400 files changed, 23163 insertions, 3943 deletions

diff --git a/tools/Makefile b/tools/Makefile
index c4f41ef9a7a7..be02c8b904db 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -20,7 +20,7 @@ help:
         @echo '  kvm_stat               - top-like utility for displaying kvm statistics'
         @echo '  leds                   - LEDs  tools'
         @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
@@ -92,8 +93,8 @@ kvm_stat: FORCE
 
 all: acpi cgroup cpupower gpio hv firewire liblockdep \
                 perf selftests spi turbostat usb \
-                virtio vm net x86_energy_perf_policy \
-                tmon freefall iio objtool kvm_stat
+                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 iio_install perf_install spi_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:
@@ -125,8 +126,9 @@ kvm_stat_install:
 install: acpi_install cgroup_install cpupower_install gpio_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 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:
@@ -170,8 +172,8 @@ build_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/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 1f57bbe82b6f..6edd177bb1c7 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -152,6 +152,12 @@ struct kvm_arch_memory_slot {
         (__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
+/* PL1 Physical Timer Registers */
+#define KVM_REG_ARM_PTIMER_CTL          ARM_CP15_REG32(0, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CNT          ARM_CP15_REG64(0, 14)
+#define KVM_REG_ARM_PTIMER_CVAL         ARM_CP15_REG64(2, 14)
+
+/* Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL           ARM_CP15_REG32(0, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT           ARM_CP15_REG64(1, 14)
 #define KVM_REG_ARM_TIMER_CVAL          ARM_CP15_REG64(3, 14)
@@ -216,6 +222,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES  3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET            4
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT          24
diff --git a/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h b/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..b551b741653d
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 51149ec75fe4..9abbf3044654 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -196,6 +196,12 @@ struct kvm_arch_memory_slot {
 
 #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
 
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL          ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL         ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT          ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL           ARM64_SYS_REG(3, 3, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT           ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL          ARM64_SYS_REG(3, 3, 14, 0, 2)
@@ -228,6 +234,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES  3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET            4
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL        0
diff --git a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..0a8e37a519f2
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include "ptrace.h"
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9ad172dcd912..38535a57fef8 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -6,10 +6,6 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
index c36c97ffdc6f..84606b8cc49e 100644
--- a/tools/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -4,10 +4,6 @@
  *
  * Copyright 2014 IBM Corp.
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_KVM_PERF_S390_H
diff --git a/tools/arch/s390/include/uapi/asm/perf_regs.h b/tools/arch/s390/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..d17dd9e5d516
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/perf_regs.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_S390_PERF_REGS_H
+#define _ASM_S390_PERF_REGS_H
+
+enum perf_event_s390_regs {
+        PERF_REG_S390_R0,
+        PERF_REG_S390_R1,
+        PERF_REG_S390_R2,
+        PERF_REG_S390_R3,
+        PERF_REG_S390_R4,
+        PERF_REG_S390_R5,
+        PERF_REG_S390_R6,
+        PERF_REG_S390_R7,
+        PERF_REG_S390_R8,
+        PERF_REG_S390_R9,
+        PERF_REG_S390_R10,
+        PERF_REG_S390_R11,
+        PERF_REG_S390_R12,
+        PERF_REG_S390_R13,
+        PERF_REG_S390_R14,
+        PERF_REG_S390_R15,
+        PERF_REG_S390_FP0,
+        PERF_REG_S390_FP1,
+        PERF_REG_S390_FP2,
+        PERF_REG_S390_FP3,
+        PERF_REG_S390_FP4,
+        PERF_REG_S390_FP5,
+        PERF_REG_S390_FP6,
+        PERF_REG_S390_FP7,
+        PERF_REG_S390_FP8,
+        PERF_REG_S390_FP9,
+        PERF_REG_S390_FP10,
+        PERF_REG_S390_FP11,
+        PERF_REG_S390_FP12,
+        PERF_REG_S390_FP13,
+        PERF_REG_S390_FP14,
+        PERF_REG_S390_FP15,
+        PERF_REG_S390_MASK,
+        PERF_REG_S390_PC,
+
+        PERF_REG_S390_MAX
+};
+
+#endif /* _ASM_S390_PERF_REGS_H */
diff --git a/tools/arch/s390/include/uapi/asm/ptrace.h b/tools/arch/s390/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000000..543dd70e12c8
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/ptrace.h
@@ -0,0 +1,457 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2000
+ *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ */
+
+#ifndef _UAPI_S390_PTRACE_H
+#define _UAPI_S390_PTRACE_H
+
+/*
+ * Offsets in the user_regs_struct. They are used for the ptrace
+ * system call and in entry.S
+ */
+#ifndef __s390x__
+
+#define PT_PSWMASK  0x00
+#define PT_PSWADDR  0x04
+#define PT_GPR0     0x08
+#define PT_GPR1     0x0C
+#define PT_GPR2     0x10
+#define PT_GPR3     0x14
+#define PT_GPR4     0x18
+#define PT_GPR5     0x1C
+#define PT_GPR6     0x20
+#define PT_GPR7     0x24
+#define PT_GPR8     0x28
+#define PT_GPR9     0x2C
+#define PT_GPR10    0x30
+#define PT_GPR11    0x34
+#define PT_GPR12    0x38
+#define PT_GPR13    0x3C
+#define PT_GPR14    0x40
+#define PT_GPR15    0x44
+#define PT_ACR0     0x48
+#define PT_ACR1     0x4C
+#define PT_ACR2     0x50
+#define PT_ACR3     0x54
+#define PT_ACR4     0x58
+#define PT_ACR5     0x5C
+#define PT_ACR6     0x60
+#define PT_ACR7     0x64
+#define PT_ACR8     0x68
+#define PT_ACR9     0x6C
+#define PT_ACR10    0x70
+#define PT_ACR11    0x74
+#define PT_ACR12    0x78
+#define PT_ACR13    0x7C
+#define PT_ACR14    0x80
+#define PT_ACR15    0x84
+#define PT_ORIGGPR2 0x88
+#define PT_FPC      0x90
+/*
+ * A nasty fact of life that the ptrace api
+ * only supports passing of longs.
+ */
+#define PT_FPR0_HI  0x98
+#define PT_FPR0_LO  0x9C
+#define PT_FPR1_HI  0xA0
+#define PT_FPR1_LO  0xA4
+#define PT_FPR2_HI  0xA8
+#define PT_FPR2_LO  0xAC
+#define PT_FPR3_HI  0xB0
+#define PT_FPR3_LO  0xB4
+#define PT_FPR4_HI  0xB8
+#define PT_FPR4_LO  0xBC
+#define PT_FPR5_HI  0xC0
+#define PT_FPR5_LO  0xC4
+#define PT_FPR6_HI  0xC8
+#define PT_FPR6_LO  0xCC
+#define PT_FPR7_HI  0xD0
+#define PT_FPR7_LO  0xD4
+#define PT_FPR8_HI  0xD8
+#define PT_FPR8_LO  0XDC
+#define PT_FPR9_HI  0xE0
+#define PT_FPR9_LO  0xE4
+#define PT_FPR10_HI 0xE8
+#define PT_FPR10_LO 0xEC
+#define PT_FPR11_HI 0xF0
+#define PT_FPR11_LO 0xF4
+#define PT_FPR12_HI 0xF8
+#define PT_FPR12_LO 0xFC
+#define PT_FPR13_HI 0x100
+#define PT_FPR13_LO 0x104
+#define PT_FPR14_HI 0x108
+#define PT_FPR14_LO 0x10C
+#define PT_FPR15_HI 0x110
+#define PT_FPR15_LO 0x114
+#define PT_CR_9     0x118
+#define PT_CR_10    0x11C
+#define PT_CR_11    0x120
+#define PT_IEEE_IP  0x13C
+#define PT_LASTOFF  PT_IEEE_IP
+#define PT_ENDREGS  0x140-1
+
+#define GPR_SIZE        4
+#define CR_SIZE         4
+
+#define STACK_FRAME_OVERHEAD    96      /* size of minimum stack frame */
+
+#else /* __s390x__ */
+
+#define PT_PSWMASK  0x00
+#define PT_PSWADDR  0x08
+#define PT_GPR0     0x10
+#define PT_GPR1     0x18
+#define PT_GPR2     0x20
+#define PT_GPR3     0x28
+#define PT_GPR4     0x30
+#define PT_GPR5     0x38
+#define PT_GPR6     0x40
+#define PT_GPR7     0x48
+#define PT_GPR8     0x50
+#define PT_GPR9     0x58
+#define PT_GPR10    0x60
+#define PT_GPR11    0x68
+#define PT_GPR12    0x70
+#define PT_GPR13    0x78
+#define PT_GPR14    0x80
+#define PT_GPR15    0x88
+#define PT_ACR0     0x90
+#define PT_ACR1     0x94
+#define PT_ACR2     0x98
+#define PT_ACR3     0x9C
+#define PT_ACR4     0xA0
+#define PT_ACR5     0xA4
+#define PT_ACR6     0xA8
+#define PT_ACR7     0xAC
+#define PT_ACR8     0xB0
+#define PT_ACR9     0xB4
+#define PT_ACR10    0xB8
+#define PT_ACR11    0xBC
+#define PT_ACR12    0xC0
+#define PT_ACR13    0xC4
+#define PT_ACR14    0xC8
+#define PT_ACR15    0xCC
+#define PT_ORIGGPR2 0xD0
+#define PT_FPC      0xD8
+#define PT_FPR0     0xE0
+#define PT_FPR1     0xE8
+#define PT_FPR2     0xF0
+#define PT_FPR3     0xF8
+#define PT_FPR4     0x100
+#define PT_FPR5     0x108
+#define PT_FPR6     0x110
+#define PT_FPR7     0x118
+#define PT_FPR8     0x120
+#define PT_FPR9     0x128
+#define PT_FPR10    0x130
+#define PT_FPR11    0x138
+#define PT_FPR12    0x140
+#define PT_FPR13    0x148
+#define PT_FPR14    0x150
+#define PT_FPR15    0x158
+#define PT_CR_9     0x160
+#define PT_CR_10    0x168
+#define PT_CR_11    0x170
+#define PT_IEEE_IP  0x1A8
+#define PT_LASTOFF  PT_IEEE_IP
+#define PT_ENDREGS  0x1B0-1
+
+#define GPR_SIZE        8
+#define CR_SIZE         8
+
+#define STACK_FRAME_OVERHEAD    160      /* size of minimum stack frame */
+
+#endif /* __s390x__ */
+
+#define NUM_GPRS        16
+#define NUM_FPRS        16
+#define NUM_CRS         16
+#define NUM_ACRS        16
+
+#define NUM_CR_WORDS    3
+
+#define FPR_SIZE        8
+#define FPC_SIZE        4
+#define FPC_PAD_SIZE    4 /* gcc insists on aligning the fpregs */
+#define ACR_SIZE        4
+
+
+#define PTRACE_OLDSETOPTIONS         21
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+typedef union {
+        float   f;
+        double  d;
+        __u64   ui;
+        struct
+        {
+                __u32 hi;
+                __u32 lo;
+        } fp;
+} freg_t;
+
+typedef struct {
+        __u32   fpc;
+        __u32   pad;
+        freg_t  fprs[NUM_FPRS];
+} s390_fp_regs;
+
+#define FPC_EXCEPTION_MASK      0xF8000000
+#define FPC_FLAGS_MASK          0x00F80000
+#define FPC_DXC_MASK            0x0000FF00
+#define FPC_RM_MASK             0x00000003
+
+/* this typedef defines how a Program Status Word looks like */
+typedef struct {
+        unsigned long mask;
+        unsigned long addr;
+} __attribute__ ((aligned(8))) psw_t;
+
+#ifndef __s390x__
+
+#define PSW_MASK_PER            0x40000000UL
+#define PSW_MASK_DAT            0x04000000UL
+#define PSW_MASK_IO             0x02000000UL
+#define PSW_MASK_EXT            0x01000000UL
+#define PSW_MASK_KEY            0x00F00000UL
+#define PSW_MASK_BASE           0x00080000UL    /* always one */
+#define PSW_MASK_MCHECK         0x00040000UL
+#define PSW_MASK_WAIT           0x00020000UL
+#define PSW_MASK_PSTATE         0x00010000UL
+#define PSW_MASK_ASC            0x0000C000UL
+#define PSW_MASK_CC             0x00003000UL
+#define PSW_MASK_PM             0x00000F00UL
+#define PSW_MASK_RI             0x00000000UL
+#define PSW_MASK_EA             0x00000000UL
+#define PSW_MASK_BA             0x00000000UL
+
+#define PSW_MASK_USER           0x0000FF00UL
+
+#define PSW_ADDR_AMODE          0x80000000UL
+#define PSW_ADDR_INSN           0x7FFFFFFFUL
+
+#define PSW_DEFAULT_KEY         (((unsigned long) PAGE_DEFAULT_ACC) << 20)
+
+#define PSW_ASC_PRIMARY         0x00000000UL
+#define PSW_ASC_ACCREG          0x00004000UL
+#define PSW_ASC_SECONDARY       0x00008000UL
+#define PSW_ASC_HOME            0x0000C000UL
+
+#else /* __s390x__ */
+
+#define PSW_MASK_PER            0x4000000000000000UL
+#define PSW_MASK_DAT            0x0400000000000000UL
+#define PSW_MASK_IO             0x0200000000000000UL
+#define PSW_MASK_EXT            0x0100000000000000UL
+#define PSW_MASK_BASE           0x0000000000000000UL
+#define PSW_MASK_KEY            0x00F0000000000000UL
+#define PSW_MASK_MCHECK         0x0004000000000000UL
+#define PSW_MASK_WAIT           0x0002000000000000UL
+#define PSW_MASK_PSTATE         0x0001000000000000UL
+#define PSW_MASK_ASC            0x0000C00000000000UL
+#define PSW_MASK_CC             0x0000300000000000UL
+#define PSW_MASK_PM             0x00000F0000000000UL
+#define PSW_MASK_RI             0x0000008000000000UL
+#define PSW_MASK_EA             0x0000000100000000UL
+#define PSW_MASK_BA             0x0000000080000000UL
+
+#define PSW_MASK_USER           0x0000FF0180000000UL
+
+#define PSW_ADDR_AMODE          0x0000000000000000UL
+#define PSW_ADDR_INSN           0xFFFFFFFFFFFFFFFFUL
+
+#define PSW_DEFAULT_KEY         (((unsigned long) PAGE_DEFAULT_ACC) << 52)
+
+#define PSW_ASC_PRIMARY         0x0000000000000000UL
+#define PSW_ASC_ACCREG          0x0000400000000000UL
+#define PSW_ASC_SECONDARY       0x0000800000000000UL
+#define PSW_ASC_HOME            0x0000C00000000000UL
+
+#endif /* __s390x__ */
+
+
+/*
+ * The s390_regs structure is used to define the elf_gregset_t.
+ */
+typedef struct {
+        psw_t psw;
+        unsigned long gprs[NUM_GPRS];
+        unsigned int  acrs[NUM_ACRS];
+        unsigned long orig_gpr2;
+} s390_regs;
+
+/*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct {
+        unsigned long args[1];
+        psw_t psw;
+        unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
+/*
+ * Now for the user space program event recording (trace) definitions.
+ * The following structures are used only for the ptrace interface, don't
+ * touch or even look at it if you don't want to modify the user-space
+ * ptrace interface. In particular stay away from it for in-kernel PER.
+ */
+typedef struct {
+        unsigned long cr[NUM_CR_WORDS];
+} per_cr_words;
+
+#define PER_EM_MASK 0xE8000000UL
+
+typedef struct {
+#ifdef __s390x__
+        unsigned                       : 32;
+#endif /* __s390x__ */
+        unsigned em_branching          : 1;
+        unsigned em_instruction_fetch  : 1;
+        /*
+         * Switching on storage alteration automatically fixes
+         * the storage alteration event bit in the users std.
+         */
+        unsigned em_storage_alteration : 1;
+        unsigned em_gpr_alt_unused     : 1;
+        unsigned em_store_real_address : 1;
+        unsigned                       : 3;
+        unsigned branch_addr_ctl       : 1;
+        unsigned                       : 1;
+        unsigned storage_alt_space_ctl : 1;
+        unsigned                       : 21;
+        unsigned long starting_addr;
+        unsigned long ending_addr;
+} per_cr_bits;
+
+typedef struct {
+        unsigned short perc_atmid;
+        unsigned long address;
+        unsigned char access_id;
+} per_lowcore_words;
+
+typedef struct {
+        unsigned perc_branching          : 1;
+        unsigned perc_instruction_fetch  : 1;
+        unsigned perc_storage_alteration : 1;
+        unsigned perc_gpr_alt_unused     : 1;
+        unsigned perc_store_real_address : 1;
+        unsigned                         : 3;
+        unsigned atmid_psw_bit_31        : 1;
+        unsigned atmid_validity_bit      : 1;
+        unsigned atmid_psw_bit_32        : 1;
+        unsigned atmid_psw_bit_5         : 1;
+        unsigned atmid_psw_bit_16        : 1;
+        unsigned atmid_psw_bit_17        : 1;
+        unsigned si                      : 2;
+        unsigned long address;
+        unsigned                         : 4;
+        unsigned access_id               : 4;
+} per_lowcore_bits;
+
+typedef struct {
+        union {
+                per_cr_words   words;
+                per_cr_bits    bits;
+        } control_regs;
+        /*
+         * The single_step and instruction_fetch bits are obsolete,
+         * the kernel always sets them to zero. To enable single
+         * stepping use ptrace(PTRACE_SINGLESTEP) instead.
+         */
+        unsigned  single_step       : 1;
+        unsigned  instruction_fetch : 1;
+        unsigned                    : 30;
+        /*
+         * These addresses are copied into cr10 & cr11 if single
+         * stepping is switched off
+         */
+        unsigned long starting_addr;
+        unsigned long ending_addr;
+        union {
+                per_lowcore_words words;
+                per_lowcore_bits  bits;
+        } lowcore;
+} per_struct;
+
+typedef struct {
+        unsigned int  len;
+        unsigned long kernel_addr;
+        unsigned long process_addr;
+} ptrace_area;
+
+/*
+ * S/390 specific non posix ptrace requests. I chose unusual values so
+ * they are unlikely to clash with future ptrace definitions.
+ */
+#define PTRACE_PEEKUSR_AREA           0x5000
+#define PTRACE_POKEUSR_AREA           0x5001
+#define PTRACE_PEEKTEXT_AREA          0x5002
+#define PTRACE_PEEKDATA_AREA          0x5003
+#define PTRACE_POKETEXT_AREA          0x5004
+#define PTRACE_POKEDATA_AREA          0x5005
+#define PTRACE_GET_LAST_BREAK         0x5006
+#define PTRACE_PEEK_SYSTEM_CALL       0x5007
+#define PTRACE_POKE_SYSTEM_CALL       0x5008
+#define PTRACE_ENABLE_TE              0x5009
+#define PTRACE_DISABLE_TE             0x5010
+#define PTRACE_TE_ABORT_RAND          0x5011
+
+/*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#define PTRACE_SINGLEBLOCK      12      /* resume execution until next branch */
+
+/*
+ * PT_PROT definition is loosely based on hppa bsd definition in
+ * gdb/hppab-nat.c
+ */
+#define PTRACE_PROT                       21
+
+typedef enum {
+        ptprot_set_access_watchpoint,
+        ptprot_set_write_watchpoint,
+        ptprot_disable_watchpoint
+} ptprot_flags;
+
+typedef struct {
+        unsigned long lowaddr;
+        unsigned long hiaddr;
+        ptprot_flags prot;
+} ptprot_area;
+
+/* Sequence of bytes for breakpoint illegal instruction.  */
+#define S390_BREAKPOINT     {0x0,0x1}
+#define S390_BREAKPOINT_U16 ((__u16)0x0001)
+#define S390_SYSCALL_OPCODE ((__u16)0x0a00)
+#define S390_SYSCALL_SIZE   2
+
+/*
+ * The user_regs_struct defines the way the user registers are
+ * store on the stack for signal handling.
+ */
+struct user_regs_struct {
+        psw_t psw;
+        unsigned long gprs[NUM_GPRS];
+        unsigned int  acrs[NUM_ACRS];
+        unsigned long orig_gpr2;
+        s390_fp_regs fp_regs;
+        /*
+         * These per registers are in here so that gdb can modify them
+         * itself as there is no "official" ptrace interface for hardware
+         * watchpoints. This is the way intel does it.
+         */
+        per_struct per_info;
+        unsigned long ieee_instruction_pointer; /* obsolete, always 0 */
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_S390_PTRACE_H */
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
index 7d8c3261a50d..1f5e26aae9fc 100644
--- a/tools/arch/x86/include/asm/atomic.h
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -25,7 +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/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 793690fbda36..800104c8a3ed 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,173 +13,176 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS        18      /* N 32-bit words worth of info */
-#define NBUGINTS        1       /* N 32-bit bug flags */
+#define NCAPINTS                        18         /* N 32-bit words worth of info */
+#define NBUGINTS                        1          /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
  * in /proc/cpuinfo instead of the macro name.  If the string is "",
  * this feature bit is not displayed in /proc/cpuinfo at all.
+ *
+ * When adding new features here that depend on other features,
+ * please update the table in kernel/cpu/cpuid-deps.c as well.
  */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU         ( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME         ( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE          ( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE         ( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC         ( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR         ( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE         ( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE         ( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8         ( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC        ( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP         ( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR        ( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE         ( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA         ( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV        ( 0*32+15) /* CMOV instructions */
-                                          /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT         ( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36       ( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN          ( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH     ( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS          ( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI        ( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX         ( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR        ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM         ( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2        ( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP   ( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT          ( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC         ( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64        ( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE         ( 0*32+31) /* Pending Break Enable */
+/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
+#define X86_FEATURE_FPU                 ( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME                 ( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE                  ( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE                 ( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC                 ( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR                 ( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE                 ( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE                 ( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8                 ( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC                ( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP                 ( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR                ( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE                 ( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA                 ( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV                ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT                 ( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36               ( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN                  ( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH             ( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS                  ( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI                ( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX                 ( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR                ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM                 ( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2                ( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP           ( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT                  ( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC                 ( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64                ( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE                 ( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL     ( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP          ( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX          ( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT      ( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT    ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES     ( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP      ( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM          ( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT    ( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW       ( 1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL             ( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP                  ( 1*32+19) /* MP Capable */
+#define X86_FEATURE_NX                  ( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT              ( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT            ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES             ( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP              ( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM                  ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT            ( 1*32+30) /* AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW               ( 1*32+31) /* 3DNow */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY    ( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN     ( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI        ( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY            ( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN             ( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI                ( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX       ( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR     ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR   ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8          ( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7          ( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3          ( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4          ( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP          ( 3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_ART         ( 3*32+10) /* Platform has always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS        ( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS         ( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32   ( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32  ( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD    ( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_ACC_POWER   ( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL        ( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS      ( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY   ( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID       ( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF  ( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_CXMMX               ( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR             ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR           ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR         ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+/* CPU types for specific tunings: */
+#define X86_FEATURE_K8                  ( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7                  ( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3                  ( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4                  ( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC        ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP                  ( 3*32+ 9) /* SMP kernel running on UP */
+#define X86_FEATURE_ART                 ( 3*32+10) /* Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON        ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS                ( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS                 ( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32           ( 3*32+14) /* "" syscall in IA32 userspace */
+#define X86_FEATURE_SYSENTER32          ( 3*32+15) /* "" sysenter in IA32 userspace */
+#define X86_FEATURE_REP_GOOD            ( 3*32+16) /* REP microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC        ( 3*32+17) /* "" MFENCE synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC        ( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER           ( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL                ( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS              ( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY           ( 3*32+22) /* CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE        ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC         ( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CPUID               ( 3*32+25) /* CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID         ( 3*32+26) /* Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM             ( 3*32+27) /* AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF          ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_NONSTOP_TSC_S3      ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ      ( 3*32+31) /* TSC has known frequency */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3        ( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ   ( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64      ( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT       ( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL       ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX         ( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX         ( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST         ( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2         ( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3       ( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID         ( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG        ( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA         ( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16        ( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR        ( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM        ( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID        ( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA         ( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1      ( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2      ( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC      ( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE       ( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER  ( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES         ( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE       ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE     ( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX         ( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C        ( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND      ( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR  ( 4*32+31) /* Running on a hypervisor */
+/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
+#define X86_FEATURE_XMM3                ( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ           ( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64              ( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT               ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
+#define X86_FEATURE_DSCPL               ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
+#define X86_FEATURE_VMX                 ( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX                 ( 4*32+ 6) /* Safer Mode eXtensions */
+#define X86_FEATURE_EST                 ( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2                 ( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3               ( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID                 ( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG                ( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA                 ( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16                ( 4*32+13) /* CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR                ( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM                ( 4*32+15) /* Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID                ( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA                 ( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1              ( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2              ( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC              ( 4*32+21) /* X2APIC */
+#define X86_FEATURE_MOVBE               ( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT              ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER  ( 4*32+24) /* TSC deadline timer */
+#define X86_FEATURE_AES                 ( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE               ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE             ( 4*32+27) /* "" XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX                 ( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C                ( 4*32+29) /* 16-bit FP conversions */
+#define X86_FEATURE_RDRAND              ( 4*32+30) /* RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR          ( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE      ( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN   ( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT      ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN   ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2        ( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN     ( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE         ( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN      ( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM         ( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN      ( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE              ( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN           ( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT              ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN           ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2                ( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN             ( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE                 ( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN              ( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM                 ( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN              ( 5*32+13) /* PMM enabled */
 
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM     ( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY  ( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM         ( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC     ( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY  ( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM         ( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A       ( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW        ( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS         ( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP         ( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT      ( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT         ( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP         ( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4        ( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE         ( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR  ( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM         ( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT     ( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#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_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX      ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
+#define X86_FEATURE_LAHF_LM             ( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY          ( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM                 ( 6*32+ 2) /* Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC             ( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY          ( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM                 ( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A               ( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE         ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH       ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW                ( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS                 ( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP                 ( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT              ( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT                 ( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP                 ( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4                ( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE                 ( 6*32+17) /* Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR          ( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM                 ( 6*32+21) /* Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT             ( 6*32+22) /* Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE        ( 6*32+23) /* Core performance counter extensions */
+#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_LLC         ( 6*32+28) /* Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX              ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -187,146 +190,155 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_RING3MWAIT  ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB         ( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB         ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_CAT_L3      ( 7*32+ 4) /* Cache Allocation Technology L3 */
-#define X86_FEATURE_CAT_L2      ( 7*32+ 5) /* Cache Allocation Technology L2 */
-#define X86_FEATURE_CDP_L3      ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_RING3MWAIT          ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT         ( 7*32+ 1) /* Intel CPUID faulting */
+#define X86_FEATURE_CPB                 ( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB                 ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3              ( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2              ( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3              ( 7*32+ 6) /* Code and Data Prioritization L3 */
 
-#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_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 */
-#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_INTEL_PPIN          ( 7*32+14) /* Intel Processor Inventory Number */
+#define X86_FEATURE_INTEL_PT            ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW       ( 7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS       ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
-#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_MBA                 ( 7*32+18) /* Memory Bandwidth Allocation */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_TPR_SHADOW          ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI                ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY        ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT                 ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID                ( 8*32+ 4) /* Intel Virtual Processor ID */
 
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+#define X86_FEATURE_VMMCALL             ( 8*32+15) /* Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV               ( 8*32+16) /* "" Xen paravirtual guest */
 
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE    ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST  ( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1        ( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE         ( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2        ( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP        ( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2        ( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS        ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID     ( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM         ( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM         ( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX         ( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A       ( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F     ( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ    ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#define X86_FEATURE_RDSEED      ( 9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX         ( 9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP        ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#define X86_FEATURE_CLFLUSHOPT  ( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB        ( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_AVX512PF    ( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER    ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD    ( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI      ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW    ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL    ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
+#define X86_FEATURE_FSGSBASE            ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
+#define X86_FEATURE_TSC_ADJUST          ( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_BMI1                ( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE                 ( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2                ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP                ( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2                ( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS                ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
+#define X86_FEATURE_INVPCID             ( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM                 ( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM                 ( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX                 ( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A               ( 9*32+15) /* Resource Director Technology Allocation */
+#define X86_FEATURE_AVX512F             ( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ            ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED              ( 9*32+18) /* RDSEED instruction */
+#define X86_FEATURE_ADX                 ( 9*32+19) /* ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP                ( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA          ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
+#define X86_FEATURE_CLFLUSHOPT          ( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB                ( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF            ( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER            ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD            ( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI              ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW            ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL            ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
 
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT    (10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC      (10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1     (10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES      (10*32+ 3) /* XSAVES/XRSTORS */
+/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
+#define X86_FEATURE_XSAVEOPT            (10*32+ 0) /* XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC              (10*32+ 1) /* XSAVEC instruction */
+#define X86_FEATURE_XGETBV1             (10*32+ 2) /* XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES              (10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC     (11*32+ 1) /* LLC QoS if 1 */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
+#define X86_FEATURE_CQM_LLC             (11*32+ 1) /* LLC QoS if 1 */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC       (12*32+ 0) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL       (12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL       (12*32+ 2) /* LLC Local MBM monitoring */
 
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO      (13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF      (13*32+1) /* Instructions Retired Count */
+/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
+#define X86_FEATURE_CLZERO              (13*32+ 0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF              (13*32+ 1) /* Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR          (13*32+ 2) /* Always save/restore FP error pointers */
 
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM      (14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA         (14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT        (14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN         (14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS         (14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP         (14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY  (14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP     (14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
+#define X86_FEATURE_DTHERM              (14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA                 (14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT                (14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN                 (14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS                 (14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP                 (14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY          (14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW      (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP             (14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ         (14*32+11) /* HWP Package Level Request */
 
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT         (15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV        (15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML        (15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS       (15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#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 */
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
+#define X86_FEATURE_NPT                 (15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV                (15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML                (15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS               (15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR          (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN           (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID         (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS       (15*32+ 7) /* Decode Assists support */
+#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*/
-#define X86_FEATURE_PKU         (16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE       (16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57        (16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID       (16*32+22) /* RDPID instruction */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
+#define X86_FEATURE_AVX512VBMI          (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP                (16*32+ 2) /* User Mode Instruction Protection */
+#define X86_FEATURE_PKU                 (16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE               (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VBMI2        (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_GFNI                (16*32+ 8) /* Galois Field New Instructions */
+#define X86_FEATURE_VAES                (16*32+ 9) /* Vector AES */
+#define X86_FEATURE_VPCLMULQDQ          (16*32+10) /* Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI         (16*32+11) /* Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG       (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_AVX512_VPOPCNTDQ    (16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57                (16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID               (16*32+22) /* RDPID instruction */
 
-/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR      (17*32+1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA        (17*32+3) /* Scalable MCA */
+/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV      (17*32+ 0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR              (17*32+ 1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA                (17*32+ 3) /* Scalable MCA */
 
 /*
  * BUG word(s)
  */
-#define X86_BUG(x)              (NCAPINTS*32 + (x))
+#define X86_BUG(x)                      (NCAPINTS*32 + (x))
 
-#define X86_BUG_F00F            X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV            X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA            X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH  X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E    X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP            X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK     X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_F00F                    X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV                    X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA                    X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH          X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E            X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP                    X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK             X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR         X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS         X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
  * to avoid confusion.
  */
-#define X86_BUG_ESPFIX          X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX                  X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
-#define X86_BUG_NULL_SEG        X86_BUG(10) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE    X86_BUG(11) /* SWAPGS without input dep on GS */
-#define X86_BUG_MONITOR         X86_BUG(12) /* IPI required to wake up remote CPU */
-#define X86_BUG_AMD_E400        X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_NULL_SEG                X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE            X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR                 X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400                X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..14d6d5007314 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX    (1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_INTEL_UMIP
+# define DISABLE_UMIP   0
+#else
+# define DISABLE_UMIP   (1<<(X86_FEATURE_UMIP & 31))
+#endif
+
 #ifdef CONFIG_X86_64
 # define DISABLE_VME            (1<<(X86_FEATURE_VME & 31))
 # define DISABLE_K6_MTRR        (1<<(X86_FEATURE_K6_MTRR & 31))
@@ -63,7 +69,7 @@
 #define DISABLED_MASK13 0
 #define DISABLED_MASK14 0
 #define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17 0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/tools/net/Makefile b/tools/bpf/Makefile
index 5830670feae1..07a6697466ef 100644
--- a/tools/net/Makefile
+++ b/tools/bpf/Makefile
@@ -4,6 +4,7 @@ prefix = /usr
 CC = gcc
 LEX = flex
 YACC = bison
+MAKE = make
 
 CFLAGS += -Wall -O2
 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
@@ -14,7 +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
@@ -27,10 +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..37292bb5ce60
--- /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 ?= /usr/local
+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..ec3052c0b004
--- /dev/null
+++ b/tools/bpf/bpftool/Makefile
@@ -0,0 +1,93 @@
+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/local
+bash_compdir ?= /usr/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 -m 0755 -d $(prefix)/sbin
+        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 install doc doc-install
+.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..d294bc8168be
--- /dev/null
+++ b/tools/bpf/bpftool/main.c
@@ -0,0 +1,343 @@
+/*
+ * 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;
+
+static void __noreturn clean_and_exit(int i)
+{
+        if (json_output)
+                jsonw_destroy(&json_wtr);
+
+        exit(i);
+}
+
+void usage(void)
+{
+        last_do_help(last_argc - 1, last_argv + 1);
+
+        clean_and_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);
+
+        opterr = 0;
+        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':
+                        if (!json_output) {
+                                json_wtr = jsonw_new(stdout);
+                                if (!json_wtr) {
+                                        p_err("failed to create JSON writer");
+                                        return -1;
+                                }
+                                json_output = true;
+                        }
+                        jsonw_pretty(json_wtr, pretty_output);
+                        break;
+                case 'f':
+                        show_pinned = true;
+                        break;
+                default:
+                        p_err("unrecognized option '%s'", argv[optind - 1]);
+                        if (json_output)
+                                clean_and_exit(-1);
+                        else
+                                usage();
+                }
+        }
+
+        argc -= optind;
+        argv += optind;
+        if (argc < 0)
+                usage();
+
+        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..bff330b49791
--- /dev/null
+++ b/tools/bpf/bpftool/main.h
@@ -0,0 +1,123 @@
+/*
+ * 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/compiler.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'?", *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) __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..a8c3a33dd185
--- /dev/null
+++ b/tools/bpf/bpftool/map.c
@@ -0,0 +1,901 @@
+/*
+ * 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?" : "");
+                        break;
+                }
+
+                fd = bpf_map_get_fd_by_id(id);
+                if (fd < 0) {
+                        if (errno == ENOENT)
+                                continue;
+                        p_err("can't get map by id (%u): %s",
+                              id, strerror(errno));
+                        break;
+                }
+
+                err = bpf_obj_get_info_by_fd(fd, &info, &len);
+                if (err) {
+                        p_err("can't get map info: %s", strerror(errno));
+                        close(fd);
+                        break;
+                }
+
+                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..dded77345bfb
--- /dev/null
+++ b/tools/bpf/bpftool/prog.c
@@ -0,0 +1,674 @@
+/*
+ * 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) {
+                        if (errno == ENOENT)
+                                continue;
+                        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/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/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index eaa3bec273c8..4c99c57736ce 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -193,11 +193,14 @@ static void kvp_update_mem_state(int pool)
         for (;;) {
                 readp = &record[records_read];
                 records_read += fread(readp, sizeof(struct kvp_record),
-                                        ENTRIES_PER_BLOCK * num_blocks,
-                                        filep);
+                                ENTRIES_PER_BLOCK * num_blocks - records_read,
+                                filep);
 
                 if (ferror(filep)) {
-                        syslog(LOG_ERR, "Failed to read file, pool: %d", pool);
+                        syslog(LOG_ERR,
+                                "Failed to read file, pool: %d; error: %d %s",
+                                 pool, errno, strerror(errno));
+                        kvp_release_lock(pool);
                         exit(EXIT_FAILURE);
                 }
 
@@ -210,6 +213,7 @@ static void kvp_update_mem_state(int pool)
 
                         if (record == NULL) {
                                 syslog(LOG_ERR, "malloc failed");
+                                kvp_release_lock(pool);
                                 exit(EXIT_FAILURE);
                         }
                         continue;
@@ -224,15 +228,11 @@ static void kvp_update_mem_state(int pool)
         fclose(filep);
         kvp_release_lock(pool);
 }
+
 static int kvp_file_init(void)
 {
         int  fd;
-        FILE *filep;
-        size_t records_read;
         char *fname;
-        struct kvp_record *record;
-        struct kvp_record *readp;
-        int num_blocks;
         int i;
         int alloc_unit = sizeof(struct kvp_record) * ENTRIES_PER_BLOCK;
 
@@ -246,61 +246,19 @@ static int kvp_file_init(void)
 
         for (i = 0; i < KVP_POOL_COUNT; i++) {
                 fname = kvp_file_info[i].fname;
-                records_read = 0;
-                num_blocks = 1;
                 sprintf(fname, "%s/.kvp_pool_%d", KVP_CONFIG_LOC, i);
                 fd = open(fname, O_RDWR | O_CREAT | O_CLOEXEC, 0644 /* rw-r--r-- */);
 
                 if (fd == -1)
                         return 1;
 
-
-                filep = fopen(fname, "re");
-                if (!filep) {
-                        close(fd);
-                        return 1;
-                }
-
-                record = malloc(alloc_unit * num_blocks);
-                if (record == NULL) {
-                        fclose(filep);
-                        close(fd);
-                        return 1;
-                }
-                for (;;) {
-                        readp = &record[records_read];
-                        records_read += fread(readp, sizeof(struct kvp_record),
-                                        ENTRIES_PER_BLOCK,
-                                        filep);
-
-                        if (ferror(filep)) {
-                                syslog(LOG_ERR, "Failed to read file, pool: %d",
-                                       i);
-                                exit(EXIT_FAILURE);
-                        }
-
-                        if (!feof(filep)) {
-                                /*
-                                 * We have more data to read.
-                                 */
-                                num_blocks++;
-                                record = realloc(record, alloc_unit *
-                                                num_blocks);
-                                if (record == NULL) {
-                                        fclose(filep);
-                                        close(fd);
-                                        return 1;
-                                }
-                                continue;
-                        }
-                        break;
-                }
                 kvp_file_info[i].fd = fd;
-                kvp_file_info[i].num_blocks = num_blocks;
-                kvp_file_info[i].records = record;
-                kvp_file_info[i].num_records = records_read;
-                fclose(filep);
-
+                kvp_file_info[i].num_blocks = 1;
+                kvp_file_info[i].records = malloc(alloc_unit);
+                if (kvp_file_info[i].records == NULL)
+                        return 1;
+                kvp_file_info[i].num_records = 0;
+                kvp_update_mem_state(i);
         }
 
         return 0;
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
index 40b231fb95bd..4c1966f7c77a 100644
--- a/tools/include/asm-generic/atomic-gcc.h
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -22,7 +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/linux/compiler.h b/tools/include/linux/compiler.h
index 07fd03c74a77..04e32f965ad7 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -84,8 +84,6 @@
 
 #define uninitialized_var(x) x = *(&(x))
 
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
-
 #include <linux/types.h>
 
 /*
@@ -135,20 +133,19 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 /*
  * Prevent the compiler from merging or refetching reads or writes. The
  * compiler is also forbidden from reordering successive instances of
- * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
- * compiler is aware of some particular ordering.  One way to make the
- * compiler aware of ordering is to put the two invocations of READ_ONCE,
- * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
  *
- * In contrast to ACCESS_ONCE these two macros will also work on aggregate
- * data types like structs or unions. If the size of the accessed data
- * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
- * compile-time warning.
+ * These two macros will also work on aggregate data types like structs or
+ * unions. If the size of the accessed data type exceeds the word size of
+ * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will
+ * fall back to memcpy and print a compile-time warning.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
  * mutilate accesses that either do not require ordering or that interact
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
diff --git a/tools/include/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h
deleted file mode 100644
index 2bccd2c7b897..000000000000
--- a/tools/include/linux/kmemcheck.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_
-#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_
-
-static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
-}
-
-#endif
diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h
index 940c1b075659..6b0c36a58fcb 100644
--- a/tools/include/linux/lockdep.h
+++ b/tools/include/linux/lockdep.h
@@ -48,6 +48,7 @@ static inline int debug_locks_off(void)
 #define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__)
 #define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 #define pr_warn pr_err
+#define pr_cont pr_err
 
 #define list_del_rcu list_del
 
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
index 4bf6777a8a03..9fdcd3eaac3b 100644
--- a/tools/include/linux/poison.h
+++ b/tools/include/linux/poison.h
@@ -15,6 +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
@@ -22,6 +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/uapi/asm-generic/bpf_perf_event.h b/tools/include/uapi/asm-generic/bpf_perf_event.h
new file mode 100644
index 000000000000..53815d2cd047
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bpf_perf_event.h
@@ -0,0 +1,9 @@
+#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+/* Export kernel pt_regs structure */
+typedef struct pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 6d319c46fd90..f8b134f5608f 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -17,6 +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 */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 2dffcbf705b3..653687d9771b 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -13,6 +13,7 @@
 #define MAP_NONBLOCK    0x10000         /* do not block on IO */
 #define MAP_STACK       0x20000         /* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB     0x40000         /* create a huge page mapping */
+#define MAP_SYNC        0x80000         /* perform synchronous page faults for the mapping */
 
 /* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
 
diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 000000000000..13a58531e6fa
--- /dev/null
+++ b/tools/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,7 @@
+#if defined(__aarch64__)
+#include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/uapi/asm/bpf_perf_event.h"
+#else
+#include <uapi/asm-generic/bpf_perf_event.h>
+#endif
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 97677cd6964d..6fdff5945c8a 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -737,6 +737,28 @@ struct drm_syncobj_array {
         __u32 pad;
 };
 
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+        __u32 crtc_id;          /* requested crtc_id */
+        __u32 active;           /* return: crtc output is active */
+        __u64 sequence;         /* return: most recent vblank sequence */
+        __s64 sequence_ns;      /* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE              0x00000001      /* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS          0x00000002      /* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+        __u32 crtc_id;
+        __u32 flags;
+        __u64 sequence;         /* on input, target sequence. on output, actual sequence */
+        __u64 user_data;        /* user data passed to event */
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -819,6 +841,9 @@ extern "C" {
 
 #define DRM_IOCTL_WAIT_VBLANK           DRM_IOWR(0x3a, union drm_wait_vblank)
 
+#define DRM_IOCTL_CRTC_GET_SEQUENCE     DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE   DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
 #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)
@@ -863,6 +888,11 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_RESET         DRM_IOWR(0xC4, struct drm_syncobj_array)
 #define DRM_IOCTL_SYNCOBJ_SIGNAL        DRM_IOWR(0xC5, struct drm_syncobj_array)
 
+#define DRM_IOCTL_MODE_CREATE_LEASE     DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES     DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE        DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE     DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
@@ -893,6 +923,7 @@ struct drm_event {
 
 #define DRM_EVENT_VBLANK 0x01
 #define DRM_EVENT_FLIP_COMPLETE 0x02
+#define DRM_EVENT_CRTC_SEQUENCE 0x03
 
 struct drm_event_vblank {
         struct drm_event base;
@@ -903,6 +934,16 @@ struct drm_event_vblank {
         __u32 crtc_id; /* 0 on older kernels that do not support this */
 };
 
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+        struct drm_event        base;
+        __u64                   user_data;
+        __s64                   time_ns;
+        __u64                   sequence;
+};
+
 /* typedef area */
 #ifndef __KERNEL__
 typedef struct drm_clip_rect drm_clip_rect_t;
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 9816590d3ad2..ac3c6503ca27 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -397,10 +397,20 @@ typedef struct drm_i915_irq_wait {
 #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
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
  * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
  */
 #define I915_PARAM_HAS_SCHEDULER         41
+#define   I915_SCHEDULER_CAP_ENABLED    (1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY   (1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION (1ul << 2)
+
 #define I915_PARAM_HUC_STATUS            42
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
@@ -1309,14 +1319,16 @@ struct drm_i915_reg_read {
          * be specified
          */
         __u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
         __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.
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
  *
  */
 
@@ -1359,6 +1371,10 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_GTT_SIZE     0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE     0x4
 #define I915_CONTEXT_PARAM_BANNABLE     0x5
+#define I915_CONTEXT_PARAM_PRIORITY     0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY        1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY         0
+#define   I915_CONTEXT_MIN_USER_PRIORITY        -1023 /* inclusive */
         __u64 value;
 };
 
@@ -1510,9 +1526,14 @@ struct drm_i915_perf_oa_config {
         __u32 n_boolean_regs;
         __u32 n_flex_regs;
 
-        __u64 __user mux_regs_ptr;
-        __u64 __user boolean_regs_ptr;
-        __u64 __user flex_regs_ptr;
+        /*
+         * These fields are pointers to tuples of u32 values (register
+         * address, value). For example the expected length of the buffer
+         * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+         */
+        __u64 mux_regs_ptr;
+        __u64 boolean_regs_ptr;
+        __u64 flex_regs_ptr;
 };
 
 #if defined(__cplusplus)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 30f2ce76b517..4c223ab30293 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -93,6 +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 {
@@ -112,6 +113,7 @@ enum bpf_map_type {
         BPF_MAP_TYPE_HASH_OF_MAPS,
         BPF_MAP_TYPE_DEVMAP,
         BPF_MAP_TYPE_SOCKMAP,
+        BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
@@ -130,6 +132,7 @@ enum bpf_prog_type {
         BPF_PROG_TYPE_LWT_XMIT,
         BPF_PROG_TYPE_SOCK_OPS,
         BPF_PROG_TYPE_SK_SKB,
+        BPF_PROG_TYPE_CGROUP_DEVICE,
 };
 
 enum bpf_attach_type {
@@ -139,16 +142,53 @@ enum bpf_attach_type {
         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
@@ -176,6 +216,15 @@ enum bpf_attach_type {
 /* 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 */
                 __u32   map_type;       /* one of enum bpf_map_type */
@@ -189,6 +238,7 @@ union bpf_attr {
                 __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 */
@@ -211,11 +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 */
@@ -243,6 +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 */
@@ -250,6 +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:
@@ -554,12 +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 IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @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: SOL_SOCKET or IPROTO_TCP
+ *     @level: 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_skb_adjust_room(skb, len_diff, mode, flags)
@@ -583,6 +656,27 @@ union bpf_attr {
  *      @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),                     \
@@ -639,6 +733,10 @@ union bpf_attr {
         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
@@ -682,7 +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. */
@@ -716,7 +816,7 @@ struct __sk_buff {
         __u32 data_end;
         __u32 napi_id;
 
-        /* accessed by BPF_PROG_TYPE_sk_skb types */
+        /* 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 */
@@ -724,6 +824,9 @@ struct __sk_buff {
         __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 {
@@ -784,6 +887,7 @@ enum xdp_action {
 struct xdp_md {
         __u32 data;
         __u32 data_end;
+        __u32 data_meta;
 };
 
 enum sk_action {
@@ -801,6 +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 {
@@ -810,6 +919,7 @@ 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
@@ -859,9 +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_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
index 067427259820..8f95303f9d80 100644
--- a/tools/include/uapi/linux/bpf_perf_event.h
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* Copyright (c) 2016 Facebook
  *
  * This program is free software; you can redistribute it and/or
@@ -7,11 +8,10 @@
 #ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
 #define _UAPI__LINUX_BPF_PERF_EVENT_H__
 
-#include <linux/types.h>
-#include <linux/ptrace.h>
+#include <asm/bpf_perf_event.h>
 
 struct bpf_perf_event_data {
-        struct pt_regs regs;
+        bpf_user_pt_regs_t regs;
         __u64 sample_period;
 };
 
diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h
new file mode 100644
index 000000000000..ef1305010925
--- /dev/null
+++ b/tools/include/uapi/linux/kcmp.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#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
index 7e99999d6236..496e59a2738b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -630,9 +630,9 @@ struct kvm_s390_irq {
 
 struct kvm_s390_irq_state {
         __u64 buf;
-        __u32 flags;
+        __u32 flags;        /* will stay unused for compatibility reasons */
         __u32 len;
-        __u32 reserved[4];
+        __u32 reserved[4];  /* will stay unused for compatibility reasons */
 };
 
 /* for KVM_SET_GUEST_DEBUG */
@@ -931,6 +931,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 362493a2f950..b9a4953018ed 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -942,6 +942,7 @@ enum perf_callchain_context {
 #define PERF_AUX_FLAG_TRUNCATED         0x01    /* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE         0x02    /* snapshot from overwrite mode */
 #define PERF_AUX_FLAG_PARTIAL           0x04    /* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION         0x08    /* sample collided with another */
 
 #define PERF_FLAG_FD_NO_GROUP           (1UL << 0)
 #define PERF_FLAG_FD_OUTPUT             (1UL << 1)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
new file mode 100644
index 000000000000..af5f8c2df87a
--- /dev/null
+++ b/tools/include/uapi/linux/prctl.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#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
+
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL                   50      /* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC           (1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL                   51      /* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK             0xffff
+# define PR_SVE_VL_INHERIT              (1 << 17) /* inherit across exec */
+
+#endif /* _LINUX_PRCTL_H */
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 32283d88701a..a5684d0968b4 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 or fields_filter == "help":
+        if not fields_filter:
             return True
         return re.match(fields_filter, field) is not None
 
@@ -545,8 +549,8 @@ class TracepointProvider(Provider):
 
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
-        self._fields = [field for field in self.get_available_fields()
-                        if self.is_field_wanted(fields_filter, field)]
+        self.fields = [field for field in self.get_available_fields()
+                       if self.is_field_wanted(fields_filter, field)]
 
     @staticmethod
     def get_online_cpus():
@@ -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
@@ -946,7 +950,8 @@ class Tui(object):
             curses.nocbreak()
             curses.endwin()
 
-    def get_all_gnames(self):
+    @staticmethod
+    def get_all_gnames():
         """Returns a list of (pid, gname) tuples of all running guests"""
         res = []
         try:
@@ -955,11 +960,11 @@ 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]:
-                res.append((line[0], self.get_gname_from_pid(line[0])))
+                res.append((line[0], Tui.get_gname_from_pid(line[0])))
         child.stdout.close()
 
         return res
@@ -980,7 +985,8 @@ class Tui(object):
         except Exception:
             self.screen.addstr(row + 1, 2, 'Not available')
 
-    def get_pid_from_gname(self, gname):
+    @staticmethod
+    def get_pid_from_gname(gname):
         """Fuzzy function to convert guest name to QEMU process pid.
 
         Returns a list of potential pids, can be empty if no match found.
@@ -988,7 +994,7 @@ class Tui(object):
 
         """
         pids = []
-        for line in self.get_all_gnames():
+        for line in Tui.get_all_gnames():
             if gname == line[1]:
                 pids.append(int(line[0]))
 
@@ -1005,7 +1011,7 @@ 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
@@ -1086,15 +1092,16 @@ class Tui(object):
             # sort by totals
             return (0, -stats[x][0])
         total = 0.
-        for val in stats.values():
-            total += val[0]
+        for key in stats.keys():
+            if key.find('(') is -1:
+                total += stats[key][0]
         if self._sorting == SORT_DEFAULT:
             sortkey = sortCurAvg
         else:
             sortkey = sortTotal
+        tavg = 0
         for key in sorted(stats.keys(), key=sortkey):
-
-            if row >= self.screen.getmaxyx()[0]:
+            if row >= self.screen.getmaxyx()[0] - 1:
                 break
             values = stats[key]
             if not values[0] and not values[1]:
@@ -1106,9 +1113,15 @@ class Tui(object):
                 self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' %
                                    (key, values[0], values[0] * 100 / total,
                                     cur))
+                if cur is not '' and key.find('(') is -1:
+                    tavg += cur
             row += 1
         if row == 3:
             self.screen.addstr(4, 1, 'No matching events reported yet')
+        else:
+            self.screen.addstr(row, 1, '%-40s %10d        %8s' %
+                               ('Total', total, tavg if tavg else ''),
+                               curses.A_BOLD)
         self.screen.refresh()
 
     def show_msg(self, text):
@@ -1170,7 +1183,7 @@ 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 +1217,7 @@ 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 +1246,7 @@ 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 +1286,7 @@ 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:
@@ -1354,7 +1367,7 @@ class Tui(object):
                 if char == 'x':
                     self.update_drilldown()
                     # prevents display of current values on next refresh
-                    self.stats.get()
+                    self.stats.get(self._display_guests)
             except KeyboardInterrupt:
                 break
             except curses.error:
@@ -1369,25 +1382,25 @@ 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:
@@ -1447,16 +1460,13 @@ Press any other key to refresh statistics immediately.
         try:
             pids = Tui.get_pid_from_gname(val)
         except:
-            raise optparse.OptionValueError('Error while searching for guest '
-                                            '"{}", use "-p" to specify a pid '
-                                            'instead'.format(val))
+            sys.exit('Error while searching for guest "{}". Use "-p" to '
+                     'specify a pid instead?'.format(val))
         if len(pids) == 0:
-            raise optparse.OptionValueError('No guest by the name "{}" '
-                                            'found'.format(val))
+            sys.exit('Error: No guest by the name "{}" found'.format(val))
         if len(pids) > 1:
-            raise optparse.OptionValueError('Multiple processes found (pids: '
-                                            '{}) - use "-p" to specify a pid '
-                                            'instead'.format(" ".join(pids)))
+            sys.exit('Error: Multiple processes found (pids: {}). Use "-p" '
+                     'to specify the desired pid'.format(" ".join(pids)))
         parser.values.pid = pids[0]
 
     optparser = optparse.OptionParser(description=description_text,
@@ -1514,7 +1524,16 @@ Press any other key to refresh statistics immediately.
                          help='restrict statistics to guest by name',
                          callback=cb_guest_to_pid,
                          )
-    (options, _) = optparser.parse_args(sys.argv)
+    options, unkn = optparser.parse_args(sys.argv)
+    if len(unkn) != 1:
+        sys.exit('Error: Extra argument(s): ' + ' '.join(unkn[1:]))
+    try:
+        # verify that we were passed a valid regex up front
+        re.compile(options.fields)
+    except re.error:
+        sys.exit('Error: "' + options.fields + '" is not a valid regular '
+                 'expression')
+
     return options
 
 
@@ -1560,16 +1579,13 @@ 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.fields == 'help':
+        stats.fields_filter = None
+        event_list = []
+        for key in stats.get().keys():
+            event_list.append(key.split('(', 1)[0])
+        sys.stdout.write('  ' + '\n  '.join(sorted(set(event_list))) + '\n')
+        sys.exit(0)
 
     if options.log:
         log(stats)
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
index e5cf836be8a1..b5b3810c9e94 100644
--- a/tools/kvm/kvm_stat/kvm_stat.txt
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -50,6 +50,8 @@ INTERACTIVE COMMANDS
 *s*::   set update interval
 
 *x*::   toggle reporting of stats for child trace events
+ ::     *Note*: The stats for the parents summarize the respective child trace
+                events
 
 Press any other key to refresh statistics immediately.
 
@@ -86,7 +88,7 @@ OPTIONS
 
 -f<fields>::
 --fields=<fields>::
-        fields to display (regex)
+        fields to display (regex), "-f help" for a list of available events
 
 -h::
 --help::
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1d6907d379c9..5128677e4117 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -46,6 +46,8 @@
 # endif
 #endif
 
+#define min(x, y) ((x) < (y) ? (x) : (y))
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
         return (__u64) (unsigned long) ptr;
@@ -57,10 +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_node(enum bpf_map_type map_type, int key_size,
-                        int value_size, int max_entries, __u32 map_flags,
-                        int node)
+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));
@@ -70,6 +73,8 @@ int bpf_create_map_node(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;
@@ -81,14 +86,23 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
 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, key_size, value_size,
+        return bpf_create_map_node(map_type, NULL, key_size, value_size,
                                    max_entries, map_flags, -1);
 }
 
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
-                               int inner_map_fd, int max_entries,
+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));
@@ -99,6 +113,8 @@ int bpf_create_map_in_map_node(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;
@@ -107,19 +123,24 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
         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_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, key_size, inner_map_fd,
-                                          max_entries, map_flags, -1);
+        return bpf_create_map_in_map_node(map_type, name, key_size,
+                                          inner_map_fd, max_entries, map_flags,
+                                          -1);
 }
 
-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_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;
@@ -130,6 +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)
@@ -143,6 +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,
@@ -260,6 +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)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index b8ea5843c39e..6534889e2b2f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,19 +24,28 @@
 #include <linux/bpf.h>
 #include <stddef.h>
 
-int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
-                        int value_size, int max_entries, __u32 map_flags,
-                        int node);
+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_node(enum bpf_map_type map_type, int key_size,
-                               int inner_map_fd, int max_entries,
+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, int key_size,
-                          int inner_map_fd, int max_entries, __u32 map_flags);
+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,
@@ -57,6 +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);
@@ -65,5 +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 35f6dfcdc565..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;
 }
@@ -870,11 +937,12 @@ 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;
@@ -982,7 +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;
@@ -995,8 +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;
@@ -1021,9 +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;
@@ -1067,8 +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;
@@ -1096,7 +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);
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7959086eb9c9..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;
 };
 
 /*
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/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/Makefile b/tools/objtool/Makefile
index 424b1965d06f..ae0272f9a091 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -7,9 +7,11 @@ ARCH := x86
 endif
 
 # always use the host compiler
-CC = gcc
-LD = ld
-AR = ar
+HOSTCC  ?= gcc
+HOSTLD  ?= ld
+CC       = $(HOSTCC)
+LD       = $(HOSTLD)
+AR       = ar
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
@@ -25,7 +27,9 @@ OBJTOOL_IN := $(OBJTOOL)-in.o
 
 all: $(OBJTOOL)
 
-INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi
+INCLUDES := -I$(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)
@@ -41,22 +45,8 @@ 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
-        @(test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
-        diff ../../arch/x86/include/asm/orc_types.h orc_types.h >/dev/null) \
-        || echo "warning: objtool: orc_types.h differs from kernel" >&2 )) || true
+        @./sync-check.sh
         $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
 
@@ -66,7 +56,7 @@ $(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/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 34a579f806e3..540a209b78ab 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"
@@ -138,7 +138,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                         *type = INSN_STACK;
                         op->src.type = OP_SRC_ADD;
                         op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
-                        op->dest.type = OP_SRC_REG;
+                        op->dest.type = OP_DEST_REG;
                         op->dest.reg = CFI_SP;
                 }
                 break;
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/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..9c9dc579bd7d 100644
--- a/tools/objtool/orc_types.h
+++ b/tools/objtool/arch/x86/include/asm/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..e0b85930dd77 100644
--- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt
+++ b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM
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 b02a36b2c14f..b02a36b2c14f 100644
--- a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
+++ b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c
index 4c6b5c9ef073..91e8e19ff5e0 100644
--- a/tools/objtool/builtin-orc.c
+++ b/tools/objtool/builtin-orc.c
@@ -44,6 +44,9 @@ int cmd_orc(int argc, const char **argv)
         const char *objname;
 
         argc--; argv++;
+        if (argc <= 0)
+                usage_with_options(orc_usage, check_options);
+
         if (!strncmp(argv[0], "gen", 3)) {
                 argc = parse_options(argc, argv, check_options, orc_usage, 0);
                 if (argc != 1)
@@ -52,7 +55,6 @@ int cmd_orc(int argc, const char **argv)
                 objname = argv[0];
 
                 return check(objname, no_fp, no_unreachable, true);
-
         }
 
         if (!strcmp(argv[0], "dump")) {
diff --git a/tools/objtool/orc.h b/tools/objtool/orc.h
index a4139e386ef3..b0e92a6d0903 100644
--- a/tools/objtool/orc.h
+++ b/tools/objtool/orc.h
@@ -18,7 +18,7 @@
 #ifndef _ORC_H
 #define _ORC_H
 
-#include "orc_types.h"
+#include <asm/orc_types.h>
 
 struct objtool_file;
 
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 36c5bf6a2675..c3343820916a 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -76,7 +76,8 @@ 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 nr_sections;
+        Elf64_Addr orc_ip_addr = 0;
         size_t shstrtab_idx;
         Elf *elf;
         Elf_Scn *scn;
@@ -187,10 +188,10 @@ int orc_dump(const char *_objname)
                                 return -1;
                         }
 
-                        printf("%s+%lx:", name, rela.r_addend);
+                        printf("%s+%llx:", name, (unsigned long long)rela.r_addend);
 
                 } else {
-                        printf("%lx:", orc_ip_addr + (i * sizeof(int)) + orc_ip[i]);
+                        printf("%llx:", (unsigned long long)(orc_ip_addr + (i * sizeof(int)) + orc_ip[i]));
                 }
 
 
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index e5ca31429c9b..e61fe703197b 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -165,6 +165,8 @@ int create_orc_sections(struct objtool_file *file)
 
         /* create .orc_unwind_ip and .rela.orc_unwind_ip sections */
         sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx);
+        if (!sec)
+                return -1;
 
         ip_relasec = elf_create_rela_section(file->elf, sec);
         if (!ip_relasec)
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/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-record.txt b/tools/perf/Documentation/perf-record.txt
index 63526f4416ea..5a626ef666c2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -377,6 +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 383a98d992ed..ddde2b54af57 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -434,7 +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 18dfcfa38454..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, phys_addr.
+        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 c37d61682dfb..823fce7674bb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -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 d864ea6fd367..4353262bc462 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -240,6 +240,9 @@ Default is to monitor all CPUS.
 --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/Makefile.config b/tools/perf/Makefile.config
index 63f534a0902f..0294bfb6c5f8 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -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
 
@@ -184,9 +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_NO_CLANG), 1)
-    PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
-  endif
+  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
@@ -572,14 +574,15 @@ ifndef NO_GTK2
   endif
 endif
 
-
 ifdef NO_LIBPERL
   CFLAGS += -DNO_LIBPERL
 else
   PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
   PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-  PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+  PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
+  PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
   ifneq ($(feature-libperl), 1)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 91ef44bfaf3e..68cf1360a3f3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -173,7 +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)),)
@@ -420,6 +420,13 @@ 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
@@ -441,6 +448,20 @@ 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)
@@ -539,9 +560,12 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
         $(pkey_alloc_access_rights_array) \
         $(sndrv_pcm_ioctl_array) \
         $(sndrv_ctl_ioctl_array) \
+        $(kcmp_type_array) \
         $(kvm_ioctl_array) \
         $(vhost_virtio_ioctl_array) \
-        $(perf_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) $@
@@ -802,7 +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
@@ -811,15 +838,17 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
                 $(OUTPUT)util/intel-pt-decoder/inat-tables.c \
                 $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.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)
+                $(OUTPUT)$(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 b39b16395aac..f64516d5b23e 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -24,7 +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/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 9a3e0523e2c9..6688977e4ac7 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -26,7 +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/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index b7bc04980fe8..a3f423c27cae 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -1,4 +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;
@@ -47,7 +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/s390/Makefile b/tools/perf/arch/s390/Makefile
index 21322e0385b8..09ba923debe8 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index c9a81673e8aa..e0e466c650df 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -1,4 +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;
@@ -20,7 +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 792d4c277225..671553525f41 100644
--- a/tools/perf/arch/s390/include/dwarf-regs-table.h
+++ b/tools/perf/arch/s390/include/dwarf-regs-table.h
@@ -1,9 +1,72 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifdef DEFINE_DWARF_REGSTR_TABLE
-/* This is included in perf/util/dwarf-regs.c */
+#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..bcfbaed78cc2
--- /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 <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 0dff5b2ed1e5..a8ace5cc6301 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -2,22 +2,43 @@
 /*
  * Mapping of DWARF debug register numbers into register names.
  *
- *    Copyright IBM Corp. 2010
- *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ * Copyright IBM Corp. 2010, 2017
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *            Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *
  */
 
+#include <errno.h>
 #include <stddef.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <asm/ptrace.h>
+#include <string.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 "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];
+}
+
+/*
+ * Convert the register name into an offset to struct pt_regs (kernel).
+ * This is required by the BPF prologue generator.  The BPF
+ * program is called in the BPF overflow handler in the perf
+ * core.
+ */
+int regs_query_register_offset(const char *name)
+{
+        unsigned long gpr;
+
+        if (!name || strncmp(name, "%r", 2))
+                return -EINVAL;
+
+        errno = 0;
+        gpr = strtoul(name + 2, NULL, 10);
+        if (errno || gpr >= 16)
+                return -EINVAL;
+
+        return offsetof(user_pt_regs, gprs) + 8 * gpr;
 }
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/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 4adfb4ce2864..5bd1ba8c0282 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -123,3 +123,17 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid)
 
         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/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 9834fdc7c59e..c1bd979b957b 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -9,7 +9,6 @@ struct test;
 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);
-int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
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 34a078136a47..cc1802ff5410 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -25,10 +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/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
         NULL
 };
 
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+        int i, nr_nodes = 0;
+
+        for (i = 0; i < g->p.nr_nodes; i++) {
+                if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+                        nr_nodes++;
+        }
+
+        return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+        return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+        struct bitmask *cpu = numa_allocate_cpumask();
+        unsigned int i;
+
+        if (cpu && !numa_node_to_cpus(node, cpu)) {
+                for (i = 0; i < cpu->size; i++) {
+                        if (numa_bitmask_isbitset(cpu, i))
+                                return true;
+                }
+        }
+
+        return false; /* lets fall back to nocpus safely */
+}
+
 static cpu_set_t bind_to_cpu(int target_cpu)
 {
         cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
 
 static cpu_set_t bind_to_node(int target_node)
 {
-        int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+        int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
         cpu_set_t orig_mask, mask;
         int cpu;
         int ret;
 
-        BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+        BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
         BUG_ON(!cpus_per_node);
 
         ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
                         int i;
 
                         for (i = 0; i < mul; i++) {
-                                if (t >= g->p.nr_tasks) {
+                                if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
                                         printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
                                         goto out;
                                 }
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
         sum = 0;
 
         for (node = 0; node < g->p.nr_nodes; node++) {
+                if (!is_node_present(node))
+                        continue;
                 nr = nodes[node];
                 nr_min = min(nr, nr_min);
                 nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
         process_groups = 0;
 
         for (node = 0; node < g->p.nr_nodes; node++) {
-                int processes = count_node_processes(node);
+                int processes;
 
+                if (!is_node_present(node))
+                        continue;
+                processes = count_node_processes(node);
                 nr = nodes[node];
                 tprintf(" %2d/%-2d", nr, processes);
 
@@ -1291,7 +1337,7 @@ static void print_summary(void)
 
         printf("\n ###\n");
         printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
-                g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+                g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
         printf(" #      %5dx %5ldMB global  shared mem operations\n",
                         g->p.nr_loops, g->p.bytes_global/1024/1024);
         printf(" #      %5dx %5ldMB process shared mem operations\n",
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 3d32aa45016d..f15731a3d438 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -357,7 +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;
         }
 
@@ -401,7 +401,7 @@ int cmd_annotate(int argc, const char **argv)
                         .ordering_requires_timestamps = true,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
         struct option options[] = {
@@ -411,7 +411,7 @@ int cmd_annotate(int argc, const char **argv)
                    "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"),
@@ -483,9 +483,9 @@ int cmd_annotate(int argc, const char **argv)
         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-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 5f53a7ad5ef3..3d354ba6e9c5 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -312,7 +312,7 @@ 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;
@@ -353,10 +353,10 @@ int cmd_buildid_cache(int argc, const char **argv)
                 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;
         }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index ec2f327cd79d..78abbe8d9d5f 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -51,10 +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();
@@ -64,7 +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;
 
@@ -72,7 +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;
 
@@ -80,7 +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 fd32ad08c6d4..17855c4626a0 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2524,7 +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;
@@ -2573,8 +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)
@@ -2592,7 +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;
@@ -2612,7 +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;
         }
@@ -2733,6 +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 abfa49eaf7fd..514f70f95b57 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -35,8 +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;
@@ -50,7 +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 */
@@ -162,6 +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);
@@ -232,15 +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-diff.c b/tools/perf/builtin-diff.c
index 56223bdfa205..d660cb7b222b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -48,7 +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];
@@ -708,7 +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");
@@ -777,16 +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;
                 }
 
@@ -1287,11 +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 cdd145613f60..e06e822ce634 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -22,14 +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-help.c b/tools/perf/builtin-help.c
index bd1fedef3d1c..a0f7ed2b869b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
                 add_man_viewer(value);
                 return 0;
         }
-        if (!strstarts(var, "man."))
+        if (strstarts(var, "man."))
                 return add_man_viewer_info(var, value);
 
         return 0;
@@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
         if (!perf_cmd)
                 return "perf";
-        else if (!strstarts(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 3e0e73b0dc67..16a28547ca86 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -36,7 +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;
@@ -53,7 +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;
 
@@ -146,7 +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,
@@ -155,11 +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,
@@ -638,8 +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);
@@ -694,14 +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);
@@ -776,11 +776,13 @@ int cmd_inject(int argc, const char **argv)
                 .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;
@@ -790,7 +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 "
@@ -802,7 +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),
@@ -830,15 +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 35d4b9c9a9e8..ae11e4c3516a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -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 5fb40368d5d1..0c36f2ac6a0e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -35,7 +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)
@@ -1069,10 +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;
@@ -1360,7 +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,
         };
 
@@ -1434,7 +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;
@@ -1443,7 +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 eeedbe433776..ead221e49f00 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -16,6 +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;
@@ -80,6 +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;
 
@@ -97,6 +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) {
@@ -113,6 +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 fe69cd6b89e1..6e0189df2b3b 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -865,13 +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 4db960085273..506564651cda 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -113,6 +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;
                 }
 
@@ -236,13 +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)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0c95ffefb6cc..003255910c05 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -67,7 +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;
@@ -108,7 +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;
         }
@@ -130,107 +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;
@@ -269,13 +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);
@@ -434,6 +339,22 @@ static int record__open(struct record *rec)
         struct perf_evsel_config_term *err_term;
         int rc = 0;
 
+        /*
+         * For initial_delay we need to add a dummy event so that we can track
+         * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+         * real events, the ones asked by the user.
+         */
+        if (opts->initial_delay) {
+                if (perf_evlist__add_dummy(evlist))
+                        return -ENOMEM;
+
+                pos = perf_evlist__first(evlist);
+                pos->tracking = 0;
+                pos = perf_evlist__last(evlist);
+                pos->tracking = 1;
+                pos->attr.enable_on_exec = 1;
+        }
+
         perf_evlist__config(evlist, opts, &callchain_param);
 
         evlist__for_each_entry(evlist, pos) {
@@ -494,10 +415,10 @@ 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;
 
         /*
@@ -577,8 +498,7 @@ 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;
                         }
@@ -641,14 +561,14 @@ 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);
@@ -687,7 +607,7 @@ 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"*/
@@ -705,7 +625,7 @@ 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) {
@@ -715,7 +635,7 @@ 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) {
@@ -790,16 +710,16 @@ 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) {
@@ -845,17 +765,19 @@ static int record__synthesize(struct record *rec, bool tail)
                         goto out;
         }
 
-        err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                 machine);
-        WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
-                           "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-                           "Check /proc/kallsyms permission or run as root.\n");
-
-        err = perf_event__synthesize_modules(tool, process_synthesized_event,
-                                             machine);
-        WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
-                           "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-                           "Check /proc/modules permission or run as root.\n");
+        if (!perf_evlist__exclude_kernel(rec->evlist)) {
+                err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+                                                         machine);
+                WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+                                   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                                   "Check /proc/kallsyms permission or run as root.\n");
+
+                err = perf_event__synthesize_modules(tool, process_synthesized_event,
+                                                     machine);
+                WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+                                   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                                   "Check /proc/modules permission or run as root.\n");
+        }
 
         if (perf_guest) {
                 machines__process_guests(&session->machines,
@@ -864,7 +786,7 @@ 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;
 }
@@ -878,7 +800,7 @@ 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;
@@ -904,20 +826,20 @@ 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");
@@ -953,7 +875,7 @@ 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;
@@ -1214,8 +1136,8 @@ 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:
@@ -1579,7 +1501,7 @@ 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,
@@ -1644,6 +1566,9 @@ 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,
@@ -1786,7 +1711,7 @@ int cmd_record(int argc, const char **argv)
 
         err = -ENOMEM;
 
-        if (symbol_conf.kptr_restrict)
+        if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
                 pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index fae4b0340750..af5dd038195e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -258,7 +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 &&
@@ -441,6 +441,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
         struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
         struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
+        if (perf_evlist__exclude_kernel(rep->session->evlist))
+                return;
+
         if (kernel_map == NULL ||
             (kernel_map->dso->hit &&
              (kernel_kmap->ref_reloc_sym == NULL ||
@@ -569,7 +572,7 @@ 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);
 
@@ -638,7 +641,7 @@ 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;
         }
 
@@ -880,7 +883,7 @@ 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();
@@ -941,11 +944,11 @@ 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;
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f380d91ee609..83283fedb00f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1701,14 +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;
@@ -2903,10 +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;
@@ -2931,7 +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;
 
@@ -3364,6 +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 0fe02758de7d..9b43bda45a41 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -89,6 +89,7 @@ enum perf_output_field {
         PERF_OUTPUT_BRSTACKOFF      = 1U << 24,
         PERF_OUTPUT_SYNTH           = 1U << 25,
         PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
+        PERF_OUTPUT_UREGS           = 1U << 27,
 };
 
 struct output_option {
@@ -110,6 +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},
@@ -209,6 +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) {
@@ -386,6 +433,11 @@ 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))
@@ -494,51 +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++];
-                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_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++];
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+        }
+
+        return printed;
+}
+
+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)) {
@@ -547,13 +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
@@ -565,16 +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;
@@ -587,38 +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++) {
 
@@ -635,37 +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++) {
 
@@ -682,24 +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
 
@@ -727,27 +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;
         }
 
@@ -760,36 +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));
 
@@ -798,7 +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;
@@ -806,37 +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;
@@ -844,17 +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 */
@@ -880,13 +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++;
@@ -899,9 +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
@@ -909,58 +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);
@@ -995,12 +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
@@ -1010,39 +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)) {
@@ -1055,31 +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 {
@@ -1102,7 +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);
@@ -1129,9 +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 {
@@ -1140,40 +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;
@@ -1183,154 +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 {
@@ -1341,6 +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;
@@ -1362,7 +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];
@@ -1376,7 +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,
@@ -1387,14 +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);
@@ -1402,33 +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;
@@ -1438,27 +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);
+                perf_sample__fprintf_bpf_output(sample, fp);
+        perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
 
         if (PRINT_FIELD(PHYS_ADDR))
-                printf("%16" PRIx64, sample->phys_addr);
-        printf("\n");
+                fprintf(fp, "%16" PRIx64, sample->phys_addr);
+        fprintf(fp, "\n");
 }
 
 static struct scripting_ops     *scripting_ops;
@@ -1632,7 +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:
@@ -1667,7 +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:
@@ -1700,7 +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);
 
@@ -1729,7 +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)
@@ -1764,7 +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;
@@ -1795,7 +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;
@@ -1821,7 +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;
@@ -1832,6 +1937,75 @@ 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) {
+                /*
+                 * Already setup? I.e. we may be called twice in cases like
+                 * Intel PT, one for the intel_pt// and dummy events, then
+                 * for the evsels syntheized from the auxtrace info.
+                 *
+                 * Ses perf_script__process_auxtrace_info.
+                 */
+                if (evsel->priv != NULL)
+                        continue;
+
+                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;
@@ -1853,8 +2027,16 @@ 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);
 
@@ -2419,14 +2601,16 @@ 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;
 
@@ -2664,6 +2848,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
         return set_maps(script);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_script__process_auxtrace_info(struct perf_tool *tool,
+                                              union perf_event *event,
+                                              struct perf_session *session)
+{
+        int ret = perf_event__process_auxtrace_info(tool, event, session);
+
+        if (ret == 0) {
+                struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+                ret = perf_script__setup_per_event_dump(script);
+        }
+
+        return ret;
+}
+#else
+#define perf_script__process_auxtrace_info 0
+#endif
+
 int cmd_script(int argc, const char **argv)
 {
         bool show_full_info = false;
@@ -2692,7 +2895,7 @@ int cmd_script(int argc, const char **argv)
                         .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,
+                        .auxtrace_info   = perf_script__process_auxtrace_info,
                         .auxtrace        = perf_event__process_auxtrace,
                         .auxtrace_error  = perf_event__process_auxtrace_error,
                         .stat            = perf_event__process_stat_event,
@@ -2704,7 +2907,7 @@ 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[] = {
@@ -2740,7 +2943,7 @@ 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,"
+                     "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,
@@ -2772,6 +2975,8 @@ 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"),
@@ -2802,13 +3007,15 @@ 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);
@@ -2975,7 +3182,7 @@ 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;
 
@@ -3016,7 +3223,8 @@ 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) {
@@ -3030,7 +3238,7 @@ 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");
@@ -3076,7 +3284,8 @@ 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 69523ed55894..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)
 {
@@ -245,7 +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;
 
         /*
@@ -287,7 +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;
         }
@@ -407,6 +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);
 }
 
@@ -582,6 +592,32 @@ 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;
@@ -592,7 +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) {
@@ -618,6 +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).
@@ -674,10 +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);
@@ -800,7 +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);
 }
 
@@ -1199,7 +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);
@@ -1222,8 +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));
                 }
         }
@@ -1325,6 +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))
@@ -1384,7 +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]);
@@ -1468,6 +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;
@@ -1522,6 +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;
@@ -1530,7 +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);
 }
@@ -1643,7 +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)
@@ -1668,12 +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;
@@ -1681,8 +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:
@@ -1754,6 +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"),
@@ -1819,6 +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()
 };
 
@@ -2334,20 +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;
@@ -2405,7 +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);
@@ -2513,10 +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;
 
@@ -2787,7 +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);
@@ -2801,7 +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 ee954bde7e3e..9e0d2645ae13 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -77,6 +77,7 @@
 #include "sane_ctype.h"
 
 static volatile int done;
+static volatile int resize;
 
 #define HEADER_LINE_NR  5
 
@@ -85,11 +86,13 @@ static void perf_top__update_print_entries(struct perf_top *top)
         top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void perf_top__sig_winch(int sig __maybe_unused,
-                                siginfo_t *info __maybe_unused, void *arg)
+static void winch_sig(int sig __maybe_unused)
 {
-        struct perf_top *top = arg;
+        resize = 1;
+}
 
+static void perf_top__resize(struct perf_top *top)
+{
         get_term_dimensions(&top->winsize);
         perf_top__update_print_entries(top);
 }
@@ -473,12 +476,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
                 case 'e':
                         prompt_integer(&top->print_entries, "Enter display entries (lines)");
                         if (top->print_entries == 0) {
-                                struct sigaction act = {
-                                        .sa_sigaction = perf_top__sig_winch,
-                                        .sa_flags     = SA_SIGINFO,
-                                };
-                                perf_top__sig_winch(SIGWINCH, NULL, top);
-                                sigaction(SIGWINCH, &act, NULL);
+                                perf_top__resize(top);
+                                signal(SIGWINCH, winch_sig);
                         } else {
                                 signal(SIGWINCH, SIG_DFL);
                         }
@@ -732,14 +731,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
         if (!machine->kptr_restrict_warned &&
             symbol_conf.kptr_restrict &&
             al.cpumode == PERF_RECORD_MISC_KERNEL) {
-                ui__warning(
+                if (!perf_evlist__exclude_kernel(top->session->evlist)) {
+                        ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
                           al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
                           " modules" : "");
-                if (use_browser <= 0)
-                        sleep(5);
+                        if (use_browser <= 0)
+                                sleep(5);
+                }
                 machine->kptr_restrict_warned = true;
         }
 
@@ -958,8 +959,16 @@ 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);
@@ -1022,6 +1031,11 @@ static int __cmd_top(struct perf_top *top)
 
                 if (hits == top->samples)
                         ret = perf_evlist__poll(top->evlist, 100);
+
+                if (resize) {
+                        perf_top__resize(top);
+                        resize = 0;
+                }
         }
 
         ret = 0;
@@ -1112,6 +1126,7 @@ 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;
@@ -1221,6 +1236,8 @@ int cmd_top(int argc, const char **argv)
         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[] = {
@@ -1341,12 +1358,8 @@ int cmd_top(int argc, const char **argv)
 
         get_term_dimensions(&top.winsize);
         if (top.print_entries == 0) {
-                struct sigaction act = {
-                        .sa_sigaction = perf_top__sig_winch,
-                        .sa_flags     = SA_SIGINFO,
-                };
                 perf_top__update_print_entries(&top);
-                sigaction(SIGWINCH, &act, NULL);
+                signal(SIGWINCH, winch_sig);
         }
 
         status = __cmd_top(&top);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d5d7fff1c211..84debdbad327 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -578,7 +578,6 @@ static struct syscall_fmt {
 } syscall_fmts[] = {
         { .name     = "access",
           .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
-        { .name     = "arch_prctl", .alias = "prctl", },
         { .name     = "bpf",
           .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
         { .name     = "brk",        .hexret = true,
@@ -634,6 +633,12 @@ static struct syscall_fmt {
 #else
                    [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
 #endif
+        { .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",
@@ -703,6 +708,10 @@ static struct syscall_fmt {
                    [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",
@@ -985,6 +994,23 @@ size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
         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)
 {
@@ -1126,12 +1152,14 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
         if (trace->host == NULL)
                 return -ENOMEM;
 
-        if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
-                return -errno;
+        err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
+        if (err < 0)
+                goto out;
 
         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);
+out:
         if (err)
                 symbol__exit();
 
@@ -1836,16 +1864,14 @@ 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:
@@ -1858,13 +1884,15 @@ 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,
@@ -2086,6 +2114,7 @@ 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;
                 }
         }
@@ -2538,10 +2567,12 @@ 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;
@@ -2564,7 +2595,7 @@ 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;
 
@@ -2740,20 +2771,23 @@ 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;
 }
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 50cd6228f506..3e64f10b6d66 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,8 +5,10 @@ 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
@@ -19,6 +21,7 @@ arch/x86/include/asm/cpufeatures.h
 arch/arm/include/uapi/asm/perf_regs.h
 arch/arm64/include/uapi/asm/perf_regs.h
 arch/powerpc/include/uapi/asm/perf_regs.h
+arch/s390/include/uapi/asm/perf_regs.h
 arch/x86/include/uapi/asm/perf_regs.h
 arch/x86/include/uapi/asm/kvm.h
 arch/x86/include/uapi/asm/kvm_perf.h
@@ -28,6 +31,7 @@ arch/x86/include/uapi/asm/vmx.h
 arch/powerpc/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
@@ -58,6 +62,11 @@ check () {
 }
 
 
+# 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
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index cf36de7ea255..0c6d1002b524 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -384,13 +384,13 @@ jvmti_write_code(void *agent, char const *sym,
 }
 
 int
-jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
-                       jvmti_line_info_t *li, int nr_lines)
+jvmti_write_debug_info(void *agent, uint64_t code,
+    int nr_lines, jvmti_line_info_t *li,
+    const char * const * file_names)
 {
         struct jr_code_debug_info rec;
-        size_t sret, len, size, flen;
+        size_t sret, len, size, flen = 0;
         uint64_t addr;
-        const char *fn = file;
         FILE *fp = agent;
         int i;
 
@@ -405,7 +405,9 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
                 return -1;
         }
 
-        flen = strlen(file) + 1;
+        for (i = 0; i < nr_lines; ++i) {
+            flen += strlen(file_names[i]) + 1;
+        }
 
         rec.p.id        = JIT_CODE_DEBUG_INFO;
         size            = sizeof(rec);
@@ -421,7 +423,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
          * file[]   : source file name
          */
         size += nr_lines * sizeof(struct debug_entry);
-        size += flen * nr_lines;
+        size += flen;
         rec.p.total_size = size;
 
         /*
@@ -452,7 +454,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
                 if (sret != 1)
                         goto error;
 
-                sret = fwrite_unlocked(fn, flen, 1, fp);
+                sret = fwrite_unlocked(file_names[i], strlen(file_names[i]) + 1, 1, fp);
                 if (sret != 1)
                         goto error;
         }
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
index fe32d8344a82..6ed82f6c06dd 100644
--- a/tools/perf/jvmti/jvmti_agent.h
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -14,6 +14,7 @@ typedef struct {
         unsigned long   pc;
         int             line_number;
         int             discrim; /* discriminator -- 0 for now */
+        jmethodID       methodID;
 } jvmti_line_info_t;
 
 void *jvmti_open(void);
@@ -22,11 +23,9 @@ int   jvmti_write_code(void *agent, char const *symbol_name,
                        uint64_t vma, void const *code,
                        const unsigned int code_size);
 
-int   jvmti_write_debug_info(void *agent,
-                             uint64_t code,
-                             const char *file,
+int   jvmti_write_debug_info(void *agent, uint64_t code, int nr_lines,
                              jvmti_line_info_t *li,
-                             int nr_lines);
+                             const char * const * file_names);
 
 #if defined(__cplusplus)
 }
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
index c62c9fc9a525..6add3e982614 100644
--- a/tools/perf/jvmti/libjvmti.c
+++ b/tools/perf/jvmti/libjvmti.c
@@ -47,6 +47,7 @@ do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
                         tab[lines].pc = (unsigned long)pc;
                         tab[lines].line_number = loc_tab[i].line_number;
                         tab[lines].discrim = 0; /* not yet used */
+                        tab[lines].methodID = m;
                         lines++;
                 } else {
                         break;
@@ -125,6 +126,99 @@ get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **
         return JVMTI_ERROR_NONE;
 }
 
+static void
+copy_class_filename(const char * class_sign, const char * file_name, char * result, size_t max_length)
+{
+        /*
+        * Assume path name is class hierarchy, this is a common practice with Java programs
+        */
+        if (*class_sign == 'L') {
+                int j, i = 0;
+                char *p = strrchr(class_sign, '/');
+                if (p) {
+                        /* drop the 'L' prefix and copy up to the final '/' */
+                        for (i = 0; i < (p - class_sign); i++)
+                                result[i] = class_sign[i+1];
+                }
+                /*
+                * append file name, we use loops and not string ops to avoid modifying
+                * class_sign which is used later for the symbol name
+                */
+                for (j = 0; i < (max_length - 1) && file_name && j < strlen(file_name); j++, i++)
+                        result[i] = file_name[j];
+
+                result[i] = '\0';
+        } else {
+                /* fallback case */
+                size_t file_name_len = strlen(file_name);
+                strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length);
+        }
+}
+
+static jvmtiError
+get_source_filename(jvmtiEnv *jvmti, jmethodID methodID, char ** buffer)
+{
+        jvmtiError ret;
+        jclass decl_class;
+        char *file_name = NULL;
+        char *class_sign = NULL;
+        char fn[PATH_MAX];
+        size_t len;
+
+        ret = (*jvmti)->GetMethodDeclaringClass(jvmti, methodID, &decl_class);
+        if (ret != JVMTI_ERROR_NONE) {
+                print_error(jvmti, "GetMethodDeclaringClass", ret);
+                return ret;
+        }
+
+        ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name);
+        if (ret != JVMTI_ERROR_NONE) {
+                print_error(jvmti, "GetSourceFileName", ret);
+                return ret;
+        }
+
+        ret = (*jvmti)->GetClassSignature(jvmti, decl_class, &class_sign, NULL);
+        if (ret != JVMTI_ERROR_NONE) {
+                print_error(jvmti, "GetClassSignature", ret);
+                goto free_file_name_error;
+        }
+
+        copy_class_filename(class_sign, file_name, fn, PATH_MAX);
+        len = strlen(fn);
+        *buffer = malloc((len + 1) * sizeof(char));
+        if (!*buffer) {
+                print_error(jvmti, "GetClassSignature", ret);
+                ret = JVMTI_ERROR_OUT_OF_MEMORY;
+                goto free_class_sign_error;
+        }
+        strcpy(*buffer, fn);
+        ret = JVMTI_ERROR_NONE;
+
+free_class_sign_error:
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
+free_file_name_error:
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
+
+        return ret;
+}
+
+static jvmtiError
+fill_source_filenames(jvmtiEnv *jvmti, int nr_lines,
+                      const jvmti_line_info_t * line_tab,
+                      char ** file_names)
+{
+        int index;
+        jvmtiError ret;
+
+        for (index = 0; index < nr_lines; ++index) {
+                ret = get_source_filename(jvmti, line_tab[index].methodID, &(file_names[index]));
+                if (ret != JVMTI_ERROR_NONE)
+                        return ret;
+        }
+
+        return JVMTI_ERROR_NONE;
+}
+
 static void JNICALL
 compiled_method_load_cb(jvmtiEnv *jvmti,
                         jmethodID method,
@@ -135,16 +229,18 @@ compiled_method_load_cb(jvmtiEnv *jvmti,
                         const void *compile_info)
 {
         jvmti_line_info_t *line_tab = NULL;
+        char ** line_file_names = NULL;
         jclass decl_class;
         char *class_sign = NULL;
         char *func_name = NULL;
         char *func_sign = NULL;
-        char *file_name= NULL;
+        char *file_name = NULL;
         char fn[PATH_MAX];
         uint64_t addr = (uint64_t)(uintptr_t)code_addr;
         jvmtiError ret;
         int nr_lines = 0; /* in line_tab[] */
         size_t len;
+        int output_debug_info = 0;
 
         ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method,
                                                 &decl_class);
@@ -158,6 +254,19 @@ compiled_method_load_cb(jvmtiEnv *jvmti,
                 if (ret != JVMTI_ERROR_NONE) {
                         warnx("jvmti: cannot get line table for method");
                         nr_lines = 0;
+                } else if (nr_lines > 0) {
+                        line_file_names = malloc(sizeof(char*) * nr_lines);
+                        if (!line_file_names) {
+                                warnx("jvmti: cannot allocate space for line table method names");
+                        } else {
+                                memset(line_file_names, 0, sizeof(char*) * nr_lines);
+                                ret = fill_source_filenames(jvmti, nr_lines, line_tab, line_file_names);
+                                if (ret != JVMTI_ERROR_NONE) {
+                                        warnx("jvmti: fill_source_filenames failed");
+                                } else {
+                                        output_debug_info = 1;
+                                }
+                        }
                 }
         }
 
@@ -181,33 +290,14 @@ compiled_method_load_cb(jvmtiEnv *jvmti,
                 goto error;
         }
 
-        /*
-         * Assume path name is class hierarchy, this is a common practice with Java programs
-         */
-        if (*class_sign == 'L') {
-                int j, i = 0;
-                char *p = strrchr(class_sign, '/');
-                if (p) {
-                        /* drop the 'L' prefix and copy up to the final '/' */
-                        for (i = 0; i < (p - class_sign); i++)
-                                fn[i] = class_sign[i+1];
-                }
-                /*
-                 * append file name, we use loops and not string ops to avoid modifying
-                 * class_sign which is used later for the symbol name
-                 */
-                for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++)
-                        fn[i] = file_name[j];
-                fn[i] = '\0';
-        } else {
-                /* fallback case */
-                strcpy(fn, file_name);
-        }
+        copy_class_filename(class_sign, file_name, fn, PATH_MAX);
+
         /*
          * write source line info record if we have it
          */
-        if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines))
-                warnx("jvmti: write_debug_info() failed");
+        if (output_debug_info)
+                if (jvmti_write_debug_info(jvmti_agent, addr, nr_lines, line_tab, (const char * const *) line_file_names))
+                        warnx("jvmti: write_debug_info() failed");
 
         len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2;
         {
@@ -223,6 +313,13 @@ error:
         (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
         (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
         free(line_tab);
+        while (line_file_names && (nr_lines > 0)) {
+            if (line_file_names[nr_lines - 1]) {
+                free(line_file_names[nr_lines - 1]);
+            }
+            nr_lines -= 1;
+        }
+        free(line_file_names);
 }
 
 static void JNICALL
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index f75f3dec7485..2357f4ccc9c7 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -66,6 +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/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 4ea068366c3e..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
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/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/jevents.c b/tools/perf/pmu-events/jevents.c
index d51dc9ca8861..9eb7047bafe4 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -292,7 +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;
@@ -304,8 +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])
@@ -320,6 +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;
@@ -357,6 +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;
@@ -369,7 +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;
@@ -397,6 +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;
@@ -476,6 +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++)
@@ -501,10 +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);
@@ -516,6 +527,7 @@ int json_events(const char *fn,
                 free(unit);
                 free(metric_expr);
                 free(metric_name);
+                free(metric_group);
                 if (err)
                         break;
                 tok += j;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index d87efd2685b8..4684c673c445 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -7,7 +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/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index e08789ddfe6c..92a4d15ee0b9 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -16,6 +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/tests/attr.c b/tools/perf/tests/attr.c
index c180bbcdbef6..0e1367f90af5 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -167,7 +167,7 @@ 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(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 907b1b2f56ad..ff9b60b99f52 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -238,6 +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)
@@ -254,7 +255,10 @@ class Test(object):
                 if exp_event.optional():
                     log.debug("    %s does not match, but is optional" % exp_name)
                 else:
-                    exp_event.diff(res_event)
+                    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 31e0b1da830b..37940665f736 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -23,7 +23,7 @@ comm=1
 freq=1
 inherit_stat=0
 enable_on_exec=1
-task=0
+task=1
 watermark=0
 precise_ip=0|1|2|3
 mmap_data=0
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index 6e7961f6f7a5..618ba1c17474 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -17,5 +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 ef59afd6d635..f906b793196f 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -23,7 +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 87a222d014d8..48e8bd12fe46 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -18,5 +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-stat-C0 b/tools/perf/tests/attr/test-stat-C0
index 67717fe6a65d..a2c76d10b2bb 100644
--- a/tools/perf/tests/attr/test-stat-C0
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -7,3 +7,4 @@ ret     = 1
 # 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 e911dbd4eb47..d9e99b3f77e6 100644
--- a/tools/perf/tests/attr/test-stat-default
+++ b/tools/perf/tests/attr/test-stat-default
@@ -32,6 +32,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -52,15 +53,18 @@ optional=1
 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 b39270a08e74..8b04a055d154 100644
--- a/tools/perf/tests/attr/test-stat-detailed-1
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -33,6 +33,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -53,18 +54,21 @@ optional=1
 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  |
@@ -74,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -83,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -92,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -101,3 +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 45f8e6ea34f8..4fca9f1bfbf8 100644
--- a/tools/perf/tests/attr/test-stat-detailed-2
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -33,6 +33,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -53,18 +54,21 @@ optional=1
 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  |
@@ -74,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -83,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -92,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -101,6 +108,7 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -120,6 +128,7 @@ optional=1
 fd=16
 type=3
 config=65537
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -129,6 +138,7 @@ config=65537
 fd=17
 type=3
 config=3
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -138,6 +148,7 @@ config=3
 fd=18
 type=3
 config=65539
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -147,6 +158,7 @@ config=65539
 fd=19
 type=3
 config=4
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -156,3 +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 30ae0fb7a3fd..4bb58e1c82a6 100644
--- a/tools/perf/tests/attr/test-stat-detailed-3
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -33,6 +33,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -53,18 +54,21 @@ optional=1
 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  |
@@ -74,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -83,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -92,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -101,6 +108,7 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -120,6 +128,7 @@ optional=1
 fd=16
 type=3
 config=65537
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -129,6 +138,7 @@ config=65537
 fd=17
 type=3
 config=3
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -138,6 +148,7 @@ config=3
 fd=18
 type=3
 config=65539
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -147,6 +158,7 @@ config=65539
 fd=19
 type=3
 config=4
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -156,6 +168,7 @@ config=4
 fd=20
 type=3
 config=65540
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
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/builtin-test.c b/tools/perf/tests/builtin-test.c
index 53d06f37406a..766573e236e4 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -4,6 +4,7 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <fcntl.h>
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 3c3f3e029e33..868d82b501f4 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -132,7 +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)
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 7a84d73324e3..8b3da21a08f1 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,8 +10,8 @@
 
 . $(dirname $0)/lib/probe.sh
 
-ld=$(realpath /lib64/ld*.so.* | uniq)
-libc=$(echo $ld | sed 's/ld/libc/g')
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
         idx=0
@@ -37,6 +37,9 @@ trace_libc_inet_pton_backtrace() {
         done
 }
 
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
 skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2e68c5f120da..2a9ef080efd0 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,8 +17,10 @@ skip_if_no_perf_probe || exit 2
 file=$(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]+$"
+        test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; }
+
+        perf trace -e ${svc:-open} touch $file 2>&1 | \
+        egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a7344e274..89c8e1604ca7 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
         evsel = perf_evlist__first(evlist);
         evsel->attr.task = 1;
+#ifdef __s390x__
+        evsel->attr.sample_freq = 1000000;
+#else
         evsel->attr.sample_freq = 1;
+#endif
         evsel->attr.inherit = 0;
         evsel->attr.watermark = 0;
         evsel->attr.wakeup_events = 1;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index a59db7c45a65..17cb1bb3448c 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -30,12 +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();
@@ -47,7 +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);
 
@@ -57,13 +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++) {
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 175d633c6b49..066bbf0f4a74 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -3,5 +3,7 @@ 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 d80655cd1881..a6dfd04beaee 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -4,6 +4,7 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <sys/types.h>
 
 struct strarray {
         int         offset;
@@ -27,6 +28,8 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 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
@@ -79,12 +82,27 @@ size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_ar
 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
 
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/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 51f1cea406f5..417e3ecfe9d7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -62,6 +62,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
         P_MMAP_FLAG(POPULATE);
         P_MMAP_FLAG(STACK);
         P_MMAP_FLAG(UNINITIALIZED);
+#ifdef MAP_SYNC
+        P_MMAP_FLAG(SYNC);
+#endif
 #undef P_MMAP_FLAG
 
         if (flags)
@@ -95,35 +98,21 @@ 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/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/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 628ad5f7eddb..68146f4620a5 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -155,57 +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;
-
-        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)) {
@@ -216,12 +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 == '+')
@@ -273,7 +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);
@@ -282,10 +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;
         }
@@ -433,19 +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;
@@ -477,12 +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);
 
@@ -842,71 +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,
@@ -918,7 +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--;
@@ -955,12 +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)
@@ -1384,12 +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,
@@ -1421,8 +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;
                                 }
@@ -1464,15 +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/progress.c b/tools/perf/ui/progress.c
index b5a5df14d702..bbfbc91a0fa4 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -28,13 +28,17 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
         }
 }
 
-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 ?: 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 594bbe6935dd..4f52c37b2f09 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -9,12 +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/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index de2810ae16be..25dd1e0ecc58 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -22,64 +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;
-
-        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)
 {
@@ -138,9 +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;
 }
 
@@ -315,13 +254,6 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
                         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;
         }
@@ -601,7 +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,
@@ -623,13 +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/progress.c b/tools/perf/ui/tui/progress.c
index 236bcb620ae4..bc134b82829d 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,13 +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,
@@ -19,13 +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;
@@ -50,8 +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/util/Build b/tools/perf/util/Build
index 94518c1bf8b6..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
@@ -34,6 +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
@@ -78,6 +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/
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index aa66791b1bfc..3369c7830260 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -49,10 +49,9 @@ struct arch {
         void            *priv;
         unsigned int    model;
         unsigned int    family;
-        int             (*init)(struct arch *arch);
+        int             (*init)(struct arch *arch, char *cpuid);
         bool            (*ins_is_fused)(struct arch *arch, const char *ins1,
                                         const char *ins2);
-        int             (*cpuid_parse)(struct arch *arch, char *cpuid);
         struct          {
                 char comment_char;
                 char skip_functions_char;
@@ -132,10 +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,
-                .cpuid_parse = x86__cpuid_parse,
                 .objdump =  {
                         .comment_char = '#',
                 },
@@ -166,7 +165,7 @@ static void ins__delete(struct ins_operands *ops)
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
                               struct ins_operands *ops)
 {
-        return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+        return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
@@ -231,12 +230,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
                            struct ins_operands *ops)
 {
         if (ops->target.name)
-                return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+                return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
 
         if (ops->target.addr == 0)
                 return ins__raw_scnprintf(ins, bf, size, ops);
 
-        return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+        return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -300,7 +299,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
                         c++;
         }
 
-        return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+        return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
                          ins->name, c ? c - ops->raw : 0, ops->raw,
                          ops->target.offset);
 }
@@ -373,7 +372,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
         if (ops->locked.ins.ops == NULL)
                 return ins__raw_scnprintf(ins, bf, size, ops);
 
-        printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+        printed = scnprintf(bf, size, "%-6s ", ins->name);
         return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
                                         size - printed, ops->locked.ops);
 }
@@ -449,7 +448,7 @@ out_free_source:
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
                            struct ins_operands *ops)
 {
-        return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+        return scnprintf(bf, size, "%-6s %s,%s", ins->name,
                          ops->source.name ?: ops->source.raw,
                          ops->target.name ?: ops->target.raw);
 }
@@ -489,7 +488,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
                            struct ins_operands *ops)
 {
-        return scnprintf(bf, size, "%-6.6s %s", ins->name,
+        return scnprintf(bf, size, "%-6s %s", ins->name,
                          ops->target.name ?: ops->target.raw);
 }
 
@@ -501,7 +500,7 @@ static struct ins_ops dec_ops = {
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
                           struct ins_operands *ops __maybe_unused)
 {
-        return scnprintf(bf, size, "%-6.6s", "nop");
+        return scnprintf(bf, size, "%-6s", "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -925,7 +924,7 @@ void disasm_line__free(struct disasm_line *dl)
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
 {
         if (raw || !dl->ins.ops)
-                return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw);
+                return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
 
         return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
 }
@@ -1457,16 +1456,13 @@ 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;
                 }
         }
 
-        if (arch->cpuid_parse && cpuid)
-                arch->cpuid_parse(arch, cpuid);
-
         pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
                  symfs_filename, sym->name, map->unmap_ip(map, sym->start),
                  map->unmap_ip(map, sym->end));
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/callchain.c b/tools/perf/util/callchain.c
index 6031933d811c..082505d08d72 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -567,6 +567,7 @@ 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;
@@ -645,103 +646,120 @@ 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;
-        struct dso *left_dso = NULL;
-        struct dso *right_dso = NULL;
-
-        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;
-        }
-
-        if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
-                left = cnode->ms.sym->start;
-                right = sym->start;
-                left_dso = cnode->ms.map->dso;
-                right_dso = node->map->dso;
-        } else {
-                left = cnode->ip;
-                right = node->ip;
+                        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 (left == right && left_dso == right_dso) {
-                if (node->branch) {
-                        cnode->branch_count++;
+        if (match == MATCH_EQ && node->branch) {
+                cnode->branch_count++;
 
-                        if (node->branch_from) {
-                                /*
-                                 * It's "to" of a branch
-                                 */
-                                cnode->brtype_stat.branch_to = true;
+                if (node->branch_from) {
+                        /*
+                         * It's "to" of a branch
+                         */
+                        cnode->brtype_stat.branch_to = true;
 
-                                if (node->branch_flags.predicted)
-                                        cnode->predicted_count++;
+                        if (node->branch_flags.predicted)
+                                cnode->predicted_count++;
 
-                                if (node->branch_flags.abort)
-                                        cnode->abort_count++;
+                        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->iter_cycles += node->iter_cycles;
-                        }
+                        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->iter_cycles += node->iter_cycles;
                 }
-
-                return MATCH_EQ;
         }
 
-        return left > right ? MATCH_GT : MATCH_LT;
+        return match;
 }
 
 /*
@@ -970,7 +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, 0);
+                                        false, NULL, 0, 0, 0, list->srcline);
                 list_del(&list->list);
                 map__zput(list->ms.map);
                 free(list);
@@ -1010,7 +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, u64 iter_cycles, u64 branch_from)
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+                            const char *srcline)
 {
         struct callchain_cursor_node *node = *cursor->last;
 
@@ -1029,6 +1048,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
         node->branch = branch;
         node->nr_loop_iter = nr_loop_iter;
         node->iter_cycles = iter_cycles;
+        node->srcline = srcline;
 
         if (flags)
                 memcpy(&node->branch_flags, flags,
@@ -1071,10 +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)
@@ -1116,16 +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);
 
@@ -1533,7 +1550,7 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
                                              node->branch, &node->branch_flags,
                                              node->nr_loop_iter,
                                              node->iter_cycles,
-                                             node->branch_from);
+                                             node->branch_from, node->srcline);
                 if (rc)
                         break;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index f967aa47d0a1..b79ef2478a57 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -122,7 +122,7 @@ struct callchain_list {
         u64                     iter_count;
         u64                     iter_cycles;
         struct branch_type_stat brtype_stat;
-        char                   *srcline;
+        const char              *srcline;
         struct list_head        list;
 };
 
@@ -136,6 +136,7 @@ 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;
@@ -202,7 +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, u64 iter_cycles, u64 branch_from);
+                            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)
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 8808570f8e9c..7798a2cc8a86 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include "rwsem.h"
 
 struct comm_str {
         char *str;
@@ -15,6 +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)
 {
@@ -26,7 +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);
         }
@@ -51,7 +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;
@@ -82,6 +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/config.c b/tools/perf/util/config.c
index 4b893c622236..84eb9393c7db 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -701,10 +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/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2346cecb8ea2..5744c12641a5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1577,10 +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 = {
@@ -1619,7 +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;
 
@@ -1650,7 +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.c b/tools/perf/util/data.c
index 79192758bdb3..48094fde0a68 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -4,6 +4,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
 
@@ -21,56 +22,56 @@
 #endif
 #endif
 
-static bool check_pipe(struct perf_data_file *file)
+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;
@@ -79,19 +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:
@@ -99,49 +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|O_CLOEXEC,
+        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,
@@ -150,42 +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 80241ba78101..4828f7feea89 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -10,51 +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 dc8b53b6950e..f3a71db83947 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -112,50 +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/dso.c b/tools/perf/util/dso.c
index 00c98c968cb1..d5b6f7f5baff 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,9 +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"
@@ -1201,6 +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;
@@ -1232,6 +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]);
 
@@ -1366,9 +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)
@@ -1387,9 +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;
 }
 
@@ -1416,9 +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 926ff2e7f668..c229dbe0277a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -7,7 +7,7 @@
 #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"
@@ -130,7 +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;
@@ -142,6 +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;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index fc690fecbfd6..97a8ef9980db 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,6 +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>
@@ -678,21 +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)
@@ -712,31 +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);
@@ -748,6 +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;
@@ -1498,6 +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 5524ee69279c..1ae95efbfb95 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -681,7 +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 6a0d7ffbeba0..b62e523a7035 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)
 
@@ -260,7 +257,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist)
                 .config = PERF_COUNT_SW_DUMMY,
                 .size   = sizeof(attr), /* to capture ABI version */
         };
-        struct perf_evsel *evsel = perf_evsel__new(&attr);
+        struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
 
         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)
@@ -2034,3 +1786,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 state_err:
         return;
 }
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (!evsel->attr.exclude_kernel)
+                        return false;
+        }
+
+        return true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c1750a400bb7..491f69542920 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -7,12 +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>
 
@@ -24,55 +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];
@@ -177,12 +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,
@@ -286,25 +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);
@@ -385,4 +312,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
 struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
                                             union perf_event *event);
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0dccdb89572c..d5fbcf8c7aa7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -683,7 +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 {
@@ -733,12 +733,16 @@ static void apply_config_terms(struct perf_evsel *evsel,
         list_for_each_entry(term, config_terms, list) {
                 switch (term->type) {
                 case PERF_EVSEL__CONFIG_TERM_PERIOD:
-                        attr->sample_period = term->val.period;
-                        attr->freq = 0;
+                        if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
+                                attr->sample_period = term->val.period;
+                                attr->freq = 0;
+                        }
                         break;
                 case PERF_EVSEL__CONFIG_TERM_FREQ:
-                        attr->sample_freq = term->val.freq;
-                        attr->freq = 1;
+                        if (!(term->weak && opts->user_freq != UINT_MAX)) {
+                                attr->sample_freq = term->val.freq;
+                                attr->freq = 1;
+                        }
                         break;
                 case PERF_EVSEL__CONFIG_TERM_TIME:
                         if (term->val.time)
@@ -936,6 +940,11 @@ 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);
 
@@ -1366,7 +1375,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader,
 static int
 perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
 {
-        struct perf_stat_evsel *ps = leader->priv;
+        struct perf_stat_evsel *ps = leader->stats;
         u64 read_format = leader->attr.read_format;
         int size = perf_evsel__read_size(leader);
         u64 *data = ps->group_data;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b4df79d72329..157f49e8a772 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -67,8 +67,11 @@ struct perf_evsel_config_term {
                 bool    overwrite;
                 char    *branch;
         } val;
+        bool weak;
 };
 
+struct perf_stat_evsel;
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -102,6 +105,7 @@ 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;
@@ -138,6 +142,7 @@ struct perf_evsel {
         const char *            metric_name;
         struct perf_evsel       **metric_events;
         bool                    collect_stat;
+        bool                    weak_group;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 1fd7c2e46db2..06dfb027879d 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -158,7 +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, ")");
@@ -167,41 +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/header.c b/tools/perf/util/header.c
index ba0cea8fef72..7c0e9d587bfa 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1763,7 +1763,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 
         session = container_of(ff->ph, struct perf_session, header);
 
-        if (session->file->is_pipe) {
+        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;
@@ -1772,7 +1772,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
         for (evsel = events; evsel->attr.size; evsel++)
                 perf_evlist__set_event_name(session->evlist, evsel);
 
-        if (!session->file->is_pipe)
+        if (!session->data->is_pipe)
                 free_event_desc(events);
 
         return 0;
@@ -2249,7 +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;
 
@@ -2265,7 +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: ");
@@ -2758,7 +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;
@@ -2861,13 +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)
@@ -2875,7 +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)
@@ -2890,7 +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;
@@ -3398,7 +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/hist.c b/tools/perf/util/hist.c
index 097473600d94..b6140950301e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -597,6 +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,
@@ -951,6 +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,
@@ -1142,11 +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])
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/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 125ecd2a300d..52dc8d911173 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -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/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index 12e377184ee4..e0b85930dd77 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM
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/jit.h b/tools/perf/util/jit.h
index c2582fa9fe21..6817ffc2a059 100644
--- a/tools/perf/util/jit.h
+++ b/tools/perf/util/jit.h
@@ -4,7 +4,7 @@
 
 #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 36483db032e8..a1863000e972 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -30,7 +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;
@@ -61,8 +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;
 };
 
@@ -357,7 +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;
 
@@ -752,7 +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/machine.c b/tools/perf/util/machine.c
index bd5d5b5e2218..270f3223c6df 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -31,7 +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)
@@ -41,11 +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;
@@ -121,7 +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);
@@ -130,39 +140,52 @@ 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;
+
+        if (machine == NULL)
+                return;
+
         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)
@@ -380,10 +403,11 @@ 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;
 
@@ -392,14 +416,14 @@ 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) {
@@ -407,7 +431,7 @@ 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);
                 }
@@ -424,7 +448,7 @@ 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
@@ -435,7 +459,7 @@ 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;
@@ -444,8 +468,8 @@ 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;
@@ -453,27 +477,30 @@ 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;
 }
 
@@ -565,7 +592,7 @@ 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) {
@@ -579,7 +606,7 @@ 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;
 }
 
@@ -720,21 +747,25 @@ 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;
 }
 
@@ -1293,7 +1324,7 @@ 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) {
 
@@ -1323,7 +1354,7 @@ 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);
@@ -1480,23 +1511,25 @@ 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);
 }
 
@@ -1680,6 +1713,26 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
         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;
@@ -1699,6 +1752,7 @@ static int add_callchain_ip(struct thread *thread,
         struct addr_location al;
         int nr_loop_iter = 0;
         u64 iter_cycles = 0;
+        const char *srcline = NULL;
 
         al.filtered = 0;
         al.sym = NULL;
@@ -1754,9 +1808,10 @@ static int add_callchain_ip(struct thread *thread,
                 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,
-                                       iter_cycles, branch_from);
+                                       iter_cycles, branch_from, srcline);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -2069,15 +2124,54 @@ 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, 0);
+                                       false, NULL, 0, 0, 0, srcline);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
@@ -2141,21 +2235,26 @@ 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;
 }
@@ -2184,12 +2283,16 @@ 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 d551aa80a59b..5ce860b64c74 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -7,6 +7,7 @@
 #include "map.h"
 #include "dso.h"
 #include "event.h"
+#include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
@@ -24,6 +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;
@@ -31,11 +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;
@@ -49,6 +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)
 {
@@ -244,15 +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 4e7bd2750122..6d40efd74402 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -489,7 +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)
@@ -518,9 +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)
@@ -587,7 +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);
@@ -603,7 +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;
 }
 
@@ -639,7 +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);
@@ -651,7 +651,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
                 }
         }
 
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
 
         return printed;
 }
@@ -683,7 +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);
@@ -751,7 +751,7 @@ put_map:
 
         err = 0;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
         return err;
 }
 
@@ -772,7 +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);
@@ -789,7 +789,7 @@ int map_groups__clone(struct thread *thread,
 
         err = 0;
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return err;
 }
 
@@ -816,9 +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)
@@ -829,9 +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)
@@ -839,7 +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) {
@@ -855,7 +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 1fb9b8589adc..edeb7291c8e1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -10,6 +10,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include "rwsem.h"
 
 enum map_type {
         MAP__FUNCTION = 0,
@@ -62,7 +63,7 @@ struct kmap {
 
 struct maps {
         struct rb_root   entries;
-        pthread_rwlock_t lock;
+        struct rw_semaphore lock;
 };
 
 struct map_groups {
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..3a5cb5a6e94a
--- /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 = READ_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 a58e91197729..5be021701f34 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -11,6 +11,7 @@
 #include "event.h"
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <limits.h>
 #include <sched.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 05d82601c9a6..760558dcfd18 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -9,9 +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;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 56694e3409ea..170316795a18 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -29,6 +29,7 @@
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
+#include "metricgroup.h"
 
 #define MAX_NAME_LEN 100
 
@@ -1115,6 +1116,7 @@ do {								\
         INIT_LIST_HEAD(&__t->list);                             \
         __t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;   \
         __t->val.__name = __val;                                \
+        __t->weak       = term->weak;                           \
         list_add_tail(&__t->list, head_terms);                  \
 } while (0)
 
@@ -1220,11 +1222,17 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
         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,
@@ -1368,6 +1376,7 @@ struct event_modifier {
         int exclude_GH;
         int sample_read;
         int pinned;
+        int weak;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1386,6 +1395,7 @@ 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));
 
@@ -1423,6 +1433,8 @@ 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;
 
@@ -1453,6 +1465,7 @@ 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;
 }
@@ -1466,7 +1479,7 @@ 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) {
@@ -1506,6 +1519,7 @@ 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;
@@ -1728,8 +1742,8 @@ 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];
@@ -1784,8 +1798,6 @@ 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
@@ -1797,8 +1809,10 @@ 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;
 }
@@ -2376,6 +2390,8 @@ 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)
@@ -2395,6 +2411,7 @@ static int new_term(struct parse_events_term **_term,
 
         *term = *temp;
         INIT_LIST_HEAD(&term->list);
+        term->weak = false;
 
         switch (term->type_val) {
         case PARSE_EVENTS__TERM_TYPE_NUM:
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index eed50b54bab3..88108cd11b4c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -101,6 +101,9 @@ struct parse_events_term {
         /* error string indexes for within parsed string */
         int err_term;
         int err_val;
+
+        /* Coming from implicit alias */
+        bool weak;
 };
 
 struct parse_events_error {
@@ -203,6 +206,9 @@ 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 025729510525..655ecff636a8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -179,7 +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}
 
 %%
@@ -306,6 +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); }
 
         /*
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b10b35a63138..80fb1593913a 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,6 +3,7 @@
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -404,6 +405,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
                         parse_events_terms__purge(&list);
                         return ret;
                 }
+                /*
+                 * Weak terms don't override command line options,
+                 * which we don't want for implicit terms in aliases.
+                 */
+                cloned->weak = true;
                 list_add_tail(&cloned->list, &list);
         }
         list_splice(&list, terms);
@@ -541,16 +547,8 @@ 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;
 
@@ -560,22 +558,50 @@ 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
@@ -585,8 +611,11 @@ 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)))
@@ -600,9 +629,6 @@ 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
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index eca99435f4a0..27c75e635866 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -92,4 +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 779e35c9e566..23e367063446 100644
--- a/tools/perf/util/print_binary.c
+++ b/tools/perf/util/print_binary.c
@@ -3,40 +3,42 @@
 #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 2be3075e2b05..2a1554afc957 100644
--- a/tools/perf/util/print_binary.h
+++ b/tools/perf/util/print_binary.h
@@ -3,6 +3,7 @@
 #define PERF_PRINT_BINARY_H
 
 #include <stddef.h>
+#include <stdio.h>
 
 enum binary_printer_ops {
         BINARY_PRINT_DATA_BEGIN,
@@ -17,12 +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-file.c b/tools/perf/util/probe-file.c
index cdf8d83a484c..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>
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e66dc495809a..b4f2f06722a7 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,7 @@ 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
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index 7d8972b33f6b..a920f702a74d 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -144,7 +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/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/session.c b/tools/perf/util/session.c
index da55081aefc6..5c412310f266 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -33,14 +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))
@@ -121,7 +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));
@@ -135,13 +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;
 
@@ -149,7 +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);
                         }
@@ -158,7 +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().
@@ -171,7 +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;
@@ -180,7 +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:
@@ -202,8 +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);
 }
 
@@ -291,8 +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;
 }
 
@@ -1350,7 +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);
@@ -1450,10 +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)
@@ -1688,7 +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;
@@ -1829,7 +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;
@@ -1850,7 +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) {
@@ -1946,13 +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 41caa098ed15..da1434a7c120 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -33,13 +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);
 
@@ -114,7 +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/sort.c b/tools/perf/util/sort.c
index 84a33f1e9ec9..a00eacdf02ed 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -226,6 +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);
 
@@ -284,6 +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;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b2b55e5149a7..f5901c10a563 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -130,7 +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;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 4105682afc7a..d19f05c56de6 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -11,7 +11,7 @@
 #include "util/debug.h"
 #include "util/callchain.h"
 #include "srcline.h"
-
+#include "string2.h"
 #include "symbol.h"
 
 bool srcline_full_filename;
@@ -34,28 +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);
@@ -65,6 +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
 
 /*
@@ -208,18 +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;
@@ -245,7 +298,7 @@ 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,
@@ -256,7 +309,7 @@ static int addr2line(const char *dso_name, u64 addr,
                                 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;
@@ -288,7 +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;
 
@@ -301,17 +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 */
@@ -341,7 +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];
@@ -381,16 +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");
@@ -408,26 +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;
 }
@@ -455,19 +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:
@@ -501,7 +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;
 
@@ -509,7 +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)
@@ -518,10 +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 8e73f607dfa3..847b7086182c 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -3,6 +3,7 @@
 #define PERF_SRCLINE_H
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct dso;
@@ -15,21 +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 37363869c9a1..855e35cbb1dc 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -7,6 +7,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
+#include "metricgroup.h"
 
 enum {
         CTX_BIT_USER    = 1 << 0,
@@ -56,7 +57,6 @@ struct saved_value {
         struct rb_node rb_node;
         struct perf_evsel *evsel;
         int cpu;
-        int ctx;
         struct stats stats;
 };
 
@@ -67,8 +67,6 @@ 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;
         if (a->evsel == b->evsel)
@@ -90,13 +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);
@@ -182,59 +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);
         }
 }
 
@@ -628,15 +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]);
@@ -820,33 +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];
@@ -864,6 +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 c9bae5fb8b47..151e9efd7286 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -70,7 +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;
 }
@@ -94,7 +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 */
@@ -110,7 +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]);
@@ -120,8 +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;
@@ -129,11 +129,11 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
 
         if (ps)
                 free(ps->group_data);
-        zfree(&evsel->priv);
+        zfree(&evsel->stats);
 }
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
@@ -278,7 +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;
@@ -319,9 +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;
@@ -361,8 +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 96326b1f9443..eefca5c981fd 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -83,7 +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;
@@ -92,9 +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/symbol.c b/tools/perf/util/symbol.c
index 6492ef38b090..1b67a8639dfe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -46,6 +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[] = {
@@ -227,7 +228,7 @@ 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)
@@ -247,7 +248,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
                 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)
@@ -1672,7 +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)
@@ -1682,7 +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;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6352022593c6..a4f0075b4e5c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -60,6 +60,7 @@ struct symbol {
         u8              binding;
         u8              idle:1;
         u8              ignore:1;
+        u8              inlined:1;
         u8              arch_sym;
         char            name[0];
 };
@@ -209,6 +210,7 @@ struct addr_location {
         struct thread *thread;
         struct map    *map;
         struct symbol *sym;
+        const char    *srcline;
         u64           addr;
         char          level;
         u8            filtered;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1dbcd3c8dee0..68b65b10579b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -46,6 +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)
@@ -84,18 +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);
 }
 
@@ -126,8 +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);
 
@@ -150,6 +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))
@@ -171,8 +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);
 
@@ -196,6 +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];
@@ -213,7 +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);
 
@@ -223,6 +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)
 {
@@ -265,7 +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);
@@ -273,7 +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 fdcea7c0cac1..40cfa36c022a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
+#include "rwsem.h"
 
 struct thread_stack;
 struct unwind_libunwind_ops;
@@ -30,7 +31,9 @@ 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;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 506150a75bd0..9892323cdd7c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -38,6 +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/util.c b/tools/perf/util/util.c
index 3687b720327a..a789f952b3e9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -7,6 +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>
@@ -23,6 +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;
 
@@ -175,7 +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;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b52765e6d7b4..01434509c2e9 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,7 +6,6 @@
 /* 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>
@@ -36,7 +35,6 @@ 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_ns(const char *from, const char *to, struct nsinfo *nsi);
-int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
@@ -65,4 +63,9 @@ int sched_getcpu(void);
 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/vdso.c b/tools/perf/util/vdso.c
index cffcda448c28..0acb1ec0e2f0 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -320,7 +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();
 
@@ -348,7 +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/zlib.c b/tools/perf/util/zlib.c
index 008fe68d7b76..a725b958cf31 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -1,4 +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/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/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index 943b6b614683..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",
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/system.c b/tools/power/cpupower/bench/system.c
index c25a74ae51ba..2bb3eef7d5c1 100644
--- a/tools/power/cpupower/bench/system.c
+++ b/tools/power/cpupower/bench/system.c
@@ -61,7 +61,7 @@ int set_cpufreq_governor(char *governor, unsigned int cpu)
 
         dprintf("set %s as cpufreq governor\n", governor);
 
-        if (cpupower_is_cpu_online(cpu) != 0) {
+        if (cpupower_is_cpu_online(cpu) != 1) {
                 perror("cpufreq_cpu_exists");
                 fprintf(stderr, "error: cpu %u does not exist\n", cpu);
                 return -1;
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/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
index 1b5da0066ebf..5b3205f16217 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
@@ -130,15 +130,18 @@ static struct cpuidle_monitor *cpuidle_register(void)
 {
         int num;
         char *tmp;
+        int this_cpu;
+
+        this_cpu = sched_getcpu();
 
         /* Assume idle state count is the same for all CPUs */
-        cpuidle_sysfs_monitor.hw_states_num = cpuidle_state_count(0);
+        cpuidle_sysfs_monitor.hw_states_num = cpuidle_state_count(this_cpu);
 
         if (cpuidle_sysfs_monitor.hw_states_num <= 0)
                 return NULL;
 
         for (num = 0; num < cpuidle_sysfs_monitor.hw_states_num; num++) {
-                tmp = cpuidle_state_name(0, num);
+                tmp = cpuidle_state_name(this_cpu, num);
                 if (tmp == NULL)
                         continue;
 
@@ -146,7 +149,7 @@ static struct cpuidle_monitor *cpuidle_register(void)
                 strncpy(cpuidle_cstates[num].name, tmp, CSTATE_NAME_LEN - 1);
                 free(tmp);
 
-                tmp = cpuidle_state_desc(0, num);
+                tmp = cpuidle_state_desc(this_cpu, num);
                 if (tmp == NULL)
                         continue;
                 strncpy(cpuidle_cstates[num].desc, tmp, CSTATE_DESC_LEN - 1);
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 654efd9768fd..3fab179b1aba 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -13,7 +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
 
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 65368d9027f5..db33b28c5ef3 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -70,6 +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/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index bef419d4266d..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)
@@ -1520,7 +1742,8 @@ 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);
@@ -1589,6 +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)
@@ -1613,10 +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,
         };
@@ -1767,6 +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;
 }
 
@@ -1915,6 +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);
@@ -1931,6 +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;
@@ -1966,6 +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);
@@ -1974,6 +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);
@@ -1989,6 +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/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/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 3c9c0bbe7dbb..eaf599dc2137 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-TARGETS =  bpf
+TARGETS = android
+TARGETS += bpf
 TARGETS += breakpoints
 TARGETS += capabilities
 TARGETS += cpufreq
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 eab7644a07b4..9316e648a880 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
 APIDIR := ../../../include/uapi
@@ -10,19 +11,20 @@ ifneq ($(wildcard $(GENHDR)),)
 endif
 
 CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
-LDLIBS += -lcap -lelf
+LDLIBS += -lcap -lelf -lrt
 
 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_xdp_redirect.o sockmap_parse_prog.o sockmap_verdict_prog.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_xdp_redirect.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)
 
@@ -35,8 +37,20 @@ $(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_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 50353c10573c..fd9a17fa8a8b 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -63,14 +63,25 @@ 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
@@ -110,7 +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)
@@ -123,7 +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])
@@ -136,7 +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])
@@ -149,7 +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])
@@ -162,7 +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])
@@ -173,7 +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])
@@ -183,6 +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
@@ -191,10 +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/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/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c
index fae3b96c3aa4..a1dec2b6d9c5 100644
--- a/tools/testing/selftests/bpf/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c
@@ -29,9 +29,6 @@ int bpf_prog1(struct __sk_buff *skb)
          * fields.
          */
         d[7] = 1;
-
-        bpf_printk("parse: data[0] = (%u): local_port %i remote %i\n",
-                   d[0], lport, bpf_ntohl(rport));
         return skb->len;
 }
 
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
index 2cd2d552938b..d7bea972cb21 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -58,8 +58,6 @@ int bpf_prog2(struct __sk_buff *skb)
         d[6] = 0xe;
         d[7] = 0xf;
 
-        bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
-
         if (!map)
                 return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
         return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
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_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index f93a333cbf2c..f61480641b6e 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -32,6 +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)
@@ -39,9 +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);
 
@@ -93,6 +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;
@@ -115,6 +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);
 }
 
@@ -159,7 +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;
@@ -171,6 +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;
 
@@ -224,15 +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);
          */
 }
 
@@ -332,6 +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 };
@@ -354,6 +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 50ce52d2013d..040356ecc862 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1043,6 +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);
@@ -1060,6 +1105,9 @@ static void run_all_tests(void)
         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_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 11ee25cea227..6761be18a91f 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>
@@ -273,16 +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];
+        /* 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) {
@@ -307,6 +320,7 @@ static void test_bpf_obj_id(void)
         /* 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
@@ -316,6 +330,38 @@ static void test_bpf_obj_id(void)
                         error_cnt++;
                 assert(!err);
 
+                /* 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,
+                                          &array_magic_value, 0);
+                assert(!err);
+
+                /* 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 ||
+                          map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
+                          map_infos[i].key_size != sizeof(__u32) ||
+                          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) ||
+                          strcmp((char *)map_infos[i].name, expected_map_name),
+                          "get-map-info(fd)",
+                          "err %d errno %d type %d(%d) info_len %u(%Zu) 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].name, expected_map_name))
+                        goto done;
+
                 /* Check getting prog info */
                 info_len = sizeof(struct bpf_prog_info) * 2;
                 bzero(&prog_infos[i], info_len);
@@ -325,8 +371,16 @@ static void test_bpf_obj_id(void)
                 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) ||
@@ -334,9 +388,14 @@ static void test_bpf_obj_id(void)
                           (jit_enabled &&
                            !memcmp(jited_insns, zeros, sizeof(zeros))) ||
                           !prog_infos[i].xlated_prog_len ||
-                          !memcmp(xlated_insns, zeros, sizeof(zeros)),
+                          !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\n",
+                          "err %d errno %d i %d type %d(%d) info_len %u(%Zu) 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),
@@ -344,36 +403,12 @@ static void test_bpf_obj_id(void)
                           prog_infos[i].jited_prog_len,
                           prog_infos[i].xlated_prog_len,
                           !!memcmp(jited_insns, zeros, sizeof(zeros)),
-                          !!memcmp(xlated_insns, zeros, sizeof(zeros))))
-                        goto done;
-
-                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,
-                                          &array_magic_value, 0);
-                assert(!err);
-
-                /* 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 ||
-                          map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
-                          map_infos[i].key_size != sizeof(__u32) ||
-                          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),
-                          "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, 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))
+                          !!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;
         }
 
@@ -382,6 +417,7 @@ static void test_bpf_obj_id(void)
         next_id = 0;
         while (!bpf_prog_get_next_id(next_id, &next_id)) {
                 struct bpf_prog_info prog_info = {};
+                __u32 saved_map_id;
                 int prog_fd;
 
                 info_len = sizeof(prog_info);
@@ -404,16 +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(%Zu) 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,
@@ -456,7 +509,7 @@ static void test_bpf_obj_id(void)
                       memcmp(&map_info, &map_infos[i], info_len) ||
                       array_value != array_magic_value,
                       "check get-map-info(next_id->fd)",
-                      "err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n",
+                      "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n",
                       err, errno, info_len, sizeof(struct bpf_map_info),
                       memcmp(&map_info, &map_infos[i], info_len),
                       array_value, array_magic_value);
@@ -495,6 +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 };
@@ -507,6 +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_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 64ae21f64489..b51017404c62 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -422,9 +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 subtraction from stack pointer",
-                .result_unpriv = REJECT,
-                .errstr = "R1 invalid mem access",
+                .errstr = "R1 subtraction from stack pointer",
                 .result = REJECT,
         },
         {
@@ -606,7 +604,6 @@ static struct bpf_test tests[] = {
                 },
                 .errstr = "misaligned stack access",
                 .result = REJECT,
-                .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
         },
         {
                 "invalid map_fd for function call",
@@ -1797,7 +1794,6 @@ static struct bpf_test tests[] = {
                 },
                 .result = REJECT,
                 .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",
@@ -1810,7 +1806,6 @@ static struct bpf_test tests[] = {
                 },
                 .result = REJECT,
                 .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",
@@ -1862,9 +1857,8 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .result = ACCEPT,
-                .result_unpriv = REJECT,
-                .errstr_unpriv = "R1 pointer += pointer",
+                .result = REJECT,
+                .errstr = "R1 pointer += pointer",
         },
         {
                 "unpriv: neg pointer",
@@ -2592,7 +2586,8 @@ static struct bpf_test tests[] = {
                         BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
                                     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_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, len)),
                         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),
@@ -2899,7 +2894,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "invalid access to packet",
+                .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
@@ -3579,7 +3574,7 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
-                "helper access to packet: test19, 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)),
@@ -3599,8 +3594,7 @@ 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,
         },
         {
@@ -3886,9 +3880,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3, 11 },
-                .errstr_unpriv = "R0 pointer += pointer",
-                .errstr = "R0 invalid mem access 'inv'",
-                .result_unpriv = REJECT,
+                .errstr = "R0 pointer += pointer",
                 .result = REJECT,
                 .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
         },
@@ -3929,7 +3921,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 4 },
-                .errstr = "R4 invalid mem access",
+                .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS
         },
@@ -3950,7 +3942,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 4 },
-                .errstr = "R4 invalid mem access",
+                .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS
         },
@@ -3971,7 +3963,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 4 },
-                .errstr = "R4 invalid mem access",
+                .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS
         },
@@ -4378,11 +4370,10 @@ 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 },
@@ -4482,13 +4473,12 @@ 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, 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 },
@@ -4618,13 +4608,12 @@ 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 },
@@ -4759,15 +4748,14 @@ 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 },
@@ -5200,10 +5188,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 bitwise operator &= on pointer",
-                .errstr = "invalid mem access 'inv'",
+                .errstr = "R0 bitwise operator &= on pointer",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "map element value illegal alu op, 2",
@@ -5219,10 +5205,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 32-bit pointer arithmetic prohibited",
-                .errstr = "invalid mem access 'inv'",
+                .errstr = "R0 32-bit pointer arithmetic prohibited",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "map element value illegal alu op, 3",
@@ -5238,10 +5222,8 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map2 = { 3 },
-                .errstr_unpriv = "R0 pointer arithmetic with /= operator",
-                .errstr = "invalid mem access 'inv'",
+                .errstr = "R0 pointer arithmetic with /= operator",
                 .result = REJECT,
-                .result_unpriv = REJECT,
         },
         {
                 "map element value illegal alu op, 4",
@@ -5350,7 +5332,7 @@ 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,
         },
@@ -5505,7 +5487,7 @@ 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,
         },
@@ -5636,7 +5618,7 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
         {
-                "helper access to variable memory: size = 0 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),
@@ -5650,7 +5632,7 @@ static struct bpf_test tests[] = {
                 .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 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),
@@ -5668,7 +5650,7 @@ static struct bpf_test tests[] = {
                 .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),
@@ -5681,11 +5663,201 @@ 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),
@@ -5834,8 +6006,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map_in_map = { 3 },
-                .errstr = "R1 type=inv expected=map_ptr",
-                .errstr_unpriv = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited",
+                .errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited",
                 .result = REJECT,
         },
         {
@@ -5932,6 +6103,30 @@ static struct bpf_test tests[] = {
                 .result = ACCEPT,
         },
         {
+                "ld_abs: tests on r6 and skb data reload helper",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+                        BPF_LD_ABS(BPF_B, 0),
+                        BPF_LD_ABS(BPF_H, 0),
+                        BPF_LD_ABS(BPF_W, 0),
+                        BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+                        BPF_MOV64_IMM(BPF_REG_6, 0),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+                        BPF_MOV64_IMM(BPF_REG_2, 1),
+                        BPF_MOV64_IMM(BPF_REG_3, 2),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_skb_vlan_push),
+                        BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+                        BPF_LD_ABS(BPF_B, 0),
+                        BPF_LD_ABS(BPF_H, 0),
+                        BPF_LD_ABS(BPF_W, 0),
+                        BPF_MOV64_IMM(BPF_REG_0, 42),
+                        BPF_EXIT_INSN(),
+                },
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+                .result = ACCEPT,
+        },
+        {
                 "ld_ind: check calling conv, r1",
                 .insns = {
                         BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
@@ -6115,7 +6310,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6139,7 +6334,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6165,7 +6360,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R8 invalid mem access 'inv'",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6190,7 +6385,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R8 invalid mem access 'inv'",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6238,7 +6433,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6309,7 +6504,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6360,7 +6555,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6387,7 +6582,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6413,7 +6608,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6442,7 +6637,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6472,7 +6667,7 @@ static struct bpf_test tests[] = {
                         BPF_JMP_IMM(BPF_JA, 0, 0, -7),
                 },
                 .fixup_map1 = { 4 },
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
         },
         {
@@ -6500,8 +6695,7 @@ static struct bpf_test tests[] = {
                         BPF_EXIT_INSN(),
                 },
                 .fixup_map1 = { 3 },
-                .errstr_unpriv = "R0 pointer comparison prohibited",
-                .errstr = "R0 min value is negative",
+                .errstr = "unbounded min value",
                 .result = REJECT,
                 .result_unpriv = REJECT,
         },
@@ -6557,6 +6751,462 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
         },
         {
+                "bounds check based on zero-extended MOV",
+                .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, 4),
+                        /* r2 = 0x0000'0000'ffff'ffff */
+                        BPF_MOV32_IMM(BPF_REG_2, 0xffffffff),
+                        /* r2 = 0 */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32),
+                        /* no-op */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
+                        /* access at offset 0 */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT
+        },
+        {
+                "bounds check based on sign-extended MOV. test1",
+                .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, 4),
+                        /* r2 = 0xffff'ffff'ffff'ffff */
+                        BPF_MOV64_IMM(BPF_REG_2, 0xffffffff),
+                        /* r2 = 0xffff'ffff */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32),
+                        /* r0 = <oob pointer> */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
+                        /* access to OOB pointer */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "map_value pointer and 4294967295",
+                .result = REJECT
+        },
+        {
+                "bounds check based on sign-extended MOV. test2",
+                .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, 4),
+                        /* r2 = 0xffff'ffff'ffff'ffff */
+                        BPF_MOV64_IMM(BPF_REG_2, 0xffffffff),
+                        /* r2 = 0xfff'ffff */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36),
+                        /* r0 = <oob pointer> */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
+                        /* access to OOB pointer */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "R0 min value is outside of the array range",
+                .result = REJECT
+        },
+        {
+                "bounds check based on reg_off + var_off + insn_off. test1",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+                                    offsetof(struct __sk_buff, mark)),
+                        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, 4),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 29) - 1),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 4 },
+                .errstr = "value_size=8 off=1073741825",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "bounds check based on reg_off + var_off + insn_off. test2",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+                                    offsetof(struct __sk_buff, mark)),
+                        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, 4),
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 30) - 1),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1),
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 4 },
+                .errstr = "value 1073741823",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "bounds check after truncation of non-boundary-crossing range",
+                .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),
+                        /* r1 = [0x00, 0xff] */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_MOV64_IMM(BPF_REG_2, 1),
+                        /* r2 = 0x10'0000'0000 */
+                        BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 36),
+                        /* r1 = [0x10'0000'0000, 0x10'0000'00ff] */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
+                        /* r1 = [0x10'7fff'ffff, 0x10'8000'00fe] */
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
+                        /* r1 = [0x00, 0xff] */
+                        BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 0x7fffffff),
+                        /* r1 = 0 */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
+                        /* no-op */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        /* access at offset 0 */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT
+        },
+        {
+                "bounds check after truncation of boundary-crossing range (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),
+                        /* r1 = [0x00, 0xff] */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = [0xffff'ff80, 0x1'0000'007f] */
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = [0xffff'ff80, 0xffff'ffff] or
+                         *      [0x0000'0000, 0x0000'007f]
+                         */
+                        BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 0),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = [0x00, 0xff] or
+                         *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
+                         */
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = 0 or
+                         *      [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
+                         */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
+                        /* no-op or OOB pointer computation */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        /* potentially OOB access */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                /* not actually fully unbounded, but the bound is very high */
+                .errstr = "R0 unbounded memory access",
+                .result = REJECT
+        },
+        {
+                "bounds check after truncation of boundary-crossing range (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, 9),
+                        /* r1 = [0x00, 0xff] */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = [0xffff'ff80, 0x1'0000'007f] */
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = [0xffff'ff80, 0xffff'ffff] or
+                         *      [0x0000'0000, 0x0000'007f]
+                         * difference to previous test: truncation via MOV32
+                         * instead of ALU32.
+                         */
+                        BPF_MOV32_REG(BPF_REG_1, BPF_REG_1),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = [0x00, 0xff] or
+                         *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
+                         */
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
+                        /* r1 = 0 or
+                         *      [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
+                         */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
+                        /* no-op or OOB pointer computation */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        /* potentially OOB access */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                /* not actually fully unbounded, but the bound is very high */
+                .errstr = "R0 unbounded memory access",
+                .result = REJECT
+        },
+        {
+                "bounds check after wrapping 32-bit addition",
+                .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, 5),
+                        /* r1 = 0x7fff'ffff */
+                        BPF_MOV64_IMM(BPF_REG_1, 0x7fffffff),
+                        /* r1 = 0xffff'fffe */
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
+                        /* r1 = 0 */
+                        BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 2),
+                        /* no-op */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        /* access at offset 0 */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT
+        },
+        {
+                "bounds check after shift with oversized count operand",
+                .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_IMM(BPF_REG_2, 32),
+                        BPF_MOV64_IMM(BPF_REG_1, 1),
+                        /* r1 = (u32)1 << (u32)32 = ? */
+                        BPF_ALU32_REG(BPF_LSH, BPF_REG_1, BPF_REG_2),
+                        /* r1 = [0x0000, 0xffff] */
+                        BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xffff),
+                        /* computes unknown pointer, potentially OOB */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        /* potentially OOB access */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        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
+        },
+        {
+                "bounds check after right shift of maybe-negative number",
+                .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),
+                        /* r1 = [0x00, 0xff] */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        /* r1 = [-0x01, 0xfe] */
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+                        /* r1 = 0 or 0xff'ffff'ffff'ffff */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
+                        /* r1 = 0 or 0xffff'ffff'ffff */
+                        BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
+                        /* computes unknown pointer, potentially OOB */
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        /* potentially OOB access */
+                        BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+                        /* exit */
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "R0 unbounded memory access",
+                .result = REJECT
+        },
+        {
+                "bounds check map access with off+size signed 32bit overflow. test1",
+                .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_JNE, BPF_REG_0, 0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7ffffffe),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_JMP_A(0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "map_value pointer and 2147483646",
+                .result = REJECT
+        },
+        {
+                "bounds check map access with off+size signed 32bit overflow. test2",
+                .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_JNE, BPF_REG_0, 0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_JMP_A(0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "pointer offset 1073741822",
+                .result = REJECT
+        },
+        {
+                "bounds check map access with off+size signed 32bit overflow. test3",
+                .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_JNE, BPF_REG_0, 0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff),
+                        BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2),
+                        BPF_JMP_A(0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "pointer offset -1073741822",
+                .result = REJECT
+        },
+        {
+                "bounds check map access with off+size signed 32bit overflow. test4",
+                .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_JNE, BPF_REG_0, 0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_1, 1000000),
+                        BPF_ALU64_IMM(BPF_MUL, BPF_REG_1, 1000000),
+                        BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2),
+                        BPF_JMP_A(0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .errstr = "map_value pointer and 1000000000000",
+                .result = REJECT
+        },
+        {
+                "pointer/scalar confusion in state equality check (way 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, 2),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_JMP_A(1),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+                        BPF_JMP_A(0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+                .errstr_unpriv = "R0 leaks addr as return value"
+        },
+        {
+                "pointer/scalar confusion in state equality check (way 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_JNE, BPF_REG_0, 0, 2),
+                        BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+                        BPF_JMP_A(1),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = ACCEPT,
+                .result_unpriv = REJECT,
+                .errstr_unpriv = "R0 leaks addr as return value"
+        },
+        {
                 "variable-offset ctx access",
                 .insns = {
                         /* Get an unknown value */
@@ -6598,6 +7248,71 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_LWT_IN,
         },
         {
+                "indirect 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 indirectly */
+                        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_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 5 },
+                .errstr = "variable stack read R2",
+                .result = REJECT,
+                .prog_type = BPF_PROG_TYPE_LWT_IN,
+        },
+        {
+                "direct stack access with 32-bit wraparound. test1",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
+                        BPF_MOV32_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_EXIT_INSN()
+                },
+                .errstr = "fp pointer and 2147483647",
+                .result = REJECT
+        },
+        {
+                "direct stack access with 32-bit wraparound. test2",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff),
+                        BPF_MOV32_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_EXIT_INSN()
+                },
+                .errstr = "fp pointer and 1073741823",
+                .result = REJECT
+        },
+        {
+                "direct stack access with 32-bit wraparound. test3",
+                .insns = {
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff),
+                        BPF_MOV32_IMM(BPF_REG_0, 0),
+                        BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+                        BPF_EXIT_INSN()
+                },
+                .errstr = "fp pointer offset 1073741822",
+                .result = REJECT
+        },
+        {
                 "liveness pruning and write screening",
                 .insns = {
                         /* Get an unknown value */
@@ -6658,6 +7373,253 @@ static struct bpf_test tests[] = {
                 .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,
@@ -6672,6 +7634,19 @@ static struct bpf_test tests[] = {
                 .prog_type = BPF_PROG_TYPE_SCHED_CLS,
         },
         {
+                "pkt_end - pkt_start is allowed",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data_end)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct __sk_buff, data)),
+                        BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2),
+                        BPF_EXIT_INSN(),
+                },
+                .result = ACCEPT,
+                .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,
@@ -6686,7 +7661,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "R1 offset is outside of the packet",
+                .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_XDP,
         },
@@ -6705,7 +7680,7 @@ static struct bpf_test tests[] = {
                         BPF_MOV64_IMM(BPF_REG_0, 0),
                         BPF_EXIT_INSN(),
                 },
-                .errstr = "R1 offset is outside of the packet",
+                .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_XDP,
         },
@@ -7151,6 +8126,520 @@ static struct bpf_test tests[] = {
                 .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)
@@ -7198,7 +8687,7 @@ 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..e9626cf5607a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_verifier_log.c
@@ -0,0 +1,178 @@
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/time.h>
+#include <sys/resource.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)
+{
+        struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
+        char full_log[LOG_SIZE];
+        char log[LOG_SIZE];
+        size_t want_len;
+        int i;
+
+        /* allow unlimited locked memory to have more consistent error code */
+        if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0)
+                perror("Unable to lift memlock rlimit");
+
+        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/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/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/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/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh
index a52a3bab532b..34a42c68ebfb 100755
--- a/tools/testing/selftests/firmware/fw_fallback.sh
+++ b/tools/testing/selftests/firmware/fw_fallback.sh
@@ -86,6 +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"
 
@@ -108,11 +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"
 
@@ -133,6 +144,7 @@ load_fw_custom_cancel()
 
         # Wait for request to finish.
         wait
+        return 0
 }
 
 load_fw_fallback_with_child()
@@ -227,20 +239,22 @@ 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
-else
-        echo "$0: cancelling custom fallback mechanism works"
+if load_fw_custom_cancel "nope-$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
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 62f2d6f54929..b1f20fef36c7 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -70,9 +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.
@@ -105,17 +109,21 @@ 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
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 abc706cf7702..f9a9d424c980 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -222,7 +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))
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 6ff851a75884..9daf034186f5 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -11,7 +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 cc14feec6e1f..132478b305c2 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -13,7 +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 85094904aa79..6a37a8642ee6 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -11,7 +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 cc1cf4d30ef5..4e9b6e2c0219 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -10,7 +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 45df747887e0..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
@@ -28,7 +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 0387e22e7577..9f8d27ca39cf 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -18,7 +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-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 78524fcc25ae..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
@@ -51,7 +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 9d4afcca1e36..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
@@ -27,7 +27,7 @@ do_reset() {
 fail() { # mesg
     do_reset
     echo $1
-    exit $FAIL
+    exit_fail
 }
 
 SLEEP_TIME=".1"
@@ -48,8 +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 fe0dc5a7ea26..b2d5a8febfe8 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -32,7 +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 5ad723724adb..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
@@ -26,14 +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 cdc92a371cd7..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
@@ -27,7 +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 d7f48b55df51..4fa0f79144f4 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc
@@ -11,7 +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 ddda62203366..b84651283bf3 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
@@ -11,7 +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/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index 0e6f415c6152..bbc443a9190c 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -9,7 +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 679bbd23bcc3..8b43c6804fc3 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -14,5 +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 17d33ba192f6..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
@@ -35,4 +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/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index f1825bdbe3f3..321954683aaa 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -14,4 +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/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 839ac4320b24..28cc355a3a7b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
@@ -12,7 +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 66873c4b12c9..a48e23eb8a8b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
@@ -12,7 +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 4237b32769f1..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
@@ -12,7 +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 d24e2b8bd863..449fe9ff91a2 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -12,7 +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 4c0774fff378..c5ef8b9d02b3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -12,7 +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 3fc6321e081f..ed38f0050d77 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
@@ -11,7 +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 3652824f81ed..3121d795a868 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
@@ -11,7 +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 6d9051cdf408..c59d9eb546da 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
@@ -11,7 +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/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 845e5f67b6f0..132a54f74e88 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -515,7 +515,7 @@ static void mfd_assert_grow_write(int fd)
 
         buf = malloc(mfd_def_size * 8);
         if (!buf) {
-                printf("malloc(%d) failed: %m\n", mfd_def_size * 8);
+                printf("malloc(%zu) failed: %m\n", mfd_def_size * 8);
                 abort();
         }
 
@@ -535,7 +535,7 @@ static void mfd_fail_grow_write(int fd)
 
         buf = malloc(mfd_def_size * 8);
         if (!buf) {
-                printf("malloc(%d) failed: %m\n", mfd_def_size * 8);
+                printf("malloc(%zu) failed: %m\n", mfd_def_size * 8);
                 abort();
         }
 
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 23db11c94b59..86636d207adf 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -4,10 +4,10 @@ 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/net/config b/tools/testing/selftests/net/config
index e57b4ac40e72..7177bea1fdfa 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -1,3 +1,4 @@
 CONFIG_USER_NS=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_TEST_BPF=m
+CONFIG_NUMA=y
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 57b5ff576240..5215493166c9 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -15,6 +15,14 @@ check_err()
         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
@@ -29,6 +37,26 @@ kci_del_dummy()
         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()
 {
@@ -55,6 +83,11 @@ kci_test_bridge()
         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 $?
 
@@ -92,6 +125,9 @@ kci_test_gre()
         check_err $?
         ip addr > /dev/null
         check_err $?
+
+        kci_test_netconf "$gredev"
+
         ip addr del dev "$devdummy" 10.23.7.11/24
         check_err $?
 
@@ -235,6 +271,237 @@ kci_test_addrlabel()
         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
@@ -249,6 +516,10 @@ kci_test_rtnl()
         kci_test_gre
         kci_test_bridge
         kci_test_addrlabel
+        kci_test_ifalias
+        kci_test_vrf
+        kci_test_encap
+        kci_test_macsec
 
         kci_del_dummy
 }
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/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/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 fca7c7f5e640..8ed6f8c57230 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -3,7 +3,7 @@ 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
@@ -17,6 +17,7 @@ $(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-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/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh
index 49fa51726ce3..ef7fcbac3d42 100755
--- a/tools/testing/selftests/rcutorture/bin/config_override.sh
+++ b/tools/testing/selftests/rcutorture/bin/config_override.sh
@@ -42,7 +42,7 @@ else
         exit 1
 fi
 
-T=/tmp/config_override.sh.$$
+T=${TMPDIR-/tmp}/config_override.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
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/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 46752c164676..fb66d0173638 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -35,7 +35,7 @@ then
         exit 1
 fi
 
-T=/tmp/test-linux.sh.$$
+T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
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 0af36a721b9c..ab14b97c942c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -38,7 +38,7 @@
 #
 # 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
 mkdir $T
 
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index b55895fb10ed..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
 
@@ -222,7 +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 '
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/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
index be3fdd351937..3f95a768a03b 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
@@ -35,8 +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/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/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 6973bdc5b5bf..000000000000
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json
+++ /dev/null
@@ -1,1165 +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": [
-            "$TC actions flush action gact"
-        ]
-    },
-    {
-        "id": "a568",
-        "name": "Add action with ife type",
-        "category": [
-            "actions",
-            "ife"
-        ],
-        "setup": [
-            [
-                "$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"
-        ]
-    }
-]
\ 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 b8462e1b74f9..fc373fdf2bdc 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -50,7 +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")
@@ -180,15 +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
 
 
@@ -210,7 +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')
@@ -367,10 +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:")
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index eb188c729dd6..a023d0d62b25 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -18,3 +18,17 @@ NAMES = {
           # 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 ccf2d2458703..db381120a566 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -16,7 +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))
 
 
@@ -58,7 +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/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 e49eca1915f8..7f45806bd863 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -18,6 +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/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/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 7b1adeee4b0f..939a337128db 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -11,7 +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)
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/mpx-hw.h b/tools/testing/selftests/x86/mpx-hw.h
index 3f0093911f03..d1b61ab870f8 100644
--- a/tools/testing/selftests/x86/mpx-hw.h
+++ b/tools/testing/selftests/x86/mpx-hw.h
@@ -52,14 +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/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
index 3818f25391c2..b3cb7670e026 100644
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ b/tools/testing/selftests/x86/pkey-helpers.h
@@ -30,6 +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);
@@ -39,7 +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 7a1cc0e56d2d..bc1b0735bb50 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -250,7 +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;
@@ -292,9 +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) ||
@@ -306,7 +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/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 21169322baea..735a510230c3 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -1,10 +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+=
@@ -19,12 +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/usb/usbip/Makefile.am b/tools/usb/usbip/Makefile.am
index da3a430849a8..5961e9c18812 100644
--- a/tools/usb/usbip/Makefile.am
+++ b/tools/usb/usbip/Makefile.am
@@ -2,6 +2,7 @@
 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/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
index 5727dfb15a83..c9c81614a66a 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.c
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -50,14 +50,14 @@ static int parse_status(const char *value)
 
         while (*c != '\0') {
                 int port, status, speed, devid;
-                unsigned long socket;
+                int sockfd;
                 char lbusid[SYSFS_BUS_ID_SIZE];
                 struct usbip_imported_device *idev;
                 char hub[3];
 
-                ret = sscanf(c, "%2s  %d %d %d %x %lx %31s\n",
+                ret = sscanf(c, "%2s  %d %d %d %x %u %31s\n",
                                 hub, &port, &status, &speed,
-                                &devid, &socket, lbusid);
+                                &devid, &sockfd, lbusid);
 
                 if (ret < 5) {
                         dbg("sscanf failed: %d", ret);
@@ -66,7 +66,7 @@ static int parse_status(const char *value)
 
                 dbg("hub %s port %d status %d speed %d devid %x",
                                 hub, port, status, speed, devid);
-                dbg("socket %lx lbusid %s", socket, lbusid);
+                dbg("sockfd %u lbusid %s", sockfd, lbusid);
 
                 /* if a device is connected, look at it */
                 idev = &vhci_driver->idev[port];
@@ -106,7 +106,7 @@ static int parse_status(const char *value)
         return 0;
 }
 
-#define MAX_STATUS_NAME 16
+#define MAX_STATUS_NAME 18
 
 static int refresh_imported_device_list(void)
 {
@@ -329,9 +329,17 @@ err:
 int usbip_vhci_get_free_port(uint32_t speed)
 {
         for (int i = 0; i < vhci_driver->nports; i++) {
-                if (speed == USB_SPEED_SUPER &&
-                    vhci_driver->idev[i].hub != HUB_SPEED_SUPER)
-                        continue;
+
+                switch (speed) {
+                case    USB_SPEED_SUPER:
+                        if (vhci_driver->idev[i].hub != HUB_SPEED_SUPER)
+                                continue;
+                break;
+                default:
+                        if (vhci_driver->idev[i].hub != HUB_SPEED_HIGH)
+                                continue;
+                break;
+                }
 
                 if (vhci_driver->idev[i].status == VDEV_ST_NULL)
                         return vhci_driver->idev[i].port;
diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c
index 2b3d6d235015..3d7b42e77299 100644
--- a/tools/usb/usbip/src/utils.c
+++ b/tools/usb/usbip/src/utils.c
@@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add)
         char command[SYSFS_BUS_ID_SIZE + 4];
         char match_busid_attr_path[SYSFS_PATH_MAX];
         int rc;
+        int cmd_size;
 
         snprintf(match_busid_attr_path, sizeof(match_busid_attr_path),
                  "%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME,
@@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add)
                  attr_name);
 
         if (add)
-                snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid);
+                cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s",
+                                    busid);
         else
-                snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid);
+                cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s",
+                                    busid);
 
         rc = write_sysfs_attribute(match_busid_attr_path, command,
-                                   sizeof(command));
+                                   cmd_size);
         if (rc < 0) {
                 dbg("failed to write match_busid: %s", strerror(errno));
                 return -1;
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/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index 38bb171aceba..e6e81305ef46 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -16,24 +16,41 @@
 #define unlikely(x)    (__builtin_expect(!!(x), 0))
 #define likely(x)    (__builtin_expect(!!(x), 1))
 #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a))
+#define SIZE_MAX        (~(size_t)0)
+
 typedef pthread_spinlock_t  spinlock_t;
 
 typedef int gfp_t;
-static void *kmalloc(unsigned size, gfp_t gfp)
-{
-        return memalign(64, size);
-}
+#define __GFP_ZERO 0x1
 
-static void *kzalloc(unsigned size, gfp_t gfp)
+static void *kmalloc(unsigned size, gfp_t gfp)
 {
         void *p = memalign(64, size);
         if (!p)
                 return p;
-        memset(p, 0, size);
 
+        if (gfp & __GFP_ZERO)
+                memset(p, 0, size);
         return p;
 }
 
+static inline void *kzalloc(unsigned size, gfp_t flags)
+{
+        return kmalloc(size, flags | __GFP_ZERO);
+}
+
+static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
+{
+        if (size != 0 && n > SIZE_MAX / size)
+                return NULL;
+        return kmalloc(n * size, flags);
+}
+
+static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
+{
+        return kmalloc_array(n, size, flags | __GFP_ZERO);
+}
+
 static void kfree(void *p)
 {
         if (p)
diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/vm/slabinfo-gnuplot.sh
index 35b039864b77..0cf28aa6f21c 100644
--- a/tools/vm/slabinfo-gnuplot.sh
+++ b/tools/vm/slabinfo-gnuplot.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 
 # Sergey Senozhatsky, 2015
 # sergey.senozhatsky.work@gmail.com
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index b0b7ef6d0de1..f82c2eaa859d 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -84,6 +84,7 @@ int output_lines = -1;
 int sort_loss;
 int extended_totals;
 int show_bytes;
+int unreclaim_only;
 
 /* Debug options */
 int sanity;
@@ -133,6 +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"
@@ -569,6 +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;
@@ -1347,6 +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 }
 };
 
@@ -1358,7 +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':
@@ -1439,6 +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;
+}