTED, CAP_NET_RAW);
         capng_update(CAPNG_DROP, CAPNG_EFFECTIVE, CAP_NET_RAW);
         if (capng_apply(CAPNG_SELECT_CAPS) != 0)
-                err(1, "capng_apply");
+                ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno));
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_RAW, 0, 0, 0) != -1 || errno != EPERM) {
-                printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed on a non-permitted cap\n");
+                ksft_test_result_fail(
+                        "PR_CAP_AMBIENT_RAISE should have failed on a non-permitted cap\n");
                 return 1;
         }
-        printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-permitted cap\n");
+        ksft_test_result_pass(
+                "PR_CAP_AMBIENT_RAISE failed on non-permitted cap\n");
 
         capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE);
         if (capng_apply(CAPNG_SELECT_CAPS) != 0)
-                err(1, "capng_apply");
+                ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno));
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) {
-                printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have succeeded\n");
+                ksft_test_result_fail(
+                        "PR_CAP_AMBIENT_RAISE should have succeeded\n");
                 return 1;
         }
-        printf("[OK]\tPR_CAP_AMBIENT_RAISE worked\n");
+        ksft_test_result_pass("PR_CAP_AMBIENT_RAISE worked\n");
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 1) {
-                printf("[FAIL]\tPR_CAP_AMBIENT_IS_SET is broken\n");
+                ksft_test_result_fail("PR_CAP_AMBIENT_IS_SET is broken\n");
                 return 1;
         }
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_CLEAR_ALL, 0, 0, 0, 0) != 0)
-                err(1, "PR_CAP_AMBIENT_CLEAR_ALL");
+                ksft_exit_fail_msg("PR_CAP_AMBIENT_CLEAR_ALL - %s\n",
+                                        strerror(errno));
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) {
-                printf("[FAIL]\tPR_CAP_AMBIENT_CLEAR_ALL didn't work\n");
+                ksft_test_result_fail(
+                        "PR_CAP_AMBIENT_CLEAR_ALL didn't work\n");
                 return 1;
         }
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0)
-                err(1, "PR_CAP_AMBIENT_RAISE");
+                ksft_exit_fail_msg("PR_CAP_AMBIENT_RAISE - %s\n",
+                                        strerror(errno));
 
         capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE);
         if (capng_apply(CAPNG_SELECT_CAPS) != 0)
-                err(1, "capng_apply");
+                ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno));
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) {
-                printf("[FAIL]\tDropping I should have dropped A\n");
+                ksft_test_result_fail("Dropping I should have dropped A\n");
                 return 1;
         }
 
-        printf("[OK]\tBasic manipulation appears to work\n");
+        ksft_test_result_pass("Basic manipulation appears to work\n");
 
         capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE);
         if (capng_apply(CAPNG_SELECT_CAPS) != 0)
-                err(1, "capng_apply");
+                ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno));
         if (uid == 0) {
-                printf("[RUN]\tRoot +i => eip\n");
+                ksft_print_msg("[RUN]\tRoot +i => eip\n");
                 if (fork_wait())
                         exec_validate_cap(true, true, true, false);
         } else {
-                printf("[RUN]\tNon-root +i => i\n");
+                ksft_print_msg("[RUN]\tNon-root +i => i\n");
                 if (fork_wait())
                         exec_validate_cap(false, false, true, false);
         }
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0)
-                err(1, "PR_CAP_AMBIENT_RAISE");
+                ksft_exit_fail_msg("PR_CAP_AMBIENT_RAISE - %s\n",
+                                        strerror(errno));
 
-        printf("[RUN]\tUID %d +ia => eipa\n", uid);
+        ksft_print_msg("[RUN]\tUID %d +ia => eipa\n", uid);
         if (fork_wait())
                 exec_validate_cap(true, true, true, true);
 
         /* The remaining tests need real privilege */
 
         if (!have_outer_privilege) {
-                printf("[SKIP]\tSUID/SGID tests (needs privilege)\n");
+                ksft_test_result_skip("SUID/SGID tests (needs privilege)\n");
                 goto done;
         }
 
         if (uid == 0) {
-                printf("[RUN]\tRoot +ia, suidroot => eipa\n");
+                ksft_print_msg("[RUN]\tRoot +ia, suidroot => eipa\n");
                 if (fork_wait())
                         exec_other_validate_cap("./validate_cap_suidroot",
                                                 true, true, true, true);
 
-                printf("[RUN]\tRoot +ia, suidnonroot => ip\n");
+                ksft_print_msg("[RUN]\tRoot +ia, suidnonroot => ip\n");
                 if (fork_wait())
                         exec_other_validate_cap("./validate_cap_suidnonroot",
                                                 false, true, true, false);
 
-                printf("[RUN]\tRoot +ia, sgidroot => eipa\n");
+                ksft_print_msg("[RUN]\tRoot +ia, sgidroot => eipa\n");
                 if (fork_wait())
                         exec_other_validate_cap("./validate_cap_sgidroot",
                                                 true, true, true, true);
 
                 if (fork_wait()) {
-                        printf("[RUN]\tRoot, gid != 0, +ia, sgidroot => eip\n");
+                        ksft_print_msg(
+                                "[RUN]\tRoot, gid != 0, +ia, sgidroot => eip\n");
                         if (setresgid(1, 1, 1) != 0)
-                                err(1, "setresgid");
+                                ksft_exit_fail_msg("setresgid - %s\n",
+                                                        strerror(errno));
                         exec_other_validate_cap("./validate_cap_sgidroot",
                                                 true, true, true, false);
                 }
 
-                printf("[RUN]\tRoot +ia, sgidnonroot => eip\n");
+                ksft_print_msg("[RUN]\tRoot +ia, sgidnonroot => eip\n");
                 if (fork_wait())
                         exec_other_validate_cap("./validate_cap_sgidnonroot",
                                                 true, true, true, false);
         } else {
-                printf("[RUN]\tNon-root +ia, sgidnonroot => i\n");
-                exec_other_validate_cap("./validate_cap_sgidnonroot",
+                ksft_print_msg("[RUN]\tNon-root +ia, sgidnonroot => i\n");
+                if (fork_wait())
+                        exec_other_validate_cap("./validate_cap_sgidnonroot",
                                         false, false, true, false);
 
                 if (fork_wait()) {
-                        printf("[RUN]\tNon-root +ia, sgidroot => i\n");
+                        ksft_print_msg("[RUN]\tNon-root +ia, sgidroot => i\n");
                         if (setresgid(1, 1, 1) != 0)
-                                err(1, "setresgid");
+                                ksft_exit_fail_msg("setresgid - %s\n",
+                                                        strerror(errno));
                         exec_other_validate_cap("./validate_cap_sgidroot",
                                                 false, false, true, false);
                 }
         }
 
 done:
+        ksft_print_cnts();
         return nerrs ? 1 : 0;
 }
 
@@ -400,23 +430,29 @@ int main(int argc, char **argv)
 {
         char *tmp1, *tmp2, *our_path;
 
+        ksft_print_header();
+
         /* Find our path */
         tmp1 = strdup(argv[0]);
         if (!tmp1)
-                err(1, "strdup");
+                ksft_exit_fail_msg("strdup - %s\n", strerror(errno));
         tmp2 = dirname(tmp1);
         our_path = strdup(tmp2);
         if (!our_path)
-                err(1, "strdup");
+                ksft_exit_fail_msg("strdup - %s\n", strerror(errno));
         free(tmp1);
 
+        mpid = getpid();
+
         if (fork_wait()) {
-                printf("[RUN]\t+++ Tests with uid == 0 +++\n");
+                ksft_print_msg("[RUN]\t+++ Tests with uid == 0 +++\n");
                 return do_tests(0, our_path);
         }
 
+        ksft_print_msg("==================================================\n");
+
         if (fork_wait()) {
-                printf("[RUN]\t+++ Tests with uid != 0 +++\n");
+                ksft_print_msg("[RUN]\t+++ Tests with uid != 0 +++\n");
                 return do_tests(1, our_path);
         }
 
diff --git a/tools/testing/selftests/capabilities/validate_cap.c b/tools/testing/selftests/capabilities/validate_cap.c
index dd3c45f7b23c..cdfc94268fe6 100644
--- a/tools/testing/selftests/capabilities/validate_cap.c
+++ b/tools/testing/selftests/capabilities/validate_cap.c
@@ -1,5 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <cap-ng.h>
-#include <err.h>
 #include <linux/capability.h>
 #include <stdbool.h>
 #include <string.h>
@@ -7,6 +7,8 @@
 #include <sys/prctl.h>
 #include <sys/auxv.h>
 
+#include "../kselftest.h"
+
 #ifndef PR_CAP_AMBIENT
 #define PR_CAP_AMBIENT                  47
 # define PR_CAP_AMBIENT_IS_SET          1
@@ -25,8 +27,10 @@ static bool bool_arg(char **argv, int i)
                 return false;
         else if (!strcmp(argv[i], "1"))
                 return true;
-        else
-                errx(1, "wrong argv[%d]", i);
+        else {
+                ksft_exit_fail_msg("wrong argv[%d]\n", i);
+                return false;
+        }
 }
 
 int main(int argc, char **argv)
@@ -39,7 +43,7 @@ int main(int argc, char **argv)
          */
 
         if (argc != 5)
-                errx(1, "wrong argc");
+                ksft_exit_fail_msg("wrong argc\n");
 
 #ifdef HAVE_GETAUXVAL
         if (getauxval(AT_SECURE))
@@ -51,23 +55,26 @@ int main(int argc, char **argv)
         capng_get_caps_process();
 
         if (capng_have_capability(CAPNG_EFFECTIVE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 1)) {
-                printf("[FAIL]\tWrong effective state%s\n", atsec);
+                ksft_print_msg("Wrong effective state%s\n", atsec);
                 return 1;
         }
+
         if (capng_have_capability(CAPNG_PERMITTED, CAP_NET_BIND_SERVICE) != bool_arg(argv, 2)) {
-                printf("[FAIL]\tWrong permitted state%s\n", atsec);
+                ksft_print_msg("Wrong permitted state%s\n", atsec);
                 return 1;
         }
+
         if (capng_have_capability(CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 3)) {
-                printf("[FAIL]\tWrong inheritable state%s\n", atsec);
+                ksft_print_msg("Wrong inheritable state%s\n", atsec);
                 return 1;
         }
 
         if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != bool_arg(argv, 4)) {
-                printf("[FAIL]\tWrong ambient state%s\n", atsec);
+                ksft_print_msg("Wrong ambient state%s\n", atsec);
                 return 1;
         }
 
-        printf("[OK]\tCapabilities after execve were correct\n");
+        ksft_print_msg("%s: Capabilities after execve were correct\n",
+                        "validate_cap:");
         return 0;
 }
diff --git a/tools/testing/selftests/cpu-hotplug/Makefile b/tools/testing/selftests/cpu-hotplug/Makefile
index fe1f99101c5d..d8be047ee5b6 100644
--- a/tools/testing/selftests/cpu-hotplug/Makefile
+++ b/tools/testing/selftests/cpu-hotplug/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 TEST_PROGS := cpu-on-off-test.sh
diff --git a/tools/testing/selftests/cpu-hotplug/config b/tools/testing/selftests/cpu-hotplug/config
index e6ab090cfbf3..d4aca2ad5069 100644
--- a/tools/testing/selftests/cpu-hotplug/config
+++ b/tools/testing/selftests/cpu-hotplug/config
@@ -1,2 +1 @@
 CONFIG_NOTIFIER_ERROR_INJECTION=y
-CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index 98b1d6565f2c..f3a8933c1275 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 SYSFS=
 
@@ -28,6 +29,12 @@ prerequisite()
         echo "CPU online/offline summary:"
         online_cpus=`cat $SYSFS/devices/system/cpu/online`
         online_max=${online_cpus##*-}
+
+        if [[ "$online_cpus" = "$online_max" ]]; then
+                echo "$msg: since there is only one cpu: $online_cpus"
+                exit 0
+        fi
+
         echo -e "\t Cpus in online state: $online_cpus"
 
         offline_cpus=`cat $SYSFS/devices/system/cpu/offline`
@@ -89,8 +96,10 @@ online_cpu_expect_success()
 
         if ! online_cpu $cpu; then
                 echo $FUNCNAME $cpu: unexpected fail >&2
+                exit 1
         elif ! cpu_is_online $cpu; then
                 echo $FUNCNAME $cpu: unexpected offline >&2
+                exit 1
         fi
 }
 
@@ -100,8 +109,10 @@ online_cpu_expect_fail()
 
         if online_cpu $cpu 2> /dev/null; then
                 echo $FUNCNAME $cpu: unexpected success >&2
+                exit 1
         elif ! cpu_is_offline $cpu; then
                 echo $FUNCNAME $cpu: unexpected online >&2
+                exit 1
         fi
 }
 
@@ -111,8 +122,10 @@ offline_cpu_expect_success()
 
         if ! offline_cpu $cpu; then
                 echo $FUNCNAME $cpu: unexpected fail >&2
+                exit 1
         elif ! cpu_is_offline $cpu; then
                 echo $FUNCNAME $cpu: unexpected offline >&2
+                exit 1
         fi
 }
 
@@ -122,8 +135,10 @@ offline_cpu_expect_fail()
 
         if offline_cpu $cpu 2> /dev/null; then
                 echo $FUNCNAME $cpu: unexpected success >&2
+                exit 1
         elif ! cpu_is_online $cpu; then
                 echo $FUNCNAME $cpu: unexpected offline >&2
+                exit 1
         fi
 }
 
diff --git a/tools/testing/selftests/cpufreq/Makefile b/tools/testing/selftests/cpufreq/Makefile
index 3955cd96f3a2..c86ca8342222 100644
--- a/tools/testing/selftests/cpufreq/Makefile
+++ b/tools/testing/selftests/cpufreq/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 TEST_PROGS := main.sh
diff --git a/tools/testing/selftests/cpufreq/cpu.sh b/tools/testing/selftests/cpufreq/cpu.sh
index 8e08a83d65f2..39fdcdfb8e97 100755
--- a/tools/testing/selftests/cpufreq/cpu.sh
+++ b/tools/testing/selftests/cpufreq/cpu.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # CPU helpers
 
diff --git a/tools/testing/selftests/cpufreq/cpufreq.sh b/tools/testing/selftests/cpufreq/cpufreq.sh
index 1ed3832030b4..b583a2fb4504 100755
--- a/tools/testing/selftests/cpufreq/cpufreq.sh
+++ b/tools/testing/selftests/cpufreq/cpufreq.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 # protect against multiple inclusion
 if [ $FILE_CPUFREQ ]; then
diff --git a/tools/testing/selftests/cpufreq/governor.sh b/tools/testing/selftests/cpufreq/governor.sh
index def645103555..fe37df79c087 100755
--- a/tools/testing/selftests/cpufreq/governor.sh
+++ b/tools/testing/selftests/cpufreq/governor.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # Test governors
 
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index 01bac76ac0ec..d83922de9d89 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 source cpu.sh
 source cpufreq.sh
diff --git a/tools/testing/selftests/cpufreq/module.sh b/tools/testing/selftests/cpufreq/module.sh
index 8ff2244a33a1..22563cd122e7 100755
--- a/tools/testing/selftests/cpufreq/module.sh
+++ b/tools/testing/selftests/cpufreq/module.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # Modules specific tests cases
 
diff --git a/tools/testing/selftests/cpufreq/special-tests.sh b/tools/testing/selftests/cpufreq/special-tests.sh
index 58b730f23ef7..8d40505dc468 100755
--- a/tools/testing/selftests/cpufreq/special-tests.sh
+++ b/tools/testing/selftests/cpufreq/special-tests.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # Special test cases reported by people
 
diff --git a/tools/testing/selftests/drivers/gpu/drm_mm.sh b/tools/testing/selftests/drivers/gpu/drm_mm.sh
index 96dd55c92799..b789dc8257e6 100755
--- a/tools/testing/selftests/drivers/gpu/drm_mm.sh
+++ b/tools/testing/selftests/drivers/gpu/drm_mm.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs API tests for struct drm_mm (DRM range manager)
 
 if ! /sbin/modprobe -n -q test-drm_mm; then
diff --git a/tools/testing/selftests/drivers/gpu/i915.sh b/tools/testing/selftests/drivers/gpu/i915.sh
index c06d6e8a8dcc..d3895bc714b7 100755
--- a/tools/testing/selftests/drivers/gpu/i915.sh
+++ b/tools/testing/selftests/drivers/gpu/i915.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs hardware independent tests for i915 (drivers/gpu/drm/i915)
 
 if ! /sbin/modprobe -q -r i915; then
diff --git a/tools/testing/selftests/efivarfs/create-read.c b/tools/testing/selftests/efivarfs/create-read.c
index 7feef1880968..9674a19396a3 100644
--- a/tools/testing/selftests/efivarfs/create-read.c
+++ b/tools/testing/selftests/efivarfs/create-read.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index 057278448515..c6d5790575ae 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 efivarfs_mount=/sys/firmware/efi/efivars
 test_guid=210be57c-9849-4fc7-a635-e6382d1aec27
diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c
index 4af74f733036..562742d44ac9 100644
--- a/tools/testing/selftests/efivarfs/open-unlink.c
+++ b/tools/testing/selftests/efivarfs/open-unlink.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdio.h>
 #include <stdint.h>
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 2e13035dff7f..427c41ba5151 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CFLAGS = -Wall
 
 TEST_GEN_PROGS := execveat
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index 8d5d1d2ee7c1..67cd4597db2b 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -147,7 +147,7 @@ static void exe_cp(const char *src, const char *dest)
 }
 
 #define XX_DIR_LEN 200
-static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
+static int check_execveat_pathmax(int root_dfd, const char *src, int is_script)
 {
         int fail = 0;
         int ii, count, len;
@@ -156,20 +156,30 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
 
         if (*longpath == '\0') {
                 /* Create a filename close to PATH_MAX in length */
+                char *cwd = getcwd(NULL, 0);
+
+                if (!cwd) {
+                        printf("Failed to getcwd(), errno=%d (%s)\n",
+                               errno, strerror(errno));
+                        return 2;
+                }
+                strcpy(longpath, cwd);
+                strcat(longpath, "/");
                 memset(longname, 'x', XX_DIR_LEN - 1);
                 longname[XX_DIR_LEN - 1] = '/';
                 longname[XX_DIR_LEN] = '\0';
-                count = (PATH_MAX - 3) / XX_DIR_LEN;
+                count = (PATH_MAX - 3 - strlen(cwd)) / XX_DIR_LEN;
                 for (ii = 0; ii < count; ii++) {
                         strcat(longpath, longname);
                         mkdir(longpath, 0755);
                 }
-                len = (PATH_MAX - 3) - (count * XX_DIR_LEN);
+                len = (PATH_MAX - 3 - strlen(cwd)) - (count * XX_DIR_LEN);
                 if (len <= 0)
                         len = 1;
                 memset(longname, 'y', len);
                 longname[len] = '\0';
                 strcat(longpath, longname);
+                free(cwd);
         }
         exe_cp(src, longpath);
 
@@ -190,7 +200,7 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
         }
 
         /*
-         * Execute as a long pathname relative to ".".  If this is a script,
+         * Execute as a long pathname relative to "/".  If this is a script,
          * the interpreter will launch but fail to open the script because its
          * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX.
          *
@@ -200,10 +210,10 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
          * the exit status shall be 126."), so allow either.
          */
         if (is_script)
-                fail += check_execveat_invoked_rc(dot_dfd, longpath, 0,
+                fail += check_execveat_invoked_rc(root_dfd, longpath + 1, 0,
                                                   127, 126);
         else
-                fail += check_execveat(dot_dfd, longpath, 0);
+                fail += check_execveat(root_dfd, longpath + 1, 0);
 
         return fail;
 }
@@ -218,6 +228,7 @@ static int run_tests(void)
         int subdir_dfd_ephemeral = open_or_die("subdir.ephemeral",
                                                O_DIRECTORY|O_RDONLY);
         int dot_dfd = open_or_die(".", O_DIRECTORY|O_RDONLY);
+        int root_dfd = open_or_die("/", O_DIRECTORY|O_RDONLY);
         int dot_dfd_path = open_or_die(".", O_DIRECTORY|O_RDONLY|O_PATH);
         int dot_dfd_cloexec = open_or_die(".", O_DIRECTORY|O_RDONLY|O_CLOEXEC);
         int fd = open_or_die("execveat", O_RDONLY);
@@ -353,8 +364,8 @@ static int run_tests(void)
         /* Attempt to execute relative to non-directory => ENOTDIR */
         fail += check_execveat_fail(fd, "execveat", 0, ENOTDIR);
 
-        fail += check_execveat_pathmax(dot_dfd, "execveat", 0);
-        fail += check_execveat_pathmax(dot_dfd, "script", 1);
+        fail += check_execveat_pathmax(root_dfd, "execveat", 0);
+        fail += check_execveat_pathmax(root_dfd, "script", 1);
         return fail;
 }
 
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 0ab11307b414..13a73bf725b5 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := dnotify_test
 all: $(TEST_PROGS)
 
diff --git a/tools/testing/selftests/filesystems/dnotify_test.c b/tools/testing/selftests/filesystems/dnotify_test.c
index 8b37b4a1e18d..c0a9b2d3302d 100644
--- a/tools/testing/selftests/filesystems/dnotify_test.c
+++ b/tools/testing/selftests/filesystems/dnotify_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE     /* needed to get the defines */
 #include <fcntl.h>      /* in glibc 2.2 this has the needed
                                    values defined */
diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh
index 2e4c22d5abf7..34a42c68ebfb 100755
--- a/tools/testing/selftests/firmware/fw_fallback.sh
+++ b/tools/testing/selftests/firmware/fw_fallback.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # This validates that the kernel will fall back to using the fallback mechanism
 # to load firmware it can't find on disk itself. We must request a firmware
 # that the kernel won't find, and any installed helper (e.g. udev) also
@@ -85,6 +86,11 @@ load_fw_cancel()
 
 load_fw_custom()
 {
+        if [ ! -e "$DIR"/trigger_custom_fallback ]; then
+                echo "$0: custom fallback trigger not present, ignoring test" >&2
+                return 1
+        fi
+
         local name="$1"
         local file="$2"
 
@@ -107,11 +113,17 @@ load_fw_custom()
 
         # Wait for request to finish.
         wait
+        return 0
 }
 
 
 load_fw_custom_cancel()
 {
+        if [ ! -e "$DIR"/trigger_custom_fallback ]; then
+                echo "$0: canceling custom fallback trigger not present, ignoring test" >&2
+                return 1
+        fi
+
         local name="$1"
         local file="$2"
 
@@ -132,8 +144,30 @@ load_fw_custom_cancel()
 
         # Wait for request to finish.
         wait
+        return 0
 }
 
+load_fw_fallback_with_child()
+{
+        local name="$1"
+        local file="$2"
+
+        # This is the value already set but we want to be explicit
+        echo 4 >/sys/class/firmware/timeout
+
+        sleep 1 &
+        SECONDS_BEFORE=$(date +%s)
+        echo -n "$name" >"$DIR"/trigger_request 2>/dev/null
+        SECONDS_AFTER=$(date +%s)
+        SECONDS_DELTA=$(($SECONDS_AFTER - $SECONDS_BEFORE))
+        if [ "$SECONDS_DELTA" -lt 4 ]; then
+                RET=1
+        else
+                RET=0
+        fi
+        wait
+        return $RET
+}
 
 trap "test_finish" EXIT
 
@@ -205,20 +239,32 @@ else
         echo "$0: cancelling fallback mechanism works"
 fi
 
-load_fw_custom "$NAME" "$FW"
-if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
-        echo "$0: firmware was not loaded" >&2
-        exit 1
-else
-        echo "$0: custom fallback loading mechanism works"
+if load_fw_custom "$NAME" "$FW" ; then
+        if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+                echo "$0: firmware was not loaded" >&2
+                exit 1
+        else
+                echo "$0: custom fallback loading mechanism works"
+        fi
 fi
 
-load_fw_custom_cancel "nope-$NAME" "$FW"
-if diff -q "$FW" /dev/test_firmware >/dev/null ; then
-        echo "$0: firmware was expected to be cancelled" >&2
-        exit 1
+if load_fw_custom_cancel "nope-$NAME" "$FW" ; then
+        if diff -q "$FW" /dev/test_firmware >/dev/null ; then
+                echo "$0: firmware was expected to be cancelled" >&2
+                exit 1
+        else
+                echo "$0: cancelling custom fallback mechanism works"
+        fi
+fi
+
+set +e
+load_fw_fallback_with_child "nope-signal-$NAME" "$FW"
+if [ "$?" -eq 0 ]; then
+        echo "$0: SIGCHLD on sync ignored as expected" >&2
 else
-        echo "$0: cancelling custom fallback mechanism works"
+        echo "$0: error - sync firmware request cancelled due to SIGCHLD" >&2
+        exit 1
 fi
+set -e
 
 exit 0
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index e35691239350..b1f20fef36c7 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # This validates that the kernel will load firmware out of its list of
 # firmware locations on disk. Since the user helper does similar work,
 # we reset the custom load directory to a location the user helper doesn't
@@ -25,8 +26,9 @@ if [ ! -d $DIR ]; then
 fi
 
 # CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/
-# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that
-# as an indicator for CONFIG_FW_LOADER_USER_HELPER.
+# These days most distros enable CONFIG_FW_LOADER_USER_HELPER but disable
+# CONFIG_FW_LOADER_USER_HELPER_FALLBACK. We use /sys/class/firmware/ as an
+# indicator for CONFIG_FW_LOADER_USER_HELPER.
 HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi)
 
 if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
@@ -68,9 +70,13 @@ if printf '\000' >"$DIR"/trigger_request 2> /dev/null; then
         exit 1
 fi
 
-if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
-        echo "$0: empty filename should not succeed (async)" >&2
-        exit 1
+if [ ! -e "$DIR"/trigger_async_request ]; then
+        echo "$0: empty filename: async trigger not present, ignoring test" >&2
+else
+        if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
+                echo "$0: empty filename should not succeed (async)" >&2
+                exit 1
+        fi
 fi
 
 # Request a firmware that doesn't exist, it should fail.
@@ -103,17 +109,257 @@ else
 fi
 
 # Try the asynchronous version too
-if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
-        echo "$0: could not trigger async request" >&2
-        exit 1
-fi
-
-# Verify the contents are what we expect.
-if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
-        echo "$0: firmware was not loaded (async)" >&2
-        exit 1
+if [ ! -e "$DIR"/trigger_async_request ]; then
+        echo "$0: firmware loading: async trigger not present, ignoring test" >&2
 else
-        echo "$0: async filesystem loading works"
+        if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
+                echo "$0: could not trigger async request" >&2
+                exit 1
+        fi
+
+        # Verify the contents are what we expect.
+        if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then
+                echo "$0: firmware was not loaded (async)" >&2
+                exit 1
+        else
+                echo "$0: async filesystem loading works"
+        fi
 fi
 
+### Batched requests tests
+test_config_present()
+{
+        if [ ! -f $DIR/reset ]; then
+                echo "Configuration triggers not present, ignoring test"
+                exit 0
+        fi
+}
+
+# Defaults :
+#
+# send_uevent: 1
+# sync_direct: 0
+# name: test-firmware.bin
+# num_requests: 4
+config_reset()
+{
+        echo 1 >  $DIR/reset
+}
+
+release_all_firmware()
+{
+        echo 1 >  $DIR/release_all_firmware
+}
+
+config_set_name()
+{
+        echo -n $1 >  $DIR/config_name
+}
+
+config_set_sync_direct()
+{
+        echo 1 >  $DIR/config_sync_direct
+}
+
+config_unset_sync_direct()
+{
+        echo 0 >  $DIR/config_sync_direct
+}
+
+config_set_uevent()
+{
+        echo 1 >  $DIR/config_send_uevent
+}
+
+config_unset_uevent()
+{
+        echo 0 >  $DIR/config_send_uevent
+}
+
+config_trigger_sync()
+{
+        echo -n 1 > $DIR/trigger_batched_requests 2>/dev/null
+}
+
+config_trigger_async()
+{
+        echo -n 1 > $DIR/trigger_batched_requests_async 2> /dev/null
+}
+
+config_set_read_fw_idx()
+{
+        echo -n $1 > $DIR/config_read_fw_idx 2> /dev/null
+}
+
+read_firmwares()
+{
+        for i in $(seq 0 3); do
+                config_set_read_fw_idx $i
+                # Verify the contents are what we expect.
+                # -Z required for now -- check for yourself, md5sum
+                # on $FW and DIR/read_firmware will yield the same. Even
+                # cmp agrees, so something is off.
+                if ! diff -q -Z "$FW" $DIR/read_firmware 2>/dev/null ; then
+                        echo "request #$i: firmware was not loaded" >&2
+                        exit 1
+                fi
+        done
+}
+
+read_firmwares_expect_nofile()
+{
+        for i in $(seq 0 3); do
+                config_set_read_fw_idx $i
+                # Ensures contents differ
+                if diff -q -Z "$FW" $DIR/read_firmware 2>/dev/null ; then
+                        echo "request $i: file was not expected to match" >&2
+                        exit 1
+                fi
+        done
+}
+
+test_batched_request_firmware_nofile()
+{
+        echo -n "Batched request_firmware() nofile try #$1: "
+        config_reset
+        config_set_name nope-test-firmware.bin
+        config_trigger_sync
+        read_firmwares_expect_nofile
+        release_all_firmware
+        echo "OK"
+}
+
+test_batched_request_firmware_direct_nofile()
+{
+        echo -n "Batched request_firmware_direct() nofile try #$1: "
+        config_reset
+        config_set_name nope-test-firmware.bin
+        config_set_sync_direct
+        config_trigger_sync
+        release_all_firmware
+        echo "OK"
+}
+
+test_request_firmware_nowait_uevent_nofile()
+{
+        echo -n "Batched request_firmware_nowait(uevent=true) nofile try #$1: "
+        config_reset
+        config_set_name nope-test-firmware.bin
+        config_trigger_async
+        release_all_firmware
+        echo "OK"
+}
+
+test_wait_and_cancel_custom_load()
+{
+        if [ "$HAS_FW_LOADER_USER_HELPER" != "yes" ]; then
+                return
+        fi
+        local timeout=10
+        name=$1
+        while [ ! -e "$DIR"/"$name"/loading ]; do
+                sleep 0.1
+                timeout=$(( $timeout - 1 ))
+                if [ "$timeout" -eq 0 ]; then
+                        echo "firmware interface never appeared:" >&2
+                        echo "$DIR/$name/loading" >&2
+                        exit 1
+                fi
+        done
+        echo -1 >"$DIR"/"$name"/loading
+}
+
+test_request_firmware_nowait_custom_nofile()
+{
+        echo -n "Batched request_firmware_nowait(uevent=false) nofile try #$1: "
+        config_unset_uevent
+        config_set_name nope-test-firmware.bin
+        config_trigger_async &
+        test_wait_and_cancel_custom_load nope-test-firmware.bin
+        wait
+        release_all_firmware
+        echo "OK"
+}
+
+test_batched_request_firmware()
+{
+        echo -n "Batched request_firmware() try #$1: "
+        config_reset
+        config_trigger_sync
+        read_firmwares
+        release_all_firmware
+        echo "OK"
+}
+
+test_batched_request_firmware_direct()
+{
+        echo -n "Batched request_firmware_direct() try #$1: "
+        config_reset
+        config_set_sync_direct
+        config_trigger_sync
+        release_all_firmware
+        echo "OK"
+}
+
+test_request_firmware_nowait_uevent()
+{
+        echo -n "Batched request_firmware_nowait(uevent=true) try #$1: "
+        config_reset
+        config_trigger_async
+        release_all_firmware
+        echo "OK"
+}
+
+test_request_firmware_nowait_custom()
+{
+        echo -n "Batched request_firmware_nowait(uevent=false) try #$1: "
+        config_unset_uevent
+        config_trigger_async
+        release_all_firmware
+        echo "OK"
+}
+
+# Only continue if batched request triggers are present on the
+# test-firmware driver
+test_config_present
+
+# test with the file present
+echo
+echo "Testing with the file present..."
+for i in $(seq 1 5); do
+        test_batched_request_firmware $i
+done
+
+for i in $(seq 1 5); do
+        test_batched_request_firmware_direct $i
+done
+
+for i in $(seq 1 5); do
+        test_request_firmware_nowait_uevent $i
+done
+
+for i in $(seq 1 5); do
+        test_request_firmware_nowait_custom $i
+done
+
+# Test for file not found, errors are expected, the failure would be
+# a hung task, which would require a hard reset.
+echo
+echo "Testing with the file missing..."
+for i in $(seq 1 5); do
+        test_batched_request_firmware_nofile $i
+done
+
+for i in $(seq 1 5); do
+        test_batched_request_firmware_direct_nofile $i
+done
+
+for i in $(seq 1 5); do
+        test_request_firmware_nowait_uevent_nofile $i
+done
+
+for i in $(seq 1 5); do
+        test_request_firmware_nowait_custom_nofile $i
+done
+
 exit 0
diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile
index a8a5e21850e7..cd1f5b3a7774 100644
--- a/tools/testing/selftests/ftrace/Makefile
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 TEST_PROGS := ftracetest
diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index 8a1c9f949fe0..b01924c71c09 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -1,2 +1,6 @@
 CONFIG_KPROBES=y
 CONFIG_FTRACE=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_TRACER_SNAPSHOT=y
+CONFIG_STACK_TRACER=y
+CONFIG_HIST_TRIGGERS=y
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 14a03ea1e21d..f9a9d424c980 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -8,15 +8,18 @@
 # Released under the terms of the GPL v2.
 
 usage() { # errno [message]
-[ "$2" ] && echo $2
+[ ! -z "$2" ] && echo $2
 echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]"
 echo " Options:"
 echo "          -h|--help  Show help message"
 echo "          -k|--keep  Keep passed test logs"
 echo "          -v|--verbose Increase verbosity of test messages"
 echo "          -vv        Alias of -v -v (Show all results in stdout)"
+echo "          -vvv       Alias of -v -v -v (Show all commands immediately)"
+echo "          --fail-unsupported Treat UNSUPPORTED as a failure"
 echo "          -d|--debug Debug mode (trace all shell commands)"
 echo "          -l|--logdir <dir> Save logs on the <dir>"
+echo "                      If <dir> is -, all logs output in console only"
 exit $1
 }
 
@@ -47,7 +50,7 @@ parse_opts() { # opts
   local OPT_TEST_CASES=
   local OPT_TEST_DIR=
 
-  while [ "$1" ]; do
+  while [ ! -z "$1" ]; do
     case "$1" in
     --help|-h)
       usage 0
@@ -56,15 +59,20 @@ parse_opts() { # opts
       KEEP_LOG=1
       shift 1
     ;;
-    --verbose|-v|-vv)
+    --verbose|-v|-vv|-vvv)
       VERBOSE=$((VERBOSE + 1))
       [ $1 = '-vv' ] && VERBOSE=$((VERBOSE + 1))
+      [ $1 = '-vvv' ] && VERBOSE=$((VERBOSE + 2))
       shift 1
     ;;
     --debug|-d)
       DEBUG=1
       shift 1
     ;;
+    --fail-unsupported)
+      UNSUPPORTED_RESULT=1
+      shift 1
+    ;;
     --logdir|-l)
       LOG_DIR=$2
       shift 2
@@ -88,7 +96,7 @@ parse_opts() { # opts
     ;;
     esac
   done
-  if [ "$OPT_TEST_CASES" ]; then
+  if [ ! -z "$OPT_TEST_CASES" ]; then
     TEST_CASES=$OPT_TEST_CASES
   fi
 }
@@ -108,6 +116,7 @@ LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/
 KEEP_LOG=0
 DEBUG=0
 VERBOSE=0
+UNSUPPORTED_RESULT=0
 # Parse command-line options
 parse_opts $*
 
@@ -119,14 +128,20 @@ if [ -z "$TRACING_DIR" -o ! -d "$TRACING_DIR" ]; then
 fi
 
 # Preparing logs
-LOG_FILE=$LOG_DIR/ftracetest.log
-mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR"
-date > $LOG_FILE
+if [ "x$LOG_DIR" = "x-" ]; then
+  LOG_FILE=
+  date
+else
+  LOG_FILE=$LOG_DIR/ftracetest.log
+  mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR"
+  date > $LOG_FILE
+fi
+
 prlog() { # messages
-  echo "$@" | tee -a $LOG_FILE
+  [ -z "$LOG_FILE" ] && echo "$@" || echo "$@" | tee -a $LOG_FILE
 }
 catlog() { #file
-  cat $1 | tee -a $LOG_FILE
+  [ -z "$LOG_FILE" ] && cat $1 || cat $1 | tee -a $LOG_FILE
 }
 prlog "=== Ftrace unit tests ==="
 
@@ -187,7 +202,7 @@ eval_result() { # sigval
     $UNSUPPORTED)
       prlog "   [UNSUPPORTED]"
       UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
-      return 1 # this is not a bug, but the result should be reported.
+      return $UNSUPPORTED_RESULT # depends on use case
     ;;
     $XFAIL)
       prlog "   [XFAIL]"
@@ -207,7 +222,14 @@ SIG_RESULT=
 SIG_BASE=36     # Use realtime signals
 SIG_PID=$$
 
+exit_pass () {
+  exit 0
+}
+
 SIG_FAIL=$((SIG_BASE + FAIL))
+exit_fail () {
+  exit 1
+}
 trap 'SIG_RESULT=$FAIL' $SIG_FAIL
 
 SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED))
@@ -247,12 +269,20 @@ __run_test() { # testfile
 # Run one test case
 run_test() { # testfile
   local testname=`basename $1`
-  local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX`
+  if [ ! -z "$LOG_FILE" ] ; then
+    local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX`
+  else
+    local testlog=/proc/self/fd/1
+  fi
   export TMPDIR=`mktemp -d /tmp/ftracetest-dir.XXXXXX`
   testcase $1
   echo "execute$INSTANCE: "$1 > $testlog
   SIG_RESULT=0
-  if [ $VERBOSE -ge 2 ]; then
+  if [ -z "$LOG_FILE" ]; then
+    __run_test $1 2>&1
+  elif [ $VERBOSE -ge 3 ]; then
+    __run_test $1 | tee -a $testlog 2>&1
+  elif [ $VERBOSE -eq 2 ]; then
     __run_test $1 2>> $testlog | tee -a $testlog
   else
     __run_test $1 >> $testlog 2>&1
@@ -260,9 +290,9 @@ run_test() { # testfile
   eval_result $SIG_RESULT
   if [ $? -eq 0 ]; then
     # Remove test log if the test was done as it was expected.
-    [ $KEEP_LOG -eq 0 ] && rm $testlog
+    [ $KEEP_LOG -eq 0 -a ! -z "$LOG_FILE" ] && rm $testlog
   else
-    [ $VERBOSE -ge 1 ] && catlog $testlog
+    [ $VERBOSE -eq 1 -o $VERBOSE -eq 2 ] && catlog $testlog
     TOTAL_RESULT=1
   fi
   rm -rf $TMPDIR
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
index ebfce83f35b4..531e472362df 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Basic test for tracers
 # flags: instance
 test -f available_tracers
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
index 9e33f841812f..58a2506f788e 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Basic trace clock test
 # flags: instance
 test -f trace_clock
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
index aa51f6c17359..0696098d6408 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic4.tc
@@ -2,4 +2,4 @@
 # description: Basic event tracing check
 test -f available_events -a -f set_event -a -d events
 # check scheduler events are available
-grep -q sched available_events && exit 0 || exit $FAIL
+grep -q sched available_events && exit_pass || exit_fail
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
index 283b45ecb199..9daf034186f5 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event tracing - enable/disable with event level files
 # flags: instance
 
@@ -10,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index 96c1a95be4f7..132478b305c2 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event tracing - restricts events based on pid
 # flags: instance
 
@@ -12,7 +13,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index b8fe2e5b9e67..6a37a8642ee6 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event tracing - enable/disable with subsystem level files
 # flags: instance
 
@@ -10,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
index 15e2d3fe1731..4e9b6e2c0219 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event tracing - enable/disable with top level files
 
 do_reset() {
@@ -9,7 +10,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
index 15c2dba06ea2..1aec99d108eb 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function graph filters with stack tracer
 
 # Make sure that function graph filtering works, and is not
@@ -27,7 +28,7 @@ do_reset() {
 fail() { # msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 disable_tracing
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
index 0ab2189613ef..9f8d27ca39cf 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function graph filters
 
 # Make sure that function graph filtering works
@@ -17,7 +18,7 @@ do_reset() {
 fail() { # msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 disable_tracing
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
index 8095e122daa9..589d52b211b7 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function glob filters
 
 # Make sure that function glob matching filter works.
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index bab5ff7c607e..524ce24b3c22 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function pid filters
 
 # Make sure that function pid matching filter works.
@@ -50,7 +51,7 @@ do_reset() {
 fail() { # msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 yield() {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
index 77dfb6b48186..6fed4cf2db81 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - test for function event triggers
 # flags: instance
 #
@@ -26,7 +27,7 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 SLEEP_TIME=".1"
@@ -47,8 +48,7 @@ test_event_enabled() {
 
     e=`cat $EVENT_ENABLE`
     if [ "$e" != $val ]; then
-        echo "Expected $val but found $e"
-        exit 1
+        fail "Expected $val but found $e"
     fi
 }
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
index 7808336d6f50..b2d5a8febfe8 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function profiler with function tracing
 
 # There was a bug after a rewrite of the ftrace infrastructure that
@@ -31,7 +32,7 @@ fail() { # mesg
     reset_tracer
     echo > set_ftrace_filter
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 echo "Testing function tracer with profiler:"
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index 113b4d9bc733..0f3f92622e33 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - test reading of set_ftrace_filter
 #
 # The set_ftrace_filter file of ftrace is used to list functions as well as
@@ -25,14 +26,14 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 do_reset
 
 FILTER=set_ftrace_filter
 FUNC1="schedule"
-FUNC2="do_IRQ"
+FUNC2="do_softirq"
 
 ALL_FUNCS="#### all functions enabled ####"
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
index 7a9ab4ff83b6..f6d9ac73268a 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: ftrace - test for function traceon/off triggers
 # flags: instance
 #
@@ -26,7 +27,7 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 SLEEP_TIME=".1"
diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
index 8a353314dc9b..4fa0f79144f4 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Test creation and deletion of trace instances while setting an event
 
 if [ ! -d instances ] ; then
@@ -10,7 +11,7 @@ fail() { # mesg
     rmdir foo 2>/dev/null
     echo $1
     set -e
-    exit $FAIL
+    exit_fail
 }
 
 cd instances
diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
index 1e1abe0ad354..b84651283bf3 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Test creation and deletion of trace instances
 
 if [ ! -d instances ] ; then
@@ -10,7 +11,7 @@ fail() { # mesg
     rmdir x y z 2>/dev/null
     echo $1
     set -e
-    exit $FAIL
+    exit_fail
 }
 
 cd instances
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index c3843ed49bf6..4604d2103c89 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobe dynamic event - adding and removing
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index 74507db8bbc8..bbc443a9190c 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobe dynamic event - busy event check
 
 [ -f kprobe_events ] || exit_unsupported
@@ -8,7 +9,7 @@ echo > kprobe_events
 echo p:myevent _do_fork > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
-echo > kprobe_events && exit 1 # this must fail
+echo > kprobe_events && exit_fail # this must fail
 echo 0 > events/kprobes/myevent/enable
 echo > kprobe_events # this must succeed
 clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index 64949d4eda69..8b43c6804fc3 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobe dynamic event with arguments
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
@@ -13,5 +14,5 @@ echo 1 > events/kprobes/testprobe/enable
 echo 0 > events/kprobes/testprobe/enable
 echo "-:testprobe" >> kprobe_events
 clear_trace
-test -d events/kprobes/testprobe && exit 1 || exit 0
+test -d events/kprobes/testprobe && exit_fail || exit_pass
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index c75faefb4fff..2a1755bfc290 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobes event arguments with types
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
@@ -34,4 +35,4 @@ check_types $ARGS
 
 echo "-:testprobe" >> kprobe_events
 clear_trace
-test -d events/kprobes/testprobe && exit 1 || exit 0
+test -d events/kprobes/testprobe && exit_fail || exit_pass
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
index b9302cc82c12..2724a1068cb1 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobe event auto/manual naming
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index d6f2f4965697..cc4cac0e60f2 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobe dynamic event with function tracer
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
index 6d634e4b7680..1e9f75f7a30f 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kprobe dynamic event - probing module
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 0d09546258fd..321954683aaa 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kretprobe dynamic event with arguments
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
@@ -13,4 +14,4 @@ echo 1 > events/kprobes/testprobe2/enable
 echo 0 > events/kprobes/testprobe2/enable
 echo '-:testprobe2' >> kprobe_events
 clear_trace
-test -d events/kprobes/testprobe2 && exit 1 || exit 0
+test -d events/kprobes/testprobe2 && exit_fail || exit_pass
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
index 7ec6f2639ad6..7c0290684c43 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Kretprobe dynamic event with maxactive
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
index 2a1cb9908746..bb16cf91f1b5 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
@@ -1,6 +1,9 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: Register/unregister many kprobe events
 
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
 # ftrace fentry skip size depends on the machine architecture.
 # Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le
 case `uname -m` in
diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template
index 5448f7abad5f..5c39ceb18a0d 100644
--- a/tools/testing/selftests/ftrace/test.d/template
+++ b/tools/testing/selftests/ftrace/test.d/template
@@ -4,6 +4,7 @@
 # Note that all tests are run with "errexit" option.
 
 exit 0 # Return 0 if the test is passed, otherwise return !0
+# Or you can call exit_pass for passed test, and exit_fail for failed test.
 # If the test could not run because of lack of feature, call exit_unsupported
 # If the test returned unclear results, call exit_unresolved
 # If the test is a dummy, or a placeholder, call exit_untested
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
index c5435adfdd93..28cc355a3a7b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test event enable/disable trigger
 # flags: instance
 
@@ -11,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
index 48849a8d577f..a48e23eb8a8b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test trigger filter
 # flags: instance
 
@@ -11,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index b7f86d10b549..8da80efc44d8 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test histogram modifiers
 # flags: instance
 
@@ -11,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
index fb66f7d9339d..449fe9ff91a2 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test histogram trigger
 # flags: instance
 
@@ -11,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index f9153087dd7c..c5ef8b9d02b3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test multiple histogram triggers
 # flags: instance
 
@@ -11,7 +12,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
index ed94f0c4e0e4..ed38f0050d77 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test snapshot-trigger
 
 do_reset() {
@@ -10,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
index 9fa23b085def..3121d795a868 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test stacktrace-trigger
 
 do_reset() {
@@ -10,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
index 87648e5f987c..c59d9eb546da 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test traceon/off trigger
 
 do_reset() {
@@ -10,7 +11,7 @@ do_reset() {
 fail() { #msg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 if [ ! -f set_event -o ! -d events/sched ]; then
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index e2fbb890aef9..cea4adcd42b8 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 SUBDIRS := functional
 
 TEST_PROGS := run.sh
@@ -7,14 +8,17 @@ TEST_PROGS := run.sh
 include ../lib.mk
 
 all:
-        for DIR in $(SUBDIRS); do               \
+        @for DIR in $(SUBDIRS); do              \
                 BUILD_TARGET=$(OUTPUT)/$$DIR;   \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+                if [ -e $$DIR/$(TEST_PROGS) ]; then
+                        rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/;
+                fi
         done
 
 override define RUN_TESTS
-        @if [ `dirname $(OUTPUT)` = $(PWD) ]; then ./run.sh; fi
+        @cd $(OUTPUT); ./run.sh
 endef
 
 override define INSTALL_RULE
@@ -33,7 +37,7 @@ override define EMIT_TESTS
 endef
 
 override define CLEAN
-        for DIR in $(SUBDIRS); do               \
+        @for DIR in $(SUBDIRS); do              \
                 BUILD_TARGET=$(OUTPUT)/$$DIR;   \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index a648e7a6cbc3..ff8feca49746 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 INCLUDES := -I../include -I../../
 CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES)
 LDFLAGS := $(LDFLAGS) -pthread -lrt
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
index d24ab7421e73..54cd5c414e82 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -394,9 +394,11 @@ int main(int argc, char *argv[])
                 }
         }
 
-        printf("%s: Test requeue functionality\n", basename(argv[0]));
-        printf("\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
-               broadcast, locked, owner, timeout_ns);
+        ksft_print_header();
+        ksft_print_msg("%s: Test requeue functionality\n", basename(argv[0]));
+        ksft_print_msg(
+                "\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
+                broadcast, locked, owner, timeout_ns);
 
         /*
          * FIXME: unit_test is obsolete now that we parse options and the
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
index e0a798ad0d21..08187a16507f 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
@@ -78,7 +78,8 @@ int main(int argc, char *argv[])
                 }
         }
 
-        printf("%s: Detect mismatched requeue_pi operations\n",
+        ksft_print_header();
+        ksft_print_msg("%s: Detect mismatched requeue_pi operations\n",
                basename(argv[0]));
 
         if (pthread_create(&child, NULL, blocking_child, NULL)) {
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
index 982f83577501..f0542a344d95 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
@@ -143,9 +143,10 @@ int main(int argc, char *argv[])
                 }
         }
 
-        printf("%s: Test signal handling during requeue_pi\n",
+        ksft_print_header();
+        ksft_print_msg("%s: Test signal handling during requeue_pi\n",
                basename(argv[0]));
-        printf("\tArguments: <none>\n");
+        ksft_print_msg("\tArguments: <none>\n");
 
         sa.sa_handler = handle_signal;
         sigemptyset(&sa.sa_mask);
diff --git a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
index bdc48dc047e5..6216de828093 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
@@ -97,8 +97,10 @@ int main(int argc, char **argv)
                 }
         }
 
-        printf("%s: Test the futex value of private file mappings in FUTEX_WAIT\n",
-               basename(argv[0]));
+        ksft_print_header();
+        ksft_print_msg(
+                "%s: Test the futex value of private file mappings in FUTEX_WAIT\n",
+                basename(argv[0]));
 
         ret = pthread_create(&thr, NULL, thr_futex_wait, NULL);
         if (ret < 0) {
diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
index 6aadd560366e..bab3dfe1787f 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
@@ -68,9 +68,10 @@ int main(int argc, char *argv[])
                 }
         }
 
-        printf("%s: Block on a futex and wait for timeout\n",
+        ksft_print_header();
+        ksft_print_msg("%s: Block on a futex and wait for timeout\n",
                basename(argv[0]));
-        printf("\tArguments: timeout=%ldns\n", timeout_ns);
+        ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns);
 
         /* initialize timeout */
         to.tv_sec = 0;
diff --git a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
index d237a8b702f0..26975322545b 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
@@ -99,7 +99,8 @@ int main(int argc, char **argv)
                 exit(1);
         }
 
-        printf("%s: Test the uninitialized futex value in FUTEX_WAIT\n",
+        ksft_print_header();
+        ksft_print_msg("%s: Test the uninitialized futex value in FUTEX_WAIT\n",
                basename(argv[0]));
 
 
diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
index 9a2c56fa7305..da15a63269b4 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
@@ -64,7 +64,8 @@ int main(int argc, char *argv[])
                 }
         }
 
-        printf("%s: Test the unexpected futex value in FUTEX_WAIT\n",
+        ksft_print_header();
+        ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n",
                basename(argv[0]));
 
         info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
diff --git a/tools/testing/selftests/futex/include/logging.h b/tools/testing/selftests/futex/include/logging.h
index 4e7944984fbb..01989644e50a 100644
--- a/tools/testing/selftests/futex/include/logging.h
+++ b/tools/testing/selftests/futex/include/logging.h
@@ -109,22 +109,20 @@ void log_verbosity(int level)
  */
 void print_result(const char *test_name, int ret)
 {
-        const char *result = "Unknown return code";
-
         switch (ret) {
         case RET_PASS:
-                ksft_inc_pass_cnt();
-                result = PASS;
-                break;
+                ksft_test_result_pass("%s\n", test_name);
+                ksft_print_cnts();
+                return;
         case RET_ERROR:
-                result = ERROR;
-                break;
+                ksft_test_result_error("%s\n", test_name);
+                ksft_print_cnts();
+                return;
         case RET_FAIL:
-                ksft_inc_fail_cnt();
-                result = FAIL;
-                break;
+                ksft_test_result_fail("%s\n", test_name);
+                ksft_print_cnts();
+                return;
         }
-        printf("selftests: %s [%s]\n", test_name, result);
 }
 
 /* log level macros */
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 298929df97e6..1bbb47565c55 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh $(BINARIES)
diff --git a/tools/testing/selftests/gpio/gpio-mockup-sysfs.sh b/tools/testing/selftests/gpio/gpio-mockup-sysfs.sh
index 085d7a39899c..dd269d877562 100755
--- a/tools/testing/selftests/gpio/gpio-mockup-sysfs.sh
+++ b/tools/testing/selftests/gpio/gpio-mockup-sysfs.sh
@@ -1,4 +1,5 @@
 
+# SPDX-License-Identifier: GPL-2.0
 is_consistent()
 {
         val=
diff --git a/tools/testing/selftests/gpio/gpio-mockup.sh b/tools/testing/selftests/gpio/gpio-mockup.sh
index b183439e058e..183fb932edbd 100755
--- a/tools/testing/selftests/gpio/gpio-mockup.sh
+++ b/tools/testing/selftests/gpio/gpio-mockup.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 #exit status
 #1: run as non-root user
diff --git a/tools/testing/selftests/ia64/Makefile b/tools/testing/selftests/ia64/Makefile
index 2b3de2d3e945..4bce1a84b3a1 100644
--- a/tools/testing/selftests/ia64/Makefile
+++ b/tools/testing/selftests/ia64/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := aliasing-test
 
 all: $(TEST_PROGS)
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
index 849a90ffe8dd..5a3f7d37e912 100644
--- a/tools/testing/selftests/intel_pstate/Makefile
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -1,7 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
 LDLIBS := $(LDLIBS) -lm
 
+ifeq (,$(filter $(ARCH),x86))
 TEST_GEN_FILES := msr aperf
+endif
 
 TEST_PROGS := run.sh
 
diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c
index cd72f3dc83e9..d21edea9c560 100644
--- a/tools/testing/selftests/intel_pstate/aperf.c
+++ b/tools/testing/selftests/intel_pstate/aperf.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <math.h>
 #include <unistd.h>
 #include <stdio.h>
diff --git a/tools/testing/selftests/intel_pstate/msr.c b/tools/testing/selftests/intel_pstate/msr.c
index abbbfc84d359..88fdd2a4b0a0 100644
--- a/tools/testing/selftests/intel_pstate/msr.c
+++ b/tools/testing/selftests/intel_pstate/msr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <math.h>
 #include <unistd.h>
 #include <stdio.h>
diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh
index 7868c106b8b1..c670359becc6 100755
--- a/tools/testing/selftests/intel_pstate/run.sh
+++ b/tools/testing/selftests/intel_pstate/run.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #
 # This test runs on Intel x86 based hardware which support the intel_pstate
 # driver.  The test checks the frequency settings from the maximum turbo
@@ -29,13 +30,12 @@
 
 EVALUATE_ONLY=0
 
-max_cpus=$(($(nproc)-1))
+if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then
+        echo "$0 # Skipped: Test can only run on x86 architectures."
+        exit 0
+fi
 
-# compile programs
-gcc aperf.c -Wall -D_GNU_SOURCE -o aperf  -lm
-[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1
-gcc -o msr msr.c -lm
-[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1
+max_cpus=$(($(nproc)-1))
 
 function run_test () {
 
diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile
index 30ef4c7f53ea..1c4448a843a4 100644
--- a/tools/testing/selftests/ipc/Makefile
+++ b/tools/testing/selftests/ipc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
 ifeq ($(ARCH),i386)
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index 1b2ce334bb3f..ee9382bdfadc 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c
index a5a4da856dfe..6ea7b9f37a41 100644
--- a/tools/testing/selftests/kcmp/kcmp_test.c
+++ b/tools/testing/selftests/kcmp/kcmp_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 
 #include <stdio.h>
@@ -8,7 +9,6 @@
 #include <errno.h>
 #include <string.h>
 #include <fcntl.h>
-
 #include <linux/unistd.h>
 #include <linux/kcmp.h>
 
@@ -16,20 +16,28 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
+#include <sys/epoll.h>
 
 #include "../kselftest.h"
 
-static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2)
+static long sys_kcmp(int pid1, int pid2, int type, unsigned long fd1, unsigned long fd2)
 {
         return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2);
 }
 
+static const unsigned int duped_num = 64;
+
 int main(int argc, char **argv)
 {
         const char kpath[] = "kcmp-test-file";
+        struct kcmp_epoll_slot epoll_slot;
+        struct epoll_event ev;
         int pid1, pid2;
+        int pipefd[2];
         int fd1, fd2;
+        int epollfd;
         int status;
+        int fddup;
 
         fd1 = open(kpath, O_RDWR | O_CREAT | O_TRUNC, 0644);
         pid1 = getpid();
@@ -39,6 +47,37 @@ int main(int argc, char **argv)
                 ksft_exit_fail();
         }
 
+        if (pipe(pipefd)) {
+                perror("Can't create pipe");
+                ksft_exit_fail();
+        }
+
+        epollfd = epoll_create1(0);
+        if (epollfd < 0) {
+                perror("epoll_create1 failed");
+                ksft_exit_fail();
+        }
+
+        memset(&ev, 0xff, sizeof(ev));
+        ev.events = EPOLLIN | EPOLLOUT;
+
+        if (epoll_ctl(epollfd, EPOLL_CTL_ADD, pipefd[0], &ev)) {
+                perror("epoll_ctl failed");
+                ksft_exit_fail();
+        }
+
+        fddup = dup2(pipefd[1], duped_num);
+        if (fddup < 0) {
+                perror("dup2 failed");
+                ksft_exit_fail();
+        }
+
+        if (epoll_ctl(epollfd, EPOLL_CTL_ADD, fddup, &ev)) {
+                perror("epoll_ctl failed");
+                ksft_exit_fail();
+        }
+        close(fddup);
+
         pid2 = fork();
         if (pid2 < 0) {
                 perror("fork failed");
@@ -95,6 +134,24 @@ int main(int argc, char **argv)
                         ksft_inc_pass_cnt();
                 }
 
+                /* Compare epoll target */
+                epoll_slot = (struct kcmp_epoll_slot) {
+                        .efd    = epollfd,
+                        .tfd    = duped_num,
+                        .toff   = 0,
+                };
+                ret = sys_kcmp(pid1, pid1, KCMP_EPOLL_TFD, pipefd[1],
+                               (unsigned long)(void *)&epoll_slot);
+                if (ret) {
+                        printf("FAIL: 0 expected but %d returned (%s)\n",
+                                ret, strerror(errno));
+                        ksft_inc_fail_cnt();
+                        ret = -1;
+                } else {
+                        printf("PASS: 0 returned as expected\n");
+                        ksft_inc_pass_cnt();
+                }
+
                 ksft_print_cnts();
 
                 if (ret)
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 8cecae9a8bca..7956ea3be667 100644..100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -473,8 +473,8 @@ usage()
         echo "    all     Runs all tests (default)"
         echo "    -t      Run test ID the number amount of times is recommended"
         echo "    -w      Watch test ID run until it runs into an error"
-        echo "    -c      Run test ID once"
-        echo "    -s      Run test ID x test-count number of times"
+        echo "    -s      Run test ID once"
+        echo "    -c      Run test ID x test-count number of times"
         echo "    -l      List all test ID list"
         echo " -h|--help  Help"
         echo
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 08e90c2cc5cb..1ae565ed9bf0 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -19,7 +19,8 @@
 #define KSFT_FAIL  1
 #define KSFT_XFAIL 2
 #define KSFT_XPASS 3
-#define KSFT_SKIP  4
+/* Treat skip as pass */
+#define KSFT_SKIP  KSFT_PASS
 
 /* counters */
 struct ksft_count {
@@ -28,6 +29,7 @@ struct ksft_count {
         unsigned int ksft_xfail;
         unsigned int ksft_xpass;
         unsigned int ksft_xskip;
+        unsigned int ksft_error;
 };
 
 static struct ksft_count ksft_cnt;
@@ -36,7 +38,7 @@ static inline int ksft_test_num(void)
 {
         return ksft_cnt.ksft_pass + ksft_cnt.ksft_fail +
                 ksft_cnt.ksft_xfail + ksft_cnt.ksft_xpass +
-                ksft_cnt.ksft_xskip;
+                ksft_cnt.ksft_xskip + ksft_cnt.ksft_error;
 }
 
 static inline void ksft_inc_pass_cnt(void) { ksft_cnt.ksft_pass++; }
@@ -44,6 +46,14 @@ static inline void ksft_inc_fail_cnt(void) { ksft_cnt.ksft_fail++; }
 static inline void ksft_inc_xfail_cnt(void) { ksft_cnt.ksft_xfail++; }
 static inline void ksft_inc_xpass_cnt(void) { ksft_cnt.ksft_xpass++; }
 static inline void ksft_inc_xskip_cnt(void) { ksft_cnt.ksft_xskip++; }
+static inline void ksft_inc_error_cnt(void) { ksft_cnt.ksft_error++; }
+
+static inline int ksft_get_pass_cnt(void) { return ksft_cnt.ksft_pass; }
+static inline int ksft_get_fail_cnt(void) { return ksft_cnt.ksft_fail; }
+static inline int ksft_get_xfail_cnt(void) { return ksft_cnt.ksft_xfail; }
+static inline int ksft_get_xpass_cnt(void) { return ksft_cnt.ksft_xpass; }
+static inline int ksft_get_xskip_cnt(void) { return ksft_cnt.ksft_xskip; }
+static inline int ksft_get_error_cnt(void) { return ksft_cnt.ksft_error; }
 
 static inline void ksft_print_header(void)
 {
@@ -52,6 +62,10 @@ static inline void ksft_print_header(void)
 
 static inline void ksft_print_cnts(void)
 {
+        printf("Pass %d Fail %d Xfail %d Xpass %d Skip %d Error %d\n",
+                ksft_cnt.ksft_pass, ksft_cnt.ksft_fail,
+                ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass,
+                ksft_cnt.ksft_xskip, ksft_cnt.ksft_error);
         printf("1..%d\n", ksft_test_num());
 }
 
@@ -101,6 +115,18 @@ static inline void ksft_test_result_skip(const char *msg, ...)
         va_end(args);
 }
 
+static inline void ksft_test_result_error(const char *msg, ...)
+{
+        va_list args;
+
+        ksft_cnt.ksft_error++;
+
+        va_start(args, msg);
+        printf("not ok %d # error ", ksft_test_num());
+        vprintf(msg, args);
+        va_end(args);
+}
+
 static inline int ksft_exit_pass(void)
 {
         ksft_print_cnts();
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index c56f72e07cd7..e81bd28bdd89 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -51,6 +51,9 @@
 #define __KSELFTEST_HARNESS_H
 
 #define _GNU_SOURCE
+#include <asm/types.h>
+#include <errno.h>
+#include <stdbool.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -84,6 +87,14 @@
  * E.g., #define TH_LOG_ENABLED 1
  *
  * If no definition is provided, logging is enabled by default.
+ *
+ * If there is no way to print an error message for the process running the
+ * test (e.g. not allowed to write to stderr), it is still possible to get the
+ * ASSERT_* number for which the test failed.  This behavior can be enabled by
+ * writing `_metadata->no_print = true;` before the check sequence that is
+ * unable to print.  When an error occur, instead of printing an error message
+ * and calling `abort(3)`, the test process call `_exit(2)` with the assert
+ * number as argument, which is then printed by the parent process.
  */
 #define TH_LOG(fmt, ...) do { \
         if (TH_LOG_ENABLED) \
@@ -555,12 +566,18 @@
  * return while still providing an optional block to the API consumer.
  */
 #define OPTIONAL_HANDLER(_assert) \
-        for (; _metadata->trigger;  _metadata->trigger = __bail(_assert))
+        for (; _metadata->trigger; _metadata->trigger = \
+                        __bail(_assert, _metadata->no_print, _metadata->step))
+
+#define __INC_STEP(_metadata) \
+        if (_metadata->passed && _metadata->step < 255) \
+                _metadata->step++;
 
 #define __EXPECT(_expected, _seen, _t, _assert) do { \
         /* Avoid multiple evaluation of the cases */ \
         __typeof__(_expected) __exp = (_expected); \
         __typeof__(_seen) __seen = (_seen); \
+        if (_assert) __INC_STEP(_metadata); \
         if (!(__exp _t __seen)) { \
                 unsigned long long __exp_print = (uintptr_t)__exp; \
                 unsigned long long __seen_print = (uintptr_t)__seen; \
@@ -576,6 +593,7 @@
 #define __EXPECT_STR(_expected, _seen, _t, _assert) do { \
         const char *__exp = (_expected); \
         const char *__seen = (_seen); \
+        if (_assert) __INC_STEP(_metadata); \
         if (!(strcmp(__exp, __seen) _t 0))  { \
                 __TH_LOG("Expected '%s' %s '%s'.", __exp, #_t, __seen); \
                 _metadata->passed = 0; \
@@ -590,6 +608,8 @@ struct __test_metadata {
         int termsig;
         int passed;
         int trigger; /* extra handler after the evaluation */
+        __u8 step;
+        bool no_print; /* manual trigger when TH_LOG_STREAM is not available */
         struct __test_metadata *prev, *next;
 };
 
@@ -634,10 +654,13 @@ static inline void __register_test(struct __test_metadata *t)
         }
 }
 
-static inline int __bail(int for_realz)
+static inline int __bail(int for_realz, bool no_print, __u8 step)
 {
-        if (for_realz)
+        if (for_realz) {
+                if (no_print)
+                        _exit(step);
                 abort();
+        }
         return 0;
 }
 
@@ -655,18 +678,24 @@ void __run_test(struct __test_metadata *t)
                 t->passed = 0;
         } else if (child_pid == 0) {
                 t->fn(t);
-                _exit(t->passed);
+                /* return the step that failed or 0 */
+                _exit(t->passed ? 0 : t->step);
         } else {
                 /* TODO(wad) add timeout support. */
                 waitpid(child_pid, &status, 0);
                 if (WIFEXITED(status)) {
-                        t->passed = t->termsig == -1 ? WEXITSTATUS(status) : 0;
+                        t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0;
                         if (t->termsig != -1) {
                                 fprintf(TH_LOG_STREAM,
                                         "%s: Test exited normally "
                                         "instead of by signal (code: %d)\n",
                                         t->name,
                                         WEXITSTATUS(status));
+                        } else if (!t->passed) {
+                                fprintf(TH_LOG_STREAM,
+                                        "%s: Test failed at step #%d\n",
+                                        t->name,
+                                        WEXITSTATUS(status));
                         }
                 } else if (WIFSIGNALED(status)) {
                         t->passed = 0;
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 959273c3a52e..5bef05d6ba39 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -6,20 +6,53 @@ ifeq (0,$(MAKELEVEL))
 OUTPUT := $(shell pwd)
 endif
 
+# The following are built by lib.mk common compile rules.
+# TEST_CUSTOM_PROGS should be used by tests that require
+# custom build rule and prevent common build rule use.
+# TEST_PROGS are for test shell scripts.
+# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests
+# and install targets. Common clean doesn't touch them.
 TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
+TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
 all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
+.ONESHELL:
 define RUN_TESTS
-        @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
+        @test_num=`echo 0`;
+        @echo "TAP version 13";
+        @for TEST in $(1); do                           \
                 BASENAME_TEST=`basename $$TEST`;        \
-                cd `dirname $$TEST`; (./$$BASENAME_TEST && echo "selftests: $$BASENAME_TEST [PASS]") || echo "selftests:  $$BASENAME_TEST [FAIL]"; cd -;\
+                test_num=`echo $$test_num+1 | bc`;      \
+                echo "selftests: $$BASENAME_TEST";      \
+                echo "========================================";        \
+                if [ ! -x $$TEST ]; then        \
+                        echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\
+                        echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \
+                else                                    \
+                if [ "X$(summary)" != "X" ]; then               \
+                                cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests:  $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
+                        else                            \
+                                cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests:  $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
+                        fi;                             \
+                fi;                                     \
         done;
 endef
 
 run_tests: all
-        $(RUN_TESTS)
+ifneq ($(KBUILD_SRC),)
+        @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then
+                @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT)
+        fi
+        @if [ "X$(TEST_PROGS)" != "X" ]; then
+                $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS))
+        else
+                $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS))
+        fi
+else
+        $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
+endif
 
 define INSTALL_RULE
         @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then                                        \
@@ -27,10 +60,10 @@ define INSTALL_RULE
                 echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";    \
                 rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;           \
         fi
-        @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then                                    \
+        @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then                                        \
                 mkdir -p ${INSTALL_PATH};                                                                               \
-                echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";        \
-                rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;               \
+                echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";   \
+                rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;          \
         fi
 endef
 
@@ -42,15 +75,20 @@ else
 endif
 
 define EMIT_TESTS
-        @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
+        @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
                 BASENAME_TEST=`basename $$TEST`;        \
-                echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
+                echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
         done;
 endef
 
 emit_tests:
         $(EMIT_TESTS)
 
+# define if isn't already. It is undefined in make O= case.
+ifeq ($(RM),)
+RM := rm -f
+endif
+
 define CLEAN
         $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 endef
@@ -58,6 +96,15 @@ endef
 clean:
         $(CLEAN)
 
+# When make O= with kselftest target from main level
+# the following aren't defined.
+#
+ifneq ($(KBUILD_SRC),)
+LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
+COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c
+LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
+endif
+
 $(OUTPUT)/%:%.c
         $(LINK.c) $^ $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh
index b073c22a3435..4dee4d2a8bbe 100755
--- a/tools/testing/selftests/lib/bitmap.sh
+++ b/tools/testing/selftests/lib/bitmap.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs bitmap infrastructure tests using test_bitmap kernel module
 if ! /sbin/modprobe -q -n test_bitmap; then
         echo "bitmap: [SKIP]"
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
index da4cbcd766f5..b363994e5e11 100755
--- a/tools/testing/selftests/lib/prime_numbers.sh
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Checks fast/slow prime_number generation for inconsistencies
 
 if ! /sbin/modprobe -q -r prime_numbers; then
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
index cbf3b124bd94..0c37377fd7d4 100755
--- a/tools/testing/selftests/lib/printf.sh
+++ b/tools/testing/selftests/lib/printf.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs printf infrastructure using test_printf kernel module
 if ! /sbin/modprobe -q -n test_printf; then
         echo "printf: [SKIP]"
diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh
index 6905da965f3b..2c3d6b1878c2 100644
--- a/tools/testing/selftests/locking/ww_mutex.sh
+++ b/tools/testing/selftests/locking/ww_mutex.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs API tests for struct ww_mutex (Wait/Wound mutexes)
 
 if /sbin/modprobe -q test-ww_mutex; then
diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile
index 6b34a0199468..be5bd4ffb895 100644
--- a/tools/testing/selftests/media_tests/Makefile
+++ b/tools/testing/selftests/media_tests/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := media_device_test media_device_open video_device_test
 all: $(TEST_PROGS)
 
diff --git a/tools/testing/selftests/media_tests/bind_unbind_sample.sh b/tools/testing/selftests/media_tests/bind_unbind_sample.sh
index 9f362f10631a..0101c1ec4ff7 100755
--- a/tools/testing/selftests/media_tests/bind_unbind_sample.sh
+++ b/tools/testing/selftests/media_tests/bind_unbind_sample.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 # Find device number in /sys/bus/usb/drivers/drivername
 # Edit this file to update the driver numer and name
 # Example test for uvcvideo driver
diff --git a/tools/testing/selftests/media_tests/open_loop_test.sh b/tools/testing/selftests/media_tests/open_loop_test.sh
index dcd3c17efc17..d4c0179bbe2c 100755
--- a/tools/testing/selftests/media_tests/open_loop_test.sh
+++ b/tools/testing/selftests/media_tests/open_loop_test.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
  i=0
 file=/dev/media$1
  while :; do
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index 21399fcf1a59..9e674d9514d1 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <linux/membarrier.h>
 #include <syscall.h>
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index ad8a0897e47f..3926a0409dda 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -1,9 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 CFLAGS += -D_FILE_OFFSET_BITS=64
 CFLAGS += -I../../../../include/uapi/
 CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
-TEST_PROGS := run_fuse_test.sh
+TEST_PROGS := run_tests.sh
 TEST_GEN_FILES := memfd_test fuse_mnt fuse_test
 
 fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
diff --git a/tools/testing/selftests/memfd/fuse_mnt.c b/tools/testing/selftests/memfd/fuse_mnt.c
index feacf1280fcd..6936f2a001f3 100644
--- a/tools/testing/selftests/memfd/fuse_mnt.c
+++ b/tools/testing/selftests/memfd/fuse_mnt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * memfd test file-system
  * This file uses FUSE to create a dummy file-system with only one file /memfd.
diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c
index 67908b18f035..1ccb7a3eb14b 100644
--- a/tools/testing/selftests/memfd/fuse_test.c
+++ b/tools/testing/selftests/memfd/fuse_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * memfd GUP test-case
  * This tests memfd interactions with get_user_pages(). We require the
@@ -33,7 +34,7 @@
 #include <unistd.h>
 
 #define MFD_DEF_SIZE 8192
-#define STACK_SIZE 65535
+#define STACK_SIZE 65536
 
 static int sys_memfd_create(const char *name,
                             unsigned int flags)
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 26546892cd54..132a54f74e88 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #define __EXPORTED_HEADERS__
 
@@ -18,12 +19,48 @@
 #include <sys/wait.h>
 #include <unistd.h>
 
+#define MEMFD_STR       "memfd:"
+#define SHARED_FT_STR   "(shared file-table)"
+
 #define MFD_DEF_SIZE 8192
 #define STACK_SIZE 65536
 
+/*
+ * Default is not to test hugetlbfs
+ */
+static int hugetlbfs_test;
+static size_t mfd_def_size = MFD_DEF_SIZE;
+
+/*
+ * Copied from mlock2-tests.c
+ */
+static unsigned long default_huge_page_size(void)
+{
+        unsigned long hps = 0;
+        char *line = NULL;
+        size_t linelen = 0;
+        FILE *f = fopen("/proc/meminfo", "r");
+
+        if (!f)
+                return 0;
+        while (getline(&line, &linelen, f) > 0) {
+                if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
+                        hps <<= 10;
+                        break;
+                }
+        }
+
+        free(line);
+        fclose(f);
+        return hps;
+}
+
 static int sys_memfd_create(const char *name,
                             unsigned int flags)
 {
+        if (hugetlbfs_test)
+                flags |= MFD_HUGETLB;
+
         return syscall(__NR_memfd_create, name, flags);
 }
 
@@ -150,7 +187,7 @@ static void *mfd_assert_mmap_shared(int fd)
         void *p;
 
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ | PROT_WRITE,
                  MAP_SHARED,
                  fd,
@@ -168,7 +205,7 @@ static void *mfd_assert_mmap_private(int fd)
         void *p;
 
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ,
                  MAP_PRIVATE,
                  fd,
@@ -223,7 +260,7 @@ static void mfd_assert_read(int fd)
 
         /* verify PROT_READ *is* allowed */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ,
                  MAP_PRIVATE,
                  fd,
@@ -232,11 +269,11 @@ static void mfd_assert_read(int fd)
                 printf("mmap() failed: %m\n");
                 abort();
         }
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
 
         /* verify MAP_PRIVATE is *always* allowed (even writable) */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ | PROT_WRITE,
                  MAP_PRIVATE,
                  fd,
@@ -245,7 +282,7 @@ static void mfd_assert_read(int fd)
                 printf("mmap() failed: %m\n");
                 abort();
         }
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
 }
 
 static void mfd_assert_write(int fd)
@@ -254,16 +291,22 @@ static void mfd_assert_write(int fd)
         void *p;
         int r;
 
-        /* verify write() succeeds */
-        l = write(fd, "\0\0\0\0", 4);
-        if (l != 4) {
-                printf("write() failed: %m\n");
-                abort();
+        /*
+         * huegtlbfs does not support write, but we want to
+         * verify everything else here.
+         */
+        if (!hugetlbfs_test) {
+                /* verify write() succeeds */
+                l = write(fd, "\0\0\0\0", 4);
+                if (l != 4) {
+                        printf("write() failed: %m\n");
+                        abort();
+                }
         }
 
         /* verify PROT_READ | PROT_WRITE is allowed */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ | PROT_WRITE,
                  MAP_SHARED,
                  fd,
@@ -273,11 +316,11 @@ static void mfd_assert_write(int fd)
                 abort();
         }
         *(char *)p = 0;
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
 
         /* verify PROT_WRITE is allowed */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_WRITE,
                  MAP_SHARED,
                  fd,
@@ -287,12 +330,12 @@ static void mfd_assert_write(int fd)
                 abort();
         }
         *(char *)p = 0;
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
 
         /* verify PROT_READ with MAP_SHARED is allowed and a following
          * mprotect(PROT_WRITE) allows writing */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ,
                  MAP_SHARED,
                  fd,
@@ -302,20 +345,20 @@ static void mfd_assert_write(int fd)
                 abort();
         }
 
-        r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE);
+        r = mprotect(p, mfd_def_size, PROT_READ | PROT_WRITE);
         if (r < 0) {
                 printf("mprotect() failed: %m\n");
                 abort();
         }
 
         *(char *)p = 0;
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
 
         /* verify PUNCH_HOLE works */
         r = fallocate(fd,
                       FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
                       0,
-                      MFD_DEF_SIZE);
+                      mfd_def_size);
         if (r < 0) {
                 printf("fallocate(PUNCH_HOLE) failed: %m\n");
                 abort();
@@ -337,7 +380,7 @@ static void mfd_fail_write(int fd)
 
         /* verify PROT_READ | PROT_WRITE is not allowed */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ | PROT_WRITE,
                  MAP_SHARED,
                  fd,
@@ -349,7 +392,7 @@ static void mfd_fail_write(int fd)
 
         /* verify PROT_WRITE is not allowed */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_WRITE,
                  MAP_SHARED,
                  fd,
@@ -362,13 +405,13 @@ static void mfd_fail_write(int fd)
         /* Verify PROT_READ with MAP_SHARED with a following mprotect is not
          * allowed. Note that for r/w the kernel already prevents the mmap. */
         p = mmap(NULL,
-                 MFD_DEF_SIZE,
+                 mfd_def_size,
                  PROT_READ,
                  MAP_SHARED,
                  fd,
                  0);
         if (p != MAP_FAILED) {
-                r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE);
+                r = mprotect(p, mfd_def_size, PROT_READ | PROT_WRITE);
                 if (r >= 0) {
                         printf("mmap()+mprotect() didn't fail as expected\n");
                         abort();
@@ -379,7 +422,7 @@ static void mfd_fail_write(int fd)
         r = fallocate(fd,
                       FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
                       0,
-                      MFD_DEF_SIZE);
+                      mfd_def_size);
         if (r >= 0) {
                 printf("fallocate(PUNCH_HOLE) didn't fail as expected\n");
                 abort();
@@ -390,13 +433,13 @@ static void mfd_assert_shrink(int fd)
 {
         int r, fd2;
 
-        r = ftruncate(fd, MFD_DEF_SIZE / 2);
+        r = ftruncate(fd, mfd_def_size / 2);
         if (r < 0) {
                 printf("ftruncate(SHRINK) failed: %m\n");
                 abort();
         }
 
-        mfd_assert_size(fd, MFD_DEF_SIZE / 2);
+        mfd_assert_size(fd, mfd_def_size / 2);
 
         fd2 = mfd_assert_open(fd,
                               O_RDWR | O_CREAT | O_TRUNC,
@@ -410,7 +453,7 @@ static void mfd_fail_shrink(int fd)
 {
         int r;
 
-        r = ftruncate(fd, MFD_DEF_SIZE / 2);
+        r = ftruncate(fd, mfd_def_size / 2);
         if (r >= 0) {
                 printf("ftruncate(SHRINK) didn't fail as expected\n");
                 abort();
@@ -425,31 +468,31 @@ static void mfd_assert_grow(int fd)
 {
         int r;
 
-        r = ftruncate(fd, MFD_DEF_SIZE * 2);
+        r = ftruncate(fd, mfd_def_size * 2);
         if (r < 0) {
                 printf("ftruncate(GROW) failed: %m\n");
                 abort();
         }
 
-        mfd_assert_size(fd, MFD_DEF_SIZE * 2);
+        mfd_assert_size(fd, mfd_def_size * 2);
 
         r = fallocate(fd,
                       0,
                       0,
-                      MFD_DEF_SIZE * 4);
+                      mfd_def_size * 4);
         if (r < 0) {
                 printf("fallocate(ALLOC) failed: %m\n");
                 abort();
         }
 
-        mfd_assert_size(fd, MFD_DEF_SIZE * 4);
+        mfd_assert_size(fd, mfd_def_size * 4);
 }
 
 static void mfd_fail_grow(int fd)
 {
         int r;
 
-        r = ftruncate(fd, MFD_DEF_SIZE * 2);
+        r = ftruncate(fd, mfd_def_size * 2);
         if (r >= 0) {
                 printf("ftruncate(GROW) didn't fail as expected\n");
                 abort();
@@ -458,7 +501,7 @@ static void mfd_fail_grow(int fd)
         r = fallocate(fd,
                       0,
                       0,
-                      MFD_DEF_SIZE * 4);
+                      mfd_def_size * 4);
         if (r >= 0) {
                 printf("fallocate(ALLOC) didn't fail as expected\n");
                 abort();
@@ -467,25 +510,37 @@ static void mfd_fail_grow(int fd)
 
 static void mfd_assert_grow_write(int fd)
 {
-        static char buf[MFD_DEF_SIZE * 8];
+        static char *buf;
         ssize_t l;
 
-        l = pwrite(fd, buf, sizeof(buf), 0);
-        if (l != sizeof(buf)) {
+        buf = malloc(mfd_def_size * 8);
+        if (!buf) {
+                printf("malloc(%zu) failed: %m\n", mfd_def_size * 8);
+                abort();
+        }
+
+        l = pwrite(fd, buf, mfd_def_size * 8, 0);
+        if (l != (mfd_def_size * 8)) {
                 printf("pwrite() failed: %m\n");
                 abort();
         }
 
-        mfd_assert_size(fd, MFD_DEF_SIZE * 8);
+        mfd_assert_size(fd, mfd_def_size * 8);
 }
 
 static void mfd_fail_grow_write(int fd)
 {
-        static char buf[MFD_DEF_SIZE * 8];
+        static char *buf;
         ssize_t l;
 
-        l = pwrite(fd, buf, sizeof(buf), 0);
-        if (l == sizeof(buf)) {
+        buf = malloc(mfd_def_size * 8);
+        if (!buf) {
+                printf("malloc(%zu) failed: %m\n", mfd_def_size * 8);
+                abort();
+        }
+
+        l = pwrite(fd, buf, mfd_def_size * 8, 0);
+        if (l == (mfd_def_size * 8)) {
                 printf("pwrite() didn't fail as expected\n");
                 abort();
         }
@@ -543,6 +598,8 @@ static void test_create(void)
         char buf[2048];
         int fd;
 
+        printf("%s CREATE\n", MEMFD_STR);
+
         /* test NULL name */
         mfd_fail_new(NULL, 0);
 
@@ -570,13 +627,18 @@ static void test_create(void)
         fd = mfd_assert_new("", 0, MFD_CLOEXEC);
         close(fd);
 
-        /* verify MFD_ALLOW_SEALING is allowed */
-        fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING);
-        close(fd);
-
-        /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */
-        fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC);
-        close(fd);
+        if (!hugetlbfs_test) {
+                /* verify MFD_ALLOW_SEALING is allowed */
+                fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING);
+                close(fd);
+
+                /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */
+                fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC);
+                close(fd);
+        } else {
+                /* sealing is not supported on hugetlbfs */
+                mfd_fail_new("", MFD_ALLOW_SEALING);
+        }
 }
 
 /*
@@ -587,8 +649,14 @@ static void test_basic(void)
 {
         int fd;
 
+        /* hugetlbfs does not contain sealing support */
+        if (hugetlbfs_test)
+                return;
+
+        printf("%s BASIC\n", MEMFD_STR);
+
         fd = mfd_assert_new("kern_memfd_basic",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
 
         /* add basic seals */
@@ -619,7 +687,7 @@ static void test_basic(void)
 
         /* verify sealing does not work without MFD_ALLOW_SEALING */
         fd = mfd_assert_new("kern_memfd_basic",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC);
         mfd_assert_has_seals(fd, F_SEAL_SEAL);
         mfd_fail_add_seals(fd, F_SEAL_SHRINK |
@@ -630,6 +698,28 @@ static void test_basic(void)
 }
 
 /*
+ * hugetlbfs doesn't support seals or write, so just verify grow and shrink
+ * on a hugetlbfs file created via memfd_create.
+ */
+static void test_hugetlbfs_grow_shrink(void)
+{
+        int fd;
+
+        printf("%s HUGETLBFS-GROW-SHRINK\n", MEMFD_STR);
+
+        fd = mfd_assert_new("kern_memfd_seal_write",
+                            mfd_def_size,
+                            MFD_CLOEXEC);
+
+        mfd_assert_read(fd);
+        mfd_assert_write(fd);
+        mfd_assert_shrink(fd);
+        mfd_assert_grow(fd);
+
+        close(fd);
+}
+
+/*
  * Test SEAL_WRITE
  * Test whether SEAL_WRITE actually prevents modifications.
  */
@@ -637,8 +727,17 @@ static void test_seal_write(void)
 {
         int fd;
 
+        /*
+         * hugetlbfs does not contain sealing or write support.  Just test
+         * basic grow and shrink via test_hugetlbfs_grow_shrink.
+         */
+        if (hugetlbfs_test)
+                return test_hugetlbfs_grow_shrink();
+
+        printf("%s SEAL-WRITE\n", MEMFD_STR);
+
         fd = mfd_assert_new("kern_memfd_seal_write",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
         mfd_assert_add_seals(fd, F_SEAL_WRITE);
@@ -661,8 +760,14 @@ static void test_seal_shrink(void)
 {
         int fd;
 
+        /* hugetlbfs does not contain sealing support */
+        if (hugetlbfs_test)
+                return;
+
+        printf("%s SEAL-SHRINK\n", MEMFD_STR);
+
         fd = mfd_assert_new("kern_memfd_seal_shrink",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
         mfd_assert_add_seals(fd, F_SEAL_SHRINK);
@@ -685,8 +790,14 @@ static void test_seal_grow(void)
 {
         int fd;
 
+        /* hugetlbfs does not contain sealing support */
+        if (hugetlbfs_test)
+                return;
+
+        printf("%s SEAL-GROW\n", MEMFD_STR);
+
         fd = mfd_assert_new("kern_memfd_seal_grow",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
         mfd_assert_add_seals(fd, F_SEAL_GROW);
@@ -709,8 +820,14 @@ static void test_seal_resize(void)
 {
         int fd;
 
+        /* hugetlbfs does not contain sealing support */
+        if (hugetlbfs_test)
+                return;
+
+        printf("%s SEAL-RESIZE\n", MEMFD_STR);
+
         fd = mfd_assert_new("kern_memfd_seal_resize",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
         mfd_assert_add_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW);
@@ -726,15 +843,52 @@ static void test_seal_resize(void)
 }
 
 /*
+ * hugetlbfs does not support seals.  Basic test to dup the memfd created
+ * fd and perform some basic operations on it.
+ */
+static void hugetlbfs_dup(char *b_suffix)
+{
+        int fd, fd2;
+
+        printf("%s HUGETLBFS-DUP %s\n", MEMFD_STR, b_suffix);
+
+        fd = mfd_assert_new("kern_memfd_share_dup",
+                            mfd_def_size,
+                            MFD_CLOEXEC);
+
+        fd2 = mfd_assert_dup(fd);
+
+        mfd_assert_read(fd);
+        mfd_assert_write(fd);
+
+        mfd_assert_shrink(fd2);
+        mfd_assert_grow(fd2);
+
+        close(fd2);
+        close(fd);
+}
+
+/*
  * Test sharing via dup()
  * Test that seals are shared between dupped FDs and they're all equal.
  */
-static void test_share_dup(void)
+static void test_share_dup(char *banner, char *b_suffix)
 {
         int fd, fd2;
 
+        /*
+         * hugetlbfs does not contain sealing support.  Perform some
+         * basic testing on dup'ed fd instead via hugetlbfs_dup.
+         */
+        if (hugetlbfs_test) {
+                hugetlbfs_dup(b_suffix);
+                return;
+        }
+
+        printf("%s %s %s\n", MEMFD_STR, banner, b_suffix);
+
         fd = mfd_assert_new("kern_memfd_share_dup",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
 
@@ -768,13 +922,19 @@ static void test_share_dup(void)
  * Test sealing with active mmap()s
  * Modifying seals is only allowed if no other mmap() refs exist.
  */
-static void test_share_mmap(void)
+static void test_share_mmap(char *banner, char *b_suffix)
 {
         int fd;
         void *p;
 
+        /* hugetlbfs does not contain sealing support */
+        if (hugetlbfs_test)
+                return;
+
+        printf("%s %s %s\n", MEMFD_STR,  banner, b_suffix);
+
         fd = mfd_assert_new("kern_memfd_share_mmap",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
 
@@ -784,14 +944,40 @@ static void test_share_mmap(void)
         mfd_assert_has_seals(fd, 0);
         mfd_assert_add_seals(fd, F_SEAL_SHRINK);
         mfd_assert_has_seals(fd, F_SEAL_SHRINK);
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
 
         /* readable ref allows sealing */
         p = mfd_assert_mmap_private(fd);
         mfd_assert_add_seals(fd, F_SEAL_WRITE);
         mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK);
-        munmap(p, MFD_DEF_SIZE);
+        munmap(p, mfd_def_size);
+
+        close(fd);
+}
+
+/*
+ * Basic test to make sure we can open the hugetlbfs fd via /proc and
+ * perform some simple operations on it.
+ */
+static void hugetlbfs_proc_open(char *b_suffix)
+{
+        int fd, fd2;
+
+        printf("%s HUGETLBFS-PROC-OPEN %s\n", MEMFD_STR, b_suffix);
 
+        fd = mfd_assert_new("kern_memfd_share_open",
+                            mfd_def_size,
+                            MFD_CLOEXEC);
+
+        fd2 = mfd_assert_open(fd, O_RDWR, 0);
+
+        mfd_assert_read(fd);
+        mfd_assert_write(fd);
+
+        mfd_assert_shrink(fd2);
+        mfd_assert_grow(fd2);
+
+        close(fd2);
         close(fd);
 }
 
@@ -801,12 +987,23 @@ static void test_share_mmap(void)
  * This is *not* like dup(), but like a real separate open(). Make sure the
  * semantics are as expected and we correctly check for RDONLY / WRONLY / RDWR.
  */
-static void test_share_open(void)
+static void test_share_open(char *banner, char *b_suffix)
 {
         int fd, fd2;
 
+        /*
+         * hugetlbfs does not contain sealing support.  So test basic
+         * functionality of using /proc fd via hugetlbfs_proc_open
+         */
+        if (hugetlbfs_test) {
+                hugetlbfs_proc_open(b_suffix);
+                return;
+        }
+
+        printf("%s %s %s\n", MEMFD_STR, banner, b_suffix);
+
         fd = mfd_assert_new("kern_memfd_share_open",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
 
@@ -841,13 +1038,19 @@ static void test_share_open(void)
  * Test sharing via fork()
  * Test whether seal-modifications work as expected with forked childs.
  */
-static void test_share_fork(void)
+static void test_share_fork(char *banner, char *b_suffix)
 {
         int fd;
         pid_t pid;
 
+        /* hugetlbfs does not contain sealing support */
+        if (hugetlbfs_test)
+                return;
+
+        printf("%s %s %s\n", MEMFD_STR, banner, b_suffix);
+
         fd = mfd_assert_new("kern_memfd_share_fork",
-                            MFD_DEF_SIZE,
+                            mfd_def_size,
                             MFD_CLOEXEC | MFD_ALLOW_SEALING);
         mfd_assert_has_seals(fd, 0);
 
@@ -870,40 +1073,40 @@ int main(int argc, char **argv)
 {
         pid_t pid;
 
-        printf("memfd: CREATE\n");
+        if (argc == 2) {
+                if (!strcmp(argv[1], "hugetlbfs")) {
+                        unsigned long hpage_size = default_huge_page_size();
+
+                        if (!hpage_size) {
+                                printf("Unable to determine huge page size\n");
+                                abort();
+                        }
+
+                        hugetlbfs_test = 1;
+                        mfd_def_size = hpage_size * 2;
+                }
+        }
+
         test_create();
-        printf("memfd: BASIC\n");
         test_basic();
 
-        printf("memfd: SEAL-WRITE\n");
         test_seal_write();
-        printf("memfd: SEAL-SHRINK\n");
         test_seal_shrink();
-        printf("memfd: SEAL-GROW\n");
         test_seal_grow();
-        printf("memfd: SEAL-RESIZE\n");
         test_seal_resize();
 
-        printf("memfd: SHARE-DUP\n");
-        test_share_dup();
-        printf("memfd: SHARE-MMAP\n");
-        test_share_mmap();
-        printf("memfd: SHARE-OPEN\n");
-        test_share_open();
-        printf("memfd: SHARE-FORK\n");
-        test_share_fork();
+        test_share_dup("SHARE-DUP", "");
+        test_share_mmap("SHARE-MMAP", "");
+        test_share_open("SHARE-OPEN", "");
+        test_share_fork("SHARE-FORK", "");
 
         /* Run test-suite in a multi-threaded environment with a shared
          * file-table. */
         pid = spawn_idle_thread(CLONE_FILES | CLONE_FS | CLONE_VM);
-        printf("memfd: SHARE-DUP (shared file-table)\n");
-        test_share_dup();
-        printf("memfd: SHARE-MMAP (shared file-table)\n");
-        test_share_mmap();
-        printf("memfd: SHARE-OPEN (shared file-table)\n");
-        test_share_open();
-        printf("memfd: SHARE-FORK (shared file-table)\n");
-        test_share_fork();
+        test_share_dup("SHARE-DUP", SHARED_FT_STR);
+        test_share_mmap("SHARE-MMAP", SHARED_FT_STR);
+        test_share_open("SHARE-OPEN", SHARED_FT_STR);
+        test_share_fork("SHARE-FORK", SHARED_FT_STR);
         join_idle_thread(pid);
 
         printf("memfd: DONE\n");
diff --git a/tools/testing/selftests/memfd/run_fuse_test.sh b/tools/testing/selftests/memfd/run_fuse_test.sh
index 69b930e1e041..407df68dfe27 100755
--- a/tools/testing/selftests/memfd/run_fuse_test.sh
+++ b/tools/testing/selftests/memfd/run_fuse_test.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 if test -d "./mnt" ; then
         fusermount -u ./mnt
diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh
new file mode 100755
index 000000000000..daabb350697c
--- /dev/null
+++ b/tools/testing/selftests/memfd/run_tests.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# please run as root
+
+#
+# Normal tests requiring no special resources
+#
+./run_fuse_test.sh
+./memfd_test
+
+#
+# To test memfd_create with hugetlbfs, there needs to be hpages_test
+# huge pages free.  Attempt to allocate enough pages to test.
+#
+hpages_test=8
+
+#
+# Get count of free huge pages from /proc/meminfo
+#
+while read name size unit; do
+        if [ "$name" = "HugePages_Free:" ]; then
+                freepgs=$size
+        fi
+done < /proc/meminfo
+
+#
+# If not enough free huge pages for test, attempt to increase
+#
+if [ -n "$freepgs" ] && [ $freepgs -lt $hpages_test ]; then
+        nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
+        hpages_needed=`expr $hpages_test - $freepgs`
+
+        echo 3 > /proc/sys/vm/drop_caches
+        echo $(( $hpages_needed + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
+        if [ $? -ne 0 ]; then
+                echo "Please run this test as root"
+                exit 1
+        fi
+        while read name size unit; do
+                if [ "$name" = "HugePages_Free:" ]; then
+                        freepgs=$size
+                fi
+        done < /proc/meminfo
+fi
+
+#
+# If still not enough huge pages available, exit.  But, give back any huge
+# pages potentially allocated above.
+#
+if [ $freepgs -lt $hpages_test ]; then
+        # nr_hugepgs non-zero only if we attempted to increase
+        if [ -n "$nr_hugepgs" ]; then
+                echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+        fi
+        printf "Not enough huge pages available (%d < %d)\n" \
+                $freepgs $needpgs
+        exit 1
+fi
+
+#
+# Run the hugetlbfs test
+#
+./memfd_test hugetlbfs
+
+#
+# Give back any huge pages allocated for the test
+#
+if [ -n "$nr_hugepgs" ]; then
+        echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+fi
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index afb2624c7048..86636d207adf 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -1,12 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 include ../lib.mk
 
 TEST_PROGS := mem-on-off-test.sh
-override RUN_TESTS := ./mem-on-off-test.sh -r 2 || echo "selftests: memory-hotplug [FAIL]"
+override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
 override EMIT_TESTS := echo "$(RUN_TESTS)"
 
 run_full_test:
-        @/bin/bash ./mem-on-off-test.sh || echo "memory-hotplug selftests: [FAIL]"
+        @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
 
 clean:
diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
index 35025ce9ca66..ae2c790d0880 100755
--- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
+++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 
 SYSFS=
 
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
index 9093d7ffe87f..e094f71c6dbc 100644
--- a/tools/testing/selftests/mount/Makefile
+++ b/tools/testing/selftests/mount/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for mount selftests.
 CFLAGS = -Wall \
          -O2
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
index 517785052f1c..584dc6bc3b06 100644
--- a/tools/testing/selftests/mount/unprivileged-remount-test.c
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <sched.h>
 #include <stdio.h>
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 79a664aeb8d7..743d3f9e5918 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CFLAGS += -O2
 LDLIBS = -lrt -lpthread -lpopt
 TEST_GEN_PROGS := mq_open_tests mq_perf_tests
@@ -5,8 +6,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests
 include ../lib.mk
 
 override define RUN_TESTS
-        @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
-        @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
+        @$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
+        @$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
 endef
 
 override define EMIT_TESTS
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index afe109e5508a..c612d6e38c62 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,3 +1,4 @@
+msg_zerocopy
 socket
 psock_fanout
 psock_tpacket
@@ -5,3 +6,4 @@ reuseport_bpf
 reuseport_bpf_cpu
 reuseport_bpf_numa
 reuseport_dualstack
+reuseaddr_conflict
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index f6c9dbf478f8..500c74db746c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -1,13 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for net selftests
 
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_GEN_FILES =  socket
-TEST_GEN_FILES += psock_fanout psock_tpacket
-TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_FILES += reuseport_dualstack
+TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
new file mode 100644
index 000000000000..3ab6ec403905
--- /dev/null
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -0,0 +1,697 @@
+/* Evaluate MSG_ZEROCOPY
+ *
+ * Send traffic between two processes over one of the supported
+ * protocols and modes:
+ *
+ * PF_INET/PF_INET6
+ * - SOCK_STREAM
+ * - SOCK_DGRAM
+ * - SOCK_DGRAM with UDP_CORK
+ * - SOCK_RAW
+ * - SOCK_RAW with IP_HDRINCL
+ *
+ * PF_PACKET
+ * - SOCK_DGRAM
+ * - SOCK_RAW
+ *
+ * Start this program on two connected hosts, one in send mode and
+ * the other with option '-r' to put it in receiver mode.
+ *
+ * If zerocopy mode ('-z') is enabled, the sender will verify that
+ * the kernel queues completions on the error queue for all zerocopy
+ * transfers.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#ifndef SO_EE_ORIGIN_ZEROCOPY
+#define SO_EE_ORIGIN_ZEROCOPY           5
+#endif
+
+#ifndef SO_ZEROCOPY
+#define SO_ZEROCOPY     60
+#endif
+
+#ifndef SO_EE_CODE_ZEROCOPY_COPIED
+#define SO_EE_CODE_ZEROCOPY_COPIED      1
+#endif
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY    0x4000000
+#endif
+
+static int  cfg_cork;
+static bool cfg_cork_mixed;
+static int  cfg_cpu             = -1;           /* default: pin to last cpu */
+static int  cfg_family          = PF_UNSPEC;
+static int  cfg_ifindex         = 1;
+static int  cfg_payload_len;
+static int  cfg_port            = 8000;
+static bool cfg_rx;
+static int  cfg_runtime_ms      = 4200;
+static int  cfg_verbose;
+static int  cfg_waittime_ms     = 500;
+static bool cfg_zerocopy;
+
+static socklen_t cfg_alen;
+static struct sockaddr_storage cfg_dst_addr;
+static struct sockaddr_storage cfg_src_addr;
+
+static char payload[IP_MAXPACKET];
+static long packets, bytes, completions, expected_completions;
+static int  zerocopied = -1;
+static uint32_t next_completion;
+
+static unsigned long gettimeofday_ms(void)
+{
+        struct timeval tv;
+
+        gettimeofday(&tv, NULL);
+        return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static uint16_t get_ip_csum(const uint16_t *start, int num_words)
+{
+        unsigned long sum = 0;
+        int i;
+
+        for (i = 0; i < num_words; i++)
+                sum += start[i];
+
+        while (sum >> 16)
+                sum = (sum & 0xFFFF) + (sum >> 16);
+
+        return ~sum;
+}
+
+static int do_setcpu(int cpu)
+{
+        cpu_set_t mask;
+
+        CPU_ZERO(&mask);
+        CPU_SET(cpu, &mask);
+        if (sched_setaffinity(0, sizeof(mask), &mask))
+                error(1, 0, "setaffinity %d", cpu);
+
+        if (cfg_verbose)
+                fprintf(stderr, "cpu: %u\n", cpu);
+
+        return 0;
+}
+
+static void do_setsockopt(int fd, int level, int optname, int val)
+{
+        if (setsockopt(fd, level, optname, &val, sizeof(val)))
+                error(1, errno, "setsockopt %d.%d: %d", level, optname, val);
+}
+
+static int do_poll(int fd, int events)
+{
+        struct pollfd pfd;
+        int ret;
+
+        pfd.events = events;
+        pfd.revents = 0;
+        pfd.fd = fd;
+
+        ret = poll(&pfd, 1, cfg_waittime_ms);
+        if (ret == -1)
+                error(1, errno, "poll");
+
+        return ret && (pfd.revents & events);
+}
+
+static int do_accept(int fd)
+{
+        int fda = fd;
+
+        fd = accept(fda, NULL, NULL);
+        if (fd == -1)
+                error(1, errno, "accept");
+        if (close(fda))
+                error(1, errno, "close listen sock");
+
+        return fd;
+}
+
+static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy)
+{
+        int ret, len, i, flags;
+
+        len = 0;
+        for (i = 0; i < msg->msg_iovlen; i++)
+                len += msg->msg_iov[i].iov_len;
+
+        flags = MSG_DONTWAIT;
+        if (do_zerocopy)
+                flags |= MSG_ZEROCOPY;
+
+        ret = sendmsg(fd, msg, flags);
+        if (ret == -1 && errno == EAGAIN)
+                return false;
+        if (ret == -1)
+                error(1, errno, "send");
+        if (cfg_verbose && ret != len)
+                fprintf(stderr, "send: ret=%u != %u\n", ret, len);
+
+        if (len) {
+                packets++;
+                bytes += ret;
+                if (do_zerocopy && ret)
+                        expected_completions++;
+        }
+
+        return true;
+}
+
+static void do_sendmsg_corked(int fd, struct msghdr *msg)
+{
+        bool do_zerocopy = cfg_zerocopy;
+        int i, payload_len, extra_len;
+
+        /* split up the packet. for non-multiple, make first buffer longer */
+        payload_len = cfg_payload_len / cfg_cork;
+        extra_len = cfg_payload_len - (cfg_cork * payload_len);
+
+        do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 1);
+
+        for (i = 0; i < cfg_cork; i++) {
+
+                /* in mixed-frags mode, alternate zerocopy and copy frags
+                 * start with non-zerocopy, to ensure attach later works
+                 */
+                if (cfg_cork_mixed)
+                        do_zerocopy = (i & 1);
+
+                msg->msg_iov[0].iov_len = payload_len + extra_len;
+                extra_len = 0;
+
+                do_sendmsg(fd, msg, do_zerocopy);
+        }
+
+        do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0);
+}
+
+static int setup_iph(struct iphdr *iph, uint16_t payload_len)
+{
+        struct sockaddr_in *daddr = (void *) &cfg_dst_addr;
+        struct sockaddr_in *saddr = (void *) &cfg_src_addr;
+
+        memset(iph, 0, sizeof(*iph));
+
+        iph->version    = 4;
+        iph->tos        = 0;
+        iph->ihl        = 5;
+        iph->ttl        = 2;
+        iph->saddr      = saddr->sin_addr.s_addr;
+        iph->daddr      = daddr->sin_addr.s_addr;
+        iph->protocol   = IPPROTO_EGP;
+        iph->tot_len    = htons(sizeof(*iph) + payload_len);
+        iph->check      = get_ip_csum((void *) iph, iph->ihl << 1);
+
+        return sizeof(*iph);
+}
+
+static int setup_ip6h(struct ipv6hdr *ip6h, uint16_t payload_len)
+{
+        struct sockaddr_in6 *daddr = (void *) &cfg_dst_addr;
+        struct sockaddr_in6 *saddr = (void *) &cfg_src_addr;
+
+        memset(ip6h, 0, sizeof(*ip6h));
+
+        ip6h->version           = 6;
+        ip6h->payload_len       = htons(payload_len);
+        ip6h->nexthdr           = IPPROTO_EGP;
+        ip6h->hop_limit         = 2;
+        ip6h->saddr             = saddr->sin6_addr;
+        ip6h->daddr             = daddr->sin6_addr;
+
+        return sizeof(*ip6h);
+}
+
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+        struct sockaddr_in6 *addr6 = (void *) sockaddr;
+        struct sockaddr_in *addr4 = (void *) sockaddr;
+
+        switch (domain) {
+        case PF_INET:
+                addr4->sin_family = AF_INET;
+                addr4->sin_port = htons(cfg_port);
+                if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+                        error(1, 0, "ipv4 parse error: %s", str_addr);
+                break;
+        case PF_INET6:
+                addr6->sin6_family = AF_INET6;
+                addr6->sin6_port = htons(cfg_port);
+                if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+                        error(1, 0, "ipv6 parse error: %s", str_addr);
+                break;
+        default:
+                error(1, 0, "illegal domain");
+        }
+}
+
+static int do_setup_tx(int domain, int type, int protocol)
+{
+        int fd;
+
+        fd = socket(domain, type, protocol);
+        if (fd == -1)
+                error(1, errno, "socket t");
+
+        do_setsockopt(fd, SOL_SOCKET, SO_SNDBUF, 1 << 21);
+        if (cfg_zerocopy)
+                do_setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, 1);
+
+        if (domain != PF_PACKET)
+                if (connect(fd, (void *) &cfg_dst_addr, cfg_alen))
+                        error(1, errno, "connect");
+
+        return fd;
+}
+
+static bool do_recv_completion(int fd)
+{
+        struct sock_extended_err *serr;
+        struct msghdr msg = {};
+        struct cmsghdr *cm;
+        uint32_t hi, lo, range;
+        int ret, zerocopy;
+        char control[100];
+
+        msg.msg_control = control;
+        msg.msg_controllen = sizeof(control);
+
+        ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+        if (ret == -1 && errno == EAGAIN)
+                return false;
+        if (ret == -1)
+                error(1, errno, "recvmsg notification");
+        if (msg.msg_flags & MSG_CTRUNC)
+                error(1, errno, "recvmsg notification: truncated");
+
+        cm = CMSG_FIRSTHDR(&msg);
+        if (!cm)
+                error(1, 0, "cmsg: no cmsg");
+        if (!((cm->cmsg_level == SOL_IP && cm->cmsg_type == IP_RECVERR) ||
+              (cm->cmsg_level == SOL_IPV6 && cm->cmsg_type == IPV6_RECVERR) ||
+              (cm->cmsg_level == SOL_PACKET && cm->cmsg_type == PACKET_TX_TIMESTAMP)))
+                error(1, 0, "serr: wrong type: %d.%d",
+                      cm->cmsg_level, cm->cmsg_type);
+
+        serr = (void *) CMSG_DATA(cm);
+        if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY)
+                error(1, 0, "serr: wrong origin: %u", serr->ee_origin);
+        if (serr->ee_errno != 0)
+                error(1, 0, "serr: wrong error code: %u", serr->ee_errno);
+
+        hi = serr->ee_data;
+        lo = serr->ee_info;
+        range = hi - lo + 1;
+
+        /* Detect notification gaps. These should not happen often, if at all.
+         * Gaps can occur due to drops, reordering and retransmissions.
+         */
+        if (lo != next_completion)
+                fprintf(stderr, "gap: %u..%u does not append to %u\n",
+                        lo, hi, next_completion);
+        next_completion = hi + 1;
+
+        zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED);
+        if (zerocopied == -1)
+                zerocopied = zerocopy;
+        else if (zerocopied != zerocopy) {
+                fprintf(stderr, "serr: inconsistent\n");
+                zerocopied = zerocopy;
+        }
+
+        if (cfg_verbose >= 2)
+                fprintf(stderr, "completed: %u (h=%u l=%u)\n",
+                        range, hi, lo);
+
+        completions += range;
+        return true;
+}
+
+/* Read all outstanding messages on the errqueue */
+static void do_recv_completions(int fd)
+{
+        while (do_recv_completion(fd)) {}
+}
+
+/* Wait for all remaining completions on the errqueue */
+static void do_recv_remaining_completions(int fd)
+{
+        int64_t tstop = gettimeofday_ms() + cfg_waittime_ms;
+
+        while (completions < expected_completions &&
+               gettimeofday_ms() < tstop) {
+                if (do_poll(fd, POLLERR))
+                        do_recv_completions(fd);
+        }
+
+        if (completions < expected_completions)
+                fprintf(stderr, "missing notifications: %lu < %lu\n",
+                        completions, expected_completions);
+}
+
+static void do_tx(int domain, int type, int protocol)
+{
+        struct iovec iov[3] = { {0} };
+        struct sockaddr_ll laddr;
+        struct msghdr msg = {0};
+        struct ethhdr eth;
+        union {
+                struct ipv6hdr ip6h;
+                struct iphdr iph;
+        } nh;
+        uint64_t tstop;
+        int fd;
+
+        fd = do_setup_tx(domain, type, protocol);
+
+        if (domain == PF_PACKET) {
+                uint16_t proto = cfg_family == PF_INET ? ETH_P_IP : ETH_P_IPV6;
+
+                /* sock_raw passes ll header as data */
+                if (type == SOCK_RAW) {
+                        memset(eth.h_dest, 0x06, ETH_ALEN);
+                        memset(eth.h_source, 0x02, ETH_ALEN);
+                        eth.h_proto = htons(proto);
+                        iov[0].iov_base = &eth;
+                        iov[0].iov_len = sizeof(eth);
+                        msg.msg_iovlen++;
+                }
+
+                /* both sock_raw and sock_dgram expect name */
+                memset(&laddr, 0, sizeof(laddr));
+                laddr.sll_family        = AF_PACKET;
+                laddr.sll_ifindex       = cfg_ifindex;
+                laddr.sll_protocol      = htons(proto);
+                laddr.sll_halen         = ETH_ALEN;
+
+                memset(laddr.sll_addr, 0x06, ETH_ALEN);
+
+                msg.msg_name            = &laddr;
+                msg.msg_namelen         = sizeof(laddr);
+        }
+
+        /* packet and raw sockets with hdrincl must pass network header */
+        if (domain == PF_PACKET || protocol == IPPROTO_RAW) {
+                if (cfg_family == PF_INET)
+                        iov[1].iov_len = setup_iph(&nh.iph, cfg_payload_len);
+                else
+                        iov[1].iov_len = setup_ip6h(&nh.ip6h, cfg_payload_len);
+
+                iov[1].iov_base = (void *) &nh;
+                msg.msg_iovlen++;
+        }
+
+        iov[2].iov_base = payload;
+        iov[2].iov_len = cfg_payload_len;
+        msg.msg_iovlen++;
+        msg.msg_iov = &iov[3 - msg.msg_iovlen];
+
+        tstop = gettimeofday_ms() + cfg_runtime_ms;
+        do {
+                if (cfg_cork)
+                        do_sendmsg_corked(fd, &msg);
+                else
+                        do_sendmsg(fd, &msg, cfg_zerocopy);
+
+                while (!do_poll(fd, POLLOUT)) {
+                        if (cfg_zerocopy)
+                                do_recv_completions(fd);
+                }
+
+        } while (gettimeofday_ms() < tstop);
+
+        if (cfg_zerocopy)
+                do_recv_remaining_completions(fd);
+
+        if (close(fd))
+                error(1, errno, "close");
+
+        fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n",
+                packets, bytes >> 20, completions,
+                zerocopied == 1 ? 'y' : 'n');
+}
+
+static int do_setup_rx(int domain, int type, int protocol)
+{
+        int fd;
+
+        /* If tx over PF_PACKET, rx over PF_INET(6)/SOCK_RAW,
+         * to recv the only copy of the packet, not a clone
+         */
+        if (domain == PF_PACKET)
+                error(1, 0, "Use PF_INET/SOCK_RAW to read");
+
+        if (type == SOCK_RAW && protocol == IPPROTO_RAW)
+                error(1, 0, "IPPROTO_RAW: not supported on Rx");
+
+        fd = socket(domain, type, protocol);
+        if (fd == -1)
+                error(1, errno, "socket r");
+
+        do_setsockopt(fd, SOL_SOCKET, SO_RCVBUF, 1 << 21);
+        do_setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, 1 << 16);
+        do_setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, 1);
+
+        if (bind(fd, (void *) &cfg_dst_addr, cfg_alen))
+                error(1, errno, "bind");
+
+        if (type == SOCK_STREAM) {
+                if (listen(fd, 1))
+                        error(1, errno, "listen");
+                fd = do_accept(fd);
+        }
+
+        return fd;
+}
+
+/* Flush all outstanding bytes for the tcp receive queue */
+static void do_flush_tcp(int fd)
+{
+        int ret;
+
+        /* MSG_TRUNC flushes up to len bytes */
+        ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT);
+        if (ret == -1 && errno == EAGAIN)
+                return;
+        if (ret == -1)
+                error(1, errno, "flush");
+        if (!ret)
+                return;
+
+        packets++;
+        bytes += ret;
+}
+
+/* Flush all outstanding datagrams. Verify first few bytes of each. */
+static void do_flush_datagram(int fd, int type)
+{
+        int ret, off = 0;
+        char buf[64];
+
+        /* MSG_TRUNC will return full datagram length */
+        ret = recv(fd, buf, sizeof(buf), MSG_DONTWAIT | MSG_TRUNC);
+        if (ret == -1 && errno == EAGAIN)
+                return;
+
+        /* raw ipv4 return with header, raw ipv6 without */
+        if (cfg_family == PF_INET && type == SOCK_RAW) {
+                off += sizeof(struct iphdr);
+                ret -= sizeof(struct iphdr);
+        }
+
+        if (ret == -1)
+                error(1, errno, "recv");
+        if (ret != cfg_payload_len)
+                error(1, 0, "recv: ret=%u != %u", ret, cfg_payload_len);
+        if (ret > sizeof(buf) - off)
+                ret = sizeof(buf) - off;
+        if (memcmp(buf + off, payload, ret))
+                error(1, 0, "recv: data mismatch");
+
+        packets++;
+        bytes += cfg_payload_len;
+}
+
+static void do_rx(int domain, int type, int protocol)
+{
+        uint64_t tstop;
+        int fd;
+
+        fd = do_setup_rx(domain, type, protocol);
+
+        tstop = gettimeofday_ms() + cfg_runtime_ms;
+        do {
+                if (type == SOCK_STREAM)
+                        do_flush_tcp(fd);
+                else
+                        do_flush_datagram(fd, type);
+
+                do_poll(fd, POLLIN);
+
+        } while (gettimeofday_ms() < tstop);
+
+        if (close(fd))
+                error(1, errno, "close");
+
+        fprintf(stderr, "rx=%lu (%lu MB)\n", packets, bytes >> 20);
+}
+
+static void do_test(int domain, int type, int protocol)
+{
+        int i;
+
+        if (cfg_cork && (domain == PF_PACKET || type != SOCK_DGRAM))
+                error(1, 0, "can only cork udp sockets");
+
+        do_setcpu(cfg_cpu);
+
+        for (i = 0; i < IP_MAXPACKET; i++)
+                payload[i] = 'a' + (i % 26);
+
+        if (cfg_rx)
+                do_rx(domain, type, protocol);
+        else
+                do_tx(domain, type, protocol);
+}
+
+static void usage(const char *filepath)
+{
+        error(1, 0, "Usage: %s [options] <test>", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+        const int max_payload_len = sizeof(payload) -
+                                    sizeof(struct ipv6hdr) -
+                                    sizeof(struct tcphdr) -
+                                    40 /* max tcp options */;
+        int c;
+
+        cfg_payload_len = max_payload_len;
+
+        while ((c = getopt(argc, argv, "46c:C:D:i:mp:rs:S:t:vz")) != -1) {
+                switch (c) {
+                case '4':
+                        if (cfg_family != PF_UNSPEC)
+                                error(1, 0, "Pass one of -4 or -6");
+                        cfg_family = PF_INET;
+                        cfg_alen = sizeof(struct sockaddr_in);
+                        break;
+                case '6':
+                        if (cfg_family != PF_UNSPEC)
+                                error(1, 0, "Pass one of -4 or -6");
+                        cfg_family = PF_INET6;
+                        cfg_alen = sizeof(struct sockaddr_in6);
+                        break;
+                case 'c':
+                        cfg_cork = strtol(optarg, NULL, 0);
+                        break;
+                case 'C':
+                        cfg_cpu = strtol(optarg, NULL, 0);
+                        break;
+                case 'D':
+                        setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+                        break;
+                case 'i':
+                        cfg_ifindex = if_nametoindex(optarg);
+                        if (cfg_ifindex == 0)
+                                error(1, errno, "invalid iface: %s", optarg);
+                        break;
+                case 'm':
+                        cfg_cork_mixed = true;
+                        break;
+                case 'p':
+                        cfg_port = htons(strtoul(optarg, NULL, 0));
+                        break;
+                case 'r':
+                        cfg_rx = true;
+                        break;
+                case 's':
+                        cfg_payload_len = strtoul(optarg, NULL, 0);
+                        break;
+                case 'S':
+                        setup_sockaddr(cfg_family, optarg, &cfg_src_addr);
+                        break;
+                case 't':
+                        cfg_runtime_ms = 200 + strtoul(optarg, NULL, 10) * 1000;
+                        break;
+                case 'v':
+                        cfg_verbose++;
+                        break;
+                case 'z':
+                        cfg_zerocopy = true;
+                        break;
+                }
+        }
+
+        if (cfg_payload_len > max_payload_len)
+                error(1, 0, "-s: payload exceeds max (%d)", max_payload_len);
+        if (cfg_cork_mixed && (!cfg_zerocopy || !cfg_cork))
+                error(1, 0, "-m: cork_mixed requires corking and zerocopy");
+
+        if (optind != argc - 1)
+                usage(argv[0]);
+}
+
+int main(int argc, char **argv)
+{
+        const char *cfg_test;
+
+        parse_opts(argc, argv);
+
+        cfg_test = argv[argc - 1];
+
+        if (!strcmp(cfg_test, "packet"))
+                do_test(PF_PACKET, SOCK_RAW, 0);
+        else if (!strcmp(cfg_test, "packet_dgram"))
+                do_test(PF_PACKET, SOCK_DGRAM, 0);
+        else if (!strcmp(cfg_test, "raw"))
+                do_test(cfg_family, SOCK_RAW, IPPROTO_EGP);
+        else if (!strcmp(cfg_test, "raw_hdrincl"))
+                do_test(cfg_family, SOCK_RAW, IPPROTO_RAW);
+        else if (!strcmp(cfg_test, "tcp"))
+                do_test(cfg_family, SOCK_STREAM, 0);
+        else if (!strcmp(cfg_test, "udp"))
+                do_test(cfg_family, SOCK_DGRAM, 0);
+        else
+                error(1, 0, "unknown cfg_test %s", cfg_test);
+
+        return 0;
+}
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
new file mode 100755
index 000000000000..d571d213418d
--- /dev/null
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+#
+# Send data between two processes across namespaces
+# Run twice: once without and once with zerocopy
+
+set -e
+
+readonly DEV="veth0"
+readonly DEV_MTU=65535
+readonly BIN="./msg_zerocopy"
+
+readonly RAND="$(mktemp -u XXXXXX)"
+readonly NSPREFIX="ns-${RAND}"
+readonly NS1="${NSPREFIX}1"
+readonly NS2="${NSPREFIX}2"
+
+readonly SADDR4='192.168.1.1'
+readonly DADDR4='192.168.1.2'
+readonly SADDR6='fd::1'
+readonly DADDR6='fd::2'
+
+readonly path_sysctl_mem="net.core.optmem_max"
+
+# Argument parsing
+if [[ "$#" -lt "2" ]]; then
+        echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>"
+        exit 1
+fi
+
+readonly IP="$1"
+shift
+readonly TXMODE="$1"
+shift
+readonly EXTRA_ARGS="$@"
+
+# Argument parsing: configure addresses
+if [[ "${IP}" == "4" ]]; then
+        readonly SADDR="${SADDR4}"
+        readonly DADDR="${DADDR4}"
+elif [[ "${IP}" == "6" ]]; then
+        readonly SADDR="${SADDR6}"
+        readonly DADDR="${DADDR6}"
+else
+        echo "Invalid IP version ${IP}"
+        exit 1
+fi
+
+# Argument parsing: select receive mode
+#
+# This differs from send mode for
+# - packet:     use raw recv, because packet receives skb clones
+# - raw_hdrinc: use raw recv, because hdrincl is a tx-only option
+case "${TXMODE}" in
+'packet' | 'packet_dgram' | 'raw_hdrincl')
+        RXMODE='raw'
+        ;;
+*)
+        RXMODE="${TXMODE}"
+        ;;
+esac
+
+# Start of state changes: install cleanup handler
+save_sysctl_mem="$(sysctl -n ${path_sysctl_mem})"
+
+cleanup() {
+        ip netns del "${NS2}"
+        ip netns del "${NS1}"
+        sysctl -w -q "${path_sysctl_mem}=${save_sysctl_mem}"
+}
+
+trap cleanup EXIT
+
+# Configure system settings
+sysctl -w -q "${path_sysctl_mem}=1000000"
+
+# Create virtual ethernet pair between network namespaces
+ip netns add "${NS1}"
+ip netns add "${NS2}"
+
+ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \
+  peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}"
+
+# Bring the devices up
+ip -netns "${NS1}" link set "${DEV}" up
+ip -netns "${NS2}" link set "${DEV}" up
+
+# Set fixed MAC addresses on the devices
+ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02
+ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06
+
+# Add fixed IP addresses to the devices
+ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}"
+ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
+ip -netns "${NS1}" addr add       fd::1/64 dev "${DEV}" nodad
+ip -netns "${NS2}" addr add       fd::2/64 dev "${DEV}" nodad
+
+# Optionally disable sg or csum offload to test edge cases
+# ip netns exec "${NS1}" ethtool -K "${DEV}" sg off
+
+do_test() {
+        local readonly ARGS="$1"
+
+        echo "ipv${IP} ${TXMODE} ${ARGS}"
+        ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" &
+        sleep 0.2
+        ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}"
+        wait
+}
+
+do_test "${EXTRA_ARGS}"
+do_test "-z ${EXTRA_ARGS}"
+echo ok
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index 4e00568d70c2..903679e0ff31 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 #
 # This test is for checking network interface
 # For the moment it tests only ethernet interface (but wifi could be easily added)
@@ -178,7 +179,7 @@ if [ "$(id -u)" -ne 0 ];then
         exit 0
 fi
 
-ip -Version 2>/dev/null >/dev/null
+ip link show 2>/dev/null >/dev/null
 if [ $? -ne 0 ];then
         echo "SKIP: Could not run test without the ip tool"
         exit 0
diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c
new file mode 100644
index 000000000000..7c5b12664b03
--- /dev/null
+++ b/tools/testing/selftests/net/reuseaddr_conflict.c
@@ -0,0 +1,114 @@
+/*
+ * Test for the regression introduced by
+ *
+ * b9470c27607b ("inet: kill smallest_size and smallest_port")
+ *
+ * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb
+ * when we open the ipv6 conterpart, which is what was happening previously.
+ */
+#include <errno.h>
+#include <error.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define PORT 9999
+
+int open_port(int ipv6, int any)
+{
+        int fd = -1;
+        int reuseaddr = 1;
+        int v6only = 1;
+        int addrlen;
+        int ret = -1;
+        struct sockaddr *addr;
+        int family = ipv6 ? AF_INET6 : AF_INET;
+
+        struct sockaddr_in6 addr6 = {
+                .sin6_family = AF_INET6,
+                .sin6_port = htons(PORT),
+                .sin6_addr = in6addr_any
+        };
+        struct sockaddr_in addr4 = {
+                .sin_family = AF_INET,
+                .sin_port = htons(PORT),
+                .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"),
+        };
+
+
+        if (ipv6) {
+                addr = (struct sockaddr*)&addr6;
+                addrlen = sizeof(addr6);
+        } else {
+                addr = (struct sockaddr*)&addr4;
+                addrlen = sizeof(addr4);
+        }
+
+        if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) {
+                perror("socket");
+                goto out;
+        }
+
+        if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only,
+                               sizeof(v6only)) < 0) {
+                perror("setsockopt IPV6_V6ONLY");
+                goto out;
+        }
+
+        if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr,
+                       sizeof(reuseaddr)) < 0) {
+                perror("setsockopt SO_REUSEADDR");
+                goto out;
+        }
+
+        if (bind(fd, addr, addrlen) < 0) {
+                perror("bind");
+                goto out;
+        }
+
+        if (any)
+                return fd;
+
+        if (listen(fd, 1) < 0) {
+                perror("listen");
+                goto out;
+        }
+        return fd;
+out:
+        close(fd);
+        return ret;
+}
+
+int main(void)
+{
+        int listenfd;
+        int fd1, fd2;
+
+        fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT);
+        listenfd = open_port(0, 0);
+        if (listenfd < 0)
+                error(1, errno, "Couldn't open listen socket");
+        fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+        fd1 = open_port(0, 1);
+        if (fd1 >= 0)
+                error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+        fprintf(stderr, "Opening in6addr_any:%d\n", PORT);
+        fd1 = open_port(1, 1);
+        if (fd1 < 0)
+                error(1, errno, "Couldn't open ipv6 reuseport");
+        fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+        fd2 = open_port(0, 1);
+        if (fd2 >= 0)
+                error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+        close(fd1);
+        fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT);
+        fd1 = open_port(0, 1);
+        if (fd1 >= 0)
+                error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6");
+        fprintf(stderr, "Success");
+        return 0;
+}
diff --git a/tools/testing/selftests/net/reuseport_bpf_cpu.c b/tools/testing/selftests/net/reuseport_bpf_cpu.c
index b23d6f54de7b..2d646174729f 100644
--- a/tools/testing/selftests/net/reuseport_bpf_cpu.c
+++ b/tools/testing/selftests/net/reuseport_bpf_cpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Test functionality of BPF filters with SO_REUSEPORT.  This program creates
  * an SO_REUSEPORT receiver group containing one socket per CPU core. It then
diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c
index 6f20bc9ff627..365c32e84189 100644
--- a/tools/testing/selftests/net/reuseport_bpf_numa.c
+++ b/tools/testing/selftests/net/reuseport_bpf_numa.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Test functionality of BPF filters with SO_REUSEPORT. Same test as
  * in reuseport_bpf_cpu, only as one socket per NUMA node.
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
index 90958aaaafb9..fe3230c55986 100644
--- a/tools/testing/selftests/net/reuseport_dualstack.c
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * It is possible to use SO_REUSEPORT to open multiple sockets bound to
  * equivalent local addresses using AF_INET and AF_INET6 at the same time.  If
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
new file mode 100755
index 000000000000..5215493166c9
--- /dev/null
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -0,0 +1,543 @@
+#!/bin/sh
+#
+# This test is for checking rtnetlink callpaths, and get as much coverage as possible.
+#
+# set -e
+
+devdummy="test-dummy0"
+ret=0
+
+# set global exit status, but never reset nonzero one.
+check_err()
+{
+        if [ $ret -eq 0 ]; then
+                ret=$1
+        fi
+}
+
+# same but inverted -- used when command must fail for test to pass
+check_fail()
+{
+        if [ $1 -eq 0 ]; then
+                ret=1
+        fi
+}
+
+kci_add_dummy()
+{
+        ip link add name "$devdummy" type dummy
+        check_err $?
+        ip link set "$devdummy" up
+        check_err $?
+}
+
+kci_del_dummy()
+{
+        ip link del dev "$devdummy"
+        check_err $?
+}
+
+kci_test_netconf()
+{
+        dev="$1"
+        r=$ret
+
+        ip netconf show dev "$dev" > /dev/null
+        check_err $?
+
+        for f in 4 6; do
+                ip -$f netconf show dev "$dev" > /dev/null
+                check_err $?
+        done
+
+        if [ $ret -ne 0 ] ;then
+                echo "FAIL: ip netconf show $dev"
+                test $r -eq 0 && ret=0
+                return 1
+        fi
+}
+
+# add a bridge with vlans on top
+kci_test_bridge()
+{
+        devbr="test-br0"
+        vlandev="testbr-vlan1"
+
+        ret=0
+        ip link add name "$devbr" type bridge
+        check_err $?
+
+        ip link set dev "$devdummy" master "$devbr"
+        check_err $?
+
+        ip link set "$devbr" up
+        check_err $?
+
+        ip link add link "$devbr" name "$vlandev" type vlan id 1
+        check_err $?
+        ip addr add dev "$vlandev" 10.200.7.23/30
+        check_err $?
+        ip -6 addr add dev "$vlandev" dead:42::1234/64
+        check_err $?
+        ip -d link > /dev/null
+        check_err $?
+        ip r s t all > /dev/null
+        check_err $?
+
+        for name in "$devbr" "$vlandev" "$devdummy" ; do
+                kci_test_netconf "$name"
+        done
+
+        ip -6 addr del dev "$vlandev" dead:42::1234/64
+        check_err $?
+
+        ip link del dev "$vlandev"
+        check_err $?
+        ip link del dev "$devbr"
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: bridge setup"
+                return 1
+        fi
+        echo "PASS: bridge setup"
+
+}
+
+kci_test_gre()
+{
+        gredev=neta
+        rem=10.42.42.1
+        loc=10.0.0.1
+
+        ret=0
+        ip tunnel add $gredev mode gre remote $rem local $loc ttl 1
+        check_err $?
+        ip link set $gredev up
+        check_err $?
+        ip addr add 10.23.7.10 dev $gredev
+        check_err $?
+        ip route add 10.23.8.0/30 dev $gredev
+        check_err $?
+        ip addr add dev "$devdummy" 10.23.7.11/24
+        check_err $?
+        ip link > /dev/null
+        check_err $?
+        ip addr > /dev/null
+        check_err $?
+
+        kci_test_netconf "$gredev"
+
+        ip addr del dev "$devdummy" 10.23.7.11/24
+        check_err $?
+
+        ip link del $gredev
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: gre tunnel endpoint"
+                return 1
+        fi
+        echo "PASS: gre tunnel endpoint"
+}
+
+# tc uses rtnetlink too, for full tc testing
+# please see tools/testing/selftests/tc-testing.
+kci_test_tc()
+{
+        dev=lo
+        ret=0
+
+        tc qdisc add dev "$dev" root handle 1: htb
+        check_err $?
+        tc class add dev "$dev" parent 1: classid 1:10 htb rate 1mbit
+        check_err $?
+        tc filter add dev "$dev" parent 1:0 prio 5 handle ffe: protocol ip u32 divisor 256
+        check_err $?
+        tc filter add dev "$dev" parent 1:0 prio 5 handle ffd: protocol ip u32 divisor 256
+        check_err $?
+        tc filter add dev "$dev" parent 1:0 prio 5 handle ffc: protocol ip u32 divisor 256
+        check_err $?
+        tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 ht ffe:2: match ip src 10.0.0.3 flowid 1:10
+        check_err $?
+        tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:2 u32 ht ffe:2: match ip src 10.0.0.2 flowid 1:10
+        check_err $?
+        tc filter show dev "$dev" parent  1:0 > /dev/null
+        check_err $?
+        tc filter del dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32
+        check_err $?
+        tc filter show dev "$dev" parent  1:0 > /dev/null
+        check_err $?
+        tc qdisc del dev "$dev" root handle 1: htb
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: tc htb hierarchy"
+                return 1
+        fi
+        echo "PASS: tc htb hierarchy"
+
+}
+
+kci_test_polrouting()
+{
+        ret=0
+        ip rule add fwmark 1 lookup 100
+        check_err $?
+        ip route add local 0.0.0.0/0 dev lo table 100
+        check_err $?
+        ip r s t all > /dev/null
+        check_err $?
+        ip rule del fwmark 1 lookup 100
+        check_err $?
+        ip route del local 0.0.0.0/0 dev lo table 100
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: policy route test"
+                return 1
+        fi
+        echo "PASS: policy routing"
+}
+
+kci_test_route_get()
+{
+        ret=0
+
+        ip route get 127.0.0.1 > /dev/null
+        check_err $?
+        ip route get 127.0.0.1 dev "$devdummy" > /dev/null
+        check_err $?
+        ip route get ::1 > /dev/null
+        check_err $?
+        ip route get fe80::1 dev "$devdummy" > /dev/null
+        check_err $?
+        ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null
+        check_err $?
+        ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null
+        check_err $?
+        ip addr add dev "$devdummy" 10.23.7.11/24
+        check_err $?
+        ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy" > /dev/null
+        check_err $?
+        ip addr del dev "$devdummy" 10.23.7.11/24
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: route get"
+                return 1
+        fi
+
+        echo "PASS: route get"
+}
+
+kci_test_addrlabel()
+{
+        ret=0
+
+        ip addrlabel add prefix dead::/64 dev lo label 1
+        check_err $?
+
+        ip addrlabel list |grep -q "prefix dead::/64 dev lo label 1"
+        check_err $?
+
+        ip addrlabel del prefix dead::/64 dev lo label 1 2> /dev/null
+        check_err $?
+
+        ip addrlabel add prefix dead::/64 label 1 2> /dev/null
+        check_err $?
+
+        ip addrlabel del prefix dead::/64 label 1 2> /dev/null
+        check_err $?
+
+        # concurrent add/delete
+        for i in $(seq 1 1000); do
+                ip addrlabel add prefix 1c3::/64 label 12345 2>/dev/null
+        done &
+
+        for i in $(seq 1 1000); do
+                ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null
+        done
+
+        wait
+
+        ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: ipv6 addrlabel"
+                return 1
+        fi
+
+        echo "PASS: ipv6 addrlabel"
+}
+
+kci_test_ifalias()
+{
+        ret=0
+        namewant=$(uuidgen)
+        syspathname="/sys/class/net/$devdummy/ifalias"
+
+        ip link set dev "$devdummy" alias "$namewant"
+        check_err $?
+
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: cannot set interface alias of $devdummy to $namewant"
+                return 1
+        fi
+
+        ip link show "$devdummy" | grep -q "alias $namewant"
+        check_err $?
+
+        if [ -r "$syspathname" ] ; then
+                read namehave < "$syspathname"
+                if [ "$namewant" != "$namehave" ]; then
+                        echo "FAIL: did set ifalias $namewant but got $namehave"
+                        return 1
+                fi
+
+                namewant=$(uuidgen)
+                echo "$namewant" > "$syspathname"
+                ip link show "$devdummy" | grep -q "alias $namewant"
+                check_err $?
+
+                # sysfs interface allows to delete alias again
+                echo "" > "$syspathname"
+
+                ip link show "$devdummy" | grep -q "alias $namewant"
+                check_fail $?
+
+                for i in $(seq 1 100); do
+                        uuidgen > "$syspathname" &
+                done
+
+                wait
+
+                # re-add the alias -- kernel should free mem when dummy dev is removed
+                ip link set dev "$devdummy" alias "$namewant"
+                check_err $?
+        fi
+
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: set interface alias $devdummy to $namewant"
+                return 1
+        fi
+
+        echo "PASS: set ifalias $namewant for $devdummy"
+}
+
+kci_test_vrf()
+{
+        vrfname="test-vrf"
+        ret=0
+
+        ip link show type vrf 2>/dev/null
+        if [ $? -ne 0 ]; then
+                echo "SKIP: vrf: iproute2 too old"
+                return 0
+        fi
+
+        ip link add "$vrfname" type vrf table 10
+        check_err $?
+        if [ $ret -ne 0 ];then
+                echo "FAIL: can't add vrf interface, skipping test"
+                return 0
+        fi
+
+        ip -br link show type vrf | grep -q "$vrfname"
+        check_err $?
+        if [ $ret -ne 0 ];then
+                echo "FAIL: created vrf device not found"
+                return 1
+        fi
+
+        ip link set dev "$vrfname" up
+        check_err $?
+
+        ip link set dev "$devdummy" master "$vrfname"
+        check_err $?
+        ip link del dev "$vrfname"
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: vrf"
+                return 1
+        fi
+
+        echo "PASS: vrf"
+}
+
+kci_test_encap_vxlan()
+{
+        ret=0
+        vxlan="test-vxlan0"
+        vlan="test-vlan0"
+        testns="$1"
+
+        ip netns exec "$testns" ip link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
+                dev "$devdummy" dstport 4789 2>/dev/null
+        if [ $? -ne 0 ]; then
+                echo "FAIL: can't add vxlan interface, skipping test"
+                return 0
+        fi
+        check_err $?
+
+        ip netns exec "$testns" ip addr add 10.2.11.49/24 dev "$vxlan"
+        check_err $?
+
+        ip netns exec "$testns" ip link set up dev "$vxlan"
+        check_err $?
+
+        ip netns exec "$testns" ip link add link "$vxlan" name "$vlan" type vlan id 1
+        check_err $?
+
+        ip netns exec "$testns" ip link del "$vxlan"
+        check_err $?
+
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: vxlan"
+                return 1
+        fi
+        echo "PASS: vxlan"
+}
+
+kci_test_encap_fou()
+{
+        ret=0
+        name="test-fou"
+        testns="$1"
+
+        ip fou help 2>&1 |grep -q 'Usage: ip fou'
+        if [ $? -ne 0 ];then
+                echo "SKIP: fou: iproute2 too old"
+                return 1
+        fi
+
+        ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null
+        if [ $? -ne 0 ];then
+                echo "FAIL: can't add fou port 7777, skipping test"
+                return 1
+        fi
+
+        ip netns exec "$testns" ip fou add port 8888 ipproto 4
+        check_err $?
+
+        ip netns exec "$testns" ip fou del port 9999 2>/dev/null
+        check_fail $?
+
+        ip netns exec "$testns" ip fou del port 7777
+        check_err $?
+
+        if [ $ret -ne 0 ]; then
+                echo "FAIL: fou"
+                return 1
+        fi
+
+        echo "PASS: fou"
+}
+
+# test various encap methods, use netns to avoid unwanted interference
+kci_test_encap()
+{
+        testns="testns"
+        ret=0
+
+        ip netns add "$testns"
+        if [ $? -ne 0 ]; then
+                echo "SKIP encap tests: cannot add net namespace $testns"
+                return 1
+        fi
+
+        ip netns exec "$testns" ip link set lo up
+        check_err $?
+
+        ip netns exec "$testns" ip link add name "$devdummy" type dummy
+        check_err $?
+        ip netns exec "$testns" ip link set "$devdummy" up
+        check_err $?
+
+        kci_test_encap_vxlan "$testns"
+        kci_test_encap_fou "$testns"
+
+        ip netns del "$testns"
+}
+
+kci_test_macsec()
+{
+        msname="test_macsec0"
+        ret=0
+
+        ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
+        if [ $? -ne 0 ]; then
+                echo "SKIP: macsec: iproute2 too old"
+                return 0
+        fi
+
+        ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
+        check_err $?
+        if [ $ret -ne 0 ];then
+                echo "FAIL: can't add macsec interface, skipping test"
+                return 1
+        fi
+
+        ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+        check_err $?
+
+        ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef"
+        check_err $?
+
+        ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef
+        check_err $?
+
+        ip macsec show > /dev/null
+        check_err $?
+
+        ip link del dev "$msname"
+        check_err $?
+
+        if [ $ret -ne 0 ];then
+                echo "FAIL: macsec"
+                return 1
+        fi
+
+        echo "PASS: macsec"
+}
+
+kci_test_rtnl()
+{
+        kci_add_dummy
+        if [ $ret -ne 0 ];then
+                echo "FAIL: cannot add dummy interface"
+                return 1
+        fi
+
+        kci_test_polrouting
+        kci_test_route_get
+        kci_test_tc
+        kci_test_gre
+        kci_test_bridge
+        kci_test_addrlabel
+        kci_test_ifalias
+        kci_test_vrf
+        kci_test_encap
+        kci_test_macsec
+
+        kci_del_dummy
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+        echo "SKIP: Need root privileges"
+        exit 0
+fi
+
+for x in ip tc;do
+        $x -Version 2>/dev/null >/dev/null
+        if [ $? -ne 0 ];then
+                echo "SKIP: Could not run test without the $x tool"
+                exit 0
+        fi
+done
+
+kci_test_rtnl
+
+exit $ret
diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests
index 5246e782d6e8..21fe149e3de1 100755
--- a/tools/testing/selftests/net/run_afpackettests
+++ b/tools/testing/selftests/net/run_afpackettests
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 if [ $(id -u) != 0 ]; then
         echo $msg must be run as root >&2
diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests
index 16058bbea7a8..b093f39c298c 100755
--- a/tools/testing/selftests/net/run_netsocktests
+++ b/tools/testing/selftests/net/run_netsocktests
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 echo "--------------------"
 echo "running socket test"
diff --git a/tools/testing/selftests/net/socket.c b/tools/testing/selftests/net/socket.c
index 0f227f2f9be9..afca1ead677f 100644
--- a/tools/testing/selftests/net/socket.c
+++ b/tools/testing/selftests/net/socket.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <errno.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/net/test_bpf.sh b/tools/testing/selftests/net/test_bpf.sh
index 8b29796d46aa..65677909c574 100755
--- a/tools/testing/selftests/net/test_bpf.sh
+++ b/tools/testing/selftests/net/test_bpf.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs bpf test using test_bpf kernel module
 
 if /sbin/modprobe -q test_bpf ; then
diff --git a/tools/testing/selftests/networking/timestamping/.gitignore b/tools/testing/selftests/networking/timestamping/.gitignore
index 9e69e982fb38..d9355035e746 100644
--- a/tools/testing/selftests/networking/timestamping/.gitignore
+++ b/tools/testing/selftests/networking/timestamping/.gitignore
@@ -1,3 +1,4 @@
 timestamping
+rxtimestamp
 txtimestamp
 hwtstamp_config
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index ccbb9edbbbb9..a728040edbe1 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -1,4 +1,7 @@
-TEST_PROGS := hwtstamp_config timestamping txtimestamp
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -I../../../../../usr/include
+
+TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp
 
 all: $(TEST_PROGS)
 
diff --git a/tools/testing/selftests/networking/timestamping/hwtstamp_config.c b/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
index e8b685a7f15f..e1fdee841021 100644
--- a/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
+++ b/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Test program for SIOC{G,S}HWTSTAMP
  * Copyright 2013 Solarflare Communications
  * Author: Ben Hutchings
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
new file mode 100644
index 000000000000..dd4162fc0419
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -0,0 +1,389 @@
+#include <errno.h>
+#include <error.h>
+#include <getopt.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <sys/select.h>
+#include <sys/ioctl.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include <asm/types.h>
+#include <linux/net_tstamp.h>
+#include <linux/errqueue.h>
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+struct options {
+        int so_timestamp;
+        int so_timestampns;
+        int so_timestamping;
+};
+
+struct tstamps {
+        bool tstamp;
+        bool tstampns;
+        bool swtstamp;
+        bool hwtstamp;
+};
+
+struct socket_type {
+        char *friendly_name;
+        int type;
+        int protocol;
+        bool enabled;
+};
+
+struct test_case {
+        struct options sockopt;
+        struct tstamps expected;
+        bool enabled;
+};
+
+struct sof_flag {
+        int mask;
+        char *name;
+};
+
+static struct sof_flag sof_flags[] = {
+#define SOF_FLAG(f) { f, #f }
+        SOF_FLAG(SOF_TIMESTAMPING_SOFTWARE),
+        SOF_FLAG(SOF_TIMESTAMPING_RX_SOFTWARE),
+        SOF_FLAG(SOF_TIMESTAMPING_RX_HARDWARE),
+};
+
+static struct socket_type socket_types[] = {
+        { "ip",         SOCK_RAW,       IPPROTO_EGP },
+        { "udp",        SOCK_DGRAM,     IPPROTO_UDP },
+        { "tcp",        SOCK_STREAM,    IPPROTO_TCP },
+};
+
+static struct test_case test_cases[] = {
+        { {}, {} },
+        {
+                { so_timestamp: 1 },
+                { tstamp: true }
+        },
+        {
+                { so_timestampns: 1 },
+                { tstampns: true }
+        },
+        {
+                { so_timestamp: 1, so_timestampns: 1 },
+                { tstampns: true }
+        },
+        {
+                { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE },
+                {}
+        },
+        {
+                /* Loopback device does not support hw timestamps. */
+                { so_timestamping: SOF_TIMESTAMPING_RX_HARDWARE },
+                {}
+        },
+        {
+                { so_timestamping: SOF_TIMESTAMPING_SOFTWARE },
+                {}
+        },
+        {
+                { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE
+                        | SOF_TIMESTAMPING_RX_HARDWARE },
+                {}
+        },
+        {
+                { so_timestamping: SOF_TIMESTAMPING_SOFTWARE
+                        | SOF_TIMESTAMPING_RX_SOFTWARE },
+                { swtstamp: true }
+        },
+        {
+                { so_timestamp: 1, so_timestamping: SOF_TIMESTAMPING_SOFTWARE
+                        | SOF_TIMESTAMPING_RX_SOFTWARE },
+                { tstamp: true, swtstamp: true }
+        },
+};
+
+static struct option long_options[] = {
+        { "list_tests", no_argument, 0, 'l' },
+        { "test_num", required_argument, 0, 'n' },
+        { "op_size", required_argument, 0, 's' },
+        { "tcp", no_argument, 0, 't' },
+        { "udp", no_argument, 0, 'u' },
+        { "ip", no_argument, 0, 'i' },
+};
+
+static int next_port = 19999;
+static int op_size = 10 * 1024;
+
+void print_test_case(struct test_case *t)
+{
+        int f = 0;
+
+        printf("sockopts {");
+        if (t->sockopt.so_timestamp)
+                printf(" SO_TIMESTAMP ");
+        if (t->sockopt.so_timestampns)
+                printf(" SO_TIMESTAMPNS ");
+        if (t->sockopt.so_timestamping) {
+                printf(" SO_TIMESTAMPING: {");
+                for (f = 0; f < ARRAY_SIZE(sof_flags); f++)
+                        if (t->sockopt.so_timestamping & sof_flags[f].mask)
+                                printf(" %s |", sof_flags[f].name);
+                printf("}");
+        }
+        printf("} expected cmsgs: {");
+        if (t->expected.tstamp)
+                printf(" SCM_TIMESTAMP ");
+        if (t->expected.tstampns)
+                printf(" SCM_TIMESTAMPNS ");
+        if (t->expected.swtstamp || t->expected.hwtstamp) {
+                printf(" SCM_TIMESTAMPING {");
+                if (t->expected.swtstamp)
+                        printf("0");
+                if (t->expected.swtstamp && t->expected.hwtstamp)
+                        printf(",");
+                if (t->expected.hwtstamp)
+                        printf("2");
+                printf("}");
+        }
+        printf("}\n");
+}
+
+void do_send(int src)
+{
+        int r;
+        char *buf = malloc(op_size);
+
+        memset(buf, 'z', op_size);
+        r = write(src, buf, op_size);
+        if (r < 0)
+                error(1, errno, "Failed to sendmsg");
+
+        free(buf);
+}
+
+bool do_recv(int rcv, int read_size, struct tstamps expected)
+{
+        const int CMSG_SIZE = 1024;
+
+        struct scm_timestamping *ts;
+        struct tstamps actual = {};
+        char cmsg_buf[CMSG_SIZE];
+        struct iovec recv_iov;
+        struct cmsghdr *cmsg;
+        bool failed = false;
+        struct msghdr hdr;
+        int flags = 0;
+        int r;
+
+        memset(&hdr, 0, sizeof(hdr));
+        hdr.msg_iov = &recv_iov;
+        hdr.msg_iovlen = 1;
+        recv_iov.iov_base = malloc(read_size);
+        recv_iov.iov_len = read_size;
+
+        hdr.msg_control = cmsg_buf;
+        hdr.msg_controllen = sizeof(cmsg_buf);
+
+        r = recvmsg(rcv, &hdr, flags);
+        if (r < 0)
+                error(1, errno, "Failed to recvmsg");
+        if (r != read_size)
+                error(1, 0, "Only received %d bytes of payload.", r);
+
+        if (hdr.msg_flags & (MSG_TRUNC | MSG_CTRUNC))
+                error(1, 0, "Message was truncated.");
+
+        for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL;
+             cmsg = CMSG_NXTHDR(&hdr, cmsg)) {
+                if (cmsg->cmsg_level != SOL_SOCKET)
+                        error(1, 0, "Unexpected cmsg_level %d",
+                              cmsg->cmsg_level);
+                switch (cmsg->cmsg_type) {
+                case SCM_TIMESTAMP:
+                        actual.tstamp = true;
+                        break;
+                case SCM_TIMESTAMPNS:
+                        actual.tstampns = true;
+                        break;
+                case SCM_TIMESTAMPING:
+                        ts = (struct scm_timestamping *)CMSG_DATA(cmsg);
+                        actual.swtstamp = !!ts->ts[0].tv_sec;
+                        if (ts->ts[1].tv_sec != 0)
+                                error(0, 0, "ts[1] should not be set.");
+                        actual.hwtstamp = !!ts->ts[2].tv_sec;
+                        break;
+                default:
+                        error(1, 0, "Unexpected cmsg_type %d", cmsg->cmsg_type);
+                }
+        }
+
+#define VALIDATE(field) \
+        do { \
+                if (expected.field != actual.field) { \
+                        if (expected.field) \
+                                error(0, 0, "Expected " #field " to be set."); \
+                        else \
+                                error(0, 0, \
+                                      "Expected " #field " to not be set."); \
+                        failed = true; \
+                } \
+        } while (0)
+
+        VALIDATE(tstamp);
+        VALIDATE(tstampns);
+        VALIDATE(swtstamp);
+        VALIDATE(hwtstamp);
+#undef VALIDATE
+
+        free(recv_iov.iov_base);
+
+        return failed;
+}
+
+void config_so_flags(int rcv, struct options o)
+{
+        int on = 1;
+
+        if (setsockopt(rcv, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)) < 0)
+                error(1, errno, "Failed to enable SO_REUSEADDR");
+
+        if (o.so_timestamp &&
+            setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMP,
+                       &o.so_timestamp, sizeof(o.so_timestamp)) < 0)
+                error(1, errno, "Failed to enable SO_TIMESTAMP");
+
+        if (o.so_timestampns &&
+            setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMPNS,
+                       &o.so_timestampns, sizeof(o.so_timestampns)) < 0)
+                error(1, errno, "Failed to enable SO_TIMESTAMPNS");
+
+        if (o.so_timestamping &&
+            setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMPING,
+                       &o.so_timestamping, sizeof(o.so_timestamping)) < 0)
+                error(1, errno, "Failed to set SO_TIMESTAMPING");
+}
+
+bool run_test_case(struct socket_type s, struct test_case t)
+{
+        int port = (s.type == SOCK_RAW) ? 0 : next_port++;
+        int read_size = op_size;
+        struct sockaddr_in addr;
+        bool failed = false;
+        int src, dst, rcv;
+
+        src = socket(AF_INET, s.type, s.protocol);
+        if (src < 0)
+                error(1, errno, "Failed to open src socket");
+
+        dst = socket(AF_INET, s.type, s.protocol);
+        if (dst < 0)
+                error(1, errno, "Failed to open dst socket");
+
+        memset(&addr, 0, sizeof(addr));
+        addr.sin_family = AF_INET;
+        addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+        addr.sin_port = htons(port);
+
+        if (bind(dst, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+                error(1, errno, "Failed to bind to port %d", port);
+
+        if (s.type == SOCK_STREAM && (listen(dst, 1) < 0))
+                error(1, errno, "Failed to listen");
+
+        if (connect(src, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+                error(1, errno, "Failed to connect");
+
+        if (s.type == SOCK_STREAM) {
+                rcv = accept(dst, NULL, NULL);
+                if (rcv < 0)
+                        error(1, errno, "Failed to accept");
+                close(dst);
+        } else {
+                rcv = dst;
+        }
+
+        config_so_flags(rcv, t.sockopt);
+        usleep(20000); /* setsockopt for SO_TIMESTAMPING is asynchronous */
+        do_send(src);
+
+        if (s.type == SOCK_RAW)
+                read_size += 20;  /* for IP header */
+        failed = do_recv(rcv, read_size, t.expected);
+
+        close(rcv);
+        close(src);
+
+        return failed;
+}
+
+int main(int argc, char **argv)
+{
+        bool all_protocols = true;
+        bool all_tests = true;
+        int arg_index = 0;
+        int failures = 0;
+        int s, t;
+        char opt;
+
+        while ((opt = getopt_long(argc, argv, "", long_options,
+                                  &arg_index)) != -1) {
+                switch (opt) {
+                case 'l':
+                        for (t = 0; t < ARRAY_SIZE(test_cases); t++) {
+                                printf("%d\t", t);
+                                print_test_case(&test_cases[t]);
+                        }
+                        return 0;
+                case 'n':
+                        t = atoi(optarg);
+                        if (t >= ARRAY_SIZE(test_cases))
+                                error(1, 0, "Invalid test case: %d", t);
+                        all_tests = false;
+                        test_cases[t].enabled = true;
+                        break;
+                case 's':
+                        op_size = atoi(optarg);
+                        break;
+                case 't':
+                        all_protocols = false;
+                        socket_types[2].enabled = true;
+                        break;
+                case 'u':
+                        all_protocols = false;
+                        socket_types[1].enabled = true;
+                        break;
+                case 'i':
+                        all_protocols = false;
+                        socket_types[0].enabled = true;
+                        break;
+                default:
+                        error(1, 0, "Failed to parse parameters.");
+                }
+        }
+
+        for (s = 0; s < ARRAY_SIZE(socket_types); s++) {
+                if (!all_protocols && !socket_types[s].enabled)
+                        continue;
+
+                printf("Testing %s...\n", socket_types[s].friendly_name);
+                for (t = 0; t < ARRAY_SIZE(test_cases); t++) {
+                        if (!all_tests && !test_cases[t].enabled)
+                                continue;
+
+                        printf("Starting testcase %d...\n", t);
+                        if (run_test_case(socket_types[s], test_cases[t])) {
+                                failures++;
+                                printf("FAILURE in test case ");
+                                print_test_case(&test_cases[t]);
+                        }
+                }
+        }
+        if (!failures)
+                printf("PASSED.\n");
+        return failures;
+}
diff --git a/tools/testing/selftests/nsfs/config b/tools/testing/selftests/nsfs/config
new file mode 100644
index 000000000000..598d0a225fc9
--- /dev/null
+++ b/tools/testing/selftests/nsfs/config
@@ -0,0 +1,3 @@
+CONFIG_USER_NS=y
+CONFIG_UTS_NS=y
+CONFIG_PID_NS=y
diff --git a/tools/testing/selftests/nsfs/owner.c b/tools/testing/selftests/nsfs/owner.c
index 437205f8b714..96a976c74550 100644
--- a/tools/testing/selftests/nsfs/owner.c
+++ b/tools/testing/selftests/nsfs/owner.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <sched.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c
index ae3a0d68e966..1182d4e437a2 100644
--- a/tools/testing/selftests/nsfs/pidns.c
+++ b/tools/testing/selftests/nsfs/pidns.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <sched.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh
index 1c12b5855e4f..5fc7ad359e21 100755
--- a/tools/testing/selftests/ntb/ntb_test.sh
+++ b/tools/testing/selftests/ntb/ntb_test.sh
@@ -333,6 +333,10 @@ function ntb_tool_tests()
         link_test $LOCAL_TOOL $REMOTE_TOOL
         link_test $REMOTE_TOOL $LOCAL_TOOL
 
+        #Ensure the link is up on both sides before continuing
+        write_file Y $LOCAL_TOOL/link_event
+        write_file Y $REMOTE_TOOL/link_event
+
         for PEER_TRANS in $(ls $LOCAL_TOOL/peer_trans*); do
                 PT=$(basename $PEER_TRANS)
                 write_file $MW_SIZE $LOCAL_TOOL/$PT
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 72c3ac2323e1..f6b1338730db 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for powerpc selftests
 
 # ARCH can be overridden by the user for cross compiling
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index fb96a89bd953..a35058e3766c 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := gettimeofday context_switch mmap_bench futex_bench null_syscall
 
 CFLAGS += -O2
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index f4241339edd2..87f1f0252299 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -10,6 +10,7 @@
  */
 
 #define _GNU_SOURCE
+#include <errno.h>
 #include <sched.h>
 #include <string.h>
 #include <stdio.h>
@@ -75,6 +76,7 @@ static void touch(void)
 
 static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 {
+        int rc;
         pthread_t tid;
         cpu_set_t cpuset;
         pthread_attr_t attr;
@@ -82,14 +84,23 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
         CPU_ZERO(&cpuset);
         CPU_SET(cpu, &cpuset);
 
-        pthread_attr_init(&attr);
+        rc = pthread_attr_init(&attr);
+        if (rc) {
+                errno = rc;
+                perror("pthread_attr_init");
+                exit(1);
+        }
 
-        if (pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset)) {
+        rc = pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+        if (rc) {
+                errno = rc;
                 perror("pthread_attr_setaffinity_np");
                 exit(1);
         }
 
-        if (pthread_create(&tid, &attr, fn, arg)) {
+        rc = pthread_create(&tid, &attr, fn, arg);
+        if (rc) {
+                errno = rc;
                 perror("pthread_create");
                 exit(1);
         }
diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index b24485ab30e2..1be547434a49 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := cache_shape
 
 all: $(TEST_PROGS)
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 681ab19d0a84..ac4a52e19e59 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # The loops are all 64-bit code
 CFLAGS += -m64
 CFLAGS += -I$(CURDIR)
diff --git a/tools/testing/selftests/powerpc/copyloops/asm/export.h b/tools/testing/selftests/powerpc/copyloops/asm/export.h
index 2d14a9b4248c..0bab35f6777a 100644
--- a/tools/testing/selftests/powerpc/copyloops/asm/export.h
+++ b/tools/testing/selftests/powerpc/copyloops/asm/export.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #define EXPORT_SYMBOL(x)
diff --git a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h
index 80d34a9ffff4..5ffe04d802c9 100644
--- a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h
+++ b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <ppc-asm.h>
 
 #define CONFIG_ALTIVEC
diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c
index 7fb436f82d16..0f6873618552 100644
--- a/tools/testing/selftests/powerpc/copyloops/validate.c
+++ b/tools/testing/selftests/powerpc/copyloops/validate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <malloc.h>
 #include <string.h>
 #include <stdlib.h>
diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile
index c5639deb8887..55d7db7a616b 100644
--- a/tools/testing/selftests/powerpc/dscr/Makefile
+++ b/tools/testing/selftests/powerpc/dscr/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test   \
               dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test  \
               dscr_sysfs_thread_test
diff --git a/tools/testing/selftests/powerpc/dscr/dscr.h b/tools/testing/selftests/powerpc/dscr/dscr.h
index 18ea223bd398..cdb840bc54f2 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr.h
+++ b/tools/testing/selftests/powerpc/dscr/dscr.h
@@ -39,7 +39,7 @@
 #define rmb()  asm volatile("lwsync":::"memory")
 #define wmb()  asm volatile("lwsync":::"memory")
 
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
 
 /* Prilvilege state DSCR access */
 inline unsigned long get_dscr(void)
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c
index df17c3bab0a7..9e1a37e93b63 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c
@@ -27,7 +27,7 @@ static void *do_test(void *in)
                 unsigned long d, cur_dscr, cur_dscr_usr;
                 unsigned long s1, s2;
 
-                s1 = ACCESS_ONCE(sequence);
+                s1 = READ_ONCE(sequence);
                 if (s1 & 1)
                         continue;
                 rmb();
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
index 17fb1b43c320..1899bd85121f 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
@@ -53,6 +53,8 @@ static int check_all_cpu_dscr_defaults(unsigned long val)
         }
 
         while ((dp = readdir(sysfs))) {
+                int len;
+
                 if (!(dp->d_type & DT_DIR))
                         continue;
                 if (!strcmp(dp->d_name, "cpuidle"))
@@ -60,7 +62,9 @@ static int check_all_cpu_dscr_defaults(unsigned long val)
                 if (!strstr(dp->d_name, "cpu"))
                         continue;
 
-                sprintf(file, "%s%s/dscr", CPU_PATH, dp->d_name);
+                len = snprintf(file, LEN_MAX, "%s%s/dscr", CPU_PATH, dp->d_name);
+                if (len >= LEN_MAX)
+                        continue;
                 if (access(file, F_OK))
                         continue;
 
diff --git a/tools/testing/selftests/powerpc/include/basic_asm.h b/tools/testing/selftests/powerpc/include/basic_asm.h
index 12eaddf72e66..886dc026fe7a 100644
--- a/tools/testing/selftests/powerpc/include/basic_asm.h
+++ b/tools/testing/selftests/powerpc/include/basic_asm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _SELFTESTS_POWERPC_BASIC_ASM_H
 #define _SELFTESTS_POWERPC_BASIC_ASM_H
 
diff --git a/tools/testing/selftests/powerpc/include/instructions.h b/tools/testing/selftests/powerpc/include/instructions.h
index 0fb0bd3b28c9..f36061eb6f0f 100644
--- a/tools/testing/selftests/powerpc/include/instructions.h
+++ b/tools/testing/selftests/powerpc/include/instructions.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _SELFTESTS_POWERPC_INSTRUCTIONS_H
 #define _SELFTESTS_POWERPC_INSTRUCTIONS_H
 
diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile
index fa8bae920c91..0dd3a01fdab9 100644
--- a/tools/testing/selftests/powerpc/math/Makefile
+++ b/tools/testing/selftests/powerpc/math/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 1cffe54dccfb..bf315bcbe663 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 noarg:
         $(MAKE) -C ../
 
diff --git a/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c b/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c
index 49003674de4f..9932359ce38f 100644
--- a/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c
+++ b/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <sys/mman.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index e4e55d1d3e0f..6e1629bf5b09 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 noarg:
         $(MAKE) -C ../
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 6001fb0a377a..c4e64bc2e265 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 noarg:
         $(MAKE) -C ../../
 
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index fe6bc60dfc60..480305266504 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \
               ptrace-tm-spd-vsx ptrace-tm-spr
@@ -6,7 +7,7 @@ include ../../lib.mk
 
 all: $(TEST_PROGS)
 
-CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm
+CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
 $(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h
 
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index f0eef27458e2..a7cbd5082e27 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := signal signal_tm
 
 all: $(TEST_PROGS)
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 557b9379f3bb..1125e489055e 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # The loops are all 64-bit code
 CFLAGS += -m64
 CFLAGS += -I$(CURDIR)
diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
index 11bece87e880..136242ec4b0e 100644
--- a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
+++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <ppc-asm.h>
 
 #ifndef r1
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp.c b/tools/testing/selftests/powerpc/stringloops/memcmp.c
index 30b1222380ca..8250db25b379 100644
--- a/tools/testing/selftests/powerpc/stringloops/memcmp.c
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <malloc.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index b92c2a132c4f..30b8ff8fb82e 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := switch_endian_test
 
 ASFLAGS += -O2 -Wall -g -nostdlib -m64
diff --git a/tools/testing/selftests/powerpc/switch_endian/check.S b/tools/testing/selftests/powerpc/switch_endian/check.S
index e2484d2c24f4..927a5c675e83 100644
--- a/tools/testing/selftests/powerpc/switch_endian/check.S
+++ b/tools/testing/selftests/powerpc/switch_endian/check.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include "common.h"
 
 /*
diff --git a/tools/testing/selftests/powerpc/switch_endian/common.h b/tools/testing/selftests/powerpc/switch_endian/common.h
index 69e399698c64..1434cbc2a6ad 100644
--- a/tools/testing/selftests/powerpc/switch_endian/common.h
+++ b/tools/testing/selftests/powerpc/switch_endian/common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <ppc-asm.h>
 #include <asm/unistd.h>
 
diff --git a/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S b/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S
index ef7c971abb67..cc4930467235 100644
--- a/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S
+++ b/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include "common.h"
 
         .data
@@ -8,7 +9,7 @@ message:
         .section ".toc"
         .balign 8
 pattern:
-        .llong 0x5555AAAA5555AAAA
+        .8byte 0x5555AAAA5555AAAA
 
         .text
 FUNC_START(_start)
diff --git a/tools/testing/selftests/powerpc/syscalls/ipc.h b/tools/testing/selftests/powerpc/syscalls/ipc.h
index fbebc022edf6..26a20682c9a4 100644
--- a/tools/testing/selftests/powerpc/syscalls/ipc.h
+++ b/tools/testing/selftests/powerpc/syscalls/ipc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef __NR_semop
 DO_TEST(semop, __NR_semop)
 #endif
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 2f1f7b013293..241a4a4ee0e4 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -12,3 +12,4 @@ tm-signal-context-chk-gpr
 tm-signal-context-chk-vmx
 tm-signal-context-chk-vsx
 tm-vmx-unavail
+tm-unavailable
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 958c11c14acd..8ed6f8c57230 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,8 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
 SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu \
         tm-signal-context-chk-vmx tm-signal-context-chk-vsx
 
 TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
-        tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \
+        tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable \
         $(SIGNAL_CONTEXT_CHK_TESTS)
 
 include ../../lib.mk
@@ -15,6 +16,8 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S
 $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
 $(OUTPUT)/tm-tmspr: CFLAGS += -pthread
 $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
+$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o
+$(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 
 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
index e79ccd6aada1..4cdb83964bb3 100644
--- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Test context switching to see if the DSCR SPR is correctly preserved
  * when within a transaction.
  *
@@ -30,6 +31,7 @@
 
 #include "utils.h"
 #include "tm.h"
+#include "../pmu/lib.h"
 
 #define SPRN_DSCR       0x03
 
@@ -75,8 +77,6 @@ int test_body(void)
                 );
                 assert(rv); /* make sure the transaction aborted */
                 if ((texasr >> 56) != TM_CAUSE_RESCHED) {
-                        putchar('.');
-                        fflush(stdout);
                         continue;
                 }
                 if (dscr2 != dscr1) {
@@ -89,7 +89,12 @@ int test_body(void)
         }
 }
 
-int main(void)
+static int tm_resched_dscr(void)
 {
-        return test_harness(test_body, "tm_resched_dscr");
+        return eat_cpu(test_body);
+}
+
+int main(int argc, const char *argv[])
+{
+        return test_harness(tm_resched_dscr, "tm_resched_dscr");
 }
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S
index 431f61ae2368..bd1ca25febe4 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <ppc-asm.h>
 #include <asm/unistd.h>
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
new file mode 100644
index 000000000000..96c37f84ce54
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
@@ -0,0 +1,371 @@
+/*
+ * Copyright 2017, Gustavo Romero, Breno Leitao, Cyril Bur, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Force FP, VEC and VSX unavailable exception during transaction in all
+ * possible scenarios regarding the MSR.FP and MSR.VEC state, e.g. when FP
+ * is enable and VEC is disable, when FP is disable and VEC is enable, and
+ * so on. Then we check if the restored state is correctly set for the
+ * FP and VEC registers to the previous state we set just before we entered
+ * in TM, i.e. we check if it corrupts somehow the recheckpointed FP and
+ * VEC/Altivec registers on abortion due to an unavailable exception in TM.
+ * N.B. In this test we do not test all the FP/Altivec/VSX registers for
+ * corruption, but only for registers vs0 and vs32, which are respectively
+ * representatives of FP and VEC/Altivec reg sets.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sched.h>
+
+#include "tm.h"
+
+#define DEBUG 0
+
+/* Unavailable exceptions to test in HTM */
+#define FP_UNA_EXCEPTION        0
+#define VEC_UNA_EXCEPTION       1
+#define VSX_UNA_EXCEPTION       2
+
+#define NUM_EXCEPTIONS          3
+
+struct Flags {
+        int touch_fp;
+        int touch_vec;
+        int result;
+        int exception;
+} flags;
+
+bool expecting_failure(void)
+{
+        if (flags.touch_fp && flags.exception == FP_UNA_EXCEPTION)
+                return false;
+
+        if (flags.touch_vec && flags.exception == VEC_UNA_EXCEPTION)
+                return false;
+
+        /*
+         * If both FP and VEC are touched it does not mean that touching VSX
+         * won't raise an exception. However since FP and VEC state are already
+         * correctly loaded, the transaction is not aborted (i.e.
+         * treclaimed/trecheckpointed) and MSR.VSX is just set as 1, so a TM
+         * failure is not expected also in this case.
+         */
+        if ((flags.touch_fp && flags.touch_vec) &&
+             flags.exception == VSX_UNA_EXCEPTION)
+                return false;
+
+        return true;
+}
+
+/* Check if failure occurred whilst in transaction. */
+bool is_failure(uint64_t condition_reg)
+{
+        /*
+         * When failure handling occurs, CR0 is set to 0b1010 (0xa). Otherwise
+         * transaction completes without failure and hence reaches out 'tend.'
+         * that sets CR0 to 0b0100 (0x4).
+         */
+        return ((condition_reg >> 28) & 0xa) == 0xa;
+}
+
+void *ping(void *input)
+{
+
+        /*
+         * Expected values for vs0 and vs32 after a TM failure. They must never
+         * change, otherwise they got corrupted.
+         */
+        uint64_t high_vs0 = 0x5555555555555555;
+        uint64_t low_vs0 = 0xffffffffffffffff;
+        uint64_t high_vs32 = 0x5555555555555555;
+        uint64_t low_vs32 = 0xffffffffffffffff;
+
+        /* Counter for busy wait */
+        uint64_t counter = 0x1ff000000;
+
+        /*
+         * Variable to keep a copy of CR register content taken just after we
+         * leave the transactional state.
+         */
+        uint64_t cr_ = 0;
+
+        /*
+         * Wait a bit so thread can get its name "ping". This is not important
+         * to reproduce the issue but it's nice to have for systemtap debugging.
+         */
+        if (DEBUG)
+                sleep(1);
+
+        printf("If MSR.FP=%d MSR.VEC=%d: ", flags.touch_fp, flags.touch_vec);
+
+        if (flags.exception != FP_UNA_EXCEPTION &&
+            flags.exception != VEC_UNA_EXCEPTION &&
+            flags.exception != VSX_UNA_EXCEPTION) {
+                printf("No valid exception specified to test.\n");
+                return NULL;
+        }
+
+        asm (
+                /* Prepare to merge low and high. */
+                "       mtvsrd          33, %[high_vs0]         ;"
+                "       mtvsrd          34, %[low_vs0]          ;"
+
+                /*
+                 * Adjust VS0 expected value after an TM failure,
+                 * i.e. vs0 = 0x5555555555555555555FFFFFFFFFFFFFFFF
+                 */
+                "       xxmrghd         0, 33, 34               ;"
+
+                /*
+                 * Adjust VS32 expected value after an TM failure,
+                 * i.e. vs32 = 0x5555555555555555555FFFFFFFFFFFFFFFF
+                 */
+                "       xxmrghd         32, 33, 34              ;"
+
+                /*
+                 * Wait an amount of context switches so load_fp and load_vec
+                 * overflow and MSR.FP, MSR.VEC, and MSR.VSX become zero (off).
+                 */
+                "       mtctr           %[counter]              ;"
+
+                /* Decrement CTR branch if CTR non zero. */
+                "1:     bdnz 1b                                 ;"
+
+                /*
+                 * Check if we want to touch FP prior to the test in order
+                 * to set MSR.FP = 1 before provoking an unavailable
+                 * exception in TM.
+                 */
+                "       cmpldi          %[touch_fp], 0          ;"
+                "       beq             no_fp                   ;"
+                "       fadd            10, 10, 10              ;"
+                "no_fp:                                         ;"
+
+                /*
+                 * Check if we want to touch VEC prior to the test in order
+                 * to set MSR.VEC = 1 before provoking an unavailable
+                 * exception in TM.
+                 */
+                "       cmpldi          %[touch_vec], 0         ;"
+                "       beq             no_vec                  ;"
+                "       vaddcuw         10, 10, 10              ;"
+                "no_vec:                                        ;"
+
+                /*
+                 * Perhaps it would be a better idea to do the
+                 * compares outside transactional context and simply
+                 * duplicate code.
+                 */
+                "       tbegin.                                 ;"
+                "       beq             trans_fail              ;"
+
+                /* Do we do FP Unavailable? */
+                "       cmpldi          %[exception], %[ex_fp]  ;"
+                "       bne             1f                      ;"
+                "       fadd            10, 10, 10              ;"
+                "       b               done                    ;"
+
+                /* Do we do VEC Unavailable? */
+                "1:     cmpldi          %[exception], %[ex_vec] ;"
+                "       bne             2f                      ;"
+                "       vaddcuw         10, 10, 10              ;"
+                "       b               done                    ;"
+
+                /*
+                 * Not FP or VEC, therefore VSX. Ensure this
+                 * instruction always generates a VSX Unavailable.
+                 * ISA 3.0 is tricky here.
+                 * (xxmrghd will on ISA 2.07 and ISA 3.0)
+                 */
+                "2:     xxmrghd         10, 10, 10              ;"
+
+                "done:  tend. ;"
+
+                "trans_fail: ;"
+
+                /* Give values back to C. */
+                "       mfvsrd          %[high_vs0], 0          ;"
+                "       xxsldwi         3, 0, 0, 2              ;"
+                "       mfvsrd          %[low_vs0], 3           ;"
+                "       mfvsrd          %[high_vs32], 32        ;"
+                "       xxsldwi         3, 32, 32, 2            ;"
+                "       mfvsrd          %[low_vs32], 3          ;"
+
+                /* Give CR back to C so that it can check what happened. */
+                "       mfcr            %[cr_]          ;"
+
+                : [high_vs0]  "+r" (high_vs0),
+                  [low_vs0]   "+r" (low_vs0),
+                  [high_vs32] "=r" (high_vs32),
+                  [low_vs32]  "=r" (low_vs32),
+                  [cr_]       "+r" (cr_)
+                : [touch_fp]  "r"  (flags.touch_fp),
+                  [touch_vec] "r"  (flags.touch_vec),
+                  [exception] "r"  (flags.exception),
+                  [ex_fp]     "i"  (FP_UNA_EXCEPTION),
+                  [ex_vec]    "i"  (VEC_UNA_EXCEPTION),
+                  [ex_vsx]    "i"  (VSX_UNA_EXCEPTION),
+                  [counter]   "r"  (counter)
+
+                : "cr0", "ctr", "v10", "vs0", "vs10", "vs3", "vs32", "vs33",
+                  "vs34", "fr10"
+
+                );
+
+        /*
+         * Check if we were expecting a failure and it did not occur by checking
+         * CR0 state just after we leave the transaction. Either way we check if
+         * vs0 or vs32 got corrupted.
+         */
+        if (expecting_failure() && !is_failure(cr_)) {
+                printf("\n\tExpecting the transaction to fail, %s",
+                        "but it didn't\n\t");
+                flags.result++;
+        }
+
+        /* Check if we were not expecting a failure and a it occurred. */
+        if (!expecting_failure() && is_failure(cr_)) {
+                printf("\n\tUnexpected transaction failure 0x%02lx\n\t",
+                        failure_code());
+                return (void *) -1;
+        }
+
+        /*
+         * Check if TM failed due to the cause we were expecting. 0xda is a
+         * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause.
+         */
+        if (is_failure(cr_) && !failure_is_unavailable()) {
+                printf("\n\tUnexpected failure cause 0x%02lx\n\t",
+                        failure_code());
+                return (void *) -1;
+        }
+
+        /* 0x4 is a success and 0xa is a fail. See comment in is_failure(). */
+        if (DEBUG)
+                printf("CR0: 0x%1lx ", cr_ >> 28);
+
+        /* Check FP (vs0) for the expected value. */
+        if (high_vs0 != 0x5555555555555555 || low_vs0 != 0xFFFFFFFFFFFFFFFF) {
+                printf("FP corrupted!");
+                        printf("  high = %#16" PRIx64 "  low = %#16" PRIx64 " ",
+                                high_vs0, low_vs0);
+                flags.result++;
+        } else
+                printf("FP ok ");
+
+        /* Check VEC (vs32) for the expected value. */
+        if (high_vs32 != 0x5555555555555555 || low_vs32 != 0xFFFFFFFFFFFFFFFF) {
+                printf("VEC corrupted!");
+                        printf("  high = %#16" PRIx64 "  low = %#16" PRIx64,
+                                high_vs32, low_vs32);
+                flags.result++;
+        } else
+                printf("VEC ok");
+
+        putchar('\n');
+
+        return NULL;
+}
+
+/* Thread to force context switch */
+void *pong(void *not_used)
+{
+        /* Wait thread get its name "pong". */
+        if (DEBUG)
+                sleep(1);
+
+        /* Classed as an interactive-like thread. */
+        while (1)
+                sched_yield();
+}
+
+/* Function that creates a thread and launches the "ping" task. */
+void test_fp_vec(int fp, int vec, pthread_attr_t *attr)
+{
+        int retries = 2;
+        void *ret_value;
+        pthread_t t0;
+
+        flags.touch_fp = fp;
+        flags.touch_vec = vec;
+
+        /*
+         * Without luck it's possible that the transaction is aborted not due to
+         * the unavailable exception caught in the middle as we expect but also,
+         * for instance, due to a context switch or due to a KVM reschedule (if
+         * it's running on a VM). Thus we try a few times before giving up,
+         * checking if the failure cause is the one we expect.
+         */
+        do {
+                /* Bind 'ping' to CPU 0, as specified in 'attr'. */
+                pthread_create(&t0, attr, ping, (void *) &flags);
+                pthread_setname_np(t0, "ping");
+                pthread_join(t0, &ret_value);
+                retries--;
+        } while (ret_value != NULL && retries);
+
+        if (!retries) {
+                flags.result = 1;
+                if (DEBUG)
+                        printf("All transactions failed unexpectedly\n");
+
+        }
+}
+
+int main(int argc, char **argv)
+{
+        int exception; /* FP = 0, VEC = 1, VSX = 2 */
+        pthread_t t1;
+        pthread_attr_t attr;
+        cpu_set_t cpuset;
+
+        /* Set only CPU 0 in the mask. Both threads will be bound to CPU 0. */
+        CPU_ZERO(&cpuset);
+        CPU_SET(0, &cpuset);
+
+        /* Init pthread attribute. */
+        pthread_attr_init(&attr);
+
+        /* Set CPU 0 mask into the pthread attribute. */
+        pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+
+        pthread_create(&t1, &attr /* Bind 'pong' to CPU 0 */, pong, NULL);
+        pthread_setname_np(t1, "pong"); /* Name it for systemtap convenience */
+
+        flags.result = 0;
+
+        for (exception = 0; exception < NUM_EXCEPTIONS; exception++) {
+                printf("Checking if FP/VEC registers are sane after");
+
+                if (exception == FP_UNA_EXCEPTION)
+                        printf(" a FP unavailable exception...\n");
+
+                else if (exception == VEC_UNA_EXCEPTION)
+                        printf(" a VEC unavailable exception...\n");
+
+                else
+                        printf(" a VSX unavailable exception...\n");
+
+                flags.exception = exception;
+
+                test_fp_vec(0, 0, &attr);
+                test_fp_vec(1, 0, &attr);
+                test_fp_vec(0, 1, &attr);
+                test_fp_vec(1, 1, &attr);
+
+        }
+
+        if (flags.result > 0) {
+                printf("result: failed!\n");
+                exit(1);
+        } else {
+                printf("result: success\n");
+                exit(0);
+        }
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index 0ffff04433c5..df4204247d45 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -47,6 +47,11 @@ static inline bool failure_is_syscall(void)
         return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL;
 }
 
+static inline bool failure_is_unavailable(void)
+{
+        return (failure_code() & TM_CAUSE_FAC_UNAV) == TM_CAUSE_FAC_UNAV;
+}
+
 static inline bool failure_is_nesting(void)
 {
         return (__builtin_get_texasru() & 0x400000);
diff --git a/tools/testing/selftests/powerpc/vphn/test-vphn.c b/tools/testing/selftests/powerpc/vphn/test-vphn.c
index 5742f6876b25..81d3069ffb84 100644
--- a/tools/testing/selftests/powerpc/vphn/test-vphn.c
+++ b/tools/testing/selftests/powerpc/vphn/test-vphn.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <byteswap.h>
 #include "utils.h"
diff --git a/tools/testing/selftests/prctl/Makefile b/tools/testing/selftests/prctl/Makefile
index 35aa1c8f2df2..c7923b205222 100644
--- a/tools/testing/selftests/prctl/Makefile
+++ b/tools/testing/selftests/prctl/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifndef CROSS_COMPILE
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
diff --git a/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c b/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c
index f7499d1c0415..62a93cc61b7c 100644
--- a/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c
+++ b/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Tests for prctl(PR_GET_TSC, ...) / prctl(PR_SET_TSC, ...)
  *
diff --git a/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c b/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c
index a06f027e9d16..79950f9a26fd 100644
--- a/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c
+++ b/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Tests for prctl(PR_GET_TSC, ...) / prctl(PR_SET_TSC, ...)
  *
diff --git a/tools/testing/selftests/prctl/disable-tsc-test.c b/tools/testing/selftests/prctl/disable-tsc-test.c
index 8d494f7bebdb..f84d4ee111d3 100644
--- a/tools/testing/selftests/prctl/disable-tsc-test.c
+++ b/tools/testing/selftests/prctl/disable-tsc-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Tests for prctl(PR_GET_TSC, ...) / prctl(PR_SET_TSC, ...)
  *
diff --git a/tools/testing/selftests/pstore/.gitignore b/tools/testing/selftests/pstore/.gitignore
new file mode 100644
index 000000000000..5a4a26e5464b
--- /dev/null
+++ b/tools/testing/selftests/pstore/.gitignore
@@ -0,0 +1,2 @@
+logs
+*uuid
diff --git a/tools/testing/selftests/pstore/Makefile b/tools/testing/selftests/pstore/Makefile
index c5f2440ba1f7..5ef57855a2be 100644
--- a/tools/testing/selftests/pstore/Makefile
+++ b/tools/testing/selftests/pstore/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for pstore selftests.
 # Expects pstore backend is registered.
 
diff --git a/tools/testing/selftests/ptp/Makefile b/tools/testing/selftests/ptp/Makefile
index 83dd42b2129e..ef06de0898b7 100644
--- a/tools/testing/selftests/ptp/Makefile
+++ b/tools/testing/selftests/ptp/Makefile
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -I../../../../usr/include/
 TEST_PROGS := testptp
 LDLIBS += -lrt
 all: $(TEST_PROGS)
diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c
index c34cd8ac8aaa..54900657eb44 100644
--- a/tools/testing/selftests/ptrace/peeksiginfo.c
+++ b/tools/testing/selftests/ptrace/peeksiginfo.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <stdio.h>
 #include <signal.h>
diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh
new file mode 100755
index 000000000000..ef7fcbac3d42
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/config_override.sh
@@ -0,0 +1,61 @@
+#!/bin/bash
+#
+# config_override.sh base override
+#
+# Combines base and override, removing any Kconfig options from base
+# that conflict with any in override, concatenating what remains and
+# sending the result to standard output.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2017
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+base=$1
+if test -r $base
+then
+        :
+else
+        echo Base file $base unreadable!!!
+        exit 1
+fi
+
+override=$2
+if test -r $override
+then
+        :
+else
+        echo Override file $override unreadable!!!
+        exit 1
+fi
+
+T=${TMPDIR-/tmp}/config_override.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+sed < $override -e 's/^/grep -v "/' -e 's/=.*$/="/' |
+        awk '
+        {
+                if (last)
+                        print last " |";
+                last = $0;
+        }
+        END {
+                if (last)
+                        print last;
+        }' > $T/script
+sh $T/script < $base
+cat $override
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
index 70fca318a82b..197deece7c7c 100755
--- a/tools/testing/selftests/rcutorture/bin/configcheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -19,7 +19,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/abat-chk-config.sh.$$
+T=${TMPDIR-/tmp}/abat-chk-config.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 3f81a1095206..51f66a7ce876 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -32,7 +32,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/configinit.sh.$$
+T=${TMPDIR-/tmp}/configinit.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 1426a9b97494..07a13779eece 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -66,9 +66,34 @@ configfrag_boot_params () {
 
 # configfrag_boot_cpus bootparam-string config-fragment-file config-cpus
 #
-# Decreases number of CPUs based on any maxcpus= boot parameters specified.
+# Decreases number of CPUs based on any nr_cpus= boot parameters specified.
 configfrag_boot_cpus () {
         local bootargs="`configfrag_boot_params "$1" "$2"`"
+        local nr_cpus
+        if echo "${bootargs}" | grep -q 'nr_cpus=[0-9]'
+        then
+                nr_cpus="`echo "${bootargs}" | sed -e 's/^.*nr_cpus=\([0-9]*\).*$/\1/'`"
+                if test "$3" -gt "$nr_cpus"
+                then
+                        echo $nr_cpus
+                else
+                        echo $3
+                fi
+        else
+                echo $3
+        fi
+}
+
+# configfrag_boot_maxcpus bootparam-string config-fragment-file config-cpus
+#
+# Decreases number of CPUs based on any maxcpus= boot parameters specified.
+# This allows tests where additional CPUs come online later during the
+# test run.  However, the torture parameters will be set based on the
+# number of CPUs initially present, so the scripting should schedule
+# test runs based on the maxcpus= boot parameter controlling the initial
+# number of CPUs instead of on the ultimate number of CPUs.
+configfrag_boot_maxcpus () {
+        local bootargs="`configfrag_boot_params "$1" "$2"`"
         local maxcpus
         if echo "${bootargs}" | grep -q 'maxcpus=[0-9]'
         then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index c29f2ec0bf9f..fb66d0173638 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: kvm-build.sh config-template build-dir more-configs
+# Usage: kvm-build.sh config-template build-dir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -34,24 +34,17 @@ then
         echo "kvm-build.sh :$builddir: Not a writable directory, cannot build into it"
         exit 1
 fi
-moreconfigs=${3}
-if test -z "$moreconfigs" -o ! -r "$moreconfigs"
-then
-        echo "kvm-build.sh :$moreconfigs: Not a readable file"
-        exit 1
-fi
 
-T=/tmp/test-linux.sh.$$
+T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
-grep -v 'CONFIG_[A-Z]*_TORTURE_TEST=' < ${config_template} > $T/config
+cp ${config_template} $T/config
 cat << ___EOF___ >> $T/config
 CONFIG_INITRAMFS_SOURCE="$TORTURE_INITRD"
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
-cat $moreconfigs >> $T/config
 
 configinit.sh $T/config O=$builddir
 retval=$?
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 93eede4e8fbe..ab14b97c942c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -38,9 +38,9 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/kvm-test-1-run.sh.$$
+T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
-touch $T
+mkdir $T
 
 . $KVM/bin/functions.sh
 . $CONFIGFRAG/ver_functions.sh
@@ -60,37 +60,33 @@ then
         echo "kvm-test-1-run.sh :$resdir: Not a writable directory, cannot store results into it"
         exit 1
 fi
-cp $config_template $resdir/ConfigFragment
 echo ' ---' `date`: Starting build
 echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
+touch $resdir/ConfigFragment.input $resdir/ConfigFragment
 if test -r "$config_dir/CFcommon"
 then
-        cat < $config_dir/CFcommon >> $T
+        echo " --- $config_dir/CFcommon" >> $resdir/ConfigFragment.input
+        cat < $config_dir/CFcommon >> $resdir/ConfigFragment.input
+        config_override.sh $config_dir/CFcommon $config_template > $T/Kc1
+        grep '#CHECK#' $config_dir/CFcommon >> $resdir/ConfigFragment
+else
+        cp $config_template $T/Kc1
 fi
-# Optimizations below this point
-# CONFIG_USB=n
-# CONFIG_SECURITY=n
-# CONFIG_NFS_FS=n
-# CONFIG_SOUND=n
-# CONFIG_INPUT_JOYSTICK=n
-# CONFIG_INPUT_TABLET=n
-# CONFIG_INPUT_TOUCHSCREEN=n
-# CONFIG_INPUT_MISC=n
-# CONFIG_INPUT_MOUSE=n
-# # CONFIG_NET=n # disables console access, so accept the slower build.
-# CONFIG_SCSI=n
-# CONFIG_ATA=n
-# CONFIG_FAT_FS=n
-# CONFIG_MSDOS_FS=n
-# CONFIG_VFAT_FS=n
-# CONFIG_ISO9660_FS=n
-# CONFIG_QUOTA=n
-# CONFIG_HID=n
-# CONFIG_CRYPTO=n
-# CONFIG_PCCARD=n
-# CONFIG_PCMCIA=n
-# CONFIG_CARDBUS=n
-# CONFIG_YENTA=n
+echo " --- $config_template" >> $resdir/ConfigFragment.input
+cat $config_template >> $resdir/ConfigFragment.input
+grep '#CHECK#' $config_template >> $resdir/ConfigFragment
+if test -n "$TORTURE_KCONFIG_ARG"
+then
+        echo $TORTURE_KCONFIG_ARG | tr -s " " "\012" > $T/cmdline
+        echo " --- --kconfig argument" >> $resdir/ConfigFragment.input
+        cat $T/cmdline >> $resdir/ConfigFragment.input
+        config_override.sh $T/Kc1 $T/cmdline > $T/Kc2
+        # Note that "#CHECK#" is not permitted on commandline.
+else
+        cp $T/Kc1 $T/Kc2
+fi
+cat $T/Kc2 >> $resdir/ConfigFragment
+
 base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'`
 if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux
 then
@@ -100,7 +96,9 @@ then
         KERNEL=$base_resdir/${BOOT_IMAGE##*/} # use the last component of ${BOOT_IMAGE}
         ln -s $base_resdir/Make*.out $resdir  # for kvm-recheck.sh
         ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
-elif kvm-build.sh $config_template $builddir $T
+        # Arch-independent indicator
+        touch $resdir/builtkernel
+elif kvm-build.sh $T/Kc2 $builddir
 then
         # Had to build a kernel for this test.
         QEMU="`identify_qemu $builddir/vmlinux`"
@@ -112,6 +110,8 @@ then
         then
                 cp $builddir/$BOOT_IMAGE $resdir
                 KERNEL=$resdir/${BOOT_IMAGE##*/}
+                # Arch-independent indicator
+                touch $resdir/builtkernel
         else
                 echo No identifiable boot image, not running KVM, see $resdir.
                 echo Do the torture scripts know about your architecture?
@@ -149,7 +149,7 @@ fi
 
 # Generate -smp qemu argument.
 qemu_args="-enable-kvm -nographic $qemu_args"
-cpu_count=`configNR_CPUS.sh $config_template`
+cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment`
 cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
 if test $cpu_count -gt $vcpus
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 50091de3a911..ccd49e958fd2 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -30,7 +30,7 @@
 scriptname=$0
 args="$*"
 
-T=/tmp/kvm.sh.$$
+T=${TMPDIR-/tmp}/kvm.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
@@ -41,6 +41,7 @@ PATH=${KVM}/bin:$PATH; export PATH
 TORTURE_DEFCONFIG=defconfig
 TORTURE_BOOT_IMAGE=""
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
+TORTURE_KCONFIG_ARG=""
 TORTURE_KMAKE_ARG=""
 TORTURE_SHUTDOWN_GRACE=180
 TORTURE_SUITE=rcu
@@ -65,6 +66,7 @@ usage () {
         echo "       --duration minutes"
         echo "       --interactive"
         echo "       --jitter N [ maxsleep (us) [ maxspin (us) ] ]"
+        echo "       --kconfig Kconfig-options"
         echo "       --kmake-arg kernel-make-arguments"
         echo "       --mac nn:nn:nn:nn:nn:nn"
         echo "       --no-initrd"
@@ -129,6 +131,11 @@ do
                 jitter="$2"
                 shift
                 ;;
+        --kconfig)
+                checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$'
+                TORTURE_KCONFIG_ARG="$2"
+                shift
+                ;;
         --kmake-arg)
                 checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
                 TORTURE_KMAKE_ARG="$2"
@@ -205,6 +212,7 @@ do
         then
                 cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1`
                 cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
+                cpu_count=`configfrag_boot_maxcpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
                 for ((cur_rep=0;cur_rep<$config_reps;cur_rep++))
                 do
                         echo $CF1 $cpu_count >> $T/cfgcpu
@@ -214,7 +222,7 @@ do
                 exit 1
         fi
 done
-sort -k2nr $T/cfgcpu > $T/cfgcpu.sort
+sort -k2nr $T/cfgcpu -T="$T" > $T/cfgcpu.sort
 
 # Use a greedy bin-packing algorithm, sorting the list accordingly.
 awk < $T/cfgcpu.sort > $T/cfgcpu.pack -v ncpus=$cpus '
@@ -275,6 +283,7 @@ TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
 TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY
 TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG
 TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD
+TORTURE_KCONFIG_ARG="$TORTURE_KCONFIG_ARG"; export TORTURE_KCONFIG_ARG
 TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
@@ -324,6 +333,7 @@ function dump(first, pastlast, batchnum)
 {
         print "echo ----Start batch " batchnum ": `date`";
         print "echo ----Start batch " batchnum ": `date` >> " rd "/log";
+        print "needqemurun="
         jn=1
         for (j = first; j < pastlast; j++) {
                 builddir=KVM "/b" jn
@@ -359,10 +369,11 @@ function dump(first, pastlast, batchnum)
         for (j = 1; j < jn; j++) {
                 builddir=KVM "/b" j
                 print "rm -f " builddir ".ready"
-                print "if test -z \"$TORTURE_BUILDONLY\""
+                print "if test -f \"" rd cfr[j] "/builtkernel\""
                 print "then"
-                print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`";
-                print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log";
+                print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date`";
+                print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date` >> " rd "/log";
+                print "\tneedqemurun=1"
                 print "fi"
         }
         njitter = 0;
@@ -377,13 +388,22 @@ function dump(first, pastlast, batchnum)
                 njitter = 0;
                 print "echo Build-only run, so suppressing jitter >> " rd "/log"
         }
-        for (j = 0; j < njitter; j++)
-                print "jitter.sh " j " " dur " " ja[2] " " ja[3] "&"
-        print "wait"
-        print "if test -z \"$TORTURE_BUILDONLY\""
+        if (TORTURE_BUILDONLY) {
+                print "needqemurun="
+        }
+        print "if test -n \"$needqemurun\""
         print "then"
+        print "\techo ---- Starting kernels. `date`";
+        print "\techo ---- Starting kernels. `date` >> " rd "/log";
+        for (j = 0; j < njitter; j++)
+                print "\tjitter.sh " j " " dur " " ja[2] " " ja[3] "&"
+        print "\twait"
         print "\techo ---- All kernel runs complete. `date`";
         print "\techo ---- All kernel runs complete. `date` >> " rd "/log";
+        print "else"
+        print "\twait"
+        print "\techo ---- No kernel runs. `date`";
+        print "\techo ---- No kernel runs. `date` >> " rd "/log";
         print "fi"
         for (j = 1; j < jn; j++) {
                 builddir=KVM "/b" j
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index a6b57622c2e5..24fe5f822b28 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -28,7 +28,7 @@
 
 F=$1
 title=$2
-T=/tmp/parse-build.sh.$$
+T=${TMPDIR-/tmp}/parse-build.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
index e3c5f0705696..f12c38909b00 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
@@ -27,7 +27,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/parse-torture.sh.$$
+T=${TMPDIR-/tmp}/parse-torture.sh.$$
 file="$1"
 title="$2"
 
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
index 6804f9dcfc1b..be7728db42fd 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_busted
+rcutorture.torture_type=busted
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot
deleted file mode 100644
index 84a7d51b7481..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot
+++ /dev/null
@@ -1 +0,0 @@
-rcutorture.torture_type=srcud
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
index 6bc24e99862f..c15ada821e45 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
@@ -4,6 +4,7 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_TINY_SRCU=y
 CONFIG_RCU_TRACE=n
-CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
index 1d14e1383016..9f3a4d28e508 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
@@ -1,4 +1,4 @@
-rcutorture.torture_type=rcu_bh maxcpus=8
+rcutorture.torture_type=rcu_bh maxcpus=8 nr_cpus=43
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 9ad3f89c8dc7..af6fca03602f 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -69,11 +69,11 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE
 CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 CONFIG_TINY_RCU
+CONFIG_TASKS_RCU
 
         These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP.
 
 CONFIG_SRCU
-CONFIG_TASKS_RCU
 
         Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable.
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
index 16b01559fa55..4bed0b678f8b 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all: srcu.c store_buffering
 
 LINUX_SOURCE = ../../../../../..
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
index 4a3d538fef12..891ad13e95b2 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * This header has been modifies to remove definitions of types that
  * are defined in standard userspace headers or are problematic for some
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
index c9e8bc5082a7..e05182d3e47d 100755
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
@@ -1,4 +1,5 @@
 #!/usr/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
 
 # Modify SRCU for formal verification. The first argument should be srcu.h and
 # the second should be srcu.c. Outputs modified srcu.h and srcu.c into the
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
index a64955447995..570a49d9da7e 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ASSUME_H
 #define ASSUME_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
index 6687acc08e6d..3f95a768a03b 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BARRIERS_H
 #define BARRIERS_H
 
@@ -34,8 +35,7 @@
 #define rs_smp_mb() do {} while (0)
 #endif
 
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *) &(x))
-#define READ_ONCE(x) ACCESS_ONCE(x)
-#define WRITE_ONCE(x, val) (ACCESS_ONCE(x) = (val))
+#define READ_ONCE(x) (*(volatile typeof(x) *) &(x))
+#define WRITE_ONCE(x) ((*(volatile typeof(x) *) &(x)) = (val))
 
 #endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
index 2a80e91f78e7..5e7912c6a521 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BUG_ON_H
 #define BUG_ON_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
index 29eb5d2697ed..e67ee5b3dd7c 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <config.h>
 
 /* Include all source files. */
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
index a60038aeea7a..283d7103334f 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* "Cheater" definitions based on restricted Kconfig choices. */
 
 #undef CONFIG_TINY_RCU
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
index 5ec582a53018..e5202d4cff30 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <config.h>
 
 #include <assert.h>
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
index 3aad63917858..0dd27aa517a7 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef INT_TYPEDEFS_H
 #define INT_TYPEDEFS_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
index 356004665576..cf6938d679d7 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LOCKS_H
 #define LOCKS_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
index ca892e3b2351..9440cc39e3c6 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <config.h>
 
 #include "misc.h"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
index 3de5a49de49b..27e67a3f291f 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PERCPU_H
 #define PERCPU_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
index 4f1b068e9b7a..b4083ae348fb 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <config.h>
 
 #include "preempt.h"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
index 2f95ee0e4dd5..f8b762cd214c 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef PREEMPT_H
 #define PREEMPT_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
index ac9cbc62b411..97f592048e0b 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <config.h>
 
 #include <assert.h>
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
index e58c8dfd3e90..28b960300971 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef WORKQUEUES_H
 #define WORKQUEUES_H
 
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
index 3a3aee149225..ad21b925fbb4 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CBMC_FLAGS = -I../.. -I../../src -I../../include -I../../empty_includes -32 -pointer-check -mm pso
 
 all:
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
index 470b1105a112..2ce2016f7871 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <src/combined_source.c>
 
 int x;
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
index d1545972a0fa..2fe1f0339b4f 100755
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 # This script expects a mode (either --should-pass or --should-fail) followed by
 # an input file. The script uses the following environment variables. The test C
diff --git a/tools/testing/selftests/seccomp/.gitignore b/tools/testing/selftests/seccomp/.gitignore
index 346d83ca8069..5af29d3a1b0a 100644
--- a/tools/testing/selftests/seccomp/.gitignore
+++ b/tools/testing/selftests/seccomp/.gitignore
@@ -1 +1,2 @@
 seccomp_bpf
+seccomp_benchmark
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index aeb0c805f3ca..fce7f4ce0692 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,8 +1,17 @@
-TEST_GEN_PROGS := seccomp_bpf
-CFLAGS += -Wl,-no-as-needed -Wall
-LDFLAGS += -lpthread
+# SPDX-License-Identifier: GPL-2.0
+all:
 
 include ../lib.mk
 
-$(TEST_GEN_PROGS): seccomp_bpf.c ../kselftest_harness.h
-        $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+.PHONY: all clean
+
+BINARIES := seccomp_bpf seccomp_benchmark
+CFLAGS += -Wl,-no-as-needed -Wall
+
+seccomp_bpf: seccomp_bpf.c ../kselftest_harness.h
+        $(CC) $(CFLAGS) $(LDFLAGS) -lpthread $< -o $@
+
+TEST_PROGS += $(BINARIES)
+EXTRA_CLEAN := $(BINARIES)
+
+all: $(BINARIES)
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
new file mode 100644
index 000000000000..5838c8697ec3
--- /dev/null
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -0,0 +1,99 @@
+/*
+ * Strictly speaking, this is not a test. But it can report during test
+ * runs so relative performace can be measured.
+ */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#define ARRAY_SIZE(a)    (sizeof(a) / sizeof(a[0]))
+
+unsigned long long timing(clockid_t clk_id, unsigned long long samples)
+{
+        pid_t pid, ret;
+        unsigned long long i;
+        struct timespec start, finish;
+
+        pid = getpid();
+        assert(clock_gettime(clk_id, &start) == 0);
+        for (i = 0; i < samples; i++) {
+                ret = syscall(__NR_getpid);
+                assert(pid == ret);
+        }
+        assert(clock_gettime(clk_id, &finish) == 0);
+
+        i = finish.tv_sec - start.tv_sec;
+        i *= 1000000000;
+        i += finish.tv_nsec - start.tv_nsec;
+
+        printf("%lu.%09lu - %lu.%09lu = %llu\n",
+                finish.tv_sec, finish.tv_nsec,
+                start.tv_sec, start.tv_nsec,
+                i);
+
+        return i;
+}
+
+unsigned long long calibrate(void)
+{
+        unsigned long long i;
+
+        printf("Calibrating reasonable sample size...\n");
+
+        for (i = 5; ; i++) {
+                unsigned long long samples = 1 << i;
+
+                /* Find something that takes more than 5 seconds to run. */
+                if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5)
+                        return samples;
+        }
+}
+
+int main(int argc, char *argv[])
+{
+        struct sock_filter filter[] = {
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+        };
+        struct sock_fprog prog = {
+                .len = (unsigned short)ARRAY_SIZE(filter),
+                .filter = filter,
+        };
+        long ret;
+        unsigned long long samples;
+        unsigned long long native, filtered;
+
+        if (argc > 1)
+                samples = strtoull(argv[1], NULL, 0);
+        else
+                samples = calibrate();
+
+        printf("Benchmarking %llu samples...\n", samples);
+
+        native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+        printf("getpid native: %llu ns\n", native);
+
+        ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+        assert(ret == 0);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+        assert(ret == 0);
+
+        filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+        printf("getpid RET_ALLOW: %llu ns\n", filtered);
+
+        printf("Estimated seccomp overhead per syscall: %llu ns\n",
+                filtered - native);
+
+        if (filtered == native)
+                printf("Trying running again with more samples.\n");
+
+        return 0;
+}
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 73f5ea6778ce..24dbf634e2dd 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -6,10 +6,18 @@
  */
 
 #include <sys/types.h>
-#include <asm/siginfo.h>
-#define __have_siginfo_t 1
-#define __have_sigval_t 1
-#define __have_sigevent_t 1
+
+/*
+ * glibc 2.26 and later have SIGSYS in siginfo_t. Before that,
+ * we need to use the kernel's siginfo.h file and trick glibc
+ * into accepting it.
+ */
+#if !__GLIBC_PREREQ(2, 26)
+# include <asm/siginfo.h>
+# define __have_siginfo_t 1
+# define __have_sigval_t 1
+# define __have_sigevent_t 1
+#endif
 
 #include <errno.h>
 #include <linux/filter.h>
@@ -68,17 +76,7 @@
 #define SECCOMP_MODE_FILTER 2
 #endif
 
-#ifndef SECCOMP_RET_KILL
-#define SECCOMP_RET_KILL        0x00000000U /* kill the task immediately */
-#define SECCOMP_RET_TRAP        0x00030000U /* disallow and force a SIGSYS */
-#define SECCOMP_RET_ERRNO       0x00050000U /* returns an errno */
-#define SECCOMP_RET_TRACE       0x7ff00000U /* pass to a tracer or disallow */
-#define SECCOMP_RET_ALLOW       0x7fff0000U /* allow */
-
-/* Masks for the return value sections. */
-#define SECCOMP_RET_ACTION      0x7fff0000U
-#define SECCOMP_RET_DATA        0x0000ffffU
-
+#ifndef SECCOMP_RET_ALLOW
 struct seccomp_data {
         int nr;
         __u32 arch;
@@ -87,6 +85,70 @@ struct seccomp_data {
 };
 #endif
 
+#ifndef SECCOMP_RET_KILL_PROCESS
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD  0x00000000U /* kill the thread */
+#endif
+#ifndef SECCOMP_RET_KILL
+#define SECCOMP_RET_KILL         SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP         0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO        0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE        0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_ALLOW        0x7fff0000U /* allow */
+#endif
+#ifndef SECCOMP_RET_LOG
+#define SECCOMP_RET_LOG          0x7ffc0000U /* allow after logging */
+#endif
+
+#ifndef __NR_seccomp
+# if defined(__i386__)
+#  define __NR_seccomp 354
+# elif defined(__x86_64__)
+#  define __NR_seccomp 317
+# elif defined(__arm__)
+#  define __NR_seccomp 383
+# elif defined(__aarch64__)
+#  define __NR_seccomp 277
+# elif defined(__hppa__)
+#  define __NR_seccomp 338
+# elif defined(__powerpc__)
+#  define __NR_seccomp 358
+# elif defined(__s390__)
+#  define __NR_seccomp 348
+# else
+#  warning "seccomp syscall number unknown for this architecture"
+#  define __NR_seccomp 0xffff
+# endif
+#endif
+
+#ifndef SECCOMP_SET_MODE_STRICT
+#define SECCOMP_SET_MODE_STRICT 0
+#endif
+
+#ifndef SECCOMP_SET_MODE_FILTER
+#define SECCOMP_SET_MODE_FILTER 1
+#endif
+
+#ifndef SECCOMP_GET_ACTION_AVAIL
+#define SECCOMP_GET_ACTION_AVAIL 2
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_LOG
+#define SECCOMP_FILTER_FLAG_LOG 2
+#endif
+
+#ifndef seccomp
+int seccomp(unsigned int op, unsigned int flags, void *args)
+{
+        errno = 0;
+        return syscall(__NR_seccomp, op, flags, args);
+}
+#endif
+
 #if __BYTE_ORDER == __LITTLE_ENDIAN
 #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
 #elif __BYTE_ORDER == __BIG_ENDIAN
@@ -107,7 +169,7 @@ TEST(mode_strict_support)
         ASSERT_EQ(0, ret) {
                 TH_LOG("Kernel does not support CONFIG_SECCOMP");
         }
-        syscall(__NR_exit, 1);
+        syscall(__NR_exit, 0);
 }
 
 TEST_SIGNAL(mode_strict_cannot_call_prctl, SIGKILL)
@@ -136,7 +198,7 @@ TEST(no_new_privs_support)
         }
 }
 
-/* Tests kernel support by checking for a copy_from_user() fault on * NULL. */
+/* Tests kernel support by checking for a copy_from_user() fault on NULL. */
 TEST(mode_filter_support)
 {
         long ret;
@@ -342,6 +404,28 @@ TEST(empty_prog)
         EXPECT_EQ(EINVAL, errno);
 }
 
+TEST(log_all)
+{
+        struct sock_filter filter[] = {
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+        };
+        struct sock_fprog prog = {
+                .len = (unsigned short)ARRAY_SIZE(filter),
+                .filter = filter,
+        };
+        long ret;
+        pid_t parent = getppid();
+
+        ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+        ASSERT_EQ(0, ret);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+        ASSERT_EQ(0, ret);
+
+        /* getppid() should succeed and be logged (no check for logging) */
+        EXPECT_EQ(parent, syscall(__NR_getppid));
+}
+
 TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS)
 {
         struct sock_filter filter[] = {
@@ -520,6 +604,117 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
         close(fd);
 }
 
+/* This is a thread task to die via seccomp filter violation. */
+void *kill_thread(void *data)
+{
+        bool die = (bool)data;
+
+        if (die) {
+                prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
+                return (void *)SIBLING_EXIT_FAILURE;
+        }
+
+        return (void *)SIBLING_EXIT_UNKILLED;
+}
+
+/* Prepare a thread that will kill itself or both of us. */
+void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process)
+{
+        pthread_t thread;
+        void *status;
+        /* Kill only when calling __NR_prctl. */
+        struct sock_filter filter_thread[] = {
+                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+                        offsetof(struct seccomp_data, nr)),
+                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+        };
+        struct sock_fprog prog_thread = {
+                .len = (unsigned short)ARRAY_SIZE(filter_thread),
+                .filter = filter_thread,
+        };
+        struct sock_filter filter_process[] = {
+                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+                        offsetof(struct seccomp_data, nr)),
+                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+        };
+        struct sock_fprog prog_process = {
+                .len = (unsigned short)ARRAY_SIZE(filter_process),
+                .filter = filter_process,
+        };
+
+        ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+                TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+        }
+
+        ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0,
+                             kill_process ? &prog_process : &prog_thread));
+
+        /*
+         * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS
+         * flag cannot be downgraded by a new filter.
+         */
+        ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread));
+
+        /* Start a thread that will exit immediately. */
+        ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false));
+        ASSERT_EQ(0, pthread_join(thread, &status));
+        ASSERT_EQ(SIBLING_EXIT_UNKILLED, (unsigned long)status);
+
+        /* Start a thread that will die immediately. */
+        ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)true));
+        ASSERT_EQ(0, pthread_join(thread, &status));
+        ASSERT_NE(SIBLING_EXIT_FAILURE, (unsigned long)status);
+
+        /*
+         * If we get here, only the spawned thread died. Let the parent know
+         * the whole process didn't die (i.e. this thread, the spawner,
+         * stayed running).
+         */
+        exit(42);
+}
+
+TEST(KILL_thread)
+{
+        int status;
+        pid_t child_pid;
+
+        child_pid = fork();
+        ASSERT_LE(0, child_pid);
+        if (child_pid == 0) {
+                kill_thread_or_group(_metadata, false);
+                _exit(38);
+        }
+
+        ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+        /* If only the thread was killed, we'll see exit 42. */
+        ASSERT_TRUE(WIFEXITED(status));
+        ASSERT_EQ(42, WEXITSTATUS(status));
+}
+
+TEST(KILL_process)
+{
+        int status;
+        pid_t child_pid;
+
+        child_pid = fork();
+        ASSERT_LE(0, child_pid);
+        if (child_pid == 0) {
+                kill_thread_or_group(_metadata, true);
+                _exit(38);
+        }
+
+        ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+        /* If the entire process was killed, we'll see SIGSYS. */
+        ASSERT_TRUE(WIFSIGNALED(status));
+        ASSERT_EQ(SIGSYS, WTERMSIG(status));
+}
+
 /* TODO(wad) add 64-bit versus 32-bit arg tests. */
 TEST(arg_out_of_range)
 {
@@ -541,26 +736,30 @@ TEST(arg_out_of_range)
         EXPECT_EQ(EINVAL, errno);
 }
 
+#define ERRNO_FILTER(name, errno)                                       \
+        struct sock_filter _read_filter_##name[] = {                    \
+                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,                          \
+                        offsetof(struct seccomp_data, nr)),             \
+                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),       \
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | errno),     \
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),             \
+        };                                                              \
+        struct sock_fprog prog_##name = {                               \
+                .len = (unsigned short)ARRAY_SIZE(_read_filter_##name), \
+                .filter = _read_filter_##name,                          \
+        }
+
+/* Make sure basic errno values are correctly passed through a filter. */
 TEST(ERRNO_valid)
 {
-        struct sock_filter filter[] = {
-                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-                        offsetof(struct seccomp_data, nr)),
-                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | E2BIG),
-                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-        };
-        struct sock_fprog prog = {
-                .len = (unsigned short)ARRAY_SIZE(filter),
-                .filter = filter,
-        };
+        ERRNO_FILTER(valid, E2BIG);
         long ret;
         pid_t parent = getppid();
 
         ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
         ASSERT_EQ(0, ret);
 
-        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_valid);
         ASSERT_EQ(0, ret);
 
         EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -568,26 +767,17 @@ TEST(ERRNO_valid)
         EXPECT_EQ(E2BIG, errno);
 }
 
+/* Make sure an errno of zero is correctly handled by the arch code. */
 TEST(ERRNO_zero)
 {
-        struct sock_filter filter[] = {
-                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-                        offsetof(struct seccomp_data, nr)),
-                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 0),
-                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-        };
-        struct sock_fprog prog = {
-                .len = (unsigned short)ARRAY_SIZE(filter),
-                .filter = filter,
-        };
+        ERRNO_FILTER(zero, 0);
         long ret;
         pid_t parent = getppid();
 
         ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
         ASSERT_EQ(0, ret);
 
-        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_zero);
         ASSERT_EQ(0, ret);
 
         EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -595,26 +785,21 @@ TEST(ERRNO_zero)
         EXPECT_EQ(0, read(0, NULL, 0));
 }
 
+/*
+ * The SECCOMP_RET_DATA mask is 16 bits wide, but errno is smaller.
+ * This tests that the errno value gets capped correctly, fixed by
+ * 580c57f10768 ("seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO").
+ */
 TEST(ERRNO_capped)
 {
-        struct sock_filter filter[] = {
-                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-                        offsetof(struct seccomp_data, nr)),
-                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 4096),
-                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-        };
-        struct sock_fprog prog = {
-                .len = (unsigned short)ARRAY_SIZE(filter),
-                .filter = filter,
-        };
+        ERRNO_FILTER(capped, 4096);
         long ret;
         pid_t parent = getppid();
 
         ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
         ASSERT_EQ(0, ret);
 
-        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_capped);
         ASSERT_EQ(0, ret);
 
         EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -622,6 +807,37 @@ TEST(ERRNO_capped)
         EXPECT_EQ(4095, errno);
 }
 
+/*
+ * Filters are processed in reverse order: last applied is executed first.
+ * Since only the SECCOMP_RET_ACTION mask is tested for return values, the
+ * SECCOMP_RET_DATA mask results will follow the most recently applied
+ * matching filter return (and not the lowest or highest value).
+ */
+TEST(ERRNO_order)
+{
+        ERRNO_FILTER(first,  11);
+        ERRNO_FILTER(second, 13);
+        ERRNO_FILTER(third,  12);
+        long ret;
+        pid_t parent = getppid();
+
+        ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+        ASSERT_EQ(0, ret);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_first);
+        ASSERT_EQ(0, ret);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_second);
+        ASSERT_EQ(0, ret);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_third);
+        ASSERT_EQ(0, ret);
+
+        EXPECT_EQ(parent, syscall(__NR_getppid));
+        EXPECT_EQ(-1, read(0, NULL, 0));
+        EXPECT_EQ(12, errno);
+}
+
 FIXTURE_DATA(TRAP) {
         struct sock_fprog prog;
 };
@@ -676,7 +892,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS)
         syscall(__NR_getpid);
 }
 
-static struct siginfo TRAP_info;
+static siginfo_t TRAP_info;
 static volatile int TRAP_nr;
 static void TRAP_action(int nr, siginfo_t *info, void *void_context)
 {
@@ -735,6 +951,7 @@ TEST_F(TRAP, handler)
 
 FIXTURE_DATA(precedence) {
         struct sock_fprog allow;
+        struct sock_fprog log;
         struct sock_fprog trace;
         struct sock_fprog error;
         struct sock_fprog trap;
@@ -746,6 +963,13 @@ FIXTURE_SETUP(precedence)
         struct sock_filter allow_insns[] = {
                 BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
         };
+        struct sock_filter log_insns[] = {
+                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+                        offsetof(struct seccomp_data, nr)),
+                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+        };
         struct sock_filter trace_insns[] = {
                 BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
                         offsetof(struct seccomp_data, nr)),
@@ -782,6 +1006,7 @@ FIXTURE_SETUP(precedence)
         memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \
         self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns)
         FILTER_ALLOC(allow);
+        FILTER_ALLOC(log);
         FILTER_ALLOC(trace);
         FILTER_ALLOC(error);
         FILTER_ALLOC(trap);
@@ -792,6 +1017,7 @@ FIXTURE_TEARDOWN(precedence)
 {
 #define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter)
         FILTER_FREE(allow);
+        FILTER_FREE(log);
         FILTER_FREE(trace);
         FILTER_FREE(error);
         FILTER_FREE(trap);
@@ -809,6 +1035,8 @@ TEST_F(precedence, allow_ok)
 
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -833,6 +1061,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest, SIGSYS)
 
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -864,6 +1094,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest_in_any_order, SIGSYS)
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
@@ -885,6 +1117,8 @@ TEST_F_SIGNAL(precedence, trap_is_second, SIGSYS)
 
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -910,6 +1144,8 @@ TEST_F_SIGNAL(precedence, trap_is_second_in_any_order, SIGSYS)
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -931,6 +1167,8 @@ TEST_F(precedence, errno_is_third)
 
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -949,6 +1187,8 @@ TEST_F(precedence, errno_is_third_in_any_order)
         ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
         ASSERT_EQ(0, ret);
 
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
@@ -971,6 +1211,8 @@ TEST_F(precedence, trace_is_fourth)
 
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
         ASSERT_EQ(0, ret);
         /* Should work just fine. */
@@ -992,12 +1234,54 @@ TEST_F(precedence, trace_is_fourth_in_any_order)
         ASSERT_EQ(0, ret);
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
         ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
         /* Should work just fine. */
         EXPECT_EQ(parent, syscall(__NR_getppid));
         /* No ptracer */
         EXPECT_EQ(-1, syscall(__NR_getpid));
 }
 
+TEST_F(precedence, log_is_fifth)
+{
+        pid_t mypid, parent;
+        long ret;
+
+        mypid = getpid();
+        parent = getppid();
+        ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+        ASSERT_EQ(0, ret);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+        ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
+        /* Should work just fine. */
+        EXPECT_EQ(parent, syscall(__NR_getppid));
+        /* Should also work just fine */
+        EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
+TEST_F(precedence, log_is_fifth_in_any_order)
+{
+        pid_t mypid, parent;
+        long ret;
+
+        mypid = getpid();
+        parent = getppid();
+        ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+        ASSERT_EQ(0, ret);
+
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+        ASSERT_EQ(0, ret);
+        ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+        ASSERT_EQ(0, ret);
+        /* Should work just fine. */
+        EXPECT_EQ(parent, syscall(__NR_getppid));
+        /* Should also work just fine */
+        EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
 #ifndef PTRACE_O_TRACESECCOMP
 #define PTRACE_O_TRACESECCOMP   0x00000080
 #endif
@@ -1262,6 +1546,13 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
 
+/* When the syscall return can't be changed, stub out the tests for it. */
+#ifdef SYSCALL_NUM_RET_SHARE_REG
+# define EXPECT_SYSCALL_RETURN(val, action)     EXPECT_EQ(-1, action)
+#else
+# define EXPECT_SYSCALL_RETURN(val, action)     EXPECT_EQ(val, action)
+#endif
+
 /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
  * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
  */
@@ -1357,7 +1648,7 @@ void change_syscall(struct __test_metadata *_metadata,
 #ifdef SYSCALL_NUM_RET_SHARE_REG
                 TH_LOG("Can't modify syscall return on this architecture");
 #else
-                regs.SYSCALL_RET = 1;
+                regs.SYSCALL_RET = EPERM;
 #endif
 
 #ifdef HAVE_GETREGS
@@ -1426,6 +1717,8 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
 
         if (nr == __NR_getpid)
                 change_syscall(_metadata, tracee, __NR_getppid);
+        if (nr == __NR_open)
+                change_syscall(_metadata, tracee, -1);
 }
 
 FIXTURE_DATA(TRACE_syscall) {
@@ -1480,6 +1773,28 @@ FIXTURE_TEARDOWN(TRACE_syscall)
                 free(self->prog.filter);
 }
 
+TEST_F(TRACE_syscall, ptrace_syscall_redirected)
+{
+        /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+        teardown_trace_fixture(_metadata, self->tracer);
+        self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+                                           true);
+
+        /* Tracer will redirect getpid to getppid. */
+        EXPECT_NE(self->mypid, syscall(__NR_getpid));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+{
+        /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+        teardown_trace_fixture(_metadata, self->tracer);
+        self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+                                           true);
+
+        /* Tracer should skip the open syscall, resulting in EPERM. */
+        EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open));
+}
+
 TEST_F(TRACE_syscall, syscall_allowed)
 {
         long ret;
@@ -1520,13 +1835,8 @@ TEST_F(TRACE_syscall, syscall_dropped)
         ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
         ASSERT_EQ(0, ret);
 
-#ifdef SYSCALL_NUM_RET_SHARE_REG
-        /* gettid has been skipped */
-        EXPECT_EQ(-1, syscall(__NR_gettid));
-#else
         /* gettid has been skipped and an altered return value stored. */
-        EXPECT_EQ(1, syscall(__NR_gettid));
-#endif
+        EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
         EXPECT_NE(self->mytid, syscall(__NR_gettid));
 }
 
@@ -1557,6 +1867,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE)
         ASSERT_EQ(0, ret);
 
         /* Tracer will redirect getpid to getppid, and we should see EPERM. */
+        errno = 0;
         EXPECT_EQ(-1, syscall(__NR_getpid));
         EXPECT_EQ(EPERM, errno);
 }
@@ -1654,47 +1965,6 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS)
         EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-#ifndef __NR_seccomp
-# if defined(__i386__)
-#  define __NR_seccomp 354
-# elif defined(__x86_64__)
-#  define __NR_seccomp 317
-# elif defined(__arm__)
-#  define __NR_seccomp 383
-# elif defined(__aarch64__)
-#  define __NR_seccomp 277
-# elif defined(__hppa__)
-#  define __NR_seccomp 338
-# elif defined(__powerpc__)
-#  define __NR_seccomp 358
-# elif defined(__s390__)
-#  define __NR_seccomp 348
-# else
-#  warning "seccomp syscall number unknown for this architecture"
-#  define __NR_seccomp 0xffff
-# endif
-#endif
-
-#ifndef SECCOMP_SET_MODE_STRICT
-#define SECCOMP_SET_MODE_STRICT 0
-#endif
-
-#ifndef SECCOMP_SET_MODE_FILTER
-#define SECCOMP_SET_MODE_FILTER 1
-#endif
-
-#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
-#endif
-
-#ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, void *args)
-{
-        errno = 0;
-        return syscall(__NR_seccomp, op, flags, args);
-}
-#endif
-
 TEST(seccomp_syscall)
 {
         struct sock_filter filter[] = {
@@ -1783,6 +2053,67 @@ TEST(seccomp_syscall_mode_lock)
         }
 }
 
+/*
+ * Test detection of known and unknown filter flags. Userspace needs to be able
+ * to check if a filter flag is supported by the current kernel and a good way
+ * of doing that is by attempting to enter filter mode, with the flag bit in
+ * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates
+ * that the flag is valid and EINVAL indicates that the flag is invalid.
+ */
+TEST(detect_seccomp_filter_flags)
+{
+        unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
+                                 SECCOMP_FILTER_FLAG_LOG };
+        unsigned int flag, all_flags;
+        int i;
+        long ret;
+
+        /* Test detection of known-good filter flags */
+        for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+                flag = flags[i];
+                ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+                ASSERT_NE(ENOSYS, errno) {
+                        TH_LOG("Kernel does not support seccomp syscall!");
+                }
+                EXPECT_EQ(-1, ret);
+                EXPECT_EQ(EFAULT, errno) {
+                        TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!",
+                               flag);
+                }
+
+                all_flags |= flag;
+        }
+
+        /* Test detection of all known-good filter flags */
+        ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
+        EXPECT_EQ(-1, ret);
+        EXPECT_EQ(EFAULT, errno) {
+                TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+                       all_flags);
+        }
+
+        /* Test detection of an unknown filter flag */
+        flag = -1;
+        ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+        EXPECT_EQ(-1, ret);
+        EXPECT_EQ(EINVAL, errno) {
+                TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!",
+                       flag);
+        }
+
+        /*
+         * Test detection of an unknown filter flag that may simply need to be
+         * added to this test
+         */
+        flag = flags[ARRAY_SIZE(flags) - 1] << 1;
+        ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+        EXPECT_EQ(-1, ret);
+        EXPECT_EQ(EINVAL, errno) {
+                TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?",
+                       flag);
+        }
+}
+
 TEST(TSYNC_first)
 {
         struct sock_filter filter[] = {
@@ -2421,6 +2752,99 @@ TEST(syscall_restart)
                 _metadata->passed = 0;
 }
 
+TEST_SIGNAL(filter_flag_log, SIGSYS)
+{
+        struct sock_filter allow_filter[] = {
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+        };
+        struct sock_filter kill_filter[] = {
+                BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+                        offsetof(struct seccomp_data, nr)),
+                BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+                BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+        };
+        struct sock_fprog allow_prog = {
+                .len = (unsigned short)ARRAY_SIZE(allow_filter),
+                .filter = allow_filter,
+        };
+        struct sock_fprog kill_prog = {
+                .len = (unsigned short)ARRAY_SIZE(kill_filter),
+                .filter = kill_filter,
+        };
+        long ret;
+        pid_t parent = getppid();
+
+        ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+        ASSERT_EQ(0, ret);
+
+        /* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */
+        ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG,
+                      &allow_prog);
+        ASSERT_NE(ENOSYS, errno) {
+                TH_LOG("Kernel does not support seccomp syscall!");
+        }
+        EXPECT_NE(0, ret) {
+                TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!");
+        }
+        EXPECT_EQ(EINVAL, errno) {
+                TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!");
+        }
+
+        /* Verify that a simple, permissive filter can be added with no flags */
+        ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog);
+        EXPECT_EQ(0, ret);
+
+        /* See if the same filter can be added with the FILTER_FLAG_LOG flag */
+        ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+                      &allow_prog);
+        ASSERT_NE(EINVAL, errno) {
+                TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!");
+        }
+        EXPECT_EQ(0, ret);
+
+        /* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */
+        ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+                      &kill_prog);
+        EXPECT_EQ(0, ret);
+
+        EXPECT_EQ(parent, syscall(__NR_getppid));
+        /* getpid() should never return. */
+        EXPECT_EQ(0, syscall(__NR_getpid));
+}
+
+TEST(get_action_avail)
+{
+        __u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP,
+                            SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE,
+                            SECCOMP_RET_LOG,   SECCOMP_RET_ALLOW };
+        __u32 unknown_action = 0x10000000U;
+        int i;
+        long ret;
+
+        ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]);
+        ASSERT_NE(ENOSYS, errno) {
+                TH_LOG("Kernel does not support seccomp syscall!");
+        }
+        ASSERT_NE(EINVAL, errno) {
+                TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!");
+        }
+        EXPECT_EQ(ret, 0);
+
+        for (i = 0; i < ARRAY_SIZE(actions); i++) {
+                ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]);
+                EXPECT_EQ(ret, 0) {
+                        TH_LOG("Expected action (0x%X) not available!",
+                               actions[i]);
+                }
+        }
+
+        /* Check that an unknown action is handled properly (EOPNOTSUPP) */
+        ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action);
+        EXPECT_EQ(ret, -1);
+        EXPECT_EQ(errno, EOPNOTSUPP);
+}
+
 /*
  * TODO:
  * - add microbenchmarks
@@ -2429,6 +2853,8 @@ TEST(syscall_restart)
  * - endianness checking when appropriate
  * - 64-bit arg prodding
  * - arch value testing (x86 modes especially)
+ * - verify that FILTER_FLAG_LOG filters generate log messages
+ * - verify that RET_LOG generates log messages
  * - ...
  */
 
diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c
index ccd07343d418..228c2ae47687 100644
--- a/tools/testing/selftests/sigaltstack/sas.c
+++ b/tools/testing/selftests/sigaltstack/sas.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Stas Sergeev <stsp@users.sourceforge.net>
  *
@@ -17,6 +18,8 @@
 #include <assert.h>
 #include <errno.h>
 
+#include "../kselftest.h"
+
 #ifndef SS_AUTODISARM
 #define SS_AUTODISARM  (1U << 31)
 #endif
@@ -37,12 +40,15 @@ void my_usr1(int sig, siginfo_t *si, void *u)
         stack_t stk;
         struct stk_data *p;
 
+#if __s390x__
+        register unsigned long sp asm("%15");
+#else
         register unsigned long sp asm("sp");
+#endif
 
         if (sp < (unsigned long)sstack ||
                         sp >= (unsigned long)sstack + SIGSTKSZ) {
-                printf("[FAIL]\tSP is not on sigaltstack\n");
-                exit(EXIT_FAILURE);
+                ksft_exit_fail_msg("SP is not on sigaltstack\n");
         }
         /* put some data on stack. other sighandler will try to overwrite it */
         aa = alloca(1024);
@@ -50,21 +56,22 @@ void my_usr1(int sig, siginfo_t *si, void *u)
         p = (struct stk_data *)(aa + 512);
         strcpy(p->msg, msg);
         p->flag = 1;
-        printf("[RUN]\tsignal USR1\n");
+        ksft_print_msg("[RUN]\tsignal USR1\n");
         err = sigaltstack(NULL, &stk);
         if (err) {
-                perror("[FAIL]\tsigaltstack()");
+                ksft_exit_fail_msg("sigaltstack() - %s\n", strerror(errno));
                 exit(EXIT_FAILURE);
         }
         if (stk.ss_flags != SS_DISABLE)
-                printf("[FAIL]\tss_flags=%x, should be SS_DISABLE\n",
+                ksft_test_result_fail("tss_flags=%x, should be SS_DISABLE\n",
                                 stk.ss_flags);
         else
-                printf("[OK]\tsigaltstack is disabled in sighandler\n");
+                ksft_test_result_pass(
+                                "sigaltstack is disabled in sighandler\n");
         swapcontext(&sc, &uc);
-        printf("%s\n", p->msg);
+        ksft_print_msg("%s\n", p->msg);
         if (!p->flag) {
-                printf("[RUN]\tAborting\n");
+                ksft_exit_skip("[RUN]\tAborting\n");
                 exit(EXIT_FAILURE);
         }
 }
@@ -74,13 +81,13 @@ void my_usr2(int sig, siginfo_t *si, void *u)
         char *aa;
         struct stk_data *p;
 
-        printf("[RUN]\tsignal USR2\n");
+        ksft_print_msg("[RUN]\tsignal USR2\n");
         aa = alloca(1024);
         /* dont run valgrind on this */
         /* try to find the data stored by previous sighandler */
         p = memmem(aa, 1024, msg, strlen(msg));
         if (p) {
-                printf("[FAIL]\tsigaltstack re-used\n");
+                ksft_test_result_fail("sigaltstack re-used\n");
                 /* corrupt the data */
                 strcpy(p->msg, msg2);
                 /* tell other sighandler that his data is corrupted */
@@ -90,7 +97,7 @@ void my_usr2(int sig, siginfo_t *si, void *u)
 
 static void switch_fn(void)
 {
-        printf("[RUN]\tswitched to user ctx\n");
+        ksft_print_msg("[RUN]\tswitched to user ctx\n");
         raise(SIGUSR2);
         setcontext(&sc);
 }
@@ -101,6 +108,8 @@ int main(void)
         stack_t stk;
         int err;
 
+        ksft_print_header();
+
         sigemptyset(&act.sa_mask);
         act.sa_flags = SA_ONSTACK | SA_SIGINFO;
         act.sa_sigaction = my_usr1;
@@ -110,19 +119,20 @@ int main(void)
         sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
                       MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
         if (sstack == MAP_FAILED) {
-                perror("mmap()");
+                ksft_exit_fail_msg("mmap() - %s\n", strerror(errno));
                 return EXIT_FAILURE;
         }
 
         err = sigaltstack(NULL, &stk);
         if (err) {
-                perror("[FAIL]\tsigaltstack()");
+                ksft_exit_fail_msg("sigaltstack() - %s\n", strerror(errno));
                 exit(EXIT_FAILURE);
         }
         if (stk.ss_flags == SS_DISABLE) {
-                printf("[OK]\tInitial sigaltstack state was SS_DISABLE\n");
+                ksft_test_result_pass(
+                                "Initial sigaltstack state was SS_DISABLE\n");
         } else {
-                printf("[FAIL]\tInitial sigaltstack state was %x; "
+                ksft_exit_fail_msg("Initial sigaltstack state was %x; "
                        "should have been SS_DISABLE\n", stk.ss_flags);
                 return EXIT_FAILURE;
         }
@@ -133,7 +143,8 @@ int main(void)
         err = sigaltstack(&stk, NULL);
         if (err) {
                 if (errno == EINVAL) {
-                        printf("[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n");
+                        ksft_exit_skip(
+                                "[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n");
                         /*
                          * If test cases for the !SS_AUTODISARM variant were
                          * added, we could still run them.  We don't have any
@@ -142,7 +153,9 @@ int main(void)
                          */
                         return 0;
                 } else {
-                        perror("[FAIL]\tsigaltstack(SS_ONSTACK | SS_AUTODISARM)");
+                        ksft_exit_fail_msg(
+                                "sigaltstack(SS_ONSTACK | SS_AUTODISARM)  %s\n",
+                                        strerror(errno));
                         return EXIT_FAILURE;
                 }
         }
@@ -150,7 +163,7 @@ int main(void)
         ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
                       MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
         if (ustack == MAP_FAILED) {
-                perror("mmap()");
+                ksft_exit_fail_msg("mmap() - %s\n", strerror(errno));
                 return EXIT_FAILURE;
         }
         getcontext(&uc);
@@ -162,16 +175,17 @@ int main(void)
 
         err = sigaltstack(NULL, &stk);
         if (err) {
-                perror("[FAIL]\tsigaltstack()");
+                ksft_exit_fail_msg("sigaltstack() - %s\n", strerror(errno));
                 exit(EXIT_FAILURE);
         }
         if (stk.ss_flags != SS_AUTODISARM) {
-                printf("[FAIL]\tss_flags=%x, should be SS_AUTODISARM\n",
+                ksft_exit_fail_msg("ss_flags=%x, should be SS_AUTODISARM\n",
                                 stk.ss_flags);
                 exit(EXIT_FAILURE);
         }
-        printf("[OK]\tsigaltstack is still SS_AUTODISARM after signal\n");
+        ksft_test_result_pass(
+                        "sigaltstack is still SS_AUTODISARM after signal\n");
 
-        printf("[OK]\tTest passed\n");
+        ksft_exit_pass();
         return 0;
 }
diff --git a/tools/testing/selftests/splice/.gitignore b/tools/testing/selftests/splice/.gitignore
new file mode 100644
index 000000000000..1e23fefd68e8
--- /dev/null
+++ b/tools/testing/selftests/splice/.gitignore
@@ -0,0 +1 @@
+default_file_splice_read
diff --git a/tools/testing/selftests/splice/Makefile b/tools/testing/selftests/splice/Makefile
index 9fc78e5e5451..e519b159b60d 100644
--- a/tools/testing/selftests/splice/Makefile
+++ b/tools/testing/selftests/splice/Makefile
@@ -1,7 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := default_file_splice_read.sh
-EXTRA := default_file_splice_read
-all: $(TEST_PROGS) $(EXTRA)
+TEST_GEN_PROGS_EXTENDED := default_file_splice_read
 
 include ../lib.mk
-
-EXTRA_CLEAN := $(EXTRA)
diff --git a/tools/testing/selftests/splice/default_file_splice_read.c b/tools/testing/selftests/splice/default_file_splice_read.c
index 01dd6091554c..a3c6e5672e09 100644
--- a/tools/testing/selftests/splice/default_file_splice_read.c
+++ b/tools/testing/selftests/splice/default_file_splice_read.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <fcntl.h>
 
diff --git a/tools/testing/selftests/splice/default_file_splice_read.sh b/tools/testing/selftests/splice/default_file_splice_read.sh
index 1ea2adeabc94..490db5a2e435 100755
--- a/tools/testing/selftests/splice/default_file_splice_read.sh
+++ b/tools/testing/selftests/splice/default_file_splice_read.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 n=`./default_file_splice_read </dev/null | wc -c`
 
 test "$n" = 0 && exit 0
diff --git a/tools/testing/selftests/static_keys/test_static_keys.sh b/tools/testing/selftests/static_keys/test_static_keys.sh
index 1261e3fa1e3a..24cff498b31a 100755
--- a/tools/testing/selftests/static_keys/test_static_keys.sh
+++ b/tools/testing/selftests/static_keys/test_static_keys.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs static keys kernel module tests
 
 if /sbin/modprobe -q test_static_key_base; then
diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile
index 4981c6b6d050..b3c8ba3cb668 100644
--- a/tools/testing/selftests/sync/Makefile
+++ b/tools/testing/selftests/sync/Makefile
@@ -1,13 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
 CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra
 CFLAGS += -I../../../../usr/include/
 LDFLAGS += -pthread
 
-TEST_PROGS = sync_test
-
-all: $(TEST_PROGS)
+.PHONY: all clean
 
 include ../lib.mk
 
+# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special
+# build rules. lib.mk will run and install them.
+
+TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test
+all: $(TEST_CUSTOM_PROGS)
+
 OBJS = sync_test.o sync.o
 
 TESTS += sync_alloc.o
@@ -18,6 +23,16 @@ TESTS += sync_stress_parallelism.o
 TESTS += sync_stress_consumer.o
 TESTS += sync_stress_merge.o
 
-sync_test: $(OBJS) $(TESTS)
+OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS))
+TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS))
+
+$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS)
+        $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS)
+
+$(OBJS): $(OUTPUT)/%.o: %.c
+        $(CC) -c $^ -o $@
+
+$(TESTS): $(OUTPUT)/%.o: %.c
+        $(CC) -c $^ -o $@
 
-EXTRA_CLEAN := sync_test $(OBJS) $(TESTS)
+EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS)
diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c
index 62fa666e501a..7f7938263c5c 100644
--- a/tools/testing/selftests/sync/sync_test.c
+++ b/tools/testing/selftests/sync/sync_test.c
@@ -31,62 +31,83 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
+#include <errno.h>
+#include <string.h>
 
+#include "../kselftest.h"
 #include "synctest.h"
 
 static int run_test(int (*test)(void), char *name)
 {
         int result;
         pid_t childpid;
+        int ret;
 
         fflush(stdout);
         childpid = fork();
 
         if (childpid) {
                 waitpid(childpid, &result, 0);
-                if (WIFEXITED(result))
-                        return WEXITSTATUS(result);
+                if (WIFEXITED(result)) {
+                        ret = WEXITSTATUS(result);
+                        if (!ret)
+                                ksft_test_result_pass("[RUN]\t%s\n", name);
+                        else
+                                ksft_test_result_fail("[RUN]\t%s\n", name);
+                        return ret;
+                }
                 return 1;
         }
 
-        printf("[RUN]\tExecuting %s\n", name);
         exit(test());
 }
 
-static int sync_api_supported(void)
+static void sync_api_supported(void)
 {
         struct stat sbuf;
+        int ret;
 
-        return 0 == stat("/sys/kernel/debug/sync/sw_sync", &sbuf);
+        ret = stat("/sys/kernel/debug/sync/sw_sync", &sbuf);
+        if (!ret)
+                return;
+
+        if (errno == ENOENT)
+                ksft_exit_skip("Sync framework not supported by kernel\n");
+
+        if (errno == EACCES)
+                ksft_exit_skip("Run Sync test as root.\n");
+
+        ksft_exit_fail_msg("stat failed on /sys/kernel/debug/sync/sw_sync: %s",
+                                strerror(errno));
 }
 
 int main(void)
 {
-        int err = 0;
+        int err;
 
-        if (!sync_api_supported()) {
-                printf("SKIP: Sync framework not supported by kernel\n");
-                return 0;
-        }
+        ksft_print_header();
+
+        sync_api_supported();
 
-        printf("[RUN]\tTesting sync framework\n");
+        ksft_print_msg("[RUN]\tTesting sync framework\n");
 
-        err += RUN_TEST(test_alloc_timeline);
-        err += RUN_TEST(test_alloc_fence);
-        err += RUN_TEST(test_alloc_fence_negative);
+        RUN_TEST(test_alloc_timeline);
+        RUN_TEST(test_alloc_fence);
+        RUN_TEST(test_alloc_fence_negative);
 
-        err += RUN_TEST(test_fence_one_timeline_wait);
-        err += RUN_TEST(test_fence_one_timeline_merge);
-        err += RUN_TEST(test_fence_merge_same_fence);
-        err += RUN_TEST(test_fence_multi_timeline_wait);
-        err += RUN_TEST(test_stress_two_threads_shared_timeline);
-        err += RUN_TEST(test_consumer_stress_multi_producer_single_consumer);
-        err += RUN_TEST(test_merge_stress_random_merge);
+        RUN_TEST(test_fence_one_timeline_wait);
+        RUN_TEST(test_fence_one_timeline_merge);
+        RUN_TEST(test_fence_merge_same_fence);
+        RUN_TEST(test_fence_multi_timeline_wait);
+        RUN_TEST(test_stress_two_threads_shared_timeline);
+        RUN_TEST(test_consumer_stress_multi_producer_single_consumer);
+        RUN_TEST(test_merge_stress_random_merge);
 
+        err = ksft_get_fail_cnt();
         if (err)
-                printf("[FAIL]\tsync errors: %d\n", err);
-        else
-                printf("[OK]\tsync\n");
+                ksft_exit_fail_msg("%d out of %d sync tests failed\n",
+                                        err, ksft_test_num());
 
-        return !!err;
+        /* need this return to keep gcc happy */
+        return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/sync/synctest.h b/tools/testing/selftests/sync/synctest.h
index e7d1d57dba7a..90a8e5369914 100644
--- a/tools/testing/selftests/sync/synctest.h
+++ b/tools/testing/selftests/sync/synctest.h
@@ -29,10 +29,11 @@
 #define SELFTESTS_SYNCTEST_H
 
 #include <stdio.h>
+#include "../kselftest.h"
 
 #define ASSERT(cond, msg) do { \
         if (!(cond)) { \
-                printf("[ERROR]\t%s", (msg)); \
+                ksft_print_msg("[ERROR]\t%s", (msg)); \
                 return 1; \
         } \
 } while (0)
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index ec232c3cfcaa..ec232c3cfcaa 100644..100755
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore
index c18dd8d83cee..7a60b85e148f 100644
--- a/tools/testing/selftests/tc-testing/.gitignore
+++ b/tools/testing/selftests/tc-testing/.gitignore
@@ -1 +1,2 @@
 __pycache__/
+*.pyc
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
index 4e09257bc443..00438331ba47 100644
--- a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
+++ b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt
@@ -34,6 +34,12 @@ category:     A list of single-word descriptions covering what the command
 setup:        The list of commands required to ensure the command under test
               succeeds. For example: if testing a filter, the command to create
               the qdisc would appear here.
+              This list can be empty.
+              Each command can be a string to be executed, or a list consisting
+              of a string which is a command to be executed, followed by 1 or
+              more acceptable exit codes for this command.
+              If only a string is given for the command, then an exit code of 0
+              will be expected.
 cmdUnderTest: The tc command being tested itself.
 expExitCode:  The code returned by the command under test upon its termination.
               tdc will compare this value against the actual returned value.
@@ -49,6 +55,12 @@ matchCount:   How many times the regex in matchPattern should match. A value
 teardown:     The list of commands to clean up after the test is completed.
               The environment should be returned to the same state as when
               this test was started: qdiscs deleted, actions flushed, etc.
+              This list can be empty.
+              Each command can be a string to be executed, or a list consisting
+              of a string which is a command to be executed, followed by 1 or
+              more acceptable exit codes for this command.
+              If only a string is given for the command, then an exit code of 0
+              will be expected.
 
 
 SETUP/TEARDOWN ERRORS
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/example.json b/tools/testing/selftests/tc-testing/creating-testcases/example.json
new file mode 100644
index 000000000000..5ec501200970
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/creating-testcases/example.json
@@ -0,0 +1,55 @@
+[
+    {
+        "id": "1f",
+        "name": "simple test to test framework",
+        "category": [
+            "example"
+        ],
+        "setup": [
+            "mkdir mytest"
+        ],
+        "cmdUnderTest": "touch mytest/blorfl",
+        "expExitCode": "0",
+        "verifyCmd": "ls mytest/* | grep '[b]lorfl'",
+        "matchPattern": "orfl",
+        "matchCount": "1",
+        "teardown": [
+            "rm -rf mytest"
+        ]
+    },
+    {
+        "id": "2f",
+        "name": "simple test, no need for verify",
+        "category": [
+            "example"
+        ],
+        "setup": [
+            "mkdir mytest",
+            "touch mytest/blorfl"
+        ],
+        "cmdUnderTest": "ls mytest/blorfl",
+        "expExitCode": "0",
+        "verifyCmd": "/bin/true",
+        "matchPattern": " ",
+        "matchCount": "0",
+        "teardown": [
+            "rm -rf mytest"
+        ]
+    },
+    {
+        "id": "3f",
+        "name": "simple test, no need for setup or teardown (or verify)",
+        "category": [
+            "example"
+        ],
+        "setup": [
+        ],
+        "cmdUnderTest": "ip l l lo",
+        "expExitCode": "0",
+        "verifyCmd": "/bin/true",
+        "matchPattern": " ",
+        "matchCount": "0",
+        "teardown": [
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/creating-testcases/template.json b/tools/testing/selftests/tc-testing/creating-testcases/template.json
index 87971744bdd4..8b99b86d65bd 100644
--- a/tools/testing/selftests/tc-testing/creating-testcases/template.json
+++ b/tools/testing/selftests/tc-testing/creating-testcases/template.json
@@ -26,7 +26,13 @@
             ""
         ],
         "setup": [
-            ""
+            "",
+            [
+                "",
+                0,
+                1,
+                255
+            ]
         ],
         "cmdUnderTest": "",
         "expExitCode": "",
@@ -34,7 +40,12 @@
         "matchPattern": "",
         "matchCount": "",
         "teardown": [
-            ""
+            "",
+            [
+                "",
+                0,
+                255
+            ]
         ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
new file mode 100644
index 000000000000..e2187b6e0b7a
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -0,0 +1,469 @@
+[
+    {
+        "id": "e89a",
+        "name": "Add valid pass action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pass index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "a02c",
+        "name": "Add valid pipe action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pipe index 6",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "feef",
+        "name": "Add valid reclassify action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action reclassify index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "8a7a",
+        "name": "Add valid drop action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 30",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "9a52",
+        "name": "Add valid continue action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action continue index 432",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "d700",
+        "name": "Add invalid action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pump index 386",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action.*index 386 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "9215",
+        "name": "Add action with duplicate index",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pipe index 15"
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 15",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "798e",
+        "name": "Add action with index exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 4294967296",
+        "expExitCode": "255",
+        "verifyCmd": "actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "22be",
+        "name": "Add action with index at 32-bit maximum",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action drop index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "ac2a",
+        "name": "List actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions list action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "5",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "3edf",
+        "name": "Flush gact actions",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            "$TC actions add action reclassify index 101",
+            "$TC actions add action reclassify index 102",
+            "$TC actions add action reclassify index 103",
+            "$TC actions add action reclassify index 104",
+            "$TC actions add action reclassify index 105"
+        ],
+        "cmdUnderTest": "$TC actions flush action gact",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify",
+        "matchCount": "0",
+        "teardown": []
+    },
+    {
+        "id": "63ec",
+        "name": "Delete pass action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pass index 1"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "46be",
+        "name": "Delete pipe action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pipe index 9"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 9",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "2e08",
+        "name": "Delete reclassify action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action reclassify index 65536"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 65536",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "99c4",
+        "name": "Delete drop action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 16"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 16",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "fb6b",
+        "name": "Delete continue action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action continue index 32"
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 32",
+        "expExitCode": "0",
+        "verifyCmd": "actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "0eb3",
+        "name": "Delete non-existent action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions del action gact index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "f02c",
+        "name": "Replace gact action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 10",
+            "$TC actions add action drop index 12"
+        ],
+        "cmdUnderTest": "$TC actions replace action ok index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action gact",
+        "matchPattern": "action order [0-9]*: gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    },
+    {
+        "id": "525f",
+        "name": "Get gact action by index",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action drop index 3900800700"
+        ],
+        "cmdUnderTest": "$TC actions get action gact index 3900800700",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action gact index 3900800700",
+        "matchPattern": "index 3900800700",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
new file mode 100644
index 000000000000..9f34f0753969
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -0,0 +1,52 @@
+[
+    {
+        "id": "a568",
+        "name": "Add action with ife type",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode type 0xDEAD index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action ife index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action ife index 1",
+        "matchPattern": "type 0xDEAD",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    },
+    {
+        "id": "b983",
+        "name": "Add action without ife type",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action ife index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action ife index 1",
+        "matchPattern": "type 0xED3E",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
new file mode 100644
index 000000000000..0fcccf18399b
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -0,0 +1,223 @@
+[
+    {
+        "id": "5124",
+        "name": "Add mirred mirror to egress action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "6fb4",
+        "name": "Add mirred redirect to egress action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "ba38",
+        "name": "Get mirred actions",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 1 dev lo",
+            "$TC actions add action mirred egress redirect index 2 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions show action mirred",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "[Mirror|Redirect] to device lo",
+        "matchCount": "2",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "d7c0",
+        "name": "Add invalid mirred direction",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "e213",
+        "name": "Add invalid mirred action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "2d89",
+        "name": "Add mirred action with invalid device",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "300b",
+        "name": "Add mirred action with duplicate index",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress redirect index 15 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "a70e",
+        "name": "Delete mirred mirror action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress mirror index 5 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions del action mirred index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    },
+    {
+        "id": "3fb3",
+        "name": "Delete mirred redirect action",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred egress redirect index 5 dev lo"
+        ],
+        "cmdUnderTest": "$TC actions del action mirred index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action mirred",
+        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
new file mode 100644
index 000000000000..0e602a3f9393
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -0,0 +1,527 @@
+[
+    {
+        "id": "49aa",
+        "name": "Add valid basic police action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 1Kbit burst 10Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "3abe",
+        "name": "Add police action with duplicate index",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 4Mbit burst 120k index 9"
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 8kbit burst 24k index 9",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x9",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "49fa",
+        "name": "Add valid police action with mtu",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 1k index 98",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 98",
+        "matchPattern": "action order [0-9]*:  police 0x62 rate 90Kbit burst 10Kb mtu 1Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "7943",
+        "name": "Add valid police action with peakrate",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 2kb peakrate 100kbit index 3",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x3 rate 90Kbit burst 10Kb mtu 2Kb peakrate 100Kbit",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "055e",
+        "name": "Add police action with peakrate and no mtu",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 5kbit burst 6kb peakrate 10kbit index 9",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x9 rate 5Kb burst 10Kb",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "f057",
+        "name": "Add police action with valid overhead",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1mbit burst 100k overhead 64 index 64",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 64",
+        "matchPattern": "action order [0-9]*:  police 0x40 rate 1Mbit burst 100Kb mtu 2Kb action reclassify overhead 64b",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "7ffb",
+        "name": "Add police action with ethernet linklayer type",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer ethernet index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions show action police",
+        "matchPattern": "action order [0-9]*:  police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "3dda",
+        "name": "Add police action with atm linklayer type",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer atm index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions show action police",
+        "matchPattern": "action order [0-9]*:  police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "551b",
+        "name": "Add police actions with conform-exceed control continue/drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed continue/drop index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action continue/drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "0c70",
+        "name": "Add police actions with conform-exceed control pass/reclassify",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/reclassify index 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x4 rate 3Mbit burst 250Kb mtu 2Kb action pass/reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "d946",
+        "name": "Add police actions with conform-exceed control pass/pipe",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/pipe index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x5 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "336e",
+        "name": "Delete police action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 5mbit burst 2m index 12"
+        ],
+        "cmdUnderTest": "$TC actions delete action police index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0xc rate 5Mb burst 2Mb",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "77fa",
+        "name": "Get single police action from many actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions get action police index 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 4",
+        "matchPattern": "action order [0-9]*:  police 0x4 rate 4Mbit burst 400Kb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "aa43",
+        "name": "Get single police action without specifying index",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1"
+        ],
+        "cmdUnderTest": "$TC actions get action police",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action police",
+        "matchPattern": "action order [0-9]*:  police",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "858b",
+        "name": "List police actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions list action police",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x[1-8] rate [1-8]Mbit burst [1-8]00Kb",
+        "matchCount": "8",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "1c3a",
+        "name": "Flush police actions",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            "$TC actions add action police rate 1mbit burst 100k index 1",
+            "$TC actions add action police rate 2mbit burst 200k index 2",
+            "$TC actions add action police rate 3mbit burst 300k index 3",
+            "$TC actions add action police rate 4mbit burst 400k index 4",
+            "$TC actions add action police rate 5mbit burst 500k index 5",
+            "$TC actions add action police rate 6mbit burst 600k index 6",
+            "$TC actions add action police rate 7mbit burst 700k index 7",
+            "$TC actions add action police rate 8mbit burst 800k index 8"
+        ],
+        "cmdUnderTest": "$TC actions flush action police",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police",
+        "matchCount": "0",
+        "teardown": [
+            ""
+        ]
+    },
+    {
+        "id": "7326",
+        "name": "Add police action with control continue",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "34fa",
+        "name": "Add police action with control drop",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "8dd5",
+        "name": "Add police action with control ok",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "b9d1",
+        "name": "Add police action with control reclassify",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action police index 1",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "c534",
+        "name": "Add police action with control pipe",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
new file mode 100644
index 000000000000..e89a7aa4012d
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -0,0 +1,130 @@
+[
+    {
+        "id": "b078",
+        "name": "Add simple action",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "6d4c",
+        "name": "Add simple action with duplicate index",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Aruba\" index 4"
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "2542",
+        "name": "List simple actions",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Rock\"",
+            "$TC actions add action simple sdata \"Paper\"",
+            "$TC actions add action simple sdata \"Scissors\" index 98"
+        ],
+        "cmdUnderTest": "$TC actions list action simple",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
+        "matchCount": "3",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "ea67",
+        "name": "Delete simple action",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Blinkenlights\" index 1"
+        ],
+        "cmdUnderTest": "$TC actions delete action simple index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
+    {
+        "id": "8ff1",
+        "name": "Flush simple actions",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"Kirk\"",
+            "$TC actions add action simple sdata \"Spock\" index 50",
+            "$TC actions add action simple sdata \"McCoy\" index 9"
+        ],
+        "cmdUnderTest": "$TC actions flush action simple",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
+        "matchCount": "0",
+        "teardown": [
+            ""
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
new file mode 100644
index 000000000000..99635ea4722e
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -0,0 +1,320 @@
+[
+    {
+        "id": "6236",
+        "name": "Add skbedit action with valid mark",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "407b",
+        "name": "Add skbedit action with invalid mark",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 666777888999",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "081d",
+        "name": "Add skbedit action with priority",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit prio 99",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit priority :99",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "cc37",
+        "name": "Add skbedit action with invalid priority",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit prio foo",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit priority",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "3c95",
+        "name": "Add skbedit action with queue_mapping",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "985c",
+        "name": "Add skbedit action with invalid queue_mapping",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit queue_mapping",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "224f",
+        "name": "Add skbedit action with ptype host",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype host",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype host",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "d1a3",
+        "name": "Add skbedit action with ptype otherhost",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "b9c6",
+        "name": "Add skbedit action with invalid ptype",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit ptype openair",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit ptype openair",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "5172",
+        "name": "List skbedit actions",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit ptype otherhost",
+            "$TC actions add action skbedit ptype broadcast",
+            "$TC actions add action skbedit mark 59",
+            "$TC actions add action skbedit mark 409"
+        ],
+        "cmdUnderTest": "$TC actions list action skbedit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchCount": "4",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "a6d6",
+        "name": "Add skbedit action with index",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "index 4040404040",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "38f3",
+        "name": "Delete skbedit action",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit mark 42 index 9009"
+        ],
+        "cmdUnderTest": "$TC actions del action skbedit index 9009",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit mark 42",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "ce97",
+        "name": "Flush skbedit actions",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            "$TC actions add action skbedit mark 500",
+            "$TC actions add action skbedit mark 501",
+            "$TC actions add action skbedit mark 502",
+            "$TC actions add action skbedit mark 503",
+            "$TC actions add action skbedit mark 504",
+            "$TC actions add action skbedit mark 505",
+            "$TC actions add action skbedit mark 506"
+        ],
+        "cmdUnderTest": "$TC actions flush action skbedit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
new file mode 100644
index 000000000000..e34075059c26
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -0,0 +1,372 @@
+[
+    {
+        "id": "7d50",
+        "name": "Add skbmod action to set destination mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set dmac 11:22:33:44:55:66 index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set dmac 11:22:33:44:55:66\\s+index 5",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "9b29",
+        "name": "Add skbmod action to set source mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 77:88:99:AA:BB:CC index 7",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 7",
+        "matchPattern": "action order [0-9]*: skbmod pipe set smac 77:88:99:aa:bb:cc\\s+index 7",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "1724",
+        "name": "Add skbmod action with invalid mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 00:44:55:44:55",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set smac 00:44:55:44:55",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "3cf1",
+        "name": "Add skbmod action with valid etype",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFE",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "a749",
+        "name": "Add skbmod action with invalid etype",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefef",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFEF",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "bfe6",
+        "name": "Add skbmod action to swap mac",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod swap mac",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 1",
+        "matchPattern": "action order [0-9]*: skbmod pipe swap mac",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "839b",
+        "name": "Add skbmod action with control pipe",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod swap mac pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe swap mac",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "c167",
+        "name": "Add skbmod action with control reclassify",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0xbeef reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod reclassify set etype 0xBEEF",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "0c2f",
+        "name": "Add skbmod action with control drop",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0x0001 drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 1",
+        "matchPattern": "action order [0-9]*: skbmod drop set etype 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "d113",
+        "name": "Add skbmod action with control continue",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set etype 0x1 continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod continue set etype 0x1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "7242",
+        "name": "Add skbmod action with control pass",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbmod set smac 00:00:00:00:00:01 pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pass set smac 00:00:00:00:00:01",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "58cb",
+        "name": "List skbmod actions",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions ls action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod",
+        "matchCount": "5",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "9aa8",
+        "name": "Get a single skbmod action from a list",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions ls action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action skbmod index 4",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "e93a",
+        "name": "Delete an skbmod action",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x1111 index 909"
+        ],
+        "cmdUnderTest": "$TC actions del action skbmod index 909",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x1111\\s+index 909",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    },
+    {
+        "id": "40c2",
+        "name": "Flush skbmod actions",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            "$TC actions add action skbmod set etype 0x0001",
+            "$TC actions add action skbmod set etype 0x0011",
+            "$TC actions add action skbmod set etype 0x0021",
+            "$TC actions add action skbmod set etype 0x0031",
+            "$TC actions add action skbmod set etype 0x0041"
+        ],
+        "cmdUnderTest": "$TC actions flush action skbmod",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
deleted file mode 100644
index af519bc97a8e..000000000000
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
+++ /dev/null
@@ -1,1115 +0,0 @@
-[
-    {
-        "id": "e89a",
-        "name": "Add valid pass action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pass index 8",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "a02c",
-        "name": "Add valid pipe action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pipe index 6",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "feef",
-        "name": "Add valid reclassify action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action reclassify index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "8a7a",
-        "name": "Add valid drop action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 30",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "9a52",
-        "name": "Add valid continue action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action continue index 432",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "d700",
-        "name": "Add invalid action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action pump index 386",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action.*index 386 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "9215",
-        "name": "Add action with duplicate index",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pipe index 15"
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 15",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "798e",
-        "name": "Add action with index exceeding 32-bit maximum",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 4294967296",
-        "expExitCode": "255",
-        "verifyCmd": "actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "22be",
-        "name": "Add action with index at 32-bit maximum",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action drop index 4294967295",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "ac2a",
-        "name": "List actions",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action reclassify index 101",
-            "$TC actions add action reclassify index 102",
-            "$TC actions add action reclassify index 103",
-            "$TC actions add action reclassify index 104",
-            "$TC actions add action reclassify index 105"
-        ],
-        "cmdUnderTest": "$TC actions list action gact",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify",
-        "matchCount": "5",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "63ec",
-        "name": "Delete pass action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pass index 1"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "46be",
-        "name": "Delete pipe action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action pipe index 9"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 9",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "2e08",
-        "name": "Delete reclassify action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action reclassify index 65536"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 65536",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "99c4",
-        "name": "Delete drop action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 16"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 16",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "fb6b",
-        "name": "Delete continue action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action continue index 32"
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 32",
-        "expExitCode": "0",
-        "verifyCmd": "actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "0eb3",
-        "name": "Delete non-existent action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions del action gact index 2",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action gact",
-        "matchPattern": "action order [0-9]*: gact action",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "5124",
-        "name": "Add mirred mirror to egress action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "6fb4",
-        "name": "Add mirred redirect to egress action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "ba38",
-        "name": "Get mirred actions",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 1 dev lo",
-            "$TC actions add action mirred egress redirect index 2 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions show action mirred",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "[Mirror|Redirect] to device lo",
-        "matchCount": "2",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "d7c0",
-        "name": "Add invalid mirred direction",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "e213",
-        "name": "Add invalid mirred action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "2d89",
-        "name": "Add mirred action with invalid device",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "300b",
-        "name": "Add mirred action with duplicate index",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress redirect index 15 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "a70e",
-        "name": "Delete mirred mirror action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress mirror index 5 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions del action mirred index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "3fb3",
-        "name": "Delete mirred redirect action",
-        "category": [
-            "actions",
-            "mirred"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action mirred",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action mirred egress redirect index 5 dev lo"
-        ],
-        "cmdUnderTest": "$TC actions del action mirred index 5",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action mirred",
-        "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action mirred"
-        ]
-    },
-    {
-        "id": "b078",
-        "name": "Add simple action",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "6d4c",
-        "name": "Add simple action with duplicate index",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Aruba\" index 4"
-        ],
-        "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "2542",
-        "name": "List simple actions",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Rock\"",
-            "$TC actions add action simple sdata \"Paper\"",
-            "$TC actions add action simple sdata \"Scissors\" index 98"
-        ],
-        "cmdUnderTest": "$TC actions list action simple",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
-        "matchCount": "3",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "ea67",
-        "name": "Delete simple action",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Blinkenlights\" index 1"
-        ],
-        "cmdUnderTest": "$TC actions delete action simple index 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action simple"
-        ]
-    },
-    {
-        "id": "8ff1",
-        "name": "Flush simple actions",
-        "category": [
-            "actions",
-            "simple"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action simple",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action simple sdata \"Kirk\"",
-            "$TC actions add action simple sdata \"Spock\" index 50",
-            "$TC actions add action simple sdata \"McCoy\" index 9"
-        ],
-        "cmdUnderTest": "$TC actions flush action simple",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action simple",
-        "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>",
-        "matchCount": "0",
-        "teardown": [
-            ""
-        ]
-    },
-    {
-        "id": "6236",
-        "name": "Add skbedit action with valid mark",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 1",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 1",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "407b",
-        "name": "Add skbedit action with invalid mark",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 666777888999",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "081d",
-        "name": "Add skbedit action with priority",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit prio 99",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority :99",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "cc37",
-        "name": "Add skbedit action with invalid priority",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit prio foo",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "3c95",
-        "name": "Add skbedit action with queue_mapping",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "985c",
-        "name": "Add skbedit action with invalid queue_mapping",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "224f",
-        "name": "Add skbedit action with ptype host",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype host",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "d1a3",
-        "name": "Add skbedit action with ptype otherhost",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "b9c6",
-        "name": "Add skbedit action with invalid ptype",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit ptype openair",
-        "expExitCode": "255",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype openair",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "5172",
-        "name": "List skbedit actions",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action skbedit ptype otherhost",
-            "$TC actions add action skbedit ptype broadcast",
-            "$TC actions add action skbedit mark 59",
-            "$TC actions add action skbedit mark 409"
-        ],
-        "cmdUnderTest": "$TC actions list action skbedit",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
-        "matchCount": "4",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "a6d6",
-        "name": "Add skbedit action with index",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ]
-        ],
-        "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "index 4040404040",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "38f3",
-        "name": "Delete skbedit action",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action skbedit",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action skbedit mark 42 index 9009"
-        ],
-        "cmdUnderTest": "$TC actions del action skbedit index 9009",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 42",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "ce97",
-        "name": "Flush skbedit actions",
-        "category": [
-            "actions",
-            "skbedit"
-        ],
-        "setup": [
-            "$TC actions add action skbedit mark 500",
-            "$TC actions add action skbedit mark 501",
-            "$TC actions add action skbedit mark 502",
-            "$TC actions add action skbedit mark 503",
-            "$TC actions add action skbedit mark 504",
-            "$TC actions add action skbedit mark 505",
-            "$TC actions add action skbedit mark 506"
-        ],
-        "cmdUnderTest": "$TC actions flush action skbedit",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
-        "matchCount": "0",
-        "teardown": [
-            "$TC actions flush action skbedit"
-        ]
-    },
-    {
-        "id": "f02c",
-        "name": "Replace gact action",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 10",
-            "$TC actions add action drop index 12"
-        ],
-        "cmdUnderTest": "$TC actions replace action ok index 12",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions ls action gact",
-        "matchPattern": "action order [0-9]*: gact action pass",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "525f",
-        "name": "Get gact action by index",
-        "category": [
-            "actions",
-            "gact"
-        ],
-        "setup": [
-            [
-                "$TC actions flush action gact",
-                0,
-                1,
-                255
-            ],
-            "$TC actions add action drop index 3900800700"
-        ],
-        "cmdUnderTest": "$TC actions get action gact index 3900800700",
-        "expExitCode": "0",
-        "verifyCmd": "$TC actions get action gact index 3900800700",
-        "matchPattern": "index 3900800700",
-        "matchCount": "1",
-        "teardown": [
-            "$TC actions flush action gact"
-        ]
-    }
-]
\ No newline at end of file
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index c727b96a59b0..5fa02d86b35f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -17,5 +17,26 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "d052",
+        "name": "Add 1M filters with the same action",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress",
+            "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
+        ],
+        "cmdUnderTest": "$TC -b $BATCH_FILE",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress",
+            "/bin/rm $BATCH_FILE"
+        ]
     }
-]
\ No newline at end of file
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index cd61b7844c0d..fc373fdf2bdc 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
 
 """
 tdc.py - Linux tc (Traffic Control) unit test driver
@@ -49,7 +50,7 @@ def exec_cmd(command, nsonly=True):
         stderr=subprocess.PIPE)
     (rawout, serr) = proc.communicate()
 
-    if proc.returncode != 0:
+    if proc.returncode != 0 and len(serr) > 0:
         foutput = serr.decode("utf-8")
     else:
         foutput = rawout.decode("utf-8")
@@ -88,7 +89,7 @@ def prepare_env(cmdlist):
             exit(1)
 
 
-def test_runner(filtered_tests):
+def test_runner(filtered_tests, args):
     """
     Driver function for the unit tests.
 
@@ -105,6 +106,8 @@ def test_runner(filtered_tests):
     for tidx in testlist:
         result = True
         tresult = ""
+        if "flower" in tidx["category"] and args.device == None:
+            continue
         print("Test " + tidx["id"] + ": " + tidx["name"])
         prepare_env(tidx["setup"])
         (p, procout) = exec_cmd(tidx["cmdUnderTest"])
@@ -150,7 +153,11 @@ def ns_create():
         exec_cmd(cmd, False)
         cmd = 'ip link set $DEV0 up'
         exec_cmd(cmd, False)
-        cmd = 'ip -s $NS link set $DEV1 up'
+        cmd = 'ip -n $NS link set $DEV1 up'
+        exec_cmd(cmd, False)
+        cmd = 'ip link set $DEV2 netns $NS'
+        exec_cmd(cmd, False)
+        cmd = 'ip -n $NS link set $DEV2 up'
         exec_cmd(cmd, False)
 
 
@@ -173,15 +180,20 @@ def has_blank_ids(idlist):
 
 def load_from_file(filename):
     """
-    Open the JSON file containing the test cases and return them as an
-    ordered dictionary object.
+    Open the JSON file containing the test cases and return them
+    as list of ordered dictionary objects.
     """
-    with open(filename) as test_data:
-        testlist = json.load(test_data, object_pairs_hook=OrderedDict)
-    idlist = get_id_list(testlist)
-    if (has_blank_ids(idlist)):
-        for k in testlist:
-            k['filename'] = filename
+    try:
+        with open(filename) as test_data:
+            testlist = json.load(test_data, object_pairs_hook=OrderedDict)
+    except json.JSONDecodeError as jde:
+        print('IGNORING test case file {}\n\tBECAUSE:  {}'.format(filename, jde))
+        testlist = list()
+    else:
+        idlist = get_id_list(testlist)
+        if (has_blank_ids(idlist)):
+            for k in testlist:
+                k['filename'] = filename
     return testlist
 
 
@@ -203,7 +215,7 @@ def set_args(parser):
                         help='Run tests only from the specified category, or if no category is specified, list known categories.')
     parser.add_argument('-f', '--file', type=str,
                         help='Run tests from the specified file')
-    parser.add_argument('-l', '--list', type=str, nargs='?', const="", metavar='CATEGORY',
+    parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY',
                         help='List all test cases, or those only within the specified category')
     parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID',
                         help='Display the test case with specified id')
@@ -211,7 +223,8 @@ def set_args(parser):
                         help='Execute the single test case with specified ID')
     parser.add_argument('-i', '--id', action='store_true', dest='gen_id',
                         help='Generate ID numbers for new test cases')
-    return parser
+    parser.add_argument('-d', '--device',
+                        help='Execute the test case in flower category')
     return parser
 
 
@@ -225,6 +238,8 @@ def check_default_settings(args):
 
     if args.path != None:
          NAMES['TC'] = args.path
+    if args.device != None:
+         NAMES['DEV2'] = args.device
     if not os.path.isfile(NAMES['TC']):
         print("The specified tc path " + NAMES['TC'] + " does not exist.")
         exit(1)
@@ -357,10 +372,10 @@ def set_operation_mode(args):
     testcases = get_categorized_testlist(alltests, ucat)
 
     if args.list:
-        if (len(args.list) == 0):
+        if (args.list == "++"):
             list_test_cases(alltests)
             exit(0)
-        elif(len(args.list > 0)):
+        elif(len(args.list) > 0):
             if (args.list not in ucat):
                 print("Unknown category " + args.list)
                 print("Available categories:")
@@ -381,14 +396,17 @@ def set_operation_mode(args):
             if (len(alltests) == 0):
                 print("Cannot find a test case with ID matching " + target_id)
                 exit(1)
-        catresults = test_runner(alltests)
+        catresults = test_runner(alltests, args)
         print("All test results: " + "\n\n" + catresults)
     elif (len(target_category) > 0):
+        if (target_category == "flower") and args.device == None:
+            print("Please specify a NIC device (-d) to run category flower")
+            exit(1)
         if (target_category not in ucat):
             print("Specified category is not present in this file.")
             exit(1)
         else:
-            catresults = test_runner(testcases[target_category])
+            catresults = test_runner(testcases[target_category], args)
             print("Category " + target_category + "\n\n" + catresults)
 
     ns_destroy()
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
new file mode 100755
index 000000000000..707c6bfef689
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -0,0 +1,62 @@
+#!/usr/bin/python3
+
+"""
+tdc_batch.py - a script to generate TC batch file
+
+Copyright (C) 2017 Chris Mi <chrism@mellanox.com>
+"""
+
+import argparse
+
+parser = argparse.ArgumentParser(description='TC batch file generator')
+parser.add_argument("device", help="device name")
+parser.add_argument("file", help="batch file name")
+parser.add_argument("-n", "--number", type=int,
+                    help="how many lines in batch file")
+parser.add_argument("-o", "--skip_sw",
+                    help="skip_sw (offload), by default skip_hw",
+                    action="store_true")
+parser.add_argument("-s", "--share_action",
+                    help="all filters share the same action",
+                    action="store_true")
+parser.add_argument("-p", "--prio",
+                    help="all filters have different prio",
+                    action="store_true")
+args = parser.parse_args()
+
+device = args.device
+file = open(args.file, 'w')
+
+number = 1
+if args.number:
+    number = args.number
+
+skip = "skip_hw"
+if args.skip_sw:
+    skip = "skip_sw"
+
+share_action = ""
+if args.share_action:
+    share_action = "index 1"
+
+prio = "prio 1"
+if args.prio:
+    prio = ""
+    if number > 0x4000:
+        number = 0x4000
+
+index = 0
+for i in range(0x100):
+    for j in range(0x100):
+        for k in range(0x100):
+            mac = ("%02x:%02x:%02x" % (i, j, k))
+            src_mac = "e4:11:00:" + mac
+            dst_mac = "e4:12:00:" + mac
+            cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s "
+                   "src_mac %s dst_mac %s action drop %s" %
+                   (device, prio, skip, src_mac, dst_mac, share_action))
+            file.write("%s\n" % cmd)
+            index += 1
+            if index >= number:
+                file.close()
+                exit(0)
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index 01087375a7c3..a023d0d62b25 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -1,4 +1,5 @@
 """
+# SPDX-License-Identifier: GPL-2.0
 tdc_config.py - tdc user-specified values
 
 Copyright (C) 2017 Lucas Bates <lucasb@mojatatu.com>
@@ -12,6 +13,22 @@ NAMES = {
           # Name of veth devices to be created for the namespace
           'DEV0': 'v0p0',
           'DEV1': 'v0p1',
+          'DEV2': '',
+          'BATCH_FILE': './batch.txt',
           # Name of the namespace to use
           'NS': 'tcut'
         }
+
+
+ENVIR = { }
+
+# put customizations in tdc_config_local.py
+try:
+    from tdc_config_local import *
+except ImportError as ie:
+    pass
+
+try:
+    NAMES.update(EXTRA_NAMES)
+except NameError as ne:
+    pass
diff --git a/tools/testing/selftests/tc-testing/tdc_config_local_template.py b/tools/testing/selftests/tc-testing/tdc_config_local_template.py
new file mode 100644
index 000000000000..d48fc732a399
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_config_local_template.py
@@ -0,0 +1,23 @@
+"""
+tdc_config_local.py - tdc plugin-writer-specified values
+
+Copyright (C) 2017 bjb@mojatatu.com
+"""
+
+import os
+
+ENVIR = os.environ.copy()
+
+ENV_LD_LIBRARY_PATH = os.getenv('LD_LIBRARY_PATH', '')
+ENV_OTHER_LIB = os.getenv('OTHER_LIB', '')
+
+
+# example adding value to NAMES, without editing tdc_config.py
+EXTRA_NAMES = dict()
+EXTRA_NAMES['SOME_BIN'] = os.path.join(os.getenv('OTHER_BIN', ''), 'some_bin')
+
+
+# example adding values to ENVIR, without editing tdc_config.py
+ENVIR['VALGRIND_LIB'] = '/usr/lib/valgrind'
+ENVIR['VALGRIND_BIN'] = '/usr/bin/valgrind'
+ENVIR['VGDB_BIN'] = '/usr/bin/vgdb'
diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py
index c3254f861fb2..db381120a566 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -1,4 +1,5 @@
 """
+# SPDX-License-Identifier: GPL-2.0
 tdc_helper.py - tdc helper functions
 
 Copyright (C) 2017 Lucas Bates <lucasb@mojatatu.com>
@@ -15,7 +16,7 @@ def get_categorized_testlist(alltests, ucat):
 
 
 def get_unique_item(lst):
-    """ For a list, return a set of the unique items in the list. """
+    """ For a list, return a list of the unique items in the list. """
     return list(set(lst))
 
 
@@ -57,7 +58,7 @@ def print_sll(items):
 def print_test_case(tcase):
     """ Pretty-printing of a given test case. """
     for k in tcase.keys():
-        if (type(tcase[k]) == list):
+        if (isinstance(tcase[k], list)):
             print(k + ":")
             print_list(tcase[k])
         else:
diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore
index cc986621f512..2c8ac8416299 100644
--- a/tools/testing/selftests/timers/.gitignore
+++ b/tools/testing/selftests/timers/.gitignore
@@ -18,3 +18,5 @@ threadtest
 valid-adjtimex
 adjtick
 set-tz
+freq-step
+rtctest_setdate
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index a9b86133b9b3..3496680981f2 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -1,5 +1,5 @@
-BUILD_FLAGS = -DKTEST
-CFLAGS += -O3 -Wl,-no-as-needed -Wall $(BUILD_FLAGS)
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -O3 -Wl,-no-as-needed -Wall
 LDFLAGS += -lrt -lpthread -lm
 
 # these are all "safe" tests that don't modify
@@ -7,9 +7,11 @@ LDFLAGS += -lrt -lpthread -lm
 TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \
              inconsistency-check raw_skew threadtest rtctest
 
-TEST_GEN_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \
+DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
                       skew_consistency clocksource-switch freq-step leap-a-day \
-                      leapcrash set-tai set-2038 set-tz rtctest_setdate
+                      leapcrash set-tai set-2038 set-tz
+
+TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS) rtctest_setdate
 
 
 include ../lib.mk
@@ -18,16 +20,4 @@ include ../lib.mk
 # and may modify the system time or trigger
 # other behavior like suspend
 run_destructive_tests: run_tests
-        ./alarmtimer-suspend
-        ./valid-adjtimex
-        ./adjtick
-        ./change_skew
-        ./skew_consistency
-        ./clocksource-switch
-        ./freq-step
-        ./leap-a-day -s -i 10
-        ./leapcrash
-        ./set-tz
-        ./set-tai
-        ./set-2038
-
+        $(call RUN_TESTS, $(DESTRUCTIVE_TESTS))
diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c
index 9887fd538fec..0caca3a06bd2 100644
--- a/tools/testing/selftests/timers/adjtick.c
+++ b/tools/testing/selftests/timers/adjtick.c
@@ -23,18 +23,7 @@
 #include <sys/timex.h>
 #include <time.h>
 
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define CLOCK_MONOTONIC_RAW     4
 
diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c
index 2b361b830395..4da09dbf83ba 100644
--- a/tools/testing/selftests/timers/alarmtimer-suspend.c
+++ b/tools/testing/selftests/timers/alarmtimer-suspend.c
@@ -28,18 +28,7 @@
 #include <signal.h>
 #include <stdlib.h>
 #include <pthread.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define CLOCK_REALTIME                  0
 #define CLOCK_MONOTONIC                 1
diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c
index cb1968977c04..c4eab7124990 100644
--- a/tools/testing/selftests/timers/change_skew.c
+++ b/tools/testing/selftests/timers/change_skew.c
@@ -28,18 +28,7 @@
 #include <sys/time.h>
 #include <sys/timex.h>
 #include <time.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000LL
 
diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c
index 5ff165373f8b..bfc974b4572d 100644
--- a/tools/testing/selftests/timers/clocksource-switch.c
+++ b/tools/testing/selftests/timers/clocksource-switch.c
@@ -34,18 +34,7 @@
 #include <fcntl.h>
 #include <string.h>
 #include <sys/wait.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 
 int get_clocksources(char list[][30])
@@ -61,7 +50,7 @@ int get_clocksources(char list[][30])
 
         close(fd);
 
-        for (i = 0; i < 30; i++)
+        for (i = 0; i < 10; i++)
                 list[i][0] = '\0';
 
         head = buf;
diff --git a/tools/testing/selftests/timers/freq-step.c b/tools/testing/selftests/timers/freq-step.c
index e8c61830825a..14a2b77fd012 100644
--- a/tools/testing/selftests/timers/freq-step.c
+++ b/tools/testing/selftests/timers/freq-step.c
@@ -33,6 +33,10 @@
 #define MAX_FREQ_ERROR 10e-6
 #define MAX_STDDEV 1000e-9
 
+#ifndef ADJ_SETOFFSET
+  #define ADJ_SETOFFSET 0x0100
+#endif
+
 struct sample {
         double offset;
         double time;
@@ -229,10 +233,9 @@ static void init_test(void)
         printf("CLOCK_MONOTONIC_RAW+CLOCK_MONOTONIC precision: %.0f ns\t\t",
                1e9 * precision);
 
-        if (precision > MAX_PRECISION) {
-                printf("[SKIP]\n");
-                ksft_exit_skip();
-        }
+        if (precision > MAX_PRECISION)
+                ksft_exit_skip("precision: %.0f ns > MAX_PRECISION: %.0f ns\n",
+                                1e9 * precision, 1e9 * MAX_PRECISION);
 
         printf("[OK]\n");
         srand(ts.tv_sec ^ ts.tv_nsec);
@@ -262,7 +265,7 @@ int main(int argc, char **argv)
         set_frequency(0.0);
 
         if (fails)
-                ksft_exit_fail();
+                return ksft_exit_fail();
 
-        ksft_exit_pass();
+        return ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c
index 74c60e8759a0..022d3ffe3fbf 100644
--- a/tools/testing/selftests/timers/inconsistency-check.c
+++ b/tools/testing/selftests/timers/inconsistency-check.c
@@ -28,18 +28,7 @@
 #include <sys/timex.h>
 #include <string.h>
 #include <signal.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define CALLS_PER_LOOP 64
 #define NSEC_PER_SEC 1000000000ULL
diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c
index fb46ad6ac92c..19e46ed5dfb5 100644
--- a/tools/testing/selftests/timers/leap-a-day.c
+++ b/tools/testing/selftests/timers/leap-a-day.c
@@ -48,18 +48,7 @@
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000ULL
 #define CLOCK_TAI 11
@@ -190,18 +179,18 @@ int main(int argc, char **argv)
         struct sigevent se;
         struct sigaction act;
         int signum = SIGRTMAX;
-        int settime = 0;
+        int settime = 1;
         int tai_time = 0;
         int insert = 1;
-        int iterations = -1;
+        int iterations = 10;
         int opt;
 
         /* Process arguments */
         while ((opt = getopt(argc, argv, "sti:")) != -1) {
                 switch (opt) {
-                case 's':
-                        printf("Setting time to speed up testing\n");
-                        settime = 1;
+                case 'w':
+                        printf("Only setting leap-flag, not changing time. It could take up to a day for leap to trigger.\n");
+                        settime = 0;
                         break;
                 case 'i':
                         iterations = atoi(optarg);
@@ -210,9 +199,10 @@ int main(int argc, char **argv)
                         tai_time = 1;
                         break;
                 default:
-                        printf("Usage: %s [-s] [-i <iterations>]\n", argv[0]);
-                        printf("        -s: Set time to right before leap second each iteration\n");
-                        printf("        -i: Number of iterations\n");
+                        printf("Usage: %s [-w] [-i <iterations>]\n", argv[0]);
+                        printf("        -w: Set flag and wait for leap second each iteration");
+                        printf("            (default sets time to right before leapsecond)\n");
+                        printf("        -i: Number of iterations (-1 = infinite, default is 10)\n");
                         printf("        -t: Print TAI time\n");
                         exit(-1);
                 }
diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c
index a1071bdbdeb7..830c462f605d 100644
--- a/tools/testing/selftests/timers/leapcrash.c
+++ b/tools/testing/selftests/timers/leapcrash.c
@@ -22,20 +22,7 @@
 #include <sys/timex.h>
 #include <string.h>
 #include <signal.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
-
-
 
 /* clear NTP time_status & time_state */
 int clear_time_state(void)
diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c
index a2a3924d0b41..1867db5d6f5e 100644
--- a/tools/testing/selftests/timers/mqueue-lat.c
+++ b/tools/testing/selftests/timers/mqueue-lat.c
@@ -29,18 +29,7 @@
 #include <signal.h>
 #include <errno.h>
 #include <mqueue.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000ULL
 
diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c
index ff942ff7c9b3..8adb0bb51d4d 100644
--- a/tools/testing/selftests/timers/nanosleep.c
+++ b/tools/testing/selftests/timers/nanosleep.c
@@ -27,18 +27,7 @@
 #include <sys/timex.h>
 #include <string.h>
 #include <signal.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000ULL
 
diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c
index 2d7898fda0f1..c3c3dc10db17 100644
--- a/tools/testing/selftests/timers/nsleep-lat.c
+++ b/tools/testing/selftests/timers/nsleep-lat.c
@@ -24,18 +24,7 @@
 #include <sys/timex.h>
 #include <string.h>
 #include <signal.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000ULL
 
diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c
index 30906bfd9c1b..ca6cd146aafe 100644
--- a/tools/testing/selftests/timers/raw_skew.c
+++ b/tools/testing/selftests/timers/raw_skew.c
@@ -25,19 +25,7 @@
 #include <sys/time.h>
 #include <sys/timex.h>
 #include <time.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
-
 
 #define CLOCK_MONOTONIC_RAW             4
 #define NSEC_PER_SEC 1000000000LL
diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c
index f61170f7b024..411eff625e66 100644
--- a/tools/testing/selftests/timers/rtctest.c
+++ b/tools/testing/selftests/timers/rtctest.c
@@ -221,6 +221,11 @@ test_READ:
         /* Read the current alarm settings */
         retval = ioctl(fd, RTC_ALM_READ, &rtc_tm);
         if (retval == -1) {
+                if (errno == EINVAL) {
+                        fprintf(stderr,
+                                        "\n...EINVAL reading current alarm setting.\n");
+                        goto test_PIE;
+                }
                 perror("RTC_ALM_READ ioctl");
                 exit(errno);
         }
@@ -231,7 +236,7 @@ test_READ:
         /* Enable alarm interrupts */
         retval = ioctl(fd, RTC_AIE_ON, 0);
         if (retval == -1) {
-                if (errno == EINVAL) {
+                if (errno == EINVAL || errno == EIO) {
                         fprintf(stderr,
                                 "\n...Alarm IRQs not supported.\n");
                         goto test_PIE;
diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c
index c8a7e14446b1..688cfd81b531 100644
--- a/tools/testing/selftests/timers/set-2038.c
+++ b/tools/testing/selftests/timers/set-2038.c
@@ -27,18 +27,7 @@
 #include <unistd.h>
 #include <time.h>
 #include <sys/time.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000LL
 
diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c
index dc88dbc8831f..70fed27d8fd3 100644
--- a/tools/testing/selftests/timers/set-tai.c
+++ b/tools/testing/selftests/timers/set-tai.c
@@ -23,18 +23,7 @@
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 int set_tai(int offset)
 {
diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c
index 4fc98c5b0899..50da45437daa 100644
--- a/tools/testing/selftests/timers/set-timer-lat.c
+++ b/tools/testing/selftests/timers/set-timer-lat.c
@@ -20,6 +20,7 @@
  */
 
 
+#include <errno.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <time.h>
@@ -27,18 +28,7 @@
 #include <signal.h>
 #include <stdlib.h>
 #include <pthread.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define CLOCK_REALTIME                  0
 #define CLOCK_MONOTONIC                 1
@@ -63,6 +53,7 @@ int alarmcount;
 int clock_id;
 struct timespec start_time;
 long long max_latency_ns;
+int timer_fired_early;
 
 char *clockstring(int clockid)
 {
@@ -115,16 +106,23 @@ void sigalarm(int signo)
         delta_ns -= NSEC_PER_SEC * TIMER_SECS * alarmcount;
 
         if (delta_ns < 0)
-                printf("%s timer fired early: FAIL\n", clockstring(clock_id));
+                timer_fired_early = 1;
 
         if (delta_ns > max_latency_ns)
                 max_latency_ns = delta_ns;
 }
 
-int do_timer(int clock_id, int flags)
+void describe_timer(int flags, int interval)
+{
+        printf("%-22s %s %s ",
+                        clockstring(clock_id),
+                        flags ? "ABSTIME":"RELTIME",
+                        interval ? "PERIODIC":"ONE-SHOT");
+}
+
+int setup_timer(int clock_id, int flags, int interval, timer_t *tm1)
 {
         struct sigevent se;
-        timer_t tm1;
         struct itimerspec its1, its2;
         int err;
 
@@ -136,15 +134,17 @@ int do_timer(int clock_id, int flags)
 
         max_latency_ns = 0;
         alarmcount = 0;
+        timer_fired_early = 0;
 
-        err = timer_create(clock_id, &se, &tm1);
+        err = timer_create(clock_id, &se, tm1);
         if (err) {
                 if ((clock_id == CLOCK_REALTIME_ALARM) ||
                     (clock_id == CLOCK_BOOTTIME_ALARM)) {
                         printf("%-22s %s missing CAP_WAKE_ALARM?    : [UNSUPPORTED]\n",
                                         clockstring(clock_id),
                                         flags ? "ABSTIME":"RELTIME");
-                        return 0;
+                        /* Indicate timer isn't set, so caller doesn't wait */
+                        return 1;
                 }
                 printf("%s - timer_create() failed\n", clockstring(clock_id));
                 return -1;
@@ -158,32 +158,97 @@ int do_timer(int clock_id, int flags)
                 its1.it_value.tv_sec = TIMER_SECS;
                 its1.it_value.tv_nsec = 0;
         }
-        its1.it_interval.tv_sec = TIMER_SECS;
+        its1.it_interval.tv_sec = interval;
         its1.it_interval.tv_nsec = 0;
 
-        err = timer_settime(tm1, flags, &its1, &its2);
+        err = timer_settime(*tm1, flags, &its1, &its2);
         if (err) {
                 printf("%s - timer_settime() failed\n", clockstring(clock_id));
                 return -1;
         }
 
-        while (alarmcount < 5)
-                sleep(1);
+        return 0;
+}
 
-        printf("%-22s %s max latency: %10lld ns : ",
-                        clockstring(clock_id),
-                        flags ? "ABSTIME":"RELTIME",
-                        max_latency_ns);
+int check_timer_latency(int flags, int interval)
+{
+        int err = 0;
+
+        describe_timer(flags, interval);
+        printf("timer fired early: %7d : ", timer_fired_early);
+        if (!timer_fired_early) {
+                printf("[OK]\n");
+        } else {
+                printf("[FAILED]\n");
+                err = -1;
+        }
+
+        describe_timer(flags, interval);
+        printf("max latency: %10lld ns : ", max_latency_ns);
 
-        timer_delete(tm1);
         if (max_latency_ns < UNRESONABLE_LATENCY) {
                 printf("[OK]\n");
+        } else {
+                printf("[FAILED]\n");
+                err = -1;
+        }
+        return err;
+}
+
+int check_alarmcount(int flags, int interval)
+{
+        describe_timer(flags, interval);
+        printf("count: %19d : ", alarmcount);
+        if (alarmcount == 1) {
+                printf("[OK]\n");
                 return 0;
         }
         printf("[FAILED]\n");
         return -1;
 }
 
+int do_timer(int clock_id, int flags)
+{
+        timer_t tm1;
+        const int interval = TIMER_SECS;
+        int err;
+
+        err = setup_timer(clock_id, flags, interval, &tm1);
+        /* Unsupported case - return 0 to not fail the test */
+        if (err)
+                return err == 1 ? 0 : err;
+
+        while (alarmcount < 5)
+                sleep(1);
+
+        timer_delete(tm1);
+        return check_timer_latency(flags, interval);
+}
+
+int do_timer_oneshot(int clock_id, int flags)
+{
+        timer_t tm1;
+        const int interval = 0;
+        struct timeval timeout;
+        int err;
+
+        err = setup_timer(clock_id, flags, interval, &tm1);
+        /* Unsupported case - return 0 to not fail the test */
+        if (err)
+                return err == 1 ? 0 : err;
+
+        memset(&timeout, 0, sizeof(timeout));
+        timeout.tv_sec = 5;
+        do {
+                err = select(0, NULL, NULL, NULL, &timeout);
+        } while (err == -1 && errno == EINTR);
+
+        timer_delete(tm1);
+        err = check_timer_latency(flags, interval);
+        err |= check_alarmcount(flags, interval);
+        return err;
+}
+
 int main(void)
 {
         struct sigaction act;
@@ -209,6 +274,8 @@ int main(void)
 
                 ret |= do_timer(clock_id, TIMER_ABSTIME);
                 ret |= do_timer(clock_id, 0);
+                ret |= do_timer_oneshot(clock_id, TIMER_ABSTIME);
+                ret |= do_timer_oneshot(clock_id, 0);
         }
         if (ret)
                 return ksft_exit_fail();
diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c
index f4184928b16b..877fd5532fee 100644
--- a/tools/testing/selftests/timers/set-tz.c
+++ b/tools/testing/selftests/timers/set-tz.c
@@ -23,18 +23,7 @@
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 int set_tz(int min, int dst)
 {
diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c
index 2a996e072259..022b711c78ee 100644
--- a/tools/testing/selftests/timers/skew_consistency.c
+++ b/tools/testing/selftests/timers/skew_consistency.c
@@ -35,18 +35,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/wait.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000LL
 
diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c
index e632e116f05e..759c9c06f1a0 100644
--- a/tools/testing/selftests/timers/threadtest.c
+++ b/tools/testing/selftests/timers/threadtest.c
@@ -21,19 +21,7 @@
 #include <stdlib.h>
 #include <sys/time.h>
 #include <pthread.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
-
 
 /* serializes shared list access */
 pthread_mutex_t list_lock = PTHREAD_MUTEX_INITIALIZER;
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index 60fe3c569bd9..d9d3ab93b31a 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -32,18 +32,7 @@
 #include <string.h>
 #include <signal.h>
 #include <unistd.h>
-#ifdef KTEST
 #include "../kselftest.h"
-#else
-static inline int ksft_exit_pass(void)
-{
-        exit(0);
-}
-static inline int ksft_exit_fail(void)
-{
-        exit(1);
-}
-#endif
 
 #define NSEC_PER_SEC 1000000000LL
 #define USEC_PER_SEC 1000000LL
diff --git a/tools/testing/selftests/user/test_user_copy.sh b/tools/testing/selftests/user/test_user_copy.sh
index 350107f40c1d..d60506fc77f8 100755
--- a/tools/testing/selftests/user/test_user_copy.sh
+++ b/tools/testing/selftests/user/test_user_copy.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 # Runs copy_to/from_user infrastructure using test_user_copy kernel module
 
 if /sbin/modprobe -q test_user_copy; then
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 706b68b1c372..3d5a62ff7d31 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifndef CROSS_COMPILE
 CFLAGS := -std=gnu99
 CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
diff --git a/tools/testing/selftests/vDSO/vdso_test.c b/tools/testing/selftests/vDSO/vdso_test.c
index 8daeb7d7032c..2df26bd0099c 100644
--- a/tools/testing/selftests/vDSO/vdso_test.c
+++ b/tools/testing/selftests/vDSO/vdso_test.c
@@ -19,6 +19,19 @@ extern void *vdso_sym(const char *version, const char *name);
 extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
 extern void vdso_init_from_auxv(void *auxv);
 
+/*
+ * ARM64's vDSO exports its gettimeofday() implementation with a different
+ * name and version from other architectures, so we need to handle it as
+ * a special case.
+ */
+#if defined(__aarch64__)
+const char *version = "LINUX_2.6.39";
+const char *name = "__kernel_gettimeofday";
+#else
+const char *version = "LINUX_2.6";
+const char *name = "__vdso_gettimeofday";
+#endif
+
 int main(int argc, char **argv)
 {
         unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
@@ -31,10 +44,10 @@ int main(int argc, char **argv)
 
         /* Find gettimeofday. */
         typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
-        gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+        gtod_t gtod = (gtod_t)vdso_sym(version, name);
 
         if (!gtod) {
-                printf("Could not find __vdso_gettimeofday\n");
+                printf("Could not find %s\n", name);
                 return 1;
         }
 
@@ -45,7 +58,7 @@ int main(int argc, char **argv)
                 printf("The time is %lld.%06lld\n",
                        (long long)tv.tv_sec, (long long)tv.tv_usec);
         } else {
-                printf("__vdso_gettimeofday failed\n");
+                printf("%s failed\n", name);
         }
 
         return 0;
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 142c565bb351..1ca2ee4d15b9 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -8,3 +8,5 @@ on-fault-limit
 transhuge-stress
 userfaultfd
 mlock-intersect-test
+mlock-random-test
+virtual_address_range
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index cbb29e41ef2b..7f45806bd863 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for vm selftests
 
 ifndef OUTPUT
@@ -17,6 +18,7 @@ TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += virtual_address_range
+TEST_GEN_FILES += gup_benchmark
 
 TEST_PROGS := run_vmtests
 
diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c
index 6d1437f895b8..a65b016d4c13 100644
--- a/tools/testing/selftests/vm/compaction_test.c
+++ b/tools/testing/selftests/vm/compaction_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *
  * A test for the patch "Allow compaction of unevictable pages".
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
new file mode 100644
index 000000000000..36df55132036
--- /dev/null
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -0,0 +1,91 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+#define MB (1UL << 20)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+#define GUP_FAST_BENCHMARK      _IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+        __u64 delta_usec;
+        __u64 addr;
+        __u64 size;
+        __u32 nr_pages_per_call;
+        __u32 flags;
+};
+
+int main(int argc, char **argv)
+{
+        struct gup_benchmark gup;
+        unsigned long size = 128 * MB;
+        int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+        char *p;
+
+        while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+                switch (opt) {
+                case 'm':
+                        size = atoi(optarg) * MB;
+                        break;
+                case 'r':
+                        repeats = atoi(optarg);
+                        break;
+                case 'n':
+                        nr_pages = atoi(optarg);
+                        break;
+                case 't':
+                        thp = 1;
+                        break;
+                case 'T':
+                        thp = 0;
+                        break;
+                case 'w':
+                        write = 1;
+                default:
+                        return -1;
+                }
+        }
+
+        gup.nr_pages_per_call = nr_pages;
+        gup.flags = write;
+
+        fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
+        if (fd == -1)
+                perror("open"), exit(1);
+
+        p = mmap(NULL, size, PROT_READ | PROT_WRITE,
+                        MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+        if (p == MAP_FAILED)
+                perror("mmap"), exit(1);
+        gup.addr = (unsigned long)p;
+
+        if (thp == 1)
+                madvise(p, size, MADV_HUGEPAGE);
+        else if (thp == 0)
+                madvise(p, size, MADV_NOHUGEPAGE);
+
+        for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
+                p[0] = 0;
+
+        for (i = 0; i < repeats; i++) {
+                gup.size = size;
+                if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+                        perror("ioctl"), exit(1);
+
+                printf("Time: %lld us", gup.delta_usec);
+                if (gup.size != size)
+                        printf(", truncated (size: %lld)", gup.size);
+                printf("\n");
+        }
+
+        return 0;
+}
diff --git a/tools/testing/selftests/vm/hugepage-mmap.c b/tools/testing/selftests/vm/hugepage-mmap.c
index a10f310d2362..93f9e7b81331 100644
--- a/tools/testing/selftests/vm/hugepage-mmap.c
+++ b/tools/testing/selftests/vm/hugepage-mmap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * hugepage-mmap:
  *
diff --git a/tools/testing/selftests/vm/hugepage-shm.c b/tools/testing/selftests/vm/hugepage-shm.c
index 0d0ef4fc0c04..e2527f32005b 100644
--- a/tools/testing/selftests/vm/hugepage-shm.c
+++ b/tools/testing/selftests/vm/hugepage-shm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * hugepage-shm:
  *
diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
index 77687ab59f77..9b777fa95f09 100644
--- a/tools/testing/selftests/vm/map_hugetlb.c
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Example of using hugepage memory in a user application using the mmap
  * system call with MAP_HUGETLB flag.  Before running this program make
diff --git a/tools/testing/selftests/vm/mlock-random-test.c b/tools/testing/selftests/vm/mlock-random-test.c
index 83de4f58d262..ff4d72eb74b9 100644
--- a/tools/testing/selftests/vm/mlock-random-test.c
+++ b/tools/testing/selftests/vm/mlock-random-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * It tests the mlock/mlock2() when they are invoked
  * on randomly memory region.
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
index e5dbc87b4297..4997b9222cfa 100644
--- a/tools/testing/selftests/vm/mlock2-tests.c
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <sys/mman.h>
 #include <stdint.h>
diff --git a/tools/testing/selftests/vm/mlock2.h b/tools/testing/selftests/vm/mlock2.h
index 7ee062929d3e..2a6e76c226bc 100644
--- a/tools/testing/selftests/vm/mlock2.h
+++ b/tools/testing/selftests/vm/mlock2.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <syscall.h>
 #include <errno.h>
 #include <stdio.h>
diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c
index 7f96a5c2e292..634d87dfb2a4 100644
--- a/tools/testing/selftests/vm/on-fault-limit.c
+++ b/tools/testing/selftests/vm/on-fault-limit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/mman.h>
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 07548a1fa901..cc826326de87 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 #please run as root
 
 #we need 256M, below is the size in kB
diff --git a/tools/testing/selftests/vm/thuge-gen.c b/tools/testing/selftests/vm/thuge-gen.c
index 88a2ab535e01..361ef7192cc6 100644
--- a/tools/testing/selftests/vm/thuge-gen.c
+++ b/tools/testing/selftests/vm/thuge-gen.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Test selecting other page sizes for mmap/shmget.
 
    Before running this huge pages for each huge page size must have been
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 1eae79ae5b4e..de2f9ec8a87f 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -66,6 +66,8 @@
 #include <sys/wait.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
+#include <setjmp.h>
+#include <stdbool.h>
 
 #ifdef __NR_userfaultfd
 
@@ -82,11 +84,17 @@ static int bounces;
 #define TEST_SHMEM      3
 static int test_type;
 
+/* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */
+#define ALARM_INTERVAL_SECS 10
+static volatile bool test_uffdio_copy_eexist = true;
+static volatile bool test_uffdio_zeropage_eexist = true;
+
+static bool map_shared;
 static int huge_fd;
 static char *huge_fd_off0;
 static unsigned long long *count_verify;
 static int uffd, uffd_flags, finished, *pipefd;
-static char *area_src, *area_dst;
+static char *area_src, *area_src_alias, *area_dst, *area_dst_alias;
 static char *zeropage;
 pthread_attr_t attr;
 
@@ -125,6 +133,9 @@ static void anon_allocate_area(void **alloc_area)
         }
 }
 
+static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
+{
+}
 
 /* HugeTLB memory */
 static int hugetlb_release_pages(char *rel_area)
@@ -145,17 +156,51 @@ static int hugetlb_release_pages(char *rel_area)
 
 static void hugetlb_allocate_area(void **alloc_area)
 {
+        void *area_alias = NULL;
+        char **alloc_area_alias;
         *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
-                                MAP_PRIVATE | MAP_HUGETLB, huge_fd,
-                                *alloc_area == area_src ? 0 :
-                                nr_pages * page_size);
+                           (map_shared ? MAP_SHARED : MAP_PRIVATE) |
+                           MAP_HUGETLB,
+                           huge_fd, *alloc_area == area_src ? 0 :
+                           nr_pages * page_size);
         if (*alloc_area == MAP_FAILED) {
                 fprintf(stderr, "mmap of hugetlbfs file failed\n");
                 *alloc_area = NULL;
         }
 
-        if (*alloc_area == area_src)
+        if (map_shared) {
+                area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+                                  MAP_SHARED | MAP_HUGETLB,
+                                  huge_fd, *alloc_area == area_src ? 0 :
+                                  nr_pages * page_size);
+                if (area_alias == MAP_FAILED) {
+                        if (munmap(*alloc_area, nr_pages * page_size) < 0)
+                                perror("hugetlb munmap"), exit(1);
+                        *alloc_area = NULL;
+                        return;
+                }
+        }
+        if (*alloc_area == area_src) {
                 huge_fd_off0 = *alloc_area;
+                alloc_area_alias = &area_src_alias;
+        } else {
+                alloc_area_alias = &area_dst_alias;
+        }
+        if (area_alias)
+                *alloc_area_alias = area_alias;
+}
+
+static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset)
+{
+        if (!map_shared)
+                return;
+        /*
+         * We can't zap just the pagetable with hugetlbfs because
+         * MADV_DONTEED won't work. So exercise -EEXIST on a alias
+         * mapping where the pagetables are not established initially,
+         * this way we'll exercise the -EEXEC at the fs level.
+         */
+        *start = (unsigned long) area_dst_alias + offset;
 }
 
 /* Shared memory */
@@ -185,6 +230,7 @@ struct uffd_test_ops {
         unsigned long expected_ioctls;
         void (*allocate_area)(void **alloc_area);
         int (*release_pages)(char *rel_area);
+        void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
 };
 
 #define ANON_EXPECTED_IOCTLS            ((1 << _UFFDIO_WAKE) | \
@@ -195,18 +241,21 @@ static struct uffd_test_ops anon_uffd_test_ops = {
         .expected_ioctls = ANON_EXPECTED_IOCTLS,
         .allocate_area  = anon_allocate_area,
         .release_pages  = anon_release_pages,
+        .alias_mapping = noop_alias_mapping,
 };
 
 static struct uffd_test_ops shmem_uffd_test_ops = {
-        .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC,
+        .expected_ioctls = ANON_EXPECTED_IOCTLS,
         .allocate_area  = shmem_allocate_area,
         .release_pages  = shmem_release_pages,
+        .alias_mapping = noop_alias_mapping,
 };
 
 static struct uffd_test_ops hugetlb_uffd_test_ops = {
         .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC,
         .allocate_area  = hugetlb_allocate_area,
         .release_pages  = hugetlb_release_pages,
+        .alias_mapping = hugetlb_alias_mapping,
 };
 
 static struct uffd_test_ops *uffd_test_ops;
@@ -331,7 +380,24 @@ static void *locking_thread(void *arg)
         return NULL;
 }
 
-static int copy_page(int ufd, unsigned long offset)
+static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
+                            unsigned long offset)
+{
+        uffd_test_ops->alias_mapping(&uffdio_copy->dst,
+                                     uffdio_copy->len,
+                                     offset);
+        if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) {
+                /* real retval in ufdio_copy.copy */
+                if (uffdio_copy->copy != -EEXIST)
+                        fprintf(stderr, "UFFDIO_COPY retry error %Ld\n",
+                                uffdio_copy->copy), exit(1);
+        } else {
+                fprintf(stderr, "UFFDIO_COPY retry unexpected %Ld\n",
+                        uffdio_copy->copy), exit(1);
+        }
+}
+
+static int __copy_page(int ufd, unsigned long offset, bool retry)
 {
         struct uffdio_copy uffdio_copy;
 
@@ -351,11 +417,26 @@ static int copy_page(int ufd, unsigned long offset)
         } else if (uffdio_copy.copy != page_size) {
                 fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
                         uffdio_copy.copy), exit(1);
-        } else
+        } else {
+                if (test_uffdio_copy_eexist && retry) {
+                        test_uffdio_copy_eexist = false;
+                        retry_copy_page(ufd, &uffdio_copy, offset);
+                }
                 return 1;
+        }
         return 0;
 }
 
+static int copy_page_retry(int ufd, unsigned long offset)
+{
+        return __copy_page(ufd, offset, true);
+}
+
+static int copy_page(int ufd, unsigned long offset)
+{
+        return __copy_page(ufd, offset, false);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
         unsigned long cpu = (unsigned long) arg;
@@ -408,6 +489,7 @@ static void *uffd_poll_thread(void *arg)
                                 userfaults++;
                         break;
                 case UFFD_EVENT_FORK:
+                        close(uffd);
                         uffd = msg.arg.fork.ufd;
                         pollfd[0].fd = uffd;
                         break;
@@ -472,7 +554,7 @@ static void *background_thread(void *arg)
         for (page_nr = cpu * nr_pages_per_cpu;
              page_nr < (cpu+1) * nr_pages_per_cpu;
              page_nr++)
-                copy_page(uffd, page_nr * page_size);
+                copy_page_retry(uffd, page_nr * page_size);
 
         return NULL;
 }
@@ -572,6 +654,17 @@ static int userfaultfd_open(int features)
         return 0;
 }
 
+sigjmp_buf jbuf, *sigbuf;
+
+static void sighndl(int sig, siginfo_t *siginfo, void *ptr)
+{
+        if (sig == SIGBUS) {
+                if (sigbuf)
+                        siglongjmp(*sigbuf, 1);
+                abort();
+        }
+}
+
 /*
  * For non-cooperative userfaultfd test we fork() a process that will
  * generate pagefaults, will mremap the area monitored by the
@@ -585,19 +678,59 @@ static int userfaultfd_open(int features)
  * The release of the pages currently generates event for shmem and
  * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked
  * for hugetlb.
+ * For signal test(UFFD_FEATURE_SIGBUS), signal_test = 1, we register
+ * monitored area, generate pagefaults and test that signal is delivered.
+ * Use UFFDIO_COPY to allocate missing page and retry. For signal_test = 2
+ * test robustness use case - we release monitored area, fork a process
+ * that will generate pagefaults and verify signal is generated.
+ * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal
+ * feature. Using monitor thread, verify no userfault events are generated.
  */
-static int faulting_process(void)
+static int faulting_process(int signal_test)
 {
         unsigned long nr;
         unsigned long long count;
         unsigned long split_nr_pages;
+        unsigned long lastnr;
+        struct sigaction act;
+        unsigned long signalled = 0;
 
         if (test_type != TEST_HUGETLB)
                 split_nr_pages = (nr_pages + 1) / 2;
         else
                 split_nr_pages = nr_pages;
 
+        if (signal_test) {
+                sigbuf = &jbuf;
+                memset(&act, 0, sizeof(act));
+                act.sa_sigaction = sighndl;
+                act.sa_flags = SA_SIGINFO;
+                if (sigaction(SIGBUS, &act, 0)) {
+                        perror("sigaction");
+                        return 1;
+                }
+                lastnr = (unsigned long)-1;
+        }
+
         for (nr = 0; nr < split_nr_pages; nr++) {
+                if (signal_test) {
+                        if (sigsetjmp(*sigbuf, 1) != 0) {
+                                if (nr == lastnr) {
+                                        fprintf(stderr, "Signal repeated\n");
+                                        return 1;
+                                }
+
+                                lastnr = nr;
+                                if (signal_test == 1) {
+                                        if (copy_page(uffd, nr * page_size))
+                                                signalled++;
+                                } else {
+                                        signalled++;
+                                        continue;
+                                }
+                        }
+                }
+
                 count = *area_count(area_dst, nr);
                 if (count != count_verify[nr]) {
                         fprintf(stderr,
@@ -607,6 +740,9 @@ static int faulting_process(void)
                 }
         }
 
+        if (signal_test)
+                return signalled != split_nr_pages;
+
         if (test_type == TEST_HUGETLB)
                 return 0;
 
@@ -636,7 +772,24 @@ static int faulting_process(void)
         return 0;
 }
 
-static int uffdio_zeropage(int ufd, unsigned long offset)
+static void retry_uffdio_zeropage(int ufd,
+                                  struct uffdio_zeropage *uffdio_zeropage,
+                                  unsigned long offset)
+{
+        uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start,
+                                     uffdio_zeropage->range.len,
+                                     offset);
+        if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
+                if (uffdio_zeropage->zeropage != -EEXIST)
+                        fprintf(stderr, "UFFDIO_ZEROPAGE retry error %Ld\n",
+                                uffdio_zeropage->zeropage), exit(1);
+        } else {
+                fprintf(stderr, "UFFDIO_ZEROPAGE retry unexpected %Ld\n",
+                        uffdio_zeropage->zeropage), exit(1);
+        }
+}
+
+static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 {
         struct uffdio_zeropage uffdio_zeropage;
         int ret;
@@ -670,8 +823,14 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
                 if (uffdio_zeropage.zeropage != page_size) {
                         fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
                                 uffdio_zeropage.zeropage), exit(1);
-                } else
+                } else {
+                        if (test_uffdio_zeropage_eexist && retry) {
+                                test_uffdio_zeropage_eexist = false;
+                                retry_uffdio_zeropage(ufd, &uffdio_zeropage,
+                                                      offset);
+                        }
                         return 1;
+                }
         } else {
                 fprintf(stderr,
                         "UFFDIO_ZEROPAGE succeeded %Ld\n",
@@ -681,6 +840,11 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
         return 0;
 }
 
+static int uffdio_zeropage(int ufd, unsigned long offset)
+{
+        return __uffdio_zeropage(ufd, offset, false);
+}
+
 /* exercise UFFDIO_ZEROPAGE */
 static int userfaultfd_zeropage_test(void)
 {
@@ -761,7 +925,7 @@ static int userfaultfd_events_test(void)
                 perror("fork"), exit(1);
 
         if (!pid)
-                return faulting_process();
+                return faulting_process(0);
 
         waitpid(pid, &err, 0);
         if (err)
@@ -778,6 +942,72 @@ static int userfaultfd_events_test(void)
         return userfaults != nr_pages;
 }
 
+static int userfaultfd_sig_test(void)
+{
+        struct uffdio_register uffdio_register;
+        unsigned long expected_ioctls;
+        unsigned long userfaults;
+        pthread_t uffd_mon;
+        int err, features;
+        pid_t pid;
+        char c;
+
+        printf("testing signal delivery: ");
+        fflush(stdout);
+
+        if (uffd_test_ops->release_pages(area_dst))
+                return 1;
+
+        features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS;
+        if (userfaultfd_open(features) < 0)
+                return 1;
+        fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
+
+        uffdio_register.range.start = (unsigned long) area_dst;
+        uffdio_register.range.len = nr_pages * page_size;
+        uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+        if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+                fprintf(stderr, "register failure\n"), exit(1);
+
+        expected_ioctls = uffd_test_ops->expected_ioctls;
+        if ((uffdio_register.ioctls & expected_ioctls) !=
+            expected_ioctls)
+                fprintf(stderr,
+                        "unexpected missing ioctl for anon memory\n"),
+                        exit(1);
+
+        if (faulting_process(1))
+                fprintf(stderr, "faulting process failed\n"), exit(1);
+
+        if (uffd_test_ops->release_pages(area_dst))
+                return 1;
+
+        if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
+                perror("uffd_poll_thread create"), exit(1);
+
+        pid = fork();
+        if (pid < 0)
+                perror("fork"), exit(1);
+
+        if (!pid)
+                exit(faulting_process(2));
+
+        waitpid(pid, &err, 0);
+        if (err)
+                fprintf(stderr, "faulting process failed\n"), exit(1);
+
+        if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+                perror("pipe write"), exit(1);
+        if (pthread_join(uffd_mon, (void **)&userfaults))
+                return 1;
+
+        printf("done.\n");
+        if (userfaults)
+                fprintf(stderr, "Signal test failed, userfaults: %ld\n",
+                        userfaults);
+        close(uffd);
+        return userfaults != 0;
+}
 static int userfaultfd_stress(void)
 {
         void *area;
@@ -879,6 +1109,15 @@ static int userfaultfd_stress(void)
                         return 1;
                 }
 
+                if (area_dst_alias) {
+                        uffdio_register.range.start = (unsigned long)
+                                area_dst_alias;
+                        if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
+                                fprintf(stderr, "register failure alias\n");
+                                return 1;
+                        }
+                }
+
                 /*
                  * The madvise done previously isn't enough: some
                  * uffd_thread could have read userfaults (one of
@@ -912,9 +1151,17 @@ static int userfaultfd_stress(void)
 
                 /* unregister */
                 if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) {
-                        fprintf(stderr, "register failure\n");
+                        fprintf(stderr, "unregister failure\n");
                         return 1;
                 }
+                if (area_dst_alias) {
+                        uffdio_register.range.start = (unsigned long) area_dst;
+                        if (ioctl(uffd, UFFDIO_UNREGISTER,
+                                  &uffdio_register.range)) {
+                                fprintf(stderr, "unregister failure alias\n");
+                                return 1;
+                        }
+                }
 
                 /* verification */
                 if (bounces & BOUNCE_VERIFY) {
@@ -936,6 +1183,10 @@ static int userfaultfd_stress(void)
                 area_src = area_dst;
                 area_dst = tmp_area;
 
+                tmp_area = area_src_alias;
+                area_src_alias = area_dst_alias;
+                area_dst_alias = tmp_area;
+
                 printf("userfaults:");
                 for (cpu = 0; cpu < nr_cpus; cpu++)
                         printf(" %lu", userfaults[cpu]);
@@ -946,7 +1197,8 @@ static int userfaultfd_stress(void)
                 return err;
 
         close(uffd);
-        return userfaultfd_zeropage_test() || userfaultfd_events_test();
+        return userfaultfd_zeropage_test() || userfaultfd_sig_test()
+                || userfaultfd_events_test();
 }
 
 /*
@@ -981,7 +1233,12 @@ static void set_test_type(const char *type)
         } else if (!strcmp(type, "hugetlb")) {
                 test_type = TEST_HUGETLB;
                 uffd_test_ops = &hugetlb_uffd_test_ops;
+        } else if (!strcmp(type, "hugetlb_shared")) {
+                map_shared = true;
+                test_type = TEST_HUGETLB;
+                uffd_test_ops = &hugetlb_uffd_test_ops;
         } else if (!strcmp(type, "shmem")) {
+                map_shared = true;
                 test_type = TEST_SHMEM;
                 uffd_test_ops = &shmem_uffd_test_ops;
         } else {
@@ -1001,12 +1258,25 @@ static void set_test_type(const char *type)
                 fprintf(stderr, "Impossible to run this test\n"), exit(2);
 }
 
+static void sigalrm(int sig)
+{
+        if (sig != SIGALRM)
+                abort();
+        test_uffdio_copy_eexist = true;
+        test_uffdio_zeropage_eexist = true;
+        alarm(ALARM_INTERVAL_SECS);
+}
+
 int main(int argc, char **argv)
 {
         if (argc < 4)
                 fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"),
                                 exit(1);
 
+        if (signal(SIGALRM, sigalrm) == SIG_ERR)
+                fprintf(stderr, "failed to arm SIGALRM"), exit(1);
+        alarm(ALARM_INTERVAL_SECS);
+
         set_test_type(argv[1]);
 
         nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile
index f863c664e3d1..6b5598b55252 100644
--- a/tools/testing/selftests/watchdog/Makefile
+++ b/tools/testing/selftests/watchdog/Makefile
@@ -1,8 +1,4 @@
-TEST_PROGS := watchdog-test
-
-all: $(TEST_PROGS)
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := watchdog-test
 
 include ../lib.mk
-
-clean:
-        rm -fr $(TEST_PROGS)
diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index a74c9d739d07..6e290874b70e 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Watchdog Driver Test Program
  */
@@ -9,12 +10,25 @@
 #include <unistd.h>
 #include <fcntl.h>
 #include <signal.h>
+#include <getopt.h>
 #include <sys/ioctl.h>
 #include <linux/types.h>
 #include <linux/watchdog.h>
 
+#define DEFAULT_PING_RATE       1
+
 int fd;
 const char v = 'V';
+static const char sopts[] = "bdehp:t:";
+static const struct option lopts[] = {
+        {"bootstatus",          no_argument, NULL, 'b'},
+        {"disable",             no_argument, NULL, 'd'},
+        {"enable",              no_argument, NULL, 'e'},
+        {"help",                no_argument, NULL, 'h'},
+        {"pingrate",      required_argument, NULL, 'p'},
+        {"timeout",       required_argument, NULL, 't'},
+        {NULL,                  no_argument, NULL, 0x0}
+};
 
 /*
  * This function simply sends an IOCTL to the driver, which in turn ticks
@@ -23,12 +37,12 @@ const char v = 'V';
  */
 static void keep_alive(void)
 {
-    int dummy;
-    int ret;
+        int dummy;
+        int ret;
 
-    ret = ioctl(fd, WDIOC_KEEPALIVE, &dummy);
-    if (!ret)
-        printf(".");
+        ret = ioctl(fd, WDIOC_KEEPALIVE, &dummy);
+        if (!ret)
+                printf(".");
 }
 
 /*
@@ -38,75 +52,110 @@ static void keep_alive(void)
 
 static void term(int sig)
 {
-    int ret = write(fd, &v, 1);
-
-    close(fd);
-    if (ret < 0)
-        printf("\nStopping watchdog ticks failed (%d)...\n", errno);
-    else
-        printf("\nStopping watchdog ticks...\n");
-    exit(0);
+        int ret = write(fd, &v, 1);
+
+        close(fd);
+        if (ret < 0)
+                printf("\nStopping watchdog ticks failed (%d)...\n", errno);
+        else
+                printf("\nStopping watchdog ticks...\n");
+        exit(0);
+}
+
+static void usage(char *progname)
+{
+        printf("Usage: %s [options]\n", progname);
+        printf(" -b, --bootstatus    Get last boot status (Watchdog/POR)\n");
+        printf(" -d, --disable       Turn off the watchdog timer\n");
+        printf(" -e, --enable        Turn on the watchdog timer\n");
+        printf(" -h, --help          Print the help message\n");
+        printf(" -p, --pingrate=P    Set ping rate to P seconds (default %d)\n", DEFAULT_PING_RATE);
+        printf(" -t, --timeout=T     Set timeout to T seconds\n");
+        printf("\n");
+        printf("Parameters are parsed left-to-right in real-time.\n");
+        printf("Example: %s -d -t 10 -p 5 -e\n", progname);
 }
 
 int main(int argc, char *argv[])
 {
-    int flags;
-    unsigned int ping_rate = 1;
-    int ret;
-    int i;
-
-    setbuf(stdout, NULL);
-
-    fd = open("/dev/watchdog", O_WRONLY);
-
-    if (fd == -1) {
-        printf("Watchdog device not enabled.\n");
-        exit(-1);
-    }
-
-    for (i = 1; i < argc; i++) {
-        if (!strncasecmp(argv[i], "-d", 2)) {
-            flags = WDIOS_DISABLECARD;
-            ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
-            if (!ret)
-                printf("Watchdog card disabled.\n");
-        } else if (!strncasecmp(argv[i], "-e", 2)) {
-            flags = WDIOS_ENABLECARD;
-            ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
-            if (!ret)
-                printf("Watchdog card enabled.\n");
-        } else if (!strncasecmp(argv[i], "-t", 2) && argv[2]) {
-            flags = atoi(argv[i + 1]);
-            ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags);
-            if (!ret)
-                printf("Watchdog timeout set to %u seconds.\n", flags);
-            i++;
-        } else if (!strncasecmp(argv[i], "-p", 2) && argv[2]) {
-            ping_rate = strtoul(argv[i + 1], NULL, 0);
-            printf("Watchdog ping rate set to %u seconds.\n", ping_rate);
-            i++;
-        } else {
-            printf("-d to disable, -e to enable, -t <n> to set "
-                "the timeout,\n-p <n> to set the ping rate, and ");
-            printf("run by itself to tick the card.\n");
-            printf("Parameters are parsed left-to-right in real-time.\n");
-            printf("Example: %s -d -t 10 -p 5 -e\n", argv[0]);
-            goto end;
-        }
-    }
-
-    printf("Watchdog Ticking Away!\n");
-
-    signal(SIGINT, term);
-
-    while(1) {
-        keep_alive();
-        sleep(ping_rate);
-    }
+        int flags;
+        unsigned int ping_rate = DEFAULT_PING_RATE;
+        int ret;
+        int c;
+        int oneshot = 0;
+
+        setbuf(stdout, NULL);
+
+        fd = open("/dev/watchdog", O_WRONLY);
+
+        if (fd == -1) {
+                printf("Watchdog device not enabled.\n");
+                exit(-1);
+        }
+
+        while ((c = getopt_long(argc, argv, sopts, lopts, NULL)) != -1) {
+                switch (c) {
+                case 'b':
+                        flags = 0;
+                        oneshot = 1;
+                        ret = ioctl(fd, WDIOC_GETBOOTSTATUS, &flags);
+                        if (!ret)
+                                printf("Last boot is caused by: %s.\n", (flags != 0) ?
+                                        "Watchdog" : "Power-On-Reset");
+                        else
+                                printf("WDIOC_GETBOOTSTATUS errno '%s'\n", strerror(errno));
+                        break;
+                case 'd':
+                        flags = WDIOS_DISABLECARD;
+                        ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
+                        if (!ret)
+                                printf("Watchdog card disabled.\n");
+                        else
+                                printf("WDIOS_DISABLECARD errno '%s'\n", strerror(errno));
+                        break;
+                case 'e':
+                        flags = WDIOS_ENABLECARD;
+                        ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
+                        if (!ret)
+                                printf("Watchdog card enabled.\n");
+                        else
+                                printf("WDIOS_ENABLECARD errno '%s'\n", strerror(errno));
+                        break;
+                case 'p':
+                        ping_rate = strtoul(optarg, NULL, 0);
+                        if (!ping_rate)
+                                ping_rate = DEFAULT_PING_RATE;
+                        printf("Watchdog ping rate set to %u seconds.\n", ping_rate);
+                        break;
+                case 't':
+                        flags = strtoul(optarg, NULL, 0);
+                        ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags);
+                        if (!ret)
+                                printf("Watchdog timeout set to %u seconds.\n", flags);
+                        else
+                                printf("WDIOC_SETTIMEOUT errno '%s'\n", strerror(errno));
+                        break;
+                default:
+                        usage(argv[0]);
+                        goto end;
+                }
+        }
+
+        if (oneshot)
+                goto end;
+
+        printf("Watchdog Ticking Away!\n");
+
+        signal(SIGINT, term);
+
+        while (1) {
+                keep_alive();
+                sleep(ping_rate);
+        }
 end:
-    ret = write(fd, &v, 1);
-    if (ret < 0)
-        printf("Stopping watchdog ticks failed (%d)...\n", errno);
-    close(fd);
-    return 0;
+        ret = write(fd, &v, 1);
+        if (ret < 0)
+                printf("Stopping watchdog ticks failed (%d)...\n", errno);
+        close(fd);
+        return 0;
 }
diff --git a/tools/testing/selftests/x86/5lvl.c b/tools/testing/selftests/x86/5lvl.c
new file mode 100644
index 000000000000..2eafdcd4c2b3
--- /dev/null
+++ b/tools/testing/selftests/x86/5lvl.c
@@ -0,0 +1,177 @@
+#include <stdio.h>
+#include <sys/mman.h>
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define PAGE_SIZE       4096
+#define LOW_ADDR        ((void *) (1UL << 30))
+#define HIGH_ADDR       ((void *) (1UL << 50))
+
+struct testcase {
+        void *addr;
+        unsigned long size;
+        unsigned long flags;
+        const char *msg;
+        unsigned int low_addr_required:1;
+        unsigned int keep_mapped:1;
+};
+
+static struct testcase testcases[] = {
+        {
+                .addr = NULL,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(NULL)",
+                .low_addr_required = 1,
+        },
+        {
+                .addr = LOW_ADDR,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(LOW_ADDR)",
+                .low_addr_required = 1,
+        },
+        {
+                .addr = HIGH_ADDR,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(HIGH_ADDR)",
+                .keep_mapped = 1,
+        },
+        {
+                .addr = HIGH_ADDR,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(HIGH_ADDR) again",
+                .keep_mapped = 1,
+        },
+        {
+                .addr = HIGH_ADDR,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+                .msg = "mmap(HIGH_ADDR, MAP_FIXED)",
+        },
+        {
+                .addr = (void*) -1,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(-1)",
+                .keep_mapped = 1,
+        },
+        {
+                .addr = (void*) -1,
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(-1) again",
+        },
+        {
+                .addr = (void *)((1UL << 47) - PAGE_SIZE),
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap((1UL << 47), 2 * PAGE_SIZE)",
+                .low_addr_required = 1,
+                .keep_mapped = 1,
+        },
+        {
+                .addr = (void *)((1UL << 47) - PAGE_SIZE / 2),
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap((1UL << 47), 2 * PAGE_SIZE / 2)",
+                .low_addr_required = 1,
+                .keep_mapped = 1,
+        },
+        {
+                .addr = (void *)((1UL << 47) - PAGE_SIZE),
+                .size = 2 * PAGE_SIZE,
+                .flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+                .msg = "mmap((1UL << 47) - PAGE_SIZE, 2 * PAGE_SIZE, MAP_FIXED)",
+        },
+        {
+                .addr = NULL,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(NULL, MAP_HUGETLB)",
+                .low_addr_required = 1,
+        },
+        {
+                .addr = LOW_ADDR,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(LOW_ADDR, MAP_HUGETLB)",
+                .low_addr_required = 1,
+        },
+        {
+                .addr = HIGH_ADDR,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(HIGH_ADDR, MAP_HUGETLB)",
+                .keep_mapped = 1,
+        },
+        {
+                .addr = HIGH_ADDR,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(HIGH_ADDR, MAP_HUGETLB) again",
+                .keep_mapped = 1,
+        },
+        {
+                .addr = HIGH_ADDR,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+                .msg = "mmap(HIGH_ADDR, MAP_FIXED | MAP_HUGETLB)",
+        },
+        {
+                .addr = (void*) -1,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(-1, MAP_HUGETLB)",
+                .keep_mapped = 1,
+        },
+        {
+                .addr = (void*) -1,
+                .size = 2UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap(-1, MAP_HUGETLB) again",
+        },
+        {
+                .addr = (void *)((1UL << 47) - PAGE_SIZE),
+                .size = 4UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+                .msg = "mmap((1UL << 47), 4UL << 20, MAP_HUGETLB)",
+                .low_addr_required = 1,
+                .keep_mapped = 1,
+        },
+        {
+                .addr = (void *)((1UL << 47) - (2UL << 20)),
+                .size = 4UL << 20,
+                .flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+                .msg = "mmap((1UL << 47) - (2UL << 20), 4UL << 20, MAP_FIXED | MAP_HUGETLB)",
+        },
+};
+
+int main(int argc, char **argv)
+{
+        int i;
+        void *p;
+
+        for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+                struct testcase *t = testcases + i;
+
+                p = mmap(t->addr, t->size, PROT_NONE, t->flags, -1, 0);
+
+                printf("%s: %p - ", t->msg, p);
+
+                if (p == MAP_FAILED) {
+                        printf("FAILED\n");
+                        continue;
+                }
+
+                if (t->low_addr_required && p >= (void *)(1UL << 47))
+                        printf("FAILED\n");
+                else
+                        printf("OK\n");
+                if (!t->keep_mapped)
+                        munmap(p, t->size);
+        }
+        return 0;
+}
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 97f187e2663f..939a337128db 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 include ../lib.mk
@@ -10,7 +11,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
                         test_FCMOV test_FCOMI test_FISTTP \
                         vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
@@ -20,7 +21,7 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
-CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
+CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
 
 UNAME_M := $(shell uname -m)
 CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c
index d075ea0e5ca1..361466a2eaef 100644
--- a/tools/testing/selftests/x86/entry_from_vm86.c
+++ b/tools/testing/selftests/x86/entry_from_vm86.c
@@ -95,6 +95,27 @@ asm (
         "int3\n\t"
         "vmcode_int80:\n\t"
         "int $0x80\n\t"
+        "vmcode_umip:\n\t"
+        /* addressing via displacements */
+        "smsw (2052)\n\t"
+        "sidt (2054)\n\t"
+        "sgdt (2060)\n\t"
+        /* addressing via registers */
+        "mov $2066, %bx\n\t"
+        "smsw (%bx)\n\t"
+        "mov $2068, %bx\n\t"
+        "sidt (%bx)\n\t"
+        "mov $2074, %bx\n\t"
+        "sgdt (%bx)\n\t"
+        /* register operands, only for smsw */
+        "smsw %ax\n\t"
+        "mov %ax, (2080)\n\t"
+        "int3\n\t"
+        "vmcode_umip_str:\n\t"
+        "str %eax\n\t"
+        "vmcode_umip_sldt:\n\t"
+        "sldt %eax\n\t"
+        "int3\n\t"
         ".size vmcode, . - vmcode\n\t"
         "end_vmcode:\n\t"
         ".code32\n\t"
@@ -103,7 +124,8 @@ asm (
 
 extern unsigned char vmcode[], end_vmcode[];
 extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[],
-        vmcode_sti[], vmcode_int3[], vmcode_int80[];
+        vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_umip[],
+        vmcode_umip_str[], vmcode_umip_sldt[];
 
 /* Returns false if the test was skipped. */
 static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
@@ -160,6 +182,68 @@ static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
         return true;
 }
 
+void do_umip_tests(struct vm86plus_struct *vm86, unsigned char *test_mem)
+{
+        struct table_desc {
+                unsigned short limit;
+                unsigned long base;
+        } __attribute__((packed));
+
+        /* Initialize variables with arbitrary values */
+        struct table_desc gdt1 = { .base = 0x3c3c3c3c, .limit = 0x9999 };
+        struct table_desc gdt2 = { .base = 0x1a1a1a1a, .limit = 0xaeae };
+        struct table_desc idt1 = { .base = 0x7b7b7b7b, .limit = 0xf1f1 };
+        struct table_desc idt2 = { .base = 0x89898989, .limit = 0x1313 };
+        unsigned short msw1 = 0x1414, msw2 = 0x2525, msw3 = 3737;
+
+        /* UMIP -- exit with INT3 unless kernel emulation did not trap #GP */
+        do_test(vm86, vmcode_umip - vmcode, VM86_TRAP, 3, "UMIP tests");
+
+        /* Results from displacement-only addressing */
+        msw1 = *(unsigned short *)(test_mem + 2052);
+        memcpy(&idt1, test_mem + 2054, sizeof(idt1));
+        memcpy(&gdt1, test_mem + 2060, sizeof(gdt1));
+
+        /* Results from register-indirect addressing */
+        msw2 = *(unsigned short *)(test_mem + 2066);
+        memcpy(&idt2, test_mem + 2068, sizeof(idt2));
+        memcpy(&gdt2, test_mem + 2074, sizeof(gdt2));
+
+        /* Results when using register operands */
+        msw3 = *(unsigned short *)(test_mem + 2080);
+
+        printf("[INFO]\tResult from SMSW:[0x%04x]\n", msw1);
+        printf("[INFO]\tResult from SIDT: limit[0x%04x]base[0x%08lx]\n",
+               idt1.limit, idt1.base);
+        printf("[INFO]\tResult from SGDT: limit[0x%04x]base[0x%08lx]\n",
+               gdt1.limit, gdt1.base);
+
+        if (msw1 != msw2 || msw1 != msw3)
+                printf("[FAIL]\tAll the results of SMSW should be the same.\n");
+        else
+                printf("[PASS]\tAll the results from SMSW are identical.\n");
+
+        if (memcmp(&gdt1, &gdt2, sizeof(gdt1)))
+                printf("[FAIL]\tAll the results of SGDT should be the same.\n");
+        else
+                printf("[PASS]\tAll the results from SGDT are identical.\n");
+
+        if (memcmp(&idt1, &idt2, sizeof(idt1)))
+                printf("[FAIL]\tAll the results of SIDT should be the same.\n");
+        else
+                printf("[PASS]\tAll the results from SIDT are identical.\n");
+
+        sethandler(SIGILL, sighandler, 0);
+        do_test(vm86, vmcode_umip_str - vmcode, VM86_SIGNAL, 0,
+                "STR instruction");
+        clearhandler(SIGILL);
+
+        sethandler(SIGILL, sighandler, 0);
+        do_test(vm86, vmcode_umip_sldt - vmcode, VM86_SIGNAL, 0,
+                "SLDT instruction");
+        clearhandler(SIGILL);
+}
+
 int main(void)
 {
         struct vm86plus_struct v86;
@@ -218,6 +302,9 @@ int main(void)
         v86.regs.eax = (unsigned int)-1;
         do_test(&v86, vmcode_int80 - vmcode, VM86_INTx, 0x80, "int80");
 
+        /* UMIP -- should exit with INTx 0x80 unless UMIP was not disabled */
+        do_umip_tests(&v86, addr);
+
         /* Execute a null pointer */
         v86.regs.cs = 0;
         v86.regs.ss = 0;
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index b4967d875236..f249e042b3b5 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -285,9 +285,12 @@ static void *threadproc(void *ctx)
         }
 }
 
-static void set_gs_and_switch_to(unsigned long local, unsigned long remote)
+static void set_gs_and_switch_to(unsigned long local,
+                                 unsigned short force_sel,
+                                 unsigned long remote)
 {
         unsigned long base;
+        unsigned short sel_pre_sched, sel_post_sched;
 
         bool hard_zero = false;
         if (local == HARD_ZERO) {
@@ -297,6 +300,8 @@ static void set_gs_and_switch_to(unsigned long local, unsigned long remote)
 
         printf("[RUN]\tARCH_SET_GS(0x%lx)%s, then schedule to 0x%lx\n",
                local, hard_zero ? " and clear gs" : "", remote);
+        if (force_sel)
+                printf("\tBefore schedule, set selector to 0x%hx\n", force_sel);
         if (syscall(SYS_arch_prctl, ARCH_SET_GS, local) != 0)
                 err(1, "ARCH_SET_GS");
         if (hard_zero)
@@ -307,18 +312,35 @@ static void set_gs_and_switch_to(unsigned long local, unsigned long remote)
                 printf("[FAIL]\tGSBASE wasn't set as expected\n");
         }
 
+        if (force_sel) {
+                asm volatile ("mov %0, %%gs" : : "rm" (force_sel));
+                sel_pre_sched = force_sel;
+                local = read_base(GS);
+
+                /*
+                 * Signal delivery seems to mess up weird selectors.  Put it
+                 * back.
+                 */
+                asm volatile ("mov %0, %%gs" : : "rm" (force_sel));
+        } else {
+                asm volatile ("mov %%gs, %0" : "=rm" (sel_pre_sched));
+        }
+
         remote_base = remote;
         ftx = 1;
         syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
         while (ftx != 0)
                 syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0);
 
+        asm volatile ("mov %%gs, %0" : "=rm" (sel_post_sched));
         base = read_base(GS);
-        if (base == local) {
-                printf("[OK]\tGSBASE remained 0x%lx\n", local);
+        if (base == local && sel_pre_sched == sel_post_sched) {
+                printf("[OK]\tGS/BASE remained 0x%hx/0x%lx\n",
+                       sel_pre_sched, local);
         } else {
                 nerrs++;
-                printf("[FAIL]\tGSBASE changed to 0x%lx\n", base);
+                printf("[FAIL]\tGS/BASE changed from 0x%hx/0x%lx to 0x%hx/0x%lx\n",
+                       sel_pre_sched, local, sel_post_sched, base);
         }
 }
 
@@ -381,8 +403,15 @@ int main()
 
         for (int local = 0; local < 4; local++) {
                 for (int remote = 0; remote < 4; remote++) {
-                        set_gs_and_switch_to(bases_with_hard_zero[local],
-                                             bases_with_hard_zero[remote]);
+                        for (unsigned short s = 0; s < 5; s++) {
+                                unsigned short sel = s;
+                                if (s == 4)
+                                        asm ("mov %%ss, %0" : "=rm" (sel));
+                                set_gs_and_switch_to(
+                                        bases_with_hard_zero[local],
+                                        sel,
+                                        bases_with_hard_zero[remote]);
+                        }
                 }
         }
 
diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c
index b77313ba2ab1..01de41c1b725 100644
--- a/tools/testing/selftests/x86/ioperm.c
+++ b/tools/testing/selftests/x86/ioperm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * ioperm.c - Test case for ioperm(2)
  * Copyright (c) 2015 Andrew Lutomirski
diff --git a/tools/testing/selftests/x86/iopl.c b/tools/testing/selftests/x86/iopl.c
index c496ca97bc18..6aa27f34644c 100644
--- a/tools/testing/selftests/x86/iopl.c
+++ b/tools/testing/selftests/x86/iopl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * iopl.c - Test case for a Linux on Xen 64-bit bug
  * Copyright (c) 2015 Andrew Lutomirski
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index b9a22f18566a..66e5ce5b91f0 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * ldt_gdt.c - Test cases for LDT and GDT access
  * Copyright (c) 2015 Andrew Lutomirski
@@ -114,7 +115,15 @@ static void check_valid_segment(uint16_t index, int ldt,
                 return;
         }
 
-        if (ar != expected_ar) {
+        /* The SDM says "bits 19:16 are undefined".  Thanks. */
+        ar &= ~0xF0000;
+
+        /*
+         * NB: Different Linux versions do different things with the
+         * accessed bit in set_thread_area().
+         */
+        if (ar != expected_ar &&
+            (ldt || ar != (expected_ar | AR_ACCESSED))) {
                 printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n",
                        (ldt ? "LDT" : "GDT"), index, ar, expected_ar);
                 nerrs++;
@@ -128,30 +137,51 @@ static void check_valid_segment(uint16_t index, int ldt,
         }
 }
 
-static bool install_valid_mode(const struct user_desc *desc, uint32_t ar,
-                               bool oldmode)
+static bool install_valid_mode(const struct user_desc *d, uint32_t ar,
+                               bool oldmode, bool ldt)
 {
-        int ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11,
-                          desc, sizeof(*desc));
-        if (ret < -1)
-                errno = -ret;
+        struct user_desc desc = *d;
+        int ret;
+
+        if (!ldt) {
+#ifndef __i386__
+                /* No point testing set_thread_area in a 64-bit build */
+                return false;
+#endif
+                if (!gdt_entry_num)
+                        return false;
+                desc.entry_number = gdt_entry_num;
+
+                ret = syscall(SYS_set_thread_area, &desc);
+        } else {
+                ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11,
+                              &desc, sizeof(desc));
+
+                if (ret < -1)
+                        errno = -ret;
+
+                if (ret != 0 && errno == ENOSYS) {
+                        printf("[OK]\tmodify_ldt returned -ENOSYS\n");
+                        return false;
+                }
+        }
+
         if (ret == 0) {
-                uint32_t limit = desc->limit;
-                if (desc->limit_in_pages)
+                uint32_t limit = desc.limit;
+                if (desc.limit_in_pages)
                         limit = (limit << 12) + 4095;
-                check_valid_segment(desc->entry_number, 1, ar, limit, true);
+                check_valid_segment(desc.entry_number, ldt, ar, limit, true);
                 return true;
-        } else if (errno == ENOSYS) {
-                printf("[OK]\tmodify_ldt returned -ENOSYS\n");
-                return false;
         } else {
-                if (desc->seg_32bit) {
-                        printf("[FAIL]\tUnexpected modify_ldt failure %d\n",
+                if (desc.seg_32bit) {
+                        printf("[FAIL]\tUnexpected %s failure %d\n",
+                               ldt ? "modify_ldt" : "set_thread_area",
                                errno);
                         nerrs++;
                         return false;
                 } else {
-                        printf("[OK]\tmodify_ldt rejected 16 bit segment\n");
+                        printf("[OK]\t%s rejected 16 bit segment\n",
+                               ldt ? "modify_ldt" : "set_thread_area");
                         return false;
                 }
         }
@@ -159,7 +189,15 @@ static bool install_valid_mode(const struct user_desc *desc, uint32_t ar,
 
 static bool install_valid(const struct user_desc *desc, uint32_t ar)
 {
-        return install_valid_mode(desc, ar, false);
+        bool ret = install_valid_mode(desc, ar, false, true);
+
+        if (desc->contents <= 1 && desc->seg_32bit &&
+            !desc->seg_not_present) {
+                /* Should work in the GDT, too. */
+                install_valid_mode(desc, ar, false, false);
+        }
+
+        return ret;
 }
 
 static void install_invalid(const struct user_desc *desc, bool oldmode)
@@ -366,9 +404,24 @@ static void do_simple_tests(void)
         install_invalid(&desc, false);
 
         desc.seg_not_present = 0;
-        desc.read_exec_only = 0;
         desc.seg_32bit = 1;
+        desc.read_exec_only = 0;
+        desc.limit = 0xfffff;
+
         install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P | AR_DB);
+
+        desc.limit_in_pages = 1;
+
+        install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P | AR_DB | AR_G);
+        desc.read_exec_only = 1;
+        install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S | AR_P | AR_DB | AR_G);
+        desc.contents = 1;
+        desc.read_exec_only = 0;
+        install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA_EXPDOWN | AR_S | AR_P | AR_DB | AR_G);
+        desc.read_exec_only = 1;
+        install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA_EXPDOWN | AR_S | AR_P | AR_DB | AR_G);
+
+        desc.limit = 0;
         install_invalid(&desc, true);
 }
 
diff --git a/tools/testing/selftests/x86/mpx-debug.h b/tools/testing/selftests/x86/mpx-debug.h
index 9230981f2e12..7546eba7f17a 100644
--- a/tools/testing/selftests/x86/mpx-debug.h
+++ b/tools/testing/selftests/x86/mpx-debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _MPX_DEBUG_H
 #define _MPX_DEBUG_H
 
diff --git a/tools/testing/selftests/x86/mpx-dig.c b/tools/testing/selftests/x86/mpx-dig.c
index ce85356d7e2e..c13607ef5c11 100644
--- a/tools/testing/selftests/x86/mpx-dig.c
+++ b/tools/testing/selftests/x86/mpx-dig.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Written by Dave Hansen <dave.hansen@intel.com>
  */
diff --git a/tools/testing/selftests/x86/mpx-hw.h b/tools/testing/selftests/x86/mpx-hw.h
index 093c190178a9..d1b61ab870f8 100644
--- a/tools/testing/selftests/x86/mpx-hw.h
+++ b/tools/testing/selftests/x86/mpx-hw.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _MPX_HW_H
 #define _MPX_HW_H
 
@@ -51,14 +52,14 @@
 struct mpx_bd_entry {
         union {
                 char x[MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES];
-                void *contents[1];
+                void *contents[0];
         };
 } __attribute__((packed));
 
 struct mpx_bt_entry {
         union {
                 char x[MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES];
-                unsigned long contents[1];
+                unsigned long contents[0];
         };
 } __attribute__((packed));
 
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index a8df159a8924..ec0f6b45ce8b 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -391,8 +391,7 @@ void handler(int signum, siginfo_t *si, void *vucontext)
                 br_count++;
                 dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count);
 
-#define __SI_FAULT      (3 << 16)
-#define SEGV_BNDERR     (__SI_FAULT|3)  /* failed address bound checks */
+#define SEGV_BNDERR     3  /* failed address bound checks */
 
                 dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n",
                                 status, ip, br_reason);
diff --git a/tools/testing/selftests/x86/mpx-mm.h b/tools/testing/selftests/x86/mpx-mm.h
index af706a5398f7..6dbdd66b8242 100644
--- a/tools/testing/selftests/x86/mpx-mm.h
+++ b/tools/testing/selftests/x86/mpx-mm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _MPX_MM_H
 #define _MPX_MM_H
 
diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
index b20293956eec..b3cb7670e026 100644
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ b/tools/testing/selftests/x86/pkey-helpers.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PKEYS_HELPER_H
 #define _PKEYS_HELPER_H
 #define _GNU_SOURCE
@@ -29,6 +30,7 @@ static inline void sigsafe_printf(const char *format, ...)
         if (!dprint_in_signal) {
                 vprintf(format, ap);
         } else {
+                int ret;
                 int len = vsnprintf(dprint_in_signal_buffer,
                                     DPRINT_IN_SIGNAL_BUF_SIZE,
                                     format, ap);
@@ -38,7 +40,9 @@ static inline void sigsafe_printf(const char *format, ...)
                  */
                 if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
                         len = DPRINT_IN_SIGNAL_BUF_SIZE;
-                write(1, dprint_in_signal_buffer, len);
+                ret = write(1, dprint_in_signal_buffer, len);
+                if (ret < 0)
+                        abort();
         }
         va_end(ap);
 }
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 3237bc010e1c..bc1b0735bb50 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Tests x86 Memory Protection Keys (see Documentation/x86/protection-keys.txt)
  *
@@ -188,17 +189,29 @@ void lots_o_noops_around_write(int *write_to_me)
 #define u64 uint64_t
 
 #ifdef __i386__
-#define SYS_mprotect_key 380
-#define SYS_pkey_alloc   381
-#define SYS_pkey_free    382
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 380
+#endif
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc  381
+# define SYS_pkey_free   382
+#endif
 #define REG_IP_IDX REG_EIP
 #define si_pkey_offset 0x14
+
 #else
-#define SYS_mprotect_key 329
-#define SYS_pkey_alloc   330
-#define SYS_pkey_free    331
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key 329
+#endif
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc  330
+# define SYS_pkey_free   331
+#endif
 #define REG_IP_IDX REG_RIP
 #define si_pkey_offset 0x20
+
 #endif
 
 void dump_mem(void *dumpme, int len_bytes)
@@ -212,19 +225,18 @@ void dump_mem(void *dumpme, int len_bytes)
         }
 }
 
-#define __SI_FAULT      (3 << 16)
-#define SEGV_BNDERR     (__SI_FAULT|3)  /* failed address bound checks */
-#define SEGV_PKUERR     (__SI_FAULT|4)
+#define SEGV_BNDERR     3  /* failed address bound checks */
+#define SEGV_PKUERR     4
 
 static char *si_code_str(int si_code)
 {
-        if (si_code & SEGV_MAPERR)
+        if (si_code == SEGV_MAPERR)
                 return "SEGV_MAPERR";
-        if (si_code & SEGV_ACCERR)
+        if (si_code == SEGV_ACCERR)
                 return "SEGV_ACCERR";
-        if (si_code & SEGV_BNDERR)
+        if (si_code == SEGV_BNDERR)
                 return "SEGV_BNDERR";
-        if (si_code & SEGV_PKUERR)
+        if (si_code == SEGV_PKUERR)
                 return "SEGV_PKUERR";
         return "UNKNOWN";
 }
@@ -238,7 +250,7 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
         unsigned long ip;
         char *fpregs;
         u32 *pkru_ptr;
-        u64 si_pkey;
+        u64 siginfo_pkey;
         u32 *si_pkey_ptr;
         int pkru_offset;
         fpregset_t fpregset;
@@ -280,9 +292,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
         si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
         dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
         dump_mem(si_pkey_ptr - 8, 24);
-        si_pkey = *si_pkey_ptr;
-        pkey_assert(si_pkey < NR_PKEYS);
-        last_si_pkey = si_pkey;
+        siginfo_pkey = *si_pkey_ptr;
+        pkey_assert(siginfo_pkey < NR_PKEYS);
+        last_si_pkey = siginfo_pkey;
 
         if ((si->si_code == SEGV_MAPERR) ||
             (si->si_code == SEGV_ACCERR) ||
@@ -294,7 +306,7 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
         dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
         /* need __rdpkru() version so we do not do shadow_pkru checking */
         dprintf1("signal pkru from  pkru: %08x\n", __rdpkru());
-        dprintf1("si_pkey from siginfo: %jx\n", si_pkey);
+        dprintf1("pkey from siginfo: %jx\n", siginfo_pkey);
         *(u64 *)pkru_ptr = 0x00000000;
         dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
         pkru_faults++;
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index eaea92439708..1ae1c5a7392e 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 
 #include <sys/ptrace.h>
diff --git a/tools/testing/selftests/x86/raw_syscall_helper_32.S b/tools/testing/selftests/x86/raw_syscall_helper_32.S
index 534e71e35c6a..94410fa2b5ed 100644
--- a/tools/testing/selftests/x86/raw_syscall_helper_32.S
+++ b/tools/testing/selftests/x86/raw_syscall_helper_32.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 .global sys32_helper
 sys32_helper:
         /* Args: syscall_args_32*, function pointer */
diff --git a/tools/testing/selftests/x86/test_FCMOV.c b/tools/testing/selftests/x86/test_FCMOV.c
index 4adcca0c80c4..6b5036fbb735 100644
--- a/tools/testing/selftests/x86/test_FCMOV.c
+++ b/tools/testing/selftests/x86/test_FCMOV.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #undef _GNU_SOURCE
 #define _GNU_SOURCE 1
 #undef __USE_GNU
diff --git a/tools/testing/selftests/x86/test_FCOMI.c b/tools/testing/selftests/x86/test_FCOMI.c
index db4933e31af9..aec6692c6dcf 100644
--- a/tools/testing/selftests/x86/test_FCOMI.c
+++ b/tools/testing/selftests/x86/test_FCOMI.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #undef _GNU_SOURCE
 #define _GNU_SOURCE 1
 #undef __USE_GNU
diff --git a/tools/testing/selftests/x86/test_FISTTP.c b/tools/testing/selftests/x86/test_FISTTP.c
index b8e61a047f6b..09789c0ce3e9 100644
--- a/tools/testing/selftests/x86/test_FISTTP.c
+++ b/tools/testing/selftests/x86/test_FISTTP.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #undef _GNU_SOURCE
 #define _GNU_SOURCE 1
 #undef __USE_GNU
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 65d7a2bf7e14..29973cde06d3 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * ldt_gdt.c - Test cases for LDT and GDT access
  * Copyright (c) 2011-2015 Andrew Lutomirski
diff --git a/tools/testing/selftests/zram/Makefile b/tools/testing/selftests/zram/Makefile
index c3a87e5f9d36..7f78eb1b59cb 100644
--- a/tools/testing/selftests/zram/Makefile
+++ b/tools/testing/selftests/zram/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 TEST_PROGS := zram.sh
diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh
index 683a292e3290..754de7da426a 100755
--- a/tools/testing/selftests/zram/zram.sh
+++ b/tools/testing/selftests/zram/zram.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
 TCID="zram.sh"
 
 . ./zram_lib.sh
diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore
new file mode 100644
index 000000000000..dc5f11faf530
--- /dev/null
+++ b/tools/testing/vsock/.gitignore
@@ -0,0 +1,2 @@
+*.d
+vsock_diag_test
diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
new file mode 100644
index 000000000000..66ba0924194d
--- /dev/null
+++ b/tools/testing/vsock/Makefile
@@ -0,0 +1,9 @@
+all: test
+test: vsock_diag_test
+vsock_diag_test: vsock_diag_test.o timeout.o control.o
+
+CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE
+.PHONY: all test clean
+clean:
+        ${RM} *.o *.d vsock_diag_test
+-include *.d
diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README
new file mode 100644
index 000000000000..2cc6d7302db6
--- /dev/null
+++ b/tools/testing/vsock/README
@@ -0,0 +1,36 @@
+AF_VSOCK test suite
+-------------------
+These tests exercise net/vmw_vsock/ host<->guest sockets for VMware, KVM, and
+Hyper-V.
+
+The following tests are available:
+
+  * vsock_diag_test - vsock_diag.ko module for listing open sockets
+
+The following prerequisite steps are not automated and must be performed prior
+to running tests:
+
+1. Build the kernel and these tests.
+2. Install the kernel and tests on the host.
+3. Install the kernel and tests inside the guest.
+4. Boot the guest and ensure that the AF_VSOCK transport is enabled.
+
+Invoke test binaries in both directions as follows:
+
+  # host=server, guest=client
+  (host)# $TEST_BINARY --mode=server \
+                       --control-port=1234 \
+                       --peer-cid=3
+  (guest)# $TEST_BINARY --mode=client \
+                        --control-host=$HOST_IP \
+                        --control-port=1234 \
+                        --peer-cid=2
+
+  # host=client, guest=server
+  (guest)# $TEST_BINARY --mode=server \
+                        --control-port=1234 \
+                        --peer-cid=2
+  (host)# $TEST_BINARY --mode=client \
+                       --control-port=$GUEST_IP \
+                       --control-port=1234 \
+                       --peer-cid=3
diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c
new file mode 100644
index 000000000000..90fd47f0e422
--- /dev/null
+++ b/tools/testing/vsock/control.c
@@ -0,0 +1,219 @@
+/* Control socket for client/server test execution
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/* The client and server may need to coordinate to avoid race conditions like
+ * the client attempting to connect to a socket that the server is not
+ * listening on yet.  The control socket offers a communications channel for
+ * such coordination tasks.
+ *
+ * If the client calls control_expectln("LISTENING"), then it will block until
+ * the server calls control_writeln("LISTENING").  This provides a simple
+ * mechanism for coordinating between the client and the server.
+ */
+
+#include <errno.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "timeout.h"
+#include "control.h"
+
+static int control_fd = -1;
+
+/* Open the control socket, either in server or client mode */
+void control_init(const char *control_host,
+                  const char *control_port,
+                  bool server)
+{
+        struct addrinfo hints = {
+                .ai_socktype = SOCK_STREAM,
+        };
+        struct addrinfo *result = NULL;
+        struct addrinfo *ai;
+        int ret;
+
+        ret = getaddrinfo(control_host, control_port, &hints, &result);
+        if (ret != 0) {
+                fprintf(stderr, "%s\n", gai_strerror(ret));
+                exit(EXIT_FAILURE);
+        }
+
+        for (ai = result; ai; ai = ai->ai_next) {
+                int fd;
+                int val = 1;
+
+                fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+                if (fd < 0)
+                        continue;
+
+                if (!server) {
+                        if (connect(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+                                goto next;
+                        control_fd = fd;
+                        printf("Control socket connected to %s:%s.\n",
+                               control_host, control_port);
+                        break;
+                }
+
+                if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
+                               &val, sizeof(val)) < 0) {
+                        perror("setsockopt");
+                        exit(EXIT_FAILURE);
+                }
+
+                if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0)
+                        goto next;
+                if (listen(fd, 1) < 0)
+                        goto next;
+
+                printf("Control socket listening on %s:%s\n",
+                       control_host, control_port);
+                fflush(stdout);
+
+                control_fd = accept(fd, NULL, 0);
+                close(fd);
+
+                if (control_fd < 0) {
+                        perror("accept");
+                        exit(EXIT_FAILURE);
+                }
+                printf("Control socket connection accepted...\n");
+                break;
+
+next:
+                close(fd);
+        }
+
+        if (control_fd < 0) {
+                fprintf(stderr, "Control socket initialization failed.  Invalid address %s:%s?\n",
+                        control_host, control_port);
+                exit(EXIT_FAILURE);
+        }
+
+        freeaddrinfo(result);
+}
+
+/* Free resources */
+void control_cleanup(void)
+{
+        close(control_fd);
+        control_fd = -1;
+}
+
+/* Write a line to the control socket */
+void control_writeln(const char *str)
+{
+        ssize_t len = strlen(str);
+        ssize_t ret;
+
+        timeout_begin(TIMEOUT);
+
+        do {
+                ret = send(control_fd, str, len, MSG_MORE);
+                timeout_check("send");
+        } while (ret < 0 && errno == EINTR);
+
+        if (ret != len) {
+                perror("send");
+                exit(EXIT_FAILURE);
+        }
+
+        do {
+                ret = send(control_fd, "\n", 1, 0);
+                timeout_check("send");
+        } while (ret < 0 && errno == EINTR);
+
+        if (ret != 1) {
+                perror("send");
+                exit(EXIT_FAILURE);
+        }
+
+        timeout_end();
+}
+
+/* Return the next line from the control socket (without the trailing newline).
+ *
+ * The program terminates if a timeout occurs.
+ *
+ * The caller must free() the returned string.
+ */
+char *control_readln(void)
+{
+        char *buf = NULL;
+        size_t idx = 0;
+        size_t buflen = 0;
+
+        timeout_begin(TIMEOUT);
+
+        for (;;) {
+                ssize_t ret;
+
+                if (idx >= buflen) {
+                        char *new_buf;
+
+                        new_buf = realloc(buf, buflen + 80);
+                        if (!new_buf) {
+                                perror("realloc");
+                                exit(EXIT_FAILURE);
+                        }
+
+                        buf = new_buf;
+                        buflen += 80;
+                }
+
+                do {
+                        ret = recv(control_fd, &buf[idx], 1, 0);
+                        timeout_check("recv");
+                } while (ret < 0 && errno == EINTR);
+
+                if (ret == 0) {
+                        fprintf(stderr, "unexpected EOF on control socket\n");
+                        exit(EXIT_FAILURE);
+                }
+
+                if (ret != 1) {
+                        perror("recv");
+                        exit(EXIT_FAILURE);
+                }
+
+                if (buf[idx] == '\n') {
+                        buf[idx] = '\0';
+                        break;
+                }
+
+                idx++;
+        }
+
+        timeout_end();
+
+        return buf;
+}
+
+/* Wait until a given line is received or a timeout occurs */
+void control_expectln(const char *str)
+{
+        char *line;
+
+        line = control_readln();
+        if (strcmp(str, line) != 0) {
+                fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n",
+                        str, line);
+                exit(EXIT_FAILURE);
+        }
+
+        free(line);
+}
diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h
new file mode 100644
index 000000000000..54a07efd267c
--- /dev/null
+++ b/tools/testing/vsock/control.h
@@ -0,0 +1,13 @@
+#ifndef CONTROL_H
+#define CONTROL_H
+
+#include <stdbool.h>
+
+void control_init(const char *control_host, const char *control_port,
+                  bool server);
+void control_cleanup(void);
+void control_writeln(const char *str);
+char *control_readln(void);
+void control_expectln(const char *str);
+
+#endif /* CONTROL_H */
diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c
new file mode 100644
index 000000000000..c49b3003b2db
--- /dev/null
+++ b/tools/testing/vsock/timeout.c
@@ -0,0 +1,64 @@
+/* Timeout API for single-threaded programs that use blocking
+ * syscalls (read/write/send/recv/connect/accept).
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/* Use the following pattern:
+ *
+ *   timeout_begin(TIMEOUT);
+ *   do {
+ *       ret = accept(...);
+ *       timeout_check("accept");
+ *   } while (ret < 0 && ret == EINTR);
+ *   timeout_end();
+ */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <stdio.h>
+#include "timeout.h"
+
+static volatile bool timeout;
+
+/* SIGALRM handler function.  Do not use sleep(2), alarm(2), or
+ * setitimer(2) while using this API - they may interfere with each
+ * other.
+ */
+void sigalrm(int signo)
+{
+        timeout = true;
+}
+
+/* Start a timeout.  Call timeout_check() to verify that the timeout hasn't
+ * expired.  timeout_end() must be called to stop the timeout.  Timeouts cannot
+ * be nested.
+ */
+void timeout_begin(unsigned int seconds)
+{
+        alarm(seconds);
+}
+
+/* Exit with an error message if the timeout has expired */
+void timeout_check(const char *operation)
+{
+        if (timeout) {
+                fprintf(stderr, "%s timed out\n", operation);
+                exit(EXIT_FAILURE);
+        }
+}
+
+/* Stop a timeout */
+void timeout_end(void)
+{
+        alarm(0);
+        timeout = false;
+}
diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h
new file mode 100644
index 000000000000..77db9ce9860a
--- /dev/null
+++ b/tools/testing/vsock/timeout.h
@@ -0,0 +1,14 @@
+#ifndef TIMEOUT_H
+#define TIMEOUT_H
+
+enum {
+        /* Default timeout */
+        TIMEOUT = 10 /* seconds */
+};
+
+void sigalrm(int signo);
+void timeout_begin(unsigned int seconds);
+void timeout_check(const char *operation);
+void timeout_end(void);
+
+#endif /* TIMEOUT_H */
diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c
new file mode 100644
index 000000000000..e896a4af52f4
--- /dev/null
+++ b/tools/testing/vsock/vsock_diag_test.c
@@ -0,0 +1,681 @@
+/*
+ * vsock_diag_test - vsock_diag.ko test suite
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ *
+ * Author: Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <linux/list.h>
+#include <linux/net.h>
+#include <linux/netlink.h>
+#include <linux/sock_diag.h>
+#include <netinet/tcp.h>
+
+#include "../../../include/uapi/linux/vm_sockets.h"
+#include "../../../include/uapi/linux/vm_sockets_diag.h"
+
+#include "timeout.h"
+#include "control.h"
+
+enum test_mode {
+        TEST_MODE_UNSET,
+        TEST_MODE_CLIENT,
+        TEST_MODE_SERVER
+};
+
+/* Per-socket status */
+struct vsock_stat {
+        struct list_head list;
+        struct vsock_diag_msg msg;
+};
+
+static const char *sock_type_str(int type)
+{
+        switch (type) {
+        case SOCK_DGRAM:
+                return "DGRAM";
+        case SOCK_STREAM:
+                return "STREAM";
+        default:
+                return "INVALID TYPE";
+        }
+}
+
+static const char *sock_state_str(int state)
+{
+        switch (state) {
+        case TCP_CLOSE:
+                return "UNCONNECTED";
+        case TCP_SYN_SENT:
+                return "CONNECTING";
+        case TCP_ESTABLISHED:
+                return "CONNECTED";
+        case TCP_CLOSING:
+                return "DISCONNECTING";
+        case TCP_LISTEN:
+                return "LISTEN";
+        default:
+                return "INVALID STATE";
+        }
+}
+
+static const char *sock_shutdown_str(int shutdown)
+{
+        switch (shutdown) {
+        case 1:
+                return "RCV_SHUTDOWN";
+        case 2:
+                return "SEND_SHUTDOWN";
+        case 3:
+                return "RCV_SHUTDOWN | SEND_SHUTDOWN";
+        default:
+                return "0";
+        }
+}
+
+static void print_vsock_addr(FILE *fp, unsigned int cid, unsigned int port)
+{
+        if (cid == VMADDR_CID_ANY)
+                fprintf(fp, "*:");
+        else
+                fprintf(fp, "%u:", cid);
+
+        if (port == VMADDR_PORT_ANY)
+                fprintf(fp, "*");
+        else
+                fprintf(fp, "%u", port);
+}
+
+static void print_vsock_stat(FILE *fp, struct vsock_stat *st)
+{
+        print_vsock_addr(fp, st->msg.vdiag_src_cid, st->msg.vdiag_src_port);
+        fprintf(fp, " ");
+        print_vsock_addr(fp, st->msg.vdiag_dst_cid, st->msg.vdiag_dst_port);
+        fprintf(fp, " %s %s %s %u\n",
+                sock_type_str(st->msg.vdiag_type),
+                sock_state_str(st->msg.vdiag_state),
+                sock_shutdown_str(st->msg.vdiag_shutdown),
+                st->msg.vdiag_ino);
+}
+
+static void print_vsock_stats(FILE *fp, struct list_head *head)
+{
+        struct vsock_stat *st;
+
+        list_for_each_entry(st, head, list)
+                print_vsock_stat(fp, st);
+}
+
+static struct vsock_stat *find_vsock_stat(struct list_head *head, int fd)
+{
+        struct vsock_stat *st;
+        struct stat stat;
+
+        if (fstat(fd, &stat) < 0) {
+                perror("fstat");
+                exit(EXIT_FAILURE);
+        }
+
+        list_for_each_entry(st, head, list)
+                if (st->msg.vdiag_ino == stat.st_ino)
+                        return st;
+
+        fprintf(stderr, "cannot find fd %d\n", fd);
+        exit(EXIT_FAILURE);
+}
+
+static void check_no_sockets(struct list_head *head)
+{
+        if (!list_empty(head)) {
+                fprintf(stderr, "expected no sockets\n");
+                print_vsock_stats(stderr, head);
+                exit(1);
+        }
+}
+
+static void check_num_sockets(struct list_head *head, int expected)
+{
+        struct list_head *node;
+        int n = 0;
+
+        list_for_each(node, head)
+                n++;
+
+        if (n != expected) {
+                fprintf(stderr, "expected %d sockets, found %d\n",
+                        expected, n);
+                print_vsock_stats(stderr, head);
+                exit(EXIT_FAILURE);
+        }
+}
+
+static void check_socket_state(struct vsock_stat *st, __u8 state)
+{
+        if (st->msg.vdiag_state != state) {
+                fprintf(stderr, "expected socket state %#x, got %#x\n",
+                        state, st->msg.vdiag_state);
+                exit(EXIT_FAILURE);
+        }
+}
+
+static void send_req(int fd)
+{
+        struct sockaddr_nl nladdr = {
+                .nl_family = AF_NETLINK,
+        };
+        struct {
+                struct nlmsghdr nlh;
+                struct vsock_diag_req vreq;
+        } req = {
+                .nlh = {
+                        .nlmsg_len = sizeof(req),
+                        .nlmsg_type = SOCK_DIAG_BY_FAMILY,
+                        .nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP,
+                },
+                .vreq = {
+                        .sdiag_family = AF_VSOCK,
+                        .vdiag_states = ~(__u32)0,
+                },
+        };
+        struct iovec iov = {
+                .iov_base = &req,
+                .iov_len = sizeof(req),
+        };
+        struct msghdr msg = {
+                .msg_name = &nladdr,
+                .msg_namelen = sizeof(nladdr),
+                .msg_iov = &iov,
+                .msg_iovlen = 1,
+        };
+
+        for (;;) {
+                if (sendmsg(fd, &msg, 0) < 0) {
+                        if (errno == EINTR)
+                                continue;
+
+                        perror("sendmsg");
+                        exit(EXIT_FAILURE);
+                }
+
+                return;
+        }
+}
+
+static ssize_t recv_resp(int fd, void *buf, size_t len)
+{
+        struct sockaddr_nl nladdr = {
+                .nl_family = AF_NETLINK,
+        };
+        struct iovec iov = {
+                .iov_base = buf,
+                .iov_len = len,
+        };
+        struct msghdr msg = {
+                .msg_name = &nladdr,
+                .msg_namelen = sizeof(nladdr),
+                .msg_iov = &iov,
+                .msg_iovlen = 1,
+        };
+        ssize_t ret;
+
+        do {
+                ret = recvmsg(fd, &msg, 0);
+        } while (ret < 0 && errno == EINTR);
+
+        if (ret < 0) {
+                perror("recvmsg");
+                exit(EXIT_FAILURE);
+        }
+
+        return ret;
+}
+
+static void add_vsock_stat(struct list_head *sockets,
+                           const struct vsock_diag_msg *resp)
+{
+        struct vsock_stat *st;
+
+        st = malloc(sizeof(*st));
+        if (!st) {
+                perror("malloc");
+                exit(EXIT_FAILURE);
+        }
+
+        st->msg = *resp;
+        list_add_tail(&st->list, sockets);
+}
+
+/*
+ * Read vsock stats into a list.
+ */
+static void read_vsock_stat(struct list_head *sockets)
+{
+        long buf[8192 / sizeof(long)];
+        int fd;
+
+        fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+        if (fd < 0) {
+                perror("socket");
+                exit(EXIT_FAILURE);
+        }
+
+        send_req(fd);
+
+        for (;;) {
+                const struct nlmsghdr *h;
+                ssize_t ret;
+
+                ret = recv_resp(fd, buf, sizeof(buf));
+                if (ret == 0)
+                        goto done;
+                if (ret < sizeof(*h)) {
+                        fprintf(stderr, "short read of %zd bytes\n", ret);
+                        exit(EXIT_FAILURE);
+                }
+
+                h = (struct nlmsghdr *)buf;
+
+                while (NLMSG_OK(h, ret)) {
+                        if (h->nlmsg_type == NLMSG_DONE)
+                                goto done;
+
+                        if (h->nlmsg_type == NLMSG_ERROR) {
+                                const struct nlmsgerr *err = NLMSG_DATA(h);
+
+                                if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
+                                        fprintf(stderr, "NLMSG_ERROR\n");
+                                else {
+                                        errno = -err->error;
+                                        perror("NLMSG_ERROR");
+                                }
+
+                                exit(EXIT_FAILURE);
+                        }
+
+                        if (h->nlmsg_type != SOCK_DIAG_BY_FAMILY) {
+                                fprintf(stderr, "unexpected nlmsg_type %#x\n",
+                                        h->nlmsg_type);
+                                exit(EXIT_FAILURE);
+                        }
+                        if (h->nlmsg_len <
+                            NLMSG_LENGTH(sizeof(struct vsock_diag_msg))) {
+                                fprintf(stderr, "short vsock_diag_msg\n");
+                                exit(EXIT_FAILURE);
+                        }
+
+                        add_vsock_stat(sockets, NLMSG_DATA(h));
+
+                        h = NLMSG_NEXT(h, ret);
+                }
+        }
+
+done:
+        close(fd);
+}
+
+static void free_sock_stat(struct list_head *sockets)
+{
+        struct vsock_stat *st;
+        struct vsock_stat *next;
+
+        list_for_each_entry_safe(st, next, sockets, list)
+                free(st);
+}
+
+static void test_no_sockets(unsigned int peer_cid)
+{
+        LIST_HEAD(sockets);
+
+        read_vsock_stat(&sockets);
+
+        check_no_sockets(&sockets);
+
+        free_sock_stat(&sockets);
+}
+
+static void test_listen_socket_server(unsigned int peer_cid)
+{
+        union {
+                struct sockaddr sa;
+                struct sockaddr_vm svm;
+        } addr = {
+                .svm = {
+                        .svm_family = AF_VSOCK,
+                        .svm_port = 1234,
+                        .svm_cid = VMADDR_CID_ANY,
+                },
+        };
+        LIST_HEAD(sockets);
+        struct vsock_stat *st;
+        int fd;
+
+        fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+        if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+                perror("bind");
+                exit(EXIT_FAILURE);
+        }
+
+        if (listen(fd, 1) < 0) {
+                perror("listen");
+                exit(EXIT_FAILURE);
+        }
+
+        read_vsock_stat(&sockets);
+
+        check_num_sockets(&sockets, 1);
+        st = find_vsock_stat(&sockets, fd);
+        check_socket_state(st, TCP_LISTEN);
+
+        close(fd);
+        free_sock_stat(&sockets);
+}
+
+static void test_connect_client(unsigned int peer_cid)
+{
+        union {
+                struct sockaddr sa;
+                struct sockaddr_vm svm;
+        } addr = {
+                .svm = {
+                        .svm_family = AF_VSOCK,
+                        .svm_port = 1234,
+                        .svm_cid = peer_cid,
+                },
+        };
+        int fd;
+        int ret;
+        LIST_HEAD(sockets);
+        struct vsock_stat *st;
+
+        control_expectln("LISTENING");
+
+        fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+        timeout_begin(TIMEOUT);
+        do {
+                ret = connect(fd, &addr.sa, sizeof(addr.svm));
+                timeout_check("connect");
+        } while (ret < 0 && errno == EINTR);
+        timeout_end();
+
+        if (ret < 0) {
+                perror("connect");
+                exit(EXIT_FAILURE);
+        }
+
+        read_vsock_stat(&sockets);
+
+        check_num_sockets(&sockets, 1);
+        st = find_vsock_stat(&sockets, fd);
+        check_socket_state(st, TCP_ESTABLISHED);
+
+        control_expectln("DONE");
+        control_writeln("DONE");
+
+        close(fd);
+        free_sock_stat(&sockets);
+}
+
+static void test_connect_server(unsigned int peer_cid)
+{
+        union {
+                struct sockaddr sa;
+                struct sockaddr_vm svm;
+        } addr = {
+                .svm = {
+                        .svm_family = AF_VSOCK,
+                        .svm_port = 1234,
+                        .svm_cid = VMADDR_CID_ANY,
+                },
+        };
+        union {
+                struct sockaddr sa;
+                struct sockaddr_vm svm;
+        } clientaddr;
+        socklen_t clientaddr_len = sizeof(clientaddr.svm);
+        LIST_HEAD(sockets);
+        struct vsock_stat *st;
+        int fd;
+        int client_fd;
+
+        fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+
+        if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+                perror("bind");
+                exit(EXIT_FAILURE);
+        }
+
+        if (listen(fd, 1) < 0) {
+                perror("listen");
+                exit(EXIT_FAILURE);
+        }
+
+        control_writeln("LISTENING");
+
+        timeout_begin(TIMEOUT);
+        do {
+                client_fd = accept(fd, &clientaddr.sa, &clientaddr_len);
+                timeout_check("accept");
+        } while (client_fd < 0 && errno == EINTR);
+        timeout_end();
+
+        if (client_fd < 0) {
+                perror("accept");
+                exit(EXIT_FAILURE);
+        }
+        if (clientaddr.sa.sa_family != AF_VSOCK) {
+                fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n",
+                        clientaddr.sa.sa_family);
+                exit(EXIT_FAILURE);
+        }
+        if (clientaddr.svm.svm_cid != peer_cid) {
+                fprintf(stderr, "expected peer CID %u from accept(2), got %u\n",
+                        peer_cid, clientaddr.svm.svm_cid);
+                exit(EXIT_FAILURE);
+        }
+
+        read_vsock_stat(&sockets);
+
+        check_num_sockets(&sockets, 2);
+        find_vsock_stat(&sockets, fd);
+        st = find_vsock_stat(&sockets, client_fd);
+        check_socket_state(st, TCP_ESTABLISHED);
+
+        control_writeln("DONE");
+        control_expectln("DONE");
+
+        close(client_fd);
+        close(fd);
+        free_sock_stat(&sockets);
+}
+
+static struct {
+        const char *name;
+        void (*run_client)(unsigned int peer_cid);
+        void (*run_server)(unsigned int peer_cid);
+} test_cases[] = {
+        {
+                .name = "No sockets",
+                .run_server = test_no_sockets,
+        },
+        {
+                .name = "Listen socket",
+                .run_server = test_listen_socket_server,
+        },
+        {
+                .name = "Connect",
+                .run_client = test_connect_client,
+                .run_server = test_connect_server,
+        },
+        {},
+};
+
+static void init_signals(void)
+{
+        struct sigaction act = {
+                .sa_handler = sigalrm,
+        };
+
+        sigaction(SIGALRM, &act, NULL);
+        signal(SIGPIPE, SIG_IGN);
+}
+
+static unsigned int parse_cid(const char *str)
+{
+        char *endptr = NULL;
+        unsigned long int n;
+
+        errno = 0;
+        n = strtoul(str, &endptr, 10);
+        if (errno || *endptr != '\0') {
+                fprintf(stderr, "malformed CID \"%s\"\n", str);
+                exit(EXIT_FAILURE);
+        }
+        return n;
+}
+
+static const char optstring[] = "";
+static const struct option longopts[] = {
+        {
+                .name = "control-host",
+                .has_arg = required_argument,
+                .val = 'H',
+        },
+        {
+                .name = "control-port",
+                .has_arg = required_argument,
+                .val = 'P',
+        },
+        {
+                .name = "mode",
+                .has_arg = required_argument,
+                .val = 'm',
+        },
+        {
+                .name = "peer-cid",
+                .has_arg = required_argument,
+                .val = 'p',
+        },
+        {
+                .name = "help",
+                .has_arg = no_argument,
+                .val = '?',
+        },
+        {},
+};
+
+static void usage(void)
+{
+        fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n"
+                "\n"
+                "  Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n"
+                "  Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n"
+                "\n"
+                "Run vsock_diag.ko tests.  Must be launched in both\n"
+                "guest and host.  One side must use --mode=client and\n"
+                "the other side must use --mode=server.\n"
+                "\n"
+                "A TCP control socket connection is used to coordinate tests\n"
+                "between the client and the server.  The server requires a\n"
+                "listen address and the client requires an address to\n"
+                "connect to.\n"
+                "\n"
+                "The CID of the other side must be given with --peer-cid=<cid>.\n");
+        exit(EXIT_FAILURE);
+}
+
+int main(int argc, char **argv)
+{
+        const char *control_host = NULL;
+        const char *control_port = NULL;
+        int mode = TEST_MODE_UNSET;
+        unsigned int peer_cid = VMADDR_CID_ANY;
+        int i;
+
+        init_signals();
+
+        for (;;) {
+                int opt = getopt_long(argc, argv, optstring, longopts, NULL);
+
+                if (opt == -1)
+                        break;
+
+                switch (opt) {
+                case 'H':
+                        control_host = optarg;
+                        break;
+                case 'm':
+                        if (strcmp(optarg, "client") == 0)
+                                mode = TEST_MODE_CLIENT;
+                        else if (strcmp(optarg, "server") == 0)
+                                mode = TEST_MODE_SERVER;
+                        else {
+                                fprintf(stderr, "--mode must be \"client\" or \"server\"\n");
+                                return EXIT_FAILURE;
+                        }
+                        break;
+                case 'p':
+                        peer_cid = parse_cid(optarg);
+                        break;
+                case 'P':
+                        control_port = optarg;
+                        break;
+                case '?':
+                default:
+                        usage();
+                }
+        }
+
+        if (!control_port)
+                usage();
+        if (mode == TEST_MODE_UNSET)
+                usage();
+        if (peer_cid == VMADDR_CID_ANY)
+                usage();
+
+        if (!control_host) {
+                if (mode != TEST_MODE_SERVER)
+                        usage();
+                control_host = "0.0.0.0";
+        }
+
+        control_init(control_host, control_port, mode == TEST_MODE_SERVER);
+
+        for (i = 0; test_cases[i].name; i++) {
+                void (*run)(unsigned int peer_cid);
+
+                printf("%s...", test_cases[i].name);
+                fflush(stdout);
+
+                if (mode == TEST_MODE_CLIENT)
+                        run = test_cases[i].run_client;
+                else
+                        run = test_cases[i].run_server;
+
+                if (run)
+                        run(peer_cid);
+
+                printf("ok\n");
+        }
+
+        control_cleanup();
+        return EXIT_SUCCESS;
+}
diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 3a961e998281..735a510230c3 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -1,9 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+# We need this for the "cc-option" macro.
+include ../../../scripts/Kbuild.include
+
 VERSION = 1.0
 
 BINDIR=usr/bin
 WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int
-CFLAGS+= -O1 ${WARNFLAGS} -fstack-protector
-CC=$(CROSS_COMPILE)gcc
+CFLAGS+= -O1 ${WARNFLAGS}
+# Add "-fstack-protector" only if toolchain supports it.
+CFLAGS+= $(call cc-option,-fstack-protector)
+CC?= $(CROSS_COMPILE)gcc
+PKG_CONFIG?= pkg-config
 
 CFLAGS+=-D VERSION=\"$(VERSION)\"
 LDFLAGS+=
@@ -18,12 +25,12 @@ STATIC := --static
 endif
 
 TMON_LIBS=-lm -lpthread
-TMON_LIBS += $(shell pkg-config --libs $(STATIC) panelw ncursesw 2> /dev/null || \
-                     pkg-config --libs $(STATIC) panel ncurses 2> /dev/null || \
+TMON_LIBS += $(shell $(PKG_CONFIG) --libs $(STATIC) panelw ncursesw 2> /dev/null || \
+                     $(PKG_CONFIG) --libs $(STATIC) panel ncurses 2> /dev/null || \
                      echo -lpanel -lncurses)
 
-CFLAGS    += $(shell pkg-config --cflags $(STATIC) panelw ncursesw 2> /dev/null || \
-                     pkg-config --cflags $(STATIC) panel ncurses 2> /dev/null)
+CFLAGS    += $(shell $(PKG_CONFIG) --cflags $(STATIC) panelw ncursesw 2> /dev/null || \
+                     $(PKG_CONFIG) --cflags $(STATIC) panel ncurses 2> /dev/null)
 
 OBJS = tmon.o tui.o sysfs.o pid.o
 OBJS +=
diff --git a/tools/thermal/tmon/tmon.8 b/tools/thermal/tmon/tmon.8
index 02d5179803aa..2f122de5841b 100644
--- a/tools/thermal/tmon/tmon.8
+++ b/tools/thermal/tmon/tmon.8
@@ -1,4 +1,5 @@
 .TH TMON 8
+# SPDX-License-Identifier: GPL-2.0
 .SH NAME
 \fBtmon\fP - A monitoring and testing tool for Linux kernel thermal subsystem
 
diff --git a/tools/usb/Makefile b/tools/usb/Makefile
index acf2165c04e6..4e6506078494 100644
--- a/tools/usb/Makefile
+++ b/tools/usb/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for USB tools
 
 CC = $(CROSS_COMPILE)gcc
diff --git a/tools/usb/ffs-aio-example/multibuff/host_app/Makefile b/tools/usb/ffs-aio-example/multibuff/host_app/Makefile
index 8c4a6f0aa82d..df36e4c28f61 100644
--- a/tools/usb/ffs-aio-example/multibuff/host_app/Makefile
+++ b/tools/usb/ffs-aio-example/multibuff/host_app/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC = gcc
 LIBUSB_CFLAGS = $(shell pkg-config --cflags libusb-1.0)
 LIBUSB_LIBS = $(shell pkg-config --libs libusb-1.0)
diff --git a/tools/usb/hcd-tests.sh b/tools/usb/hcd-tests.sh
index b30b3dc4c788..e8cad6a4f9c9 100644
--- a/tools/usb/hcd-tests.sh
+++ b/tools/usb/hcd-tests.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 #
 # test types can be passed on the command line:
 #
diff --git a/tools/usb/usbip/Makefile.am b/tools/usb/usbip/Makefile.am
index 66f8bf038c9f..5961e9c18812 100644
--- a/tools/usb/usbip/Makefile.am
+++ b/tools/usb/usbip/Makefile.am
@@ -1,6 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
 SUBDIRS := libsrc src
 includedir = @includedir@/usbip
 include_HEADERS := $(addprefix libsrc/, \
-                     usbip_common.h vhci_driver.h usbip_host_driver.h)
+                     usbip_common.h vhci_driver.h usbip_host_driver.h \
+                     list.h sysfs_utils.h usbip_host_common.h)
 
 dist_man_MANS := $(addprefix doc/, usbip.8 usbipd.8)
diff --git a/tools/usb/usbip/cleanup.sh b/tools/usb/usbip/cleanup.sh
index 955c3ccb729a..8028c3a5c22b 100755
--- a/tools/usb/usbip/cleanup.sh
+++ b/tools/usb/usbip/cleanup.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 if [ -r Makefile ]; then
         make distclean
diff --git a/tools/usb/usbip/libsrc/Makefile.am b/tools/usb/usbip/libsrc/Makefile.am
index 90daf95c0804..dabd2c91d311 100644
--- a/tools/usb/usbip/libsrc/Makefile.am
+++ b/tools/usb/usbip/libsrc/Makefile.am
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 libusbip_la_CPPFLAGS = -DUSBIDS_FILE='"@USBIDS_DIR@/usb.ids"'
 libusbip_la_CFLAGS   = @EXTRA_CFLAGS@
 libusbip_la_LDFLAGS  = -version-info @LIBUSBIP_VERSION@
diff --git a/tools/usb/usbip/libsrc/list.h b/tools/usb/usbip/libsrc/list.h
index 5eaaa78e2c6a..a941671e4900 100644
--- a/tools/usb/usbip/libsrc/list.h
+++ b/tools/usb/usbip/libsrc/list.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIST_H
 #define _LIST_H
 
diff --git a/tools/usb/usbip/libsrc/sysfs_utils.c b/tools/usb/usbip/libsrc/sysfs_utils.c
index 36ac88ece0b8..14d5e67d398a 100644
--- a/tools/usb/usbip/libsrc/sysfs_utils.c
+++ b/tools/usb/usbip/libsrc/sysfs_utils.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/usb/usbip/libsrc/sysfs_utils.h b/tools/usb/usbip/libsrc/sysfs_utils.h
index 32ac1d105d18..0cd5f17e7eb2 100644
--- a/tools/usb/usbip/libsrc/sysfs_utils.h
+++ b/tools/usb/usbip/libsrc/sysfs_utils.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef __SYSFS_UTILS_H
 #define __SYSFS_UTILS_H
diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c
index 1517a232ab18..001bb8e8f668 100644
--- a/tools/usb/usbip/libsrc/usbip_common.c
+++ b/tools/usb/usbip/libsrc/usbip_common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2005-2007 Takahiro Hirofuchi
  */
diff --git a/tools/usb/usbip/libsrc/usbip_common.h b/tools/usb/usbip/libsrc/usbip_common.h
index 51ef5fe485dd..e45ec9d2fdbc 100644
--- a/tools/usb/usbip/libsrc/usbip_common.h
+++ b/tools/usb/usbip/libsrc/usbip_common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2005-2007 Takahiro Hirofuchi
  */
diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
index 9bd2cd71645d..5727dfb15a83 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.c
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2005-2007 Takahiro Hirofuchi
  */
diff --git a/tools/usb/usbip/libsrc/vhci_driver.h b/tools/usb/usbip/libsrc/vhci_driver.h
index 4898d3bafb10..418b404d5121 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.h
+++ b/tools/usb/usbip/libsrc/vhci_driver.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2005-2007 Takahiro Hirofuchi
  */
diff --git a/tools/usb/usbip/src/Makefile.am b/tools/usb/usbip/src/Makefile.am
index e81a4ebadeff..e26f39e0579d 100644
--- a/tools/usb/usbip/src/Makefile.am
+++ b/tools/usb/usbip/src/Makefile.am
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 AM_CPPFLAGS = -I$(top_srcdir)/libsrc -DUSBIDS_FILE='"@USBIDS_DIR@/usb.ids"'
 AM_CFLAGS   = @EXTRA_CFLAGS@
 LDADD       = $(top_builddir)/libsrc/libusbip.la
diff --git a/tools/usb/usbip/src/usbip_attach.c b/tools/usb/usbip/src/usbip_attach.c
index 6e89768ffe30..7f07b2d50f59 100644
--- a/tools/usb/usbip/src/usbip_attach.c
+++ b/tools/usb/usbip/src/usbip_attach.c
@@ -99,29 +99,34 @@ static int import_device(int sockfd, struct usbip_usb_device *udev)
         rc = usbip_vhci_driver_open();
         if (rc < 0) {
                 err("open vhci_driver");
-                return -1;
+                goto err_out;
         }
 
-        port = usbip_vhci_get_free_port(speed);
-        if (port < 0) {
-                err("no free port");
-                usbip_vhci_driver_close();
-                return -1;
-        }
+        do {
+                port = usbip_vhci_get_free_port(speed);
+                if (port < 0) {
+                        err("no free port");
+                        goto err_driver_close;
+                }
 
-        dbg("got free port %d", port);
+                dbg("got free port %d", port);
 
-        rc = usbip_vhci_attach_device(port, sockfd, udev->busnum,
-                                      udev->devnum, udev->speed);
-        if (rc < 0) {
-                err("import device");
-                usbip_vhci_driver_close();
-                return -1;
-        }
+                rc = usbip_vhci_attach_device(port, sockfd, udev->busnum,
+                                              udev->devnum, udev->speed);
+                if (rc < 0 && errno != EBUSY) {
+                        err("import device");
+                        goto err_driver_close;
+                }
+        } while (rc < 0);
 
         usbip_vhci_driver_close();
 
         return port;
+
+err_driver_close:
+        usbip_vhci_driver_close();
+err_out:
+        return -1;
 }
 
 static int query_import_device(int sockfd, char *busid)
diff --git a/tools/usb/usbip/src/usbip_network.h b/tools/usb/usbip/src/usbip_network.h
index c1e875cf1078..7032687621d3 100644
--- a/tools/usb/usbip/src/usbip_network.h
+++ b/tools/usb/usbip/src/usbip_network.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2005-2007 Takahiro Hirofuchi
  */
diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile
index 39c89a5ea990..8e2a908115c2 100644
--- a/tools/virtio/Makefile
+++ b/tools/virtio/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all: test mod
 test: virtio_test vringh_test
 virtio_test: virtio_ring.o virtio_test.o
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
index ba34f9e96efd..0ac3caf90877 100644
--- a/tools/virtio/asm/barrier.h
+++ b/tools/virtio/asm/barrier.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #if defined(__i386__) || defined(__x86_64__)
 #define barrier() asm volatile("" ::: "memory")
 #define virt_mb() __sync_synchronize()
diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h
index fb94f0787c47..b14c2c3b6b85 100644
--- a/tools/virtio/linux/bug.h
+++ b/tools/virtio/linux/bug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BUG_H
 #define BUG_H
 
diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h
index c9ccfd42ec13..903dc9c4bd11 100644
--- a/tools/virtio/linux/compiler.h
+++ b/tools/virtio/linux/compiler.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LINUX_COMPILER_H
 #define LINUX_COMPILER_H
 
diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h
index 18601f6689b9..1571e24e9494 100644
--- a/tools/virtio/linux/dma-mapping.h
+++ b/tools/virtio/linux/dma-mapping.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_DMA_MAPPING_H
 #define _LINUX_DMA_MAPPING_H
 
diff --git a/tools/virtio/linux/err.h b/tools/virtio/linux/err.h
index e32eff8b2a14..0943c644a701 100644
--- a/tools/virtio/linux/err.h
+++ b/tools/virtio/linux/err.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ERR_H
 #define ERR_H
 #define MAX_ERRNO       4095
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index d9554fc3f340..395521a7a8d8 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef KERNEL_H
 #define KERNEL_H
 #include <stdbool.h>
diff --git a/tools/virtio/linux/module.h b/tools/virtio/linux/module.h
index 28ce95a05997..9dfa96fea2b2 100644
--- a/tools/virtio/linux/module.h
+++ b/tools/virtio/linux/module.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/export.h>
 
 #define MODULE_LICENSE(__MODULE_LICENSE_value) \
diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h
index 68c9e2adc996..9a45f90e2d08 100644
--- a/tools/virtio/linux/scatterlist.h
+++ b/tools/virtio/linux/scatterlist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef SCATTERLIST_H
 #define SCATTERLIST_H
 #include <linux/kernel.h>
diff --git a/tools/virtio/linux/slab.h b/tools/virtio/linux/slab.h
index 7e1c1197d439..319dcaa07755 100644
--- a/tools/virtio/linux/slab.h
+++ b/tools/virtio/linux/slab.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LINUX_SLAB_H
 #define GFP_KERNEL 0
 #define GFP_ATOMIC 0
diff --git a/tools/virtio/linux/uaccess.h b/tools/virtio/linux/uaccess.h
index fa05d01b2c90..991dfb263998 100644
--- a/tools/virtio/linux/uaccess.h
+++ b/tools/virtio/linux/uaccess.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef UACCESS_H
 #define UACCESS_H
 
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index d8f534025b7f..b751350d4ce8 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LINUX_VIRTIO_H
 #define LINUX_VIRTIO_H
 #include <linux/scatterlist.h>
diff --git a/tools/virtio/linux/virtio_byteorder.h b/tools/virtio/linux/virtio_byteorder.h
index 9de9e6ac1d10..5b50f7eebd9c 100644
--- a/tools/virtio/linux/virtio_byteorder.h
+++ b/tools/virtio/linux/virtio_byteorder.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_VIRTIO_BYTEORDER_STUB_H
 #define _LINUX_VIRTIO_BYTEORDER_STUB_H
 
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 9ba11815e0a1..dbf14c1e2188 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/virtio_byteorder.h>
 #include <linux/virtio.h>
 #include <uapi/linux/virtio_config.h>
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index c012edbdb13b..85c98c2810fb 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 all:
 
 all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 90b0133004e1..5706e075adf2 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -110,11 +110,15 @@ static inline void busy_wait(void)
                 barrier();
 } 
 
+#if defined(__x86_64__) || defined(__i386__)
+#define smp_mb()     asm volatile("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
+#else
 /*
  * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized
  * with other __ATOMIC_SEQ_CST calls.
  */
 #define smp_mb() __sync_synchronize()
+#endif
 
 /*
  * This abuses the atomic builtins for thread fences, and
diff --git a/tools/virtio/ringtest/noring.c b/tools/virtio/ringtest/noring.c
index b8d1c1daac7c..ce2440d5ca93 100644
--- a/tools/virtio/ringtest/noring.c
+++ b/tools/virtio/ringtest/noring.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include "main.h"
 #include <assert.h>
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index 7b22f1b20652..38bb171aceba 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include "main.h"
 #include <stdlib.h>
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 29b0d3920bfc..dcc3ea758f48 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
 
 CPUS_ONLINE=$(lscpu --online -p=cpu|grep -v -e '#')
 #use last CPU for host. Why not the first?
diff --git a/tools/virtio/uapi/linux/virtio_ring.h b/tools/virtio/uapi/linux/virtio_ring.h
index 4d99c78234d3..cf50b2e5ff02 100644
--- a/tools/virtio/uapi/linux/virtio_ring.h
+++ b/tools/virtio/uapi/linux/virtio_ring.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef VIRTIO_RING_H
 #define VIRTIO_RING_H
 #include "../../../../include/uapi/linux/virtio_ring.h"
diff --git a/tools/virtio/virtio-trace/Makefile b/tools/virtio/virtio-trace/Makefile
index 0d2381633475..7843ebcda71d 100644
--- a/tools/virtio/virtio-trace/Makefile
+++ b/tools/virtio/virtio-trace/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 CC = gcc
 CFLAGS = -O2 -Wall -pthread
 
diff --git a/tools/virtio/virtio-trace/trace-agent.h b/tools/virtio/virtio-trace/trace-agent.h
index 8de79bfeaa73..e67885969f0e 100644
--- a/tools/virtio/virtio-trace/trace-agent.h
+++ b/tools/virtio/virtio-trace/trace-agent.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TRACE_AGENT_H__
 #define __TRACE_AGENT_H__
 #include <pthread.h>
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index 0fecaec90d0d..b427def67e7e 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define _GNU_SOURCE
 #include <getopt.h>
 #include <string.h>
diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c
index 9476c616d064..293653463303 100644
--- a/tools/virtio/vringh_test.c
+++ b/tools/virtio/vringh_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Simple test of virtio code, entirely in userpsace. */
 #define _GNU_SOURCE
 #include <sched.h>
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 006029456988..be320b905ea7 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for vm tools
 #
 TARGETS=page-types slabinfo page_owner_sort
diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c
index f1c055f3c243..18fc112b65cd 100644
--- a/tools/vm/page_owner_sort.c
+++ b/tools/vm/page_owner_sort.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * User-space helper to sort the output of /sys/kernel/debug/page_owner
  *
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index b9d34b37c017..f82c2eaa859d 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Slabinfo: Tool to get reports about slabs
  *
@@ -83,6 +84,7 @@ int output_lines = -1;
 int sort_loss;
 int extended_totals;
 int show_bytes;
+int unreclaim_only;
 
 /* Debug options */
 int sanity;
@@ -132,6 +134,7 @@ static void usage(void)
                 "-L|--Loss              Sort by loss\n"
                 "-X|--Xtotals           Show extended summary information\n"
                 "-B|--Bytes             Show size in bytes\n"
+                "-U|--Unreclaim         Show unreclaimable slabs only\n"
                 "\nValid debug options (FZPUT may be combined)\n"
                 "a / A          Switch on all debug options (=FZUP)\n"
                 "-              Switch off all debug options\n"
@@ -568,6 +571,9 @@ static void slabcache(struct slabinfo *s)
         if (strcmp(s->name, "*") == 0)
                 return;
 
+        if (unreclaim_only && s->reclaim_account)
+                return;
+
         if (actual_slabs == 1) {
                 report(s);
                 return;
@@ -1346,6 +1352,7 @@ struct option opts[] = {
         { "Loss", no_argument, NULL, 'L'},
         { "Xtotals", no_argument, NULL, 'X'},
         { "Bytes", no_argument, NULL, 'B'},
+        { "Unreclaim", no_argument, NULL, 'U'},
         { NULL, 0, NULL, 0 }
 };
 
@@ -1357,7 +1364,7 @@ int main(int argc, char *argv[])
 
         page_size = getpagesize();
 
-        while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXB",
+        while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXBU",
                                                 opts, NULL)) != -1)
                 switch (c) {
                 case '1':
@@ -1438,6 +1445,9 @@ int main(int argc, char *argv[])
                 case 'B':
                         show_bytes = 1;
                         break;
+                case 'U':
+                        unreclaim_only = 1;
+                        break;
                 default:
                         fatal("%s: Invalid option '%c'\n", argv[0], optopt);
 
diff --git a/tools/wmi/Makefile b/tools/wmi/Makefile
new file mode 100644
index 000000000000..e664f1167388
--- /dev/null
+++ b/tools/wmi/Makefile
@@ -0,0 +1,18 @@
+PREFIX ?= /usr
+SBINDIR ?= sbin
+INSTALL ?= install
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+CC = $(CROSS_COMPILE)gcc
+
+TARGET = dell-smbios-example
+
+all: $(TARGET)
+
+%: %.c
+        $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $<
+
+clean:
+        $(RM) $(TARGET)
+
+install: dell-smbios-example
+        $(INSTALL) -D -m 755 $(TARGET) $(DESTDIR)$(PREFIX)/$(SBINDIR)/$(TARGET)
diff --git a/tools/wmi/dell-smbios-example.c b/tools/wmi/dell-smbios-example.c
new file mode 100644
index 000000000000..9d3bde081249
--- /dev/null
+++ b/tools/wmi/dell-smbios-example.c
@@ -0,0 +1,210 @@
+/*
+ *  Sample application for SMBIOS communication over WMI interface
+ *  Performs the following:
+ *  - Simple cmd_class/cmd_select lookup for TPM information
+ *  - Simple query of known tokens and their values
+ *  - Simple activation of a token
+ *
+ *  Copyright (C) 2017 Dell, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+/* if uapi header isn't installed, this might not yet exist */
+#ifndef __packed
+#define __packed __attribute__((packed))
+#endif
+#include <linux/wmi.h>
+
+/* It would be better to discover these using udev, but for a simple
+ * application they're hardcoded
+ */
+static const char *ioctl_devfs = "/dev/wmi/dell-smbios";
+static const char *token_sysfs =
+                        "/sys/bus/platform/devices/dell-smbios.0/tokens";
+
+static void show_buffer(struct dell_wmi_smbios_buffer *buffer)
+{
+        printf("Call: %x/%x [%x,%x,%x,%x]\nResults: [%8x,%8x,%8x,%8x]\n",
+        buffer->std.cmd_class, buffer->std.cmd_select,
+        buffer->std.input[0], buffer->std.input[1],
+        buffer->std.input[2], buffer->std.input[3],
+        buffer->std.output[0], buffer->std.output[1],
+        buffer->std.output[2], buffer->std.output[3]);
+}
+
+static int run_wmi_smbios_cmd(struct dell_wmi_smbios_buffer *buffer)
+{
+        int fd;
+        int ret;
+
+        fd = open(ioctl_devfs, O_NONBLOCK);
+        ret = ioctl(fd, DELL_WMI_SMBIOS_CMD, buffer);
+        close(fd);
+        return ret;
+}
+
+static int find_token(__u16 token, __u16 *location, __u16 *value)
+{
+        char location_sysfs[60];
+        char value_sysfs[57];
+        char buf[4096];
+        FILE *f;
+        int ret;
+
+        ret = sprintf(value_sysfs, "%s/%04x_value", token_sysfs, token);
+        if (ret < 0) {
+                printf("sprintf value failed\n");
+                return 2;
+        }
+        f = fopen(value_sysfs, "rb");
+        if (!f) {
+                printf("failed to open %s\n", value_sysfs);
+                return 2;
+        }
+        fread(buf, 1, 4096, f);
+        fclose(f);
+        *value = (__u16) strtol(buf, NULL, 16);
+
+        ret = sprintf(location_sysfs, "%s/%04x_location", token_sysfs, token);
+        if (ret < 0) {
+                printf("sprintf location failed\n");
+                return 1;
+        }
+        f = fopen(location_sysfs, "rb");
+        if (!f) {
+                printf("failed to open %s\n", location_sysfs);
+                return 2;
+        }
+        fread(buf, 1, 4096, f);
+        fclose(f);
+        *location = (__u16) strtol(buf, NULL, 16);
+
+        if (*location)
+                return 0;
+        return 2;
+}
+
+static int token_is_active(__u16 *location, __u16 *cmpvalue,
+                           struct dell_wmi_smbios_buffer *buffer)
+{
+        int ret;
+
+        buffer->std.cmd_class = CLASS_TOKEN_READ;
+        buffer->std.cmd_select = SELECT_TOKEN_STD;
+        buffer->std.input[0] = *location;
+        ret = run_wmi_smbios_cmd(buffer);
+        if (ret != 0 || buffer->std.output[0] != 0)
+                return ret;
+        ret = (buffer->std.output[1] == *cmpvalue);
+        return ret;
+}
+
+static int query_token(__u16 token, struct dell_wmi_smbios_buffer *buffer)
+{
+        __u16 location;
+        __u16 value;
+        int ret;
+
+        ret = find_token(token, &location, &value);
+        if (ret != 0) {
+                printf("unable to find token %04x\n", token);
+                return 1;
+        }
+        return token_is_active(&location, &value, buffer);
+}
+
+static int activate_token(struct dell_wmi_smbios_buffer *buffer,
+                   __u16 token)
+{
+        __u16 location;
+        __u16 value;
+        int ret;
+
+        ret = find_token(token, &location, &value);
+        if (ret != 0) {
+                printf("unable to find token %04x\n", token);
+                return 1;
+        }
+        buffer->std.cmd_class = CLASS_TOKEN_WRITE;
+        buffer->std.cmd_select = SELECT_TOKEN_STD;
+        buffer->std.input[0] = location;
+        buffer->std.input[1] = 1;
+        ret = run_wmi_smbios_cmd(buffer);
+        return ret;
+}
+
+static int query_buffer_size(__u64 *buffer_size)
+{
+        FILE *f;
+
+        f = fopen(ioctl_devfs, "rb");
+        if (!f)
+                return -EINVAL;
+        fread(buffer_size, sizeof(__u64), 1, f);
+        fclose(f);
+        return EXIT_SUCCESS;
+}
+
+int main(void)
+{
+        struct dell_wmi_smbios_buffer *buffer;
+        int ret;
+        __u64 value = 0;
+
+        ret = query_buffer_size(&value);
+        if (ret == EXIT_FAILURE || !value) {
+                printf("Unable to read buffer size\n");
+                goto out;
+        }
+        printf("Detected required buffer size %lld\n", value);
+
+        buffer = malloc(value);
+        if (buffer == NULL) {
+                printf("failed to alloc memory for ioctl\n");
+                ret = -ENOMEM;
+                goto out;
+        }
+        buffer->length = value;
+
+        /* simple SMBIOS call for looking up TPM info */
+        buffer->std.cmd_class = CLASS_FLASH_INTERFACE;
+        buffer->std.cmd_select = SELECT_FLASH_INTERFACE;
+        buffer->std.input[0] = 2;
+        ret = run_wmi_smbios_cmd(buffer);
+        if (ret) {
+                printf("smbios ioctl failed: %d\n", ret);
+                ret = EXIT_FAILURE;
+                goto out;
+        }
+        show_buffer(buffer);
+
+        /* query some tokens */
+        ret = query_token(CAPSULE_EN_TOKEN, buffer);
+        printf("UEFI Capsule enabled token is: %d\n", ret);
+        ret = query_token(CAPSULE_DIS_TOKEN, buffer);
+        printf("UEFI Capsule disabled token is: %d\n", ret);
+
+        /* activate UEFI capsule token if disabled */
+        if (ret) {
+                printf("Enabling UEFI capsule token");
+                if (activate_token(buffer, CAPSULE_EN_TOKEN)) {
+                        printf("activate failed\n");
+                        ret = -1;
+                        goto out;
+                }
+        }
+        ret = EXIT_SUCCESS;
+out:
+        free(buffer);
+        return ret;
+}