Merge tag 'misc-habanalabs-fixes-2019-03-26' of git://people.freedesktop.org/~gabbayo/linux into char-misc-next:

Oded writes: The following bug fixes are included in this tag: - Fix host crash upon resume after suspend - Fix MMU related bugs which result in user's jobs getting stuck - Fix race between user context cleanup and hard-reset which results in host crash - Fix sparse warning * tag 'misc-habanalabs-fixes-2019-03-26' of git://people.freedesktop.org/~gabbayo/linux: (265 commits) habanalabs: cast to expected type habanalabs: prevent host crash during suspend/resume habanalabs: perform accounting for active CS habanalabs: fix mapping with page size bigger than 4KB habanalabs: complete user context cleanup before hard reset habanalabs: fix bug when mapping very large memory area habanalabs: fix MMU number of pages calculation Linux 5.1-rc2 clocksource/drivers/clps711x: Remove board support ext4: prohibit fstrim in norecovery mode ext4: cleanup bh release code in ext4_ind_remove_space() ext4: brelse all indirect buffer in ext4_ind_remove_space() genirq: Mark expected switch case fall-through clocksource/drivers/riscv: Fix clocksource mask x86/gart: Exclude GART aperture from kcore cifs: update internal module version number SMB3: Fix SMB3.1.1 guest mounts to Samba cifs: Fix slab-out-of-bounds when tracing SMB tcon cifs: allow guest mounts to work for smb3.11 fix incorrect error code mapping for OBJECTID_NOT_FOUND ...
author: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 2019-03-26 04:17:40 -0400
committer: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 2019-03-26 04:17:40 -0400
commit: 80045e14423aaf1d3d51bca0524336f8a624003e (patch)
tree: 915319f6d353a2e8c1f69a16502e61d6020f3bc4
parent: 5cec2d2e5839f9c0fec319c523a911e0a7fd299f (diff)
parent: 7c22278edd0a931c565a8511dfc1bc57ffbb9166 (diff)
303 files changed, 5561 insertions, 2694 deletions
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
index 8de96a4fb2d5..f977ea7617f6 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -16,6 +16,7 @@ Required properties:
    - "renesas,irqc-r8a7793" (R-Car M2-N)
    - "renesas,irqc-r8a7794" (R-Car E2)
    - "renesas,intc-ex-r8a774a1" (RZ/G2M)
+    - "renesas,intc-ex-r8a774c0" (RZ/G2E)
    - "renesas,intc-ex-r8a7795" (R-Car H3)
    - "renesas,intc-ex-r8a7796" (R-Car M3-W)
    - "renesas,intc-ex-r8a77965" (R-Car M3-N)
diff --git a/MAINTAINERS b/MAINTAINERS
index e17ebf70b548..3e5a5d263f29 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8096,6 +8096,16 @@ F:	include/linux/iommu.h
 F:      include/linux/of_iommu.h
 F:      include/linux/iova.h
+IO_URING
+M:      Jens Axboe <axboe@kernel.dk>
+L:      linux-block@vger.kernel.org
+L:      linux-fsdevel@vger.kernel.org
+T:      git git://git.kernel.dk/linux-block
+T:      git git://git.kernel.dk/liburing
+S:      Maintained
+F:      fs/io_uring.c
+F:      include/uapi/linux/io_uring.h
 IP MASQUERADING
 M:      Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar>
 S:      Maintained
diff --git a/Makefile b/Makefile
index 99c0530489ef..c0a34064c574 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Shy Crocodile
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index df55672c59e6..c781e45d1d99 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -144,11 +144,11 @@ config ARC_CPU_770
          Support for ARC770 core introduced with Rel 4.10 (Summer 2011)
          This core has a bunch of cool new features:
          -MMU-v3: Variable Page Sz (4k, 8k, 16k), bigger J-TLB (128x4)
-                   Shared Address Spaces (for sharing TLB entries in MMU)
+                   Shared Address Spaces (for sharing TLB entries in MMU)
          -Caches: New Prog Model, Region Flush
          -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
-endif   #ISA_ARCOMPACT
+endif #ISA_ARCOMPACT
 config ARC_CPU_HS
        bool "ARC-HS"
@@ -198,7 +198,7 @@ config ARC_SMP_HALT_ON_RESET
          at designated entry point. For other case, all jump to common
          entry point and spin wait for Master's signal.
-endif   #SMP
+endif #SMP
 config ARC_MCIP
        bool "ARConnect Multicore IP (MCIP) Support "
@@ -249,7 +249,7 @@ config ARC_CACHE_VIPT_ALIASING
        bool "Support VIPT Aliasing D$"
        depends on ARC_HAS_DCACHE && ISA_ARCOMPACT
-endif   #ARC_CACHE
+endif #ARC_CACHE
 config ARC_HAS_ICCM
        bool "Use ICCM"
@@ -370,7 +370,7 @@ config ARC_FPU_SAVE_RESTORE
          based on actual usage of FPU by a task. Thus our implemn does
          this for all tasks in system.
-endif   #ISA_ARCOMPACT
+endif #ISA_ARCOMPACT
 config ARC_CANT_LLSC
        def_bool n
@@ -386,6 +386,15 @@ config ARC_HAS_SWAPE
 if ISA_ARCV2
+config ARC_USE_UNALIGNED_MEM_ACCESS
+        bool "Enable unaligned access in HW"
+        default y
+        select HAVE_EFFICIENT_UNALIGNED_ACCESS
+        help
+          The ARC HS architecture supports unaligned memory access
+          which is disabled by default. Enable unaligned access in
+          hardware and use software to use it
 config ARC_HAS_LL64
        bool "Insn: 64bit LDD/STD"
        help
@@ -414,7 +423,7 @@ config ARC_IRQ_NO_AUTOSAVE
          This is programmable and can be optionally disabled in which case
          software INTERRUPT_PROLOGUE/EPILGUE do the needed work
-endif   # ISA_ARCV2
+endif # ISA_ARCV2
 endmenu   # "ARC CPU Configuration"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index df00578c279d..e2b991f75bc5 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -28,6 +28,12 @@ cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 ifdef CONFIG_ISA_ARCV2
+ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+cflags-y                                += -munaligned-access
+else
+cflags-y                                += -mno-unaligned-access
+endif
 ifndef CONFIG_ARC_HAS_LL64
 cflags-y                                += -mno-ll64
 endif
diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi
index 02410b211433..c0bcd97522bb 100644
--- a/arch/arc/boot/dts/abilis_tb100.dtsi
+++ b/arch/arc/boot/dts/abilis_tb100.dtsi
@@ -38,7 +38,7 @@
                        clock-div = <6>;
                };
-                iomux: iomux@FF10601c {
+                iomux: iomux@ff10601c {
                        /* Port 1 */
                        pctl_tsin_s0: pctl-tsin-s0 {   /* Serial TS-in 0 */
                                abilis,function = "mis0";
@@ -162,182 +162,182 @@
                        };
                };
-                gpioa: gpio@FF140000 {
+                gpioa: gpio@ff140000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF140000 0x1000>;
+                        reg = <0xff140000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioa";
                };
-                gpiob: gpio@FF141000 {
+                gpiob: gpio@ff141000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF141000 0x1000>;
+                        reg = <0xff141000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiob";
                };
-                gpioc: gpio@FF142000 {
+                gpioc: gpio@ff142000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF142000 0x1000>;
+                        reg = <0xff142000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioc";
                };
-                gpiod: gpio@FF143000 {
+                gpiod: gpio@ff143000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF143000 0x1000>;
+                        reg = <0xff143000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiod";
                };
-                gpioe: gpio@FF144000 {
+                gpioe: gpio@ff144000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF144000 0x1000>;
+                        reg = <0xff144000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioe";
                };
-                gpiof: gpio@FF145000 {
+                gpiof: gpio@ff145000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF145000 0x1000>;
+                        reg = <0xff145000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiof";
                };
-                gpiog: gpio@FF146000 {
+                gpiog: gpio@ff146000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF146000 0x1000>;
+                        reg = <0xff146000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiog";
                };
-                gpioh: gpio@FF147000 {
+                gpioh: gpio@ff147000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF147000 0x1000>;
+                        reg = <0xff147000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioh";
                };
-                gpioi: gpio@FF148000 {
+                gpioi: gpio@ff148000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF148000 0x1000>;
+                        reg = <0xff148000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <12>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioi";
                };
-                gpioj: gpio@FF149000 {
+                gpioj: gpio@ff149000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF149000 0x1000>;
+                        reg = <0xff149000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <32>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioj";
                };
-                gpiok: gpio@FF14a000 {
+                gpiok: gpio@ff14a000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14A000 0x1000>;
+                        reg = <0xff14a000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <22>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiok";
                };
-                gpiol: gpio@FF14b000 {
+                gpiol: gpio@ff14b000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14B000 0x1000>;
+                        reg = <0xff14b000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <4>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiol";
                };
-                gpiom: gpio@FF14c000 {
+                gpiom: gpio@ff14c000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14C000 0x1000>;
+                        reg = <0xff14c000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <4>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiom";
                };
-                gpion: gpio@FF14d000 {
+                gpion: gpio@ff14d000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14D000 0x1000>;
+                        reg = <0xff14d000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <5>;
diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts
index 3acf04db8030..c968e677db46 100644
--- a/arch/arc/boot/dts/abilis_tb100_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts
@@ -37,27 +37,27 @@
        };
        soc100 {
-                uart@FF100000 {
+                uart@ff100000 {
                        pinctrl-names = "default";
                        pinctrl-0 = <&pctl_uart0>;
                };
-                ethernet@FE100000 {
+                ethernet@fe100000 {
                        phy-mode = "rgmii";
                };
-                i2c0: i2c@FF120000 {
+                i2c0: i2c@ff120000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c1: i2c@FF121000 {
+                i2c1: i2c@ff121000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c2: i2c@FF122000 {
+                i2c2: i2c@ff122000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c3: i2c@FF123000 {
+                i2c3: i2c@ff123000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c4: i2c@FF124000 {
+                i2c4: i2c@ff124000 {
                        i2c-sda-hold-time-ns = <432>;
                };
diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi
index f9e7686044eb..6a1615f58f05 100644
--- a/arch/arc/boot/dts/abilis_tb101.dtsi
+++ b/arch/arc/boot/dts/abilis_tb101.dtsi
@@ -38,7 +38,7 @@
                        clock-div = <6>;
                };
-                iomux: iomux@FF10601c {
+                iomux: iomux@ff10601c {
                        /* Port 1 */
                        pctl_tsin_s0: pctl-tsin-s0 {   /* Serial TS-in 0 */
                                abilis,function = "mis0";
@@ -171,182 +171,182 @@
                        };
                };
-                gpioa: gpio@FF140000 {
+                gpioa: gpio@ff140000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF140000 0x1000>;
+                        reg = <0xff140000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioa";
                };
-                gpiob: gpio@FF141000 {
+                gpiob: gpio@ff141000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF141000 0x1000>;
+                        reg = <0xff141000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiob";
                };
-                gpioc: gpio@FF142000 {
+                gpioc: gpio@ff142000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF142000 0x1000>;
+                        reg = <0xff142000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioc";
                };
-                gpiod: gpio@FF143000 {
+                gpiod: gpio@ff143000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF143000 0x1000>;
+                        reg = <0xff143000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiod";
                };
-                gpioe: gpio@FF144000 {
+                gpioe: gpio@ff144000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF144000 0x1000>;
+                        reg = <0xff144000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioe";
                };
-                gpiof: gpio@FF145000 {
+                gpiof: gpio@ff145000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF145000 0x1000>;
+                        reg = <0xff145000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiof";
                };
-                gpiog: gpio@FF146000 {
+                gpiog: gpio@ff146000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF146000 0x1000>;
+                        reg = <0xff146000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <3>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiog";
                };
-                gpioh: gpio@FF147000 {
+                gpioh: gpio@ff147000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF147000 0x1000>;
+                        reg = <0xff147000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <2>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioh";
                };
-                gpioi: gpio@FF148000 {
+                gpioi: gpio@ff148000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF148000 0x1000>;
+                        reg = <0xff148000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <12>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioi";
                };
-                gpioj: gpio@FF149000 {
+                gpioj: gpio@ff149000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF149000 0x1000>;
+                        reg = <0xff149000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <32>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpioj";
                };
-                gpiok: gpio@FF14a000 {
+                gpiok: gpio@ff14a000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14A000 0x1000>;
+                        reg = <0xff14a000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <22>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiok";
                };
-                gpiol: gpio@FF14b000 {
+                gpiol: gpio@ff14b000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14B000 0x1000>;
+                        reg = <0xff14b000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <4>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiol";
                };
-                gpiom: gpio@FF14c000 {
+                gpiom: gpio@ff14c000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14C000 0x1000>;
+                        reg = <0xff14c000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <4>;
                        gpio-ranges = <&iomux 0 0 0>;
                        gpio-ranges-group-names = "gpiom";
                };
-                gpion: gpio@FF14d000 {
+                gpion: gpio@ff14d000 {
                        compatible = "abilis,tb10x-gpio";
                        interrupt-controller;
                        #interrupt-cells = <1>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <27 2>;
-                        reg = <0xFF14D000 0x1000>;
+                        reg = <0xff14d000 0x1000>;
                        gpio-controller;
                        #gpio-cells = <2>;
                        abilis,ngpio = <5>;
diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts
index 37d88c5dd181..05143ce9c120 100644
--- a/arch/arc/boot/dts/abilis_tb101_dvk.dts
+++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts
@@ -37,27 +37,27 @@
        };
        soc100 {
-                uart@FF100000 {
+                uart@ff100000 {
                        pinctrl-names = "default";
                        pinctrl-0 = <&pctl_uart0>;
                };
-                ethernet@FE100000 {
+                ethernet@fe100000 {
                        phy-mode = "rgmii";
                };
-                i2c0: i2c@FF120000 {
+                i2c0: i2c@ff120000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c1: i2c@FF121000 {
+                i2c1: i2c@ff121000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c2: i2c@FF122000 {
+                i2c2: i2c@ff122000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c3: i2c@FF123000 {
+                i2c3: i2c@ff123000 {
                        i2c-sda-hold-time-ns = <432>;
                };
-                i2c4: i2c@FF124000 {
+                i2c4: i2c@ff124000 {
                        i2c-sda-hold-time-ns = <432>;
                };
diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi
index 3121536b25a3..2fbf1bdfe6de 100644
--- a/arch/arc/boot/dts/abilis_tb10x.dtsi
+++ b/arch/arc/boot/dts/abilis_tb10x.dtsi
@@ -54,7 +54,7 @@
                #size-cells     = <1>;
                device_type     = "soc";
                ranges          = <0xfe000000 0xfe000000 0x02000000
-                                0x000F0000 0x000F0000 0x00010000>;
+                                0x000f0000 0x000f0000 0x00010000>;
                compatible      = "abilis,tb10x", "simple-bus";
                pll0: oscillator {
@@ -75,10 +75,10 @@
                        clock-output-names = "ahb_clk";
                };
-                iomux: iomux@FF10601c {
+                iomux: iomux@ff10601c {
                        compatible = "abilis,tb10x-iomux";
                        #gpio-range-cells = <3>;
-                        reg = <0xFF10601c 0x4>;
+                        reg = <0xff10601c 0x4>;
                };
                intc: interrupt-controller {
@@ -88,7 +88,7 @@
                };
                tb10x_ictl: pic@fe002000 {
                        compatible = "abilis,tb10x-ictl";
-                        reg = <0xFE002000 0x20>;
+                        reg = <0xfe002000 0x20>;
                        interrupt-controller;
                        #interrupt-cells = <2>;
                        interrupt-parent = <&intc>;
@@ -96,27 +96,27 @@
                                        20 21 22 23 24 25 26 27 28 29 30 31>;
                };
-                uart@FF100000 {
+                uart@ff100000 {
                        compatible = "snps,dw-apb-uart";
-                        reg = <0xFF100000 0x100>;
+                        reg = <0xff100000 0x100>;
                        clock-frequency = <166666666>;
                        interrupts = <25 8>;
                        reg-shift = <2>;
                        reg-io-width = <4>;
                        interrupt-parent = <&tb10x_ictl>;
                };
-                ethernet@FE100000 {
+                ethernet@fe100000 {
                        compatible = "snps,dwmac-3.70a","snps,dwmac";
-                        reg = <0xFE100000 0x1058>;
+                        reg = <0xfe100000 0x1058>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <6 8>;
                        interrupt-names = "macirq";
                        clocks = <&ahb_clk>;
                        clock-names = "stmmaceth";
                };
-                dma@FE000000 {
+                dma@fe000000 {
                        compatible = "snps,dma-spear1340";
-                        reg = <0xFE000000 0x400>;
+                        reg = <0xfe000000 0x400>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <14 8>;
                        dma-channels = <6>;
@@ -132,70 +132,70 @@
                        multi-block = <1 1 1 1 1 1>;
                };
-                i2c0: i2c@FF120000 {
+                i2c0: i2c@ff120000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        compatible = "snps,designware-i2c";
-                        reg = <0xFF120000 0x1000>;
+                        reg = <0xff120000 0x1000>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <12 8>;
                        clocks = <&ahb_clk>;
                };
-                i2c1: i2c@FF121000 {
+                i2c1: i2c@ff121000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        compatible = "snps,designware-i2c";
-                        reg = <0xFF121000 0x1000>;
+                        reg = <0xff121000 0x1000>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <12 8>;
                        clocks = <&ahb_clk>;
                };
-                i2c2: i2c@FF122000 {
+                i2c2: i2c@ff122000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        compatible = "snps,designware-i2c";
-                        reg = <0xFF122000 0x1000>;
+                        reg = <0xff122000 0x1000>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <12 8>;
                        clocks = <&ahb_clk>;
                };
-                i2c3: i2c@FF123000 {
+                i2c3: i2c@ff123000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        compatible = "snps,designware-i2c";
-                        reg = <0xFF123000 0x1000>;
+                        reg = <0xff123000 0x1000>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <12 8>;
                        clocks = <&ahb_clk>;
                };
-                i2c4: i2c@FF124000 {
+                i2c4: i2c@ff124000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        compatible = "snps,designware-i2c";
-                        reg = <0xFF124000 0x1000>;
+                        reg = <0xff124000 0x1000>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <12 8>;
                        clocks = <&ahb_clk>;
                };
-                spi0: spi@0xFE010000 {
+                spi0: spi@fe010000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        cell-index = <0>;
                        compatible = "abilis,tb100-spi";
                        num-cs = <1>;
-                        reg = <0xFE010000 0x20>;
+                        reg = <0xfe010000 0x20>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <26 8>;
                        clocks = <&ahb_clk>;
                };
-                spi1: spi@0xFE011000 {
+                spi1: spi@fe011000 {
                        #address-cells = <1>;
                        #size-cells = <0>;
                        cell-index = <1>;
                        compatible = "abilis,tb100-spi";
                        num-cs = <2>;
-                        reg = <0xFE011000 0x20>;
+                        reg = <0xfe011000 0x20>;
                        interrupt-parent = <&tb10x_ictl>;
                        interrupts = <10 8>;
                        clocks = <&ahb_clk>;
@@ -226,23 +226,23 @@
                        interrupts = <20 2>, <19 2>;
                        interrupt-names = "cmd_irq", "event_irq";
                };
-                tb10x_mdsc0: tb10x-mdscr@FF300000 {
+                tb10x_mdsc0: tb10x-mdscr@ff300000 {
                        compatible = "abilis,tb100-mdscr";
-                        reg = <0xFF300000 0x7000>;
+                        reg = <0xff300000 0x7000>;
                        tb100-mdscr-manage-tsin;
                };
-                tb10x_mscr0: tb10x-mdscr@FF307000 {
+                tb10x_mscr0: tb10x-mdscr@ff307000 {
                        compatible = "abilis,tb100-mdscr";
-                        reg = <0xFF307000 0x7000>;
+                        reg = <0xff307000 0x7000>;
                };
                tb10x_scr0: tb10x-mdscr@ff30e000 {
                        compatible = "abilis,tb100-mdscr";
-                        reg = <0xFF30e000 0x4000>;
+                        reg = <0xff30e000 0x4000>;
                        tb100-mdscr-manage-tsin;
                };
                tb10x_scr1: tb10x-mdscr@ff312000 {
                        compatible = "abilis,tb100-mdscr";
-                        reg = <0xFF312000 0x4000>;
+                        reg = <0xff312000 0x4000>;
                        tb100-mdscr-manage-tsin;
                };
                tb10x_wfb: tb10x-wfb@ff319000 {
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index fdc266504ada..37be3bf03ad6 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -41,7 +41,7 @@
                 * this GPIO block ORs all interrupts on CPU card (creg,..)
                 * to uplink only 1 IRQ to ARC core intc
                 */
-                dw-apb-gpio@0x2000 {
+                dw-apb-gpio@2000 {
                        compatible = "snps,dw-apb-gpio";
                        reg = < 0x2000 0x80 >;
                        #address-cells = <1>;
@@ -60,7 +60,7 @@
                        };
                };
-                debug_uart: dw-apb-uart@0x5000 {
+                debug_uart: dw-apb-uart@5000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x5000 0x100>;
                        clock-frequency = <33333000>;
@@ -88,7 +88,7 @@
         * avoid duplicating the MB dtsi file given that IRQ from
         * this intc to cpu intc are different for axs101 and axs103
         */
-        mb_intc: dw-apb-ictl@0xe0012000 {
+        mb_intc: dw-apb-ictl@e0012000 {
                #interrupt-cells = <1>;
                compatible = "snps,dw-apb-ictl";
                reg = < 0x0 0xe0012000 0x0 0x200 >;
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index d75d65ddf8e3..effa37536d7a 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -55,7 +55,7 @@
                 * this GPIO block ORs all interrupts on CPU card (creg,..)
                 * to uplink only 1 IRQ to ARC core intc
                 */
-                dw-apb-gpio@0x2000 {
+                dw-apb-gpio@2000 {
                        compatible = "snps,dw-apb-gpio";
                        reg = < 0x2000 0x80 >;
                        #address-cells = <1>;
@@ -74,7 +74,7 @@
                        };
                };
-                debug_uart: dw-apb-uart@0x5000 {
+                debug_uart: dw-apb-uart@5000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x5000 0x100>;
                        clock-frequency = <33333000>;
@@ -102,19 +102,19 @@
         * external DMA buffer located outside of IOC aperture.
         */
        axs10x_mb {
-                ethernet@0x18000 {
+                ethernet@18000 {
                        dma-coherent;
                };
-                ehci@0x40000 {
+                ehci@40000 {
                        dma-coherent;
                };
-                ohci@0x60000 {
+                ohci@60000 {
                        dma-coherent;
                };
-                mmc@0x15000 {
+                mmc@15000 {
                        dma-coherent;
                };
        };
@@ -132,7 +132,7 @@
         * avoid duplicating the MB dtsi file given that IRQ from
         * this intc to cpu intc are different for axs101 and axs103
         */
-        mb_intc: dw-apb-ictl@0xe0012000 {
+        mb_intc: dw-apb-ictl@e0012000 {
                #interrupt-cells = <1>;
                compatible = "snps,dw-apb-ictl";
                reg = < 0x0 0xe0012000 0x0 0x200 >;
@@ -153,7 +153,7 @@
                #size-cells = <2>;
                ranges;
                /*
-                 * Move frame buffer out of IOC aperture (0x8z-0xAz).
+                 * Move frame buffer out of IOC aperture (0x8z-0xaz).
                 */
                frame_buffer: frame_buffer@be000000 {
                        compatible = "shared-dma-pool";
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index a05bb737ea63..e401e59f6180 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -62,7 +62,7 @@
                 * this GPIO block ORs all interrupts on CPU card (creg,..)
                 * to uplink only 1 IRQ to ARC core intc
                 */
-                dw-apb-gpio@0x2000 {
+                dw-apb-gpio@2000 {
                        compatible = "snps,dw-apb-gpio";
                        reg = < 0x2000 0x80 >;
                        #address-cells = <1>;
@@ -81,7 +81,7 @@
                        };
                };
-                debug_uart: dw-apb-uart@0x5000 {
+                debug_uart: dw-apb-uart@5000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x5000 0x100>;
                        clock-frequency = <33333000>;
@@ -109,19 +109,19 @@
         * external DMA buffer located outside of IOC aperture.
         */
        axs10x_mb {
-                ethernet@0x18000 {
+                ethernet@18000 {
                        dma-coherent;
                };
-                ehci@0x40000 {
+                ehci@40000 {
                        dma-coherent;
                };
-                ohci@0x60000 {
+                ohci@60000 {
                        dma-coherent;
                };
-                mmc@0x15000 {
+                mmc@15000 {
                        dma-coherent;
                };
        };
@@ -138,7 +138,7 @@
         * avoid duplicating the MB dtsi file given that IRQ from
         * this intc to cpu intc are different for axs101 and axs103
         */
-        mb_intc: dw-apb-ictl@0xe0012000 {
+        mb_intc: dw-apb-ictl@e0012000 {
                #interrupt-cells = <1>;
                compatible = "snps,dw-apb-ictl";
                reg = < 0x0 0xe0012000 0x0 0x200 >;
@@ -159,7 +159,7 @@
                #size-cells = <2>;
                ranges;
                /*
-                 * Move frame buffer out of IOC aperture (0x8z-0xAz).
+                 * Move frame buffer out of IOC aperture (0x8z-0xaz).
                 */
                frame_buffer: frame_buffer@be000000 {
                        compatible = "shared-dma-pool";
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 37bafd44e36d..4ead6dc9af2f 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -72,7 +72,7 @@
                        };
                };
-                gmac: ethernet@0x18000 {
+                gmac: ethernet@18000 {
                        #interrupt-cells = <1>;
                        compatible = "snps,dwmac";
                        reg = < 0x18000 0x2000 >;
@@ -88,13 +88,13 @@
                        mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
                };
-                ehci@0x40000 {
+                ehci@40000 {
                        compatible = "generic-ehci";
                        reg = < 0x40000 0x100 >;
                        interrupts = < 8 >;
                };
-                ohci@0x60000 {
+                ohci@60000 {
                        compatible = "generic-ohci";
                        reg = < 0x60000 0x100 >;
                        interrupts = < 8 >;
@@ -118,7 +118,7 @@
                 * dw_mci_pltfm_prepare_command() is used in generic platform
                 * code.
                 */
-                mmc@0x15000 {
+                mmc@15000 {
                        compatible = "altr,socfpga-dw-mshc";
                        reg = < 0x15000 0x400 >;
                        fifo-depth = < 16 >;
@@ -129,7 +129,7 @@
                        bus-width = < 4 >;
                };
-                uart@0x20000 {
+                uart@20000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x20000 0x100>;
                        clock-frequency = <33333333>;
@@ -139,7 +139,7 @@
                        reg-io-width = <4>;
                };
-                uart@0x21000 {
+                uart@21000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x21000 0x100>;
                        clock-frequency = <33333333>;
@@ -150,7 +150,7 @@
                };
                /* UART muxed with USB data port (ttyS3) */
-                uart@0x22000 {
+                uart@22000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x22000 0x100>;
                        clock-frequency = <33333333>;
@@ -160,7 +160,7 @@
                        reg-io-width = <4>;
                };
-                i2c@0x1d000 {
+                i2c@1d000 {
                        compatible = "snps,designware-i2c";
                        reg = <0x1d000 0x100>;
                        clock-frequency = <400000>;
@@ -177,7 +177,7 @@
                        #sound-dai-cells = <0>;
                };
-                i2c@0x1f000 {
+                i2c@1f000 {
                        compatible = "snps,designware-i2c";
                        #address-cells = <1>;
                        #size-cells = <0>;
@@ -218,13 +218,13 @@
                                };
                        };
-                        eeprom@0x54{
+                        eeprom@54{
                                compatible = "atmel,24c01";
                                reg = <0x54>;
                                pagesize = <0x8>;
                        };
-                        eeprom@0x57{
+                        eeprom@57{
                                compatible = "atmel,24c04";
                                reg = <0x57>;
                                pagesize = <0x8>;
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 43f17b51ee89..69bc1c9e8e50 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -110,12 +110,12 @@
                cgu_rst: reset-controller@8a0 {
                        compatible = "snps,hsdk-reset";
                        #reset-cells = <1>;
-                        reg = <0x8A0 0x4>, <0xFF0 0x4>;
+                        reg = <0x8a0 0x4>, <0xff0 0x4>;
                };
                core_clk: core-clk@0 {
                        compatible = "snps,hsdk-core-pll-clock";
-                        reg = <0x00 0x10>, <0x14B8 0x4>;
+                        reg = <0x00 0x10>, <0x14b8 0x4>;
                        #clock-cells = <0>;
                        clocks = <&input_clk>;
@@ -167,6 +167,18 @@
                        #clock-cells = <0>;
                };
+                dmac_core_clk: dmac-core-clk {
+                        compatible = "fixed-clock";
+                        clock-frequency = <400000000>;
+                        #clock-cells = <0>;
+                };
+                dmac_cfg_clk: dmac-gpu-cfg-clk {
+                        compatible = "fixed-clock";
+                        clock-frequency = <200000000>;
+                        #clock-cells = <0>;
+                };
                gmac: ethernet@8000 {
                        #interrupt-cells = <1>;
                        compatible = "snps,dwmac";
@@ -200,6 +212,7 @@
                        compatible = "snps,hsdk-v1.0-ohci", "generic-ohci";
                        reg = <0x60000 0x100>;
                        interrupts = <15>;
+                        resets = <&cgu_rst HSDK_USB_RESET>;
                        dma-coherent;
                };
@@ -207,6 +220,7 @@
                        compatible = "snps,hsdk-v1.0-ehci", "generic-ehci";
                        reg = <0x40000 0x100>;
                        interrupts = <15>;
+                        resets = <&cgu_rst HSDK_USB_RESET>;
                        dma-coherent;
                };
@@ -237,6 +251,21 @@
                                reg = <0>;
                        };
                };
+                dmac: dmac@80000 {
+                        compatible = "snps,axi-dma-1.01a";
+                        reg = <0x80000 0x400>;
+                        interrupts = <27>;
+                        clocks = <&dmac_core_clk>, <&dmac_cfg_clk>;
+                        clock-names = "core-clk", "cfgr-clk";
+                        dma-channels = <4>;
+                        snps,dma-masters = <2>;
+                        snps,data-width = <3>;
+                        snps,block-size = <4096 4096 4096 4096>;
+                        snps,priority = <0 1 2 3>;
+                        snps,axi-max-burst-len = <16>;
+                };
        };
        memory@80000000 {
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
index 0fd6ba985b16..84e8766c8ca2 100644
--- a/arch/arc/boot/dts/vdk_axc003.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -36,7 +36,7 @@
                        #interrupt-cells = <1>;
                };
-                debug_uart: dw-apb-uart@0x5000 {
+                debug_uart: dw-apb-uart@5000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x5000 0x100>;
                        clock-frequency = <2403200>;
@@ -49,7 +49,7 @@
        };
-        mb_intc: dw-apb-ictl@0xe0012000 {
+        mb_intc: dw-apb-ictl@e0012000 {
                #interrupt-cells = <1>;
                compatible = "snps,dw-apb-ictl";
                reg = < 0xe0012000 0x200 >;
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
index 28956f9a9f3d..eb7e705e8a27 100644
--- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -44,7 +44,7 @@
                        #interrupt-cells = <1>;
                };
-                debug_uart: dw-apb-uart@0x5000 {
+                debug_uart: dw-apb-uart@5000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x5000 0x100>;
                        clock-frequency = <2403200>;
@@ -57,7 +57,7 @@
        };
-        mb_intc: dw-apb-ictl@0xe0012000 {
+        mb_intc: dw-apb-ictl@e0012000 {
                #interrupt-cells = <1>;
                compatible = "snps,dw-apb-ictl";
                reg = < 0xe0012000 0x200 >;
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
index 48bb4b4cd234..925d5cc95dbb 100644
--- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -36,7 +36,7 @@
                        };
                };
-                ethernet@0x18000 {
+                ethernet@18000 {
                        #interrupt-cells = <1>;
                        compatible = "snps,dwmac";
                        reg = < 0x18000 0x2000 >;
@@ -49,13 +49,13 @@
                        clock-names = "stmmaceth";
                };
-                ehci@0x40000 {
+                ehci@40000 {
                        compatible = "generic-ehci";
                        reg = < 0x40000 0x100 >;
                        interrupts = < 8 >;
                };
-                uart@0x20000 {
+                uart@20000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x20000 0x100>;
                        clock-frequency = <2403200>;
@@ -65,7 +65,7 @@
                        reg-io-width = <4>;
                };
-                uart@0x21000 {
+                uart@21000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x21000 0x100>;
                        clock-frequency = <2403200>;
@@ -75,7 +75,7 @@
                        reg-io-width = <4>;
                };
-                uart@0x22000 {
+                uart@22000 {
                        compatible = "snps,dw-apb-uart";
                        reg = <0x22000 0x100>;
                        clock-frequency = <2403200>;
@@ -101,7 +101,7 @@
                        interrupt-names = "arc_ps2_irq";
                };
-                mmc@0x15000 {
+                mmc@15000 {
                        compatible = "snps,dw-mshc";
                        reg = <0x15000 0x400>;
                        fifo-depth = <1024>;
@@ -117,11 +117,11 @@
         * Embedded Vision subsystem UIO mappings; only relevant for EV VDK
         *
         * This node is intentionally put outside of MB above becase
-         * it maps areas outside of MB's 0xEz-0xFz.
+         * it maps areas outside of MB's 0xez-0xfz.
         */
-        uio_ev: uio@0xD0000000 {
+        uio_ev: uio@d0000000 {
                compatible = "generic-uio";
-                reg = <0xD0000000 0x2000 0xD1000000 0x2000 0x90000000 0x10000000 0xC0000000 0x10000000>;
+                reg = <0xd0000000 0x2000 0xd1000000 0x2000 0x90000000 0x10000000 0xc0000000 0x10000000>;
                reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
                interrupt-parent = <&mb_intc>;
                interrupts = <23>;
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 6fd3d29546af..0e5fd29ed238 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -8,6 +8,7 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index a27eafdc8260..a7d4be87b2f0 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -82,6 +82,7 @@
 #define ECR_V_DTLB_MISS                 0x05
 #define ECR_V_PROTV                     0x06
 #define ECR_V_TRAP                      0x09
+#define ECR_V_MISALIGN                  0x0d
 #endif
 /* DTLB Miss and Protection Violation Cause Codes */
@@ -167,14 +168,6 @@ struct bcr_mpy {
 #endif
 };
-struct bcr_extn_xymem {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-        unsigned int ram_org:2, num_banks:4, bank_sz:4, ver:8;
-#else
-        unsigned int ver:8, bank_sz:4, num_banks:4, ram_org:2;
-#endif
-};
 struct bcr_iccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
        unsigned int base:16, pad:5, sz:3, ver:8;
@@ -312,7 +305,7 @@ struct cpuinfo_arc {
        struct cpuinfo_arc_bpu bpu;
        struct bcr_identity core;
        struct bcr_isa_arcv2 isa;
-        const char *details, *name;
+        const char *release, *name;
        unsigned int vec_base;
        struct cpuinfo_arc_ccm iccm, dccm;
        struct {
@@ -322,7 +315,6 @@ struct cpuinfo_arc {
                             timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
        } extn;
        struct bcr_mpy extn_mpy;
-        struct bcr_extn_xymem extn_xymem;
 };
 extern struct cpuinfo_arc cpuinfo_arc700[];
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index 8a4f77ea3238..e66d0339e1d8 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -44,7 +44,13 @@
 #define ARCV2_IRQ_DEF_PRIO      1
 /* seed value for status register */
-#define ISA_INIT_STATUS_BITS    (STATUS_IE_MASK | STATUS_AD_MASK | \
+#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+#define __AD_ENB        STATUS_AD_MASK
+#else
+#define __AD_ENB        0
+#endif
+#define ISA_INIT_STATUS_BITS    (STATUS_IE_MASK | __AD_ENB | \
                                        (ARCV2_IRQ_DEF_PRIO << 1))
 #ifndef __ASSEMBLY__
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 6958545390f0..9cd7ee4fad39 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -105,10 +105,10 @@ static const char * const arc_pmu_ev_hw_map[] = {
        [PERF_COUNT_HW_INSTRUCTIONS] = "iall",
        /* All jump instructions that are taken */
        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
-        [PERF_COUNT_ARC_BPOK]         = "bpok",   /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
        [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
 #else
+        [PERF_COUNT_ARC_BPOK]         = "bpok",   /* NP-NT, PT-T, PNT-NT */
        [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
 #endif
        [PERF_COUNT_ARC_LDC] = "imemrdc",       /* Instr: mem read cached */
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index 2ba04a7db621..daa914da7968 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -21,8 +21,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
        unsigned int val;
-        smp_mb();
        __asm__ __volatile__(
        "1:     llock   %[val], [%[slock]]      \n"
        "       breq    %[val], %[LOCKED], 1b   \n"     /* spin while LOCKED */
@@ -34,6 +32,14 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
          [LOCKED]      "r"     (__ARCH_SPIN_LOCK_LOCKED__)
        : "memory", "cc");
+        /*
+         * ACQUIRE barrier to ensure load/store after taking the lock
+         * don't "bleed-up" out of the critical section (leak-in is allowed)
+         * http://www.spinics.net/lists/kernel/msg2010409.html
+         *
+         * ARCv2 only has load-load, store-store and all-all barrier
+         * thus need the full all-all barrier
+         */
        smp_mb();
 }
@@ -42,8 +48,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
        unsigned int val, got_it = 0;
-        smp_mb();
        __asm__ __volatile__(
        "1:     llock   %[val], [%[slock]]      \n"
        "       breq    %[val], %[LOCKED], 4f   \n"     /* already LOCKED, just bail */
@@ -67,9 +71,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
        smp_mb();
-        lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+        WRITE_ONCE(lock->slock, __ARCH_SPIN_LOCK_UNLOCKED__);
-        smp_mb();
 }
 /*
@@ -81,8 +83,6 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 {
        unsigned int val;
-        smp_mb();
        /*
         * zero means writer holds the lock exclusively, deny Reader.
         * Otherwise grant lock to first/subseq reader
@@ -113,8 +113,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
        unsigned int val, got_it = 0;
-        smp_mb();
        __asm__ __volatile__(
        "1:     llock   %[val], [%[rwlock]]     \n"
        "       brls    %[val], %[WR_LOCKED], 4f\n"     /* <= 0: already write locked, bail */
@@ -140,8 +138,6 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
        unsigned int val;
-        smp_mb();
        /*
         * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
         * deny writer. Otherwise if unlocked grant to writer
@@ -175,8 +171,6 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
        unsigned int val, got_it = 0;
-        smp_mb();
        __asm__ __volatile__(
        "1:     llock   %[val], [%[rwlock]]     \n"
        "       brne    %[val], %[UNLOCKED], 4f \n"     /* !UNLOCKED, bail */
@@ -217,17 +211,13 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
        : [val]         "=&r"   (val)
        : [rwlock]      "r"     (&(rw->counter))
        : "memory", "cc");
-        smp_mb();
 }
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
        smp_mb();
-        rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+        WRITE_ONCE(rw->counter, __ARCH_RW_LOCK_UNLOCKED__);
-        smp_mb();
 }
 #else   /* !CONFIG_ARC_HAS_LLSC */
@@ -237,10 +227,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
        unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
        /*
-         * This smp_mb() is technically superfluous, we only need the one
+         * Per lkmm, smp_mb() is only required after _lock (and before_unlock)
-         * after the lock for providing the ACQUIRE semantics.
+         * for ACQ and REL semantics respectively. However EX based spinlocks
-         * However doing the "right" thing was regressing hackbench
+         * need the extra smp_mb to workaround a hardware quirk.
-         * so keeping this, pending further investigation
         */
        smp_mb();
@@ -257,14 +246,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 #endif
        : "memory");
-        /*
-         * ACQUIRE barrier to ensure load/store after taking the lock
-         * don't "bleed-up" out of the critical section (leak-in is allowed)
-         * http://www.spinics.net/lists/kernel/msg2010409.html
-         *
-         * ARCv2 only has load-load, store-store and all-all barrier
-         * thus need the full all-all barrier
-         */
        smp_mb();
 }
@@ -309,8 +290,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
        : "memory");
        /*
-         * superfluous, but keeping for now - see pairing version in
+         * see pairing version/comment in arch_spin_lock above
-         * arch_spin_lock above
         */
        smp_mb();
 }
@@ -344,7 +324,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
        arch_spin_unlock(&(rw->lock_mutex));
        local_irq_restore(flags);
-        smp_mb();
        return ret;
 }
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 30e090625916..8f6e0447dd17 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -54,7 +54,12 @@
        ; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access
        ; by default
        lr      r5, [status32]
+#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
        bset    r5, r5, STATUS_AD_BIT
+#else
+        ; Although disabled at reset, bootloader might have enabled it
+        bclr    r5, r5, STATUS_AD_BIT
+#endif
        kflag   r5
 #endif
 .endm
@@ -106,6 +111,7 @@ ENTRY(stext)
        ;    r2 = pointer to uboot provided cmdline or external DTB in mem
        ; These are handled later in handle_uboot_args()
        st      r0, [@uboot_tag]
+        st      r1, [@uboot_magic]
        st      r2, [@uboot_arg]
        ; setup "current" tsk and optionally cache it in dedicated r25
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index cf18b3e5a934..c0d0124de089 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -95,7 +95,7 @@ void arc_init_IRQ(void)
        /* setup status32, don't enable intr yet as kernel doesn't want */
        tmp = read_aux_reg(ARC_REG_STATUS32);
-        tmp |= STATUS_AD_MASK | (ARCV2_IRQ_DEF_PRIO << 1);
+        tmp |= ARCV2_IRQ_DEF_PRIO << 1;
        tmp &= ~STATUS_IE_MASK;
        asm volatile("kflag %0  \n"::"r"(tmp));
 }
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 7b2340996cf8..a9c88b7e9182 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -36,6 +36,7 @@ unsigned int intr_to_DE_cnt;
 /* Part of U-boot ABI: see head.S */
 int __initdata uboot_tag;
+int __initdata uboot_magic;
 char __initdata *uboot_arg;
 const struct machine_desc *machine_desc;
@@ -44,29 +45,24 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
-static const struct id_to_str arc_cpu_rel[] = {
+static const struct id_to_str arc_legacy_rel[] = {
+        /* ID.ARCVER,   Release */
 #ifdef CONFIG_ISA_ARCOMPACT
-        { 0x34, "R4.10"},
+        { 0x34,         "R4.10"},
-        { 0x35, "R4.11"},
+        { 0x35,         "R4.11"},
 #else
-        { 0x51, "R2.0" },
+        { 0x51,         "R2.0" },
-        { 0x52, "R2.1" },
+        { 0x52,         "R2.1" },
-        { 0x53, "R3.0" },
+        { 0x53,         "R3.0" },
-        { 0x54, "R3.10a" },
 #endif
-        { 0x00, NULL   }
+        { 0x00,         NULL   }
 };
-static const struct id_to_str arc_cpu_nm[] = {
+static const struct id_to_str arc_cpu_rel[] = {
-#ifdef CONFIG_ISA_ARCOMPACT
+        /* UARCH.MAJOR, Release */
-        { 0x20, "ARC 600"   },
+        {  0,           "R3.10a"},
-        { 0x30, "ARC 770"   },  /* 750 identified seperately */
+        {  1,           "R3.50a"},
-#else
+        {  0xFF,        NULL   }
-        { 0x40, "ARC EM"  },
-        { 0x50, "ARC HS38"  },
-        { 0x54, "ARC HS48"  },
-#endif
-        { 0x00, "Unknown"   }
 };
 static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
@@ -116,31 +112,72 @@ static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
        }
 }
+static void decode_arc_core(struct cpuinfo_arc *cpu)
+{
+        struct bcr_uarch_build_arcv2 uarch;
+        const struct id_to_str *tbl;
+        /*
+         * Up until (including) the first core4 release (0x54) things were
+         * simple: AUX IDENTITY.ARCVER was sufficient to identify arc family
+         * and release: 0x50 to 0x53 was HS38, 0x54 was HS48 (dual issue)
+         */
+        if (cpu->core.family < 0x54) { /* includes arc700 */
+                for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) {
+                        if (cpu->core.family == tbl->id) {
+                                cpu->release = tbl->str;
+                                break;
+                        }
+                }
+                if (is_isa_arcompact())
+                        cpu->name = "ARC700";
+                else if (tbl->str)
+                        cpu->name = "HS38";
+                else
+                        cpu->name = cpu->release = "Unknown";
+                return;
+        }
+        /*
+         * However the subsequent HS release (same 0x54) allow HS38 or HS48
+         * configurations and encode this info in a different BCR.
+         * The BCR was introduced in 0x54 so can't be read unconditionally.
+         */
+        READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
+        if (uarch.prod == 4) {
+                cpu->name = "HS48";
+                cpu->extn.dual = 1;
+        } else {
+                cpu->name = "HS38";
+        }
+        for (tbl = &arc_cpu_rel[0]; tbl->id != 0xFF; tbl++) {
+                if (uarch.maj == tbl->id) {
+                        cpu->release = tbl->str;
+                        break;
+                }
+        }
+}
 static void read_arc_build_cfg_regs(void)
 {
        struct bcr_timer timer;
        struct bcr_generic bcr;
        struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
-        const struct id_to_str *tbl;
        struct bcr_isa_arcv2 isa;
        struct bcr_actionpoint ap;
        FIX_PTR(cpu);
        READ_BCR(AUX_IDENTITY, cpu->core);
+        decode_arc_core(cpu);
-        for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
-                if (cpu->core.family == tbl->id) {
-                        cpu->details = tbl->str;
-                        break;
-                }
-        }
-        for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
-                if ((cpu->core.family & 0xF4) == tbl->id)
-                        break;
-        }
-        cpu->name = tbl->str;
        READ_BCR(ARC_REG_TIMERS_BCR, timer);
        cpu->extn.timer0 = timer.t0;
@@ -151,16 +188,6 @@ static void read_arc_build_cfg_regs(void)
        READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
-        cpu->extn.norm = read_aux_reg(ARC_REG_NORM_BCR) > 1 ? 1 : 0; /* 2,3 */
-        cpu->extn.barrel = read_aux_reg(ARC_REG_BARREL_BCR) > 1 ? 1 : 0; /* 2,3 */
-        cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
-        cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
-        cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
-        cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 :
-                                IS_ENABLED(CONFIG_ARC_HAS_SWAPE);
-        READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
        /* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
        read_decode_ccm_bcr(cpu);
@@ -198,30 +225,12 @@ static void read_arc_build_cfg_regs(void)
                cpu->bpu.num_pred = 2048 << bpu.pte;
                cpu->bpu.ret_stk = 4 << bpu.rse;
-                if (cpu->core.family >= 0x54) {
+                /* if dual issue hardware, is it enabled ? */
+                if (cpu->extn.dual) {
-                        struct bcr_uarch_build_arcv2 uarch;
+                        unsigned int exec_ctrl;
-                        /*
-                         * The first 0x54 core (uarch maj:min 0:1 or 0:2) was
-                         * dual issue only (HS4x). But next uarch rev (1:0)
-                         * allows it be configured for single issue (HS3x)
-                         * Ensure we fiddle with dual issue only on HS4x
-                         */
-                        READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
-                        if (uarch.prod == 4) {
-                                unsigned int exec_ctrl;
-                                /* dual issue hardware always present */
-                                cpu->extn.dual = 1;
-                                READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-                                /* dual issue hardware enabled ? */
+                        READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-                                cpu->extn.dual_enb = !(exec_ctrl & 1);
+                        cpu->extn.dual_enb = !(exec_ctrl & 1);
-                        }
                }
        }
@@ -263,7 +272,8 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
        struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
        struct bcr_identity *core = &cpu->core;
-        int i, n = 0, ua = 0;
+        char mpy_opt[16];
+        int n = 0;
        FIX_PTR(cpu);
@@ -272,7 +282,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
                       core->family, core->cpu_id, core->chip_id);
        n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n",
-                       cpu_id, cpu->name, cpu->details,
+                       cpu_id, cpu->name, cpu->release,
                       is_isa_arcompact() ? "ARCompact" : "ARCv2",
                       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"),
                       IS_AVAIL3(cpu->extn.dual, cpu->extn.dual_enb, " Dual-Issue "));
@@ -283,61 +293,50 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
                       IS_AVAIL2(cpu->extn.rtc, "RTC [UP 64-bit] ", CONFIG_ARC_TIMERS_64BIT),
                       IS_AVAIL2(cpu->extn.gfrc, "GFRC [SMP 64-bit] ", CONFIG_ARC_TIMERS_64BIT));
-#ifdef __ARC_UNALIGNED__
-        ua = 1;
-#endif
-        n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s%s",
-                           IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
-                           IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
-                           IS_AVAIL1(cpu->isa.unalign, "unalign "), IS_USED_RUN(ua));
-        if (i)
-                n += scnprintf(buf + n, len - n, "\n\t\t: ");
        if (cpu->extn_mpy.ver) {
-                if (cpu->extn_mpy.ver <= 0x2) { /* ARCompact */
+                if (is_isa_arcompact()) {
-                        n += scnprintf(buf + n, len - n, "mpy ");
+                        scnprintf(mpy_opt, 16, "mpy");
                } else {
                        int opt = 2;    /* stock MPY/MPYH */
                        if (cpu->extn_mpy.dsp)  /* OPT 7-9 */
                                opt = cpu->extn_mpy.dsp + 6;
-                        n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
+                        scnprintf(mpy_opt, 16, "mpy[opt %d] ", opt);
                }
        }
        n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
-                       IS_AVAIL1(cpu->isa.div_rem, "div_rem "),
+                       IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
-                       IS_AVAIL1(cpu->extn.norm, "norm "),
+                       IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
-                       IS_AVAIL1(cpu->extn.barrel, "barrel-shift "),
+                       IS_AVAIL2(cpu->isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS),
-                       IS_AVAIL1(cpu->extn.swap, "swap "),
+                       IS_AVAIL1(cpu->extn_mpy.ver, mpy_opt),
-                       IS_AVAIL1(cpu->extn.minmax, "minmax "),
+                       IS_AVAIL1(cpu->isa.div_rem, "div_rem "));
-                       IS_AVAIL1(cpu->extn.crc, "crc "),
-                       IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE));
+        if (cpu->bpu.ver) {
-        if (cpu->bpu.ver)
                n += scnprintf(buf + n, len - n,
                              "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d",
                              IS_AVAIL1(cpu->bpu.full, "full"),
                              IS_AVAIL1(!cpu->bpu.full, "partial"),
                              cpu->bpu.num_cache, cpu->bpu.num_pred, cpu->bpu.ret_stk);
-        if (is_isa_arcv2()) {
+                if (is_isa_arcv2()) {
-                struct bcr_lpb lpb;
+                        struct bcr_lpb lpb;
-                READ_BCR(ARC_REG_LPB_BUILD, lpb);
+                        READ_BCR(ARC_REG_LPB_BUILD, lpb);
-                if (lpb.ver) {
+                        if (lpb.ver) {
-                        unsigned int ctl;
+                                unsigned int ctl;
-                        ctl = read_aux_reg(ARC_REG_LPB_CTRL);
+                                ctl = read_aux_reg(ARC_REG_LPB_CTRL);
-                        n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s",
+                                n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s",
-                                lpb.entries,
+                                               lpb.entries,
-                                IS_DISABLED_RUN(!ctl));
+                                               IS_DISABLED_RUN(!ctl));
+                        }
                }
+                n += scnprintf(buf + n, len - n, "\n");
        }
-        n += scnprintf(buf + n, len - n, "\n");
        return buf;
 }
@@ -390,11 +389,6 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
                }
        }
-        n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
-                        EF_ARC_OSABI_CURRENT >> 8,
-                        EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
-                        "no-legacy-syscalls" : "64-bit data any register aligned");
        return buf;
 }
@@ -497,6 +491,8 @@ static inline bool uboot_arg_invalid(unsigned long addr)
 #define UBOOT_TAG_NONE          0
 #define UBOOT_TAG_CMDLINE       1
 #define UBOOT_TAG_DTB           2
+/* We always pass 0 as magic from U-boot */
+#define UBOOT_MAGIC_VALUE       0
 void __init handle_uboot_args(void)
 {
@@ -511,6 +507,11 @@ void __init handle_uboot_args(void)
                goto ignore_uboot_args;
        }
+        if (uboot_magic != UBOOT_MAGIC_VALUE) {
+                pr_warn(IGNORE_ARGS "non zero uboot magic\n");
+                goto ignore_uboot_args;
+        }
        if (uboot_tag != UBOOT_TAG_NONE &&
            uboot_arg_invalid((unsigned long)uboot_arg)) {
                pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg);
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 215f515442e0..b0aa8c028331 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -145,7 +145,8 @@ static void show_ecr_verbose(struct pt_regs *regs)
        } else if (vec == ECR_V_PROTV) {
                if (cause_code == ECR_C_PROTV_INST_FETCH)
                        pr_cont("Execute from Non-exec Page\n");
-                else if (cause_code == ECR_C_PROTV_MISALIG_DATA)
+                else if (cause_code == ECR_C_PROTV_MISALIG_DATA &&
+                         IS_ENABLED(CONFIG_ISA_ARCOMPACT))
                        pr_cont("Misaligned r/w from 0x%08lx\n", address);
                else
                        pr_cont("%s access not allowed on page\n",
@@ -161,6 +162,8 @@ static void show_ecr_verbose(struct pt_regs *regs)
                        pr_cont("Bus Error from Data Mem\n");
                else
                        pr_cont("Bus Error, check PRM\n");
+        } else if (vec == ECR_V_MISALIGN) {
+                pr_cont("Misaligned r/w from 0x%08lx\n", address);
 #endif
        } else if (vec == ECR_V_TRAP) {
                if (regs->ecr_param == 5)
diff --git a/arch/arc/lib/Makefile b/arch/arc/lib/Makefile
index b1656d156097..f7537b466b23 100644
--- a/arch/arc/lib/Makefile
+++ b/arch/arc/lib/Makefile
@@ -8,4 +8,10 @@
 lib-y   := strchr-700.o strcpy-700.o strlen.o memcmp.o
 lib-$(CONFIG_ISA_ARCOMPACT)     += memcpy-700.o memset.o strcmp.o
-lib-$(CONFIG_ISA_ARCV2)         += memcpy-archs.o memset-archs.o strcmp-archs.o
+lib-$(CONFIG_ISA_ARCV2)         += memset-archs.o strcmp-archs.o
+ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+lib-$(CONFIG_ISA_ARCV2)         +=memcpy-archs-unaligned.o
+else
+lib-$(CONFIG_ISA_ARCV2)         +=memcpy-archs.o
+endif
diff --git a/arch/arc/lib/memcpy-archs-unaligned.S b/arch/arc/lib/memcpy-archs-unaligned.S
new file mode 100644
index 000000000000..28993a73fdde
--- /dev/null
+++ b/arch/arc/lib/memcpy-archs-unaligned.S
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * ARCv2 memcpy implementation optimized for unaligned memory access using.
+ *
+ * Copyright (C) 2019 Synopsys
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+#include <linux/linkage.h>
+#ifdef CONFIG_ARC_HAS_LL64
+# define LOADX(DST,RX)          ldd.ab  DST, [RX, 8]
+# define STOREX(SRC,RX)         std.ab  SRC, [RX, 8]
+# define ZOLSHFT                5
+# define ZOLAND                 0x1F
+#else
+# define LOADX(DST,RX)          ld.ab   DST, [RX, 4]
+# define STOREX(SRC,RX)         st.ab   SRC, [RX, 4]
+# define ZOLSHFT                4
+# define ZOLAND                 0xF
+#endif
+ENTRY_CFI(memcpy)
+        mov     r3, r0          ; don;t clobber ret val
+        lsr.f   lp_count, r2, ZOLSHFT
+        lpnz    @.Lcopy32_64bytes
+        ;; LOOP START
+        LOADX   (r6, r1)
+        LOADX   (r8, r1)
+        LOADX   (r10, r1)
+        LOADX   (r4, r1)
+        STOREX  (r6, r3)
+        STOREX  (r8, r3)
+        STOREX  (r10, r3)
+        STOREX  (r4, r3)
+.Lcopy32_64bytes:
+        and.f   lp_count, r2, ZOLAND ;Last remaining 31 bytes
+        lpnz    @.Lcopyremainingbytes
+        ;; LOOP START
+        ldb.ab  r5, [r1, 1]
+        stb.ab  r5, [r3, 1]
+.Lcopyremainingbytes:
+        j       [blink]
+END_CFI(memcpy)
diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig
index 8eff057efcae..2eaecfb063a7 100644
--- a/arch/arc/plat-eznps/Kconfig
+++ b/arch/arc/plat-eznps/Kconfig
@@ -26,8 +26,8 @@ config EZNPS_MTM_EXT
        help
          Here we add new hierarchy for CPUs topology.
          We got:
-                Core
+            Core
-                Thread
+            Thread
          At the new thread level each CPU represent one HW thread.
          At highest hierarchy each core contain 16 threads,
          any of them seem like CPU from Linux point of view.
@@ -35,10 +35,10 @@ config EZNPS_MTM_EXT
          core and HW scheduler round robin between them.
 config EZNPS_MEM_ERROR_ALIGN
-       bool "ARC-EZchip Memory error as an exception"
+        bool "ARC-EZchip Memory error as an exception"
-       depends on EZNPS_MTM_EXT
+        depends on EZNPS_MTM_EXT
-       default n
+        default n
-       help
+        help
          On the real chip of the NPS, user memory errors are handled
          as a machine check exception, which is fatal, whereas on
          simulator platform for NPS, is handled as a Level 2 interrupt
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index 7d5a44a06648..f676592d8402 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -90,7 +90,7 @@ void __init cns3xxx_map_io(void)
 /* used by entry-macro.S */
 void __init cns3xxx_init_irq(void)
 {
-        gic_init(0, 29, IOMEM(CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT),
+        gic_init(IOMEM(CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT),
                 IOMEM(CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT));
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 117b2541ef3d..7e34b9eba5de 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -159,7 +159,6 @@ config ARM64
        select IRQ_DOMAIN
        select IRQ_FORCED_THREADING
        select MODULES_USE_ELF_RELA
-        select MULTI_IRQ_HANDLER
        select NEED_DMA_MAP_STATE
        select NEED_SG_DMA_LENGTH
        select OF
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 2afb1338b48a..5f1437099b99 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -77,6 +77,7 @@
 #define ARM_CPU_IMP_QCOM                0x51
 #define ARM_CPU_IMP_NVIDIA              0x4E
 #define ARM_CPU_IMP_FUJITSU             0x46
+#define ARM_CPU_IMP_HISI                0x48
 #define ARM_CPU_PART_AEM_V8             0xD0F
 #define ARM_CPU_PART_FOUNDATION         0xD00
@@ -107,6 +108,8 @@
 #define FUJITSU_CPU_PART_A64FX          0x001
+#define HISI_CPU_PART_TSV110            0xD01
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -126,10 +129,11 @@
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
+#define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001             MIDR_FUJITSU_A64FX
-#define MIDR_FUJITSU_ERRATUM_010001_MASK        (~MIDR_VARIANT(1))
+#define MIDR_FUJITSU_ERRATUM_010001_MASK        (~MIDR_CPU_VAR_REV(1, 0))
 #define TCR_CLEAR_FUJITSU_ERRATUM_010001        (TCR_NFD1 | TCR_NFD0)
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index e24e94d28767..4061de10cea6 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -963,6 +963,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
                MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
                MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
                MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+                MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
                { /* sentinel */ }
        };
        char const *str = "command line option";
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 7fb6f3aa5ceb..7a679caf4585 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -91,8 +91,6 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
        unsigned long probe_addr = (unsigned long)p->addr;
-        extern char __start_rodata[];
-        extern char __end_rodata[];
        if (probe_addr & 0x3)
                return -EINVAL;
@@ -100,10 +98,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
        /* copy instruction */
        p->opcode = le32_to_cpu(*p->addr);
-        if (in_exception_text(probe_addr))
+        if (search_exception_tables(probe_addr))
-                return -EINVAL;
-        if (probe_addr >= (unsigned long) __start_rodata &&
-            probe_addr <= (unsigned long) __end_rodata)
                return -EINVAL;
        /* decode instruction */
@@ -476,26 +471,37 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
        return DBG_HOOK_HANDLED;
 }
-bool arch_within_kprobe_blacklist(unsigned long addr)
+/*
+ * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
+ * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
+ */
+int __init arch_populate_kprobe_blacklist(void)
 {
-        if ((addr >= (unsigned long)__kprobes_text_start &&
+        int ret;
-            addr < (unsigned long)__kprobes_text_end) ||
-            (addr >= (unsigned long)__entry_text_start &&
+        ret = kprobe_add_area_blacklist((unsigned long)__entry_text_start,
-            addr < (unsigned long)__entry_text_end) ||
+                                        (unsigned long)__entry_text_end);
-            (addr >= (unsigned long)__idmap_text_start &&
+        if (ret)
-            addr < (unsigned long)__idmap_text_end) ||
+                return ret;
-            (addr >= (unsigned long)__hyp_text_start &&
+        ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
-            addr < (unsigned long)__hyp_text_end) ||
+                                        (unsigned long)__irqentry_text_end);
-            !!search_exception_tables(addr))
+        if (ret)
-                return true;
+                return ret;
+        ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start,
-        if (!is_kernel_in_hyp_mode()) {
+                                        (unsigned long)__exception_text_end);
-                if ((addr >= (unsigned long)__hyp_idmap_text_start &&
+        if (ret)
-                    addr < (unsigned long)__hyp_idmap_text_end))
+                return ret;
-                        return true;
+        ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start,
-        }
+                                        (unsigned long)__idmap_text_end);
+        if (ret)
-        return false;
+                return ret;
+        ret = kprobe_add_area_blacklist((unsigned long)__hyp_text_start,
+                                        (unsigned long)__hyp_text_end);
+        if (ret || is_kernel_in_hyp_mode())
+                return ret;
+        ret = kprobe_add_area_blacklist((unsigned long)__hyp_idmap_text_start,
+                                        (unsigned long)__hyp_idmap_text_end);
+        return ret;
 }
 void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 1a29f2695ff2..d908b5e9e949 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -143,6 +143,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
        if (trace->nr_entries < trace->max_entries)
                trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);
 static noinline void __save_stack_trace(struct task_struct *tsk,
        struct stack_trace *trace, unsigned int nosched)
diff --git a/arch/mips/bcm47xx/workarounds.c b/arch/mips/bcm47xx/workarounds.c
index 46eddbec8d9f..0ab95dd431b3 100644
--- a/arch/mips/bcm47xx/workarounds.c
+++ b/arch/mips/bcm47xx/workarounds.c
@@ -24,6 +24,7 @@ void __init bcm47xx_workarounds(void)
        case BCM47XX_BOARD_NETGEAR_WNR3500L:
                bcm47xx_workarounds_enable_usb_power(12);
                break;
+        case BCM47XX_BOARD_NETGEAR_WNDR3400V2:
        case BCM47XX_BOARD_NETGEAR_WNDR3400_V3:
                bcm47xx_workarounds_enable_usb_power(21);
                break;
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index e77672539e8e..e4456e450f94 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -21,15 +21,15 @@
 #endif
 #ifdef CONFIG_CPU_MICROMIPS
-#define NOP_INSN "nop32"
+#define B_INSN "b32"
 #else
-#define NOP_INSN "nop"
+#define B_INSN "b"
 #endif
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-        asm_volatile_goto("1:\t" NOP_INSN "\n\t"
+        asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
-                "nop\n\t"
+                "2:\tnop\n\t"
                ".pushsection __jump_table,  \"aw\"\n\t"
                WORD_INSN " 1b, %l[l_yes], %0\n\t"
                ".popsection\n\t"
diff --git a/arch/mips/include/uapi/asm/posix_types.h b/arch/mips/include/uapi/asm/posix_types.h
index 6aa49c10f88f..f0ccb5b90ce9 100644
--- a/arch/mips/include/uapi/asm/posix_types.h
+++ b/arch/mips/include/uapi/asm/posix_types.h
@@ -21,13 +21,6 @@
 typedef long            __kernel_daddr_t;
 #define __kernel_daddr_t __kernel_daddr_t
-#if (_MIPS_SZLONG == 32)
-typedef struct {
-        long    val[2];
-} __kernel_fsid_t;
-#define __kernel_fsid_t __kernel_fsid_t
-#endif
 #include <asm-generic/posix_types.h>
 #endif /* _ASM_POSIX_TYPES_H */
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index cb7e9ed7a453..33ee0d18fb0a 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -140,6 +140,13 @@ SECTIONS
        PERCPU_SECTION(1 << CONFIG_MIPS_L1_CACHE_SHIFT)
 #endif
+#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+        .appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
+                *(.appended_dtb)
+                KEEP(*(.appended_dtb))
+        }
+#endif
 #ifdef CONFIG_RELOCATABLE
        . = ALIGN(4);
@@ -164,11 +171,6 @@ SECTIONS
        __appended_dtb = .;
        /* leave space for appended DTB */
        . += 0x100000;
-#elif defined(CONFIG_MIPS_ELF_APPENDED_DTB)
-        .appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
-                *(.appended_dtb)
-                KEEP(*(.appended_dtb))
-        }
 #endif
        /*
         * Align to 64K in attempt to eliminate holes before the
diff --git a/arch/mips/loongson64/lemote-2f/irq.c b/arch/mips/loongson64/lemote-2f/irq.c
index 9e33e45aa17c..b213cecb8e3a 100644
--- a/arch/mips/loongson64/lemote-2f/irq.c
+++ b/arch/mips/loongson64/lemote-2f/irq.c
@@ -103,7 +103,7 @@ static struct irqaction ip6_irqaction = {
 static struct irqaction cascade_irqaction = {
        .handler = no_action,
        .name = "cascade",
-        .flags = IRQF_NO_THREAD,
+        .flags = IRQF_NO_THREAD | IRQF_NO_SUSPEND,
 };
 void __init mach_init_irq(void)
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index d34ad1657d7b..598cdcdd1355 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -352,7 +352,7 @@ static inline bool strict_kernel_rwx_enabled(void)
 #if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) &&   \
        defined (CONFIG_PPC_64K_PAGES)
 #define MAX_PHYSMEM_BITS        51
-#else
+#elif defined(CONFIG_SPARSEMEM)
 #define MAX_PHYSMEM_BITS        46
 #endif
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 1afe90ade595..bbc06bd72b1f 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -82,10 +82,10 @@ struct vdso_data {
        __u32 icache_block_size;                /* L1 i-cache block size     */
        __u32 dcache_log_block_size;            /* L1 d-cache log block size */
        __u32 icache_log_block_size;            /* L1 i-cache log block size */
-        __s32 wtom_clock_sec;                   /* Wall to monotonic clock */
+        __u32 stamp_sec_fraction;               /* fractional seconds of stamp_xtime */
-        __s32 wtom_clock_nsec;
+        __s32 wtom_clock_nsec;                  /* Wall to monotonic clock nsec */
-        struct timespec stamp_xtime;    /* xtime as at tb_orig_stamp */
+        __s64 wtom_clock_sec;                   /* Wall to monotonic clock sec */
-        __u32 stamp_sec_fraction;       /* fractional seconds of stamp_xtime */
+        struct timespec stamp_xtime;            /* xtime as at tb_orig_stamp */
        __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
        __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index 6f1c11e0691f..7534ecff5e92 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -24,9 +24,6 @@ BEGIN_MMU_FTR_SECTION
        li      r10,0
        mtspr   SPRN_SPRG_603_LRU,r10           /* init SW LRU tracking */
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
-        lis     r10, (swapper_pg_dir - PAGE_OFFSET)@h
-        ori     r10, r10, (swapper_pg_dir - PAGE_OFFSET)@l
-        mtspr   SPRN_SPRG_PGDIR, r10
 BEGIN_FTR_SECTION
        bl      __init_fpu_registers
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index ce6a972f2584..48051c8977c5 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -855,6 +855,9 @@ __secondary_start:
        li      r3,0
        stw     r3, RTAS_SP(r4)         /* 0 => not in RTAS */
 #endif
+        lis     r4, (swapper_pg_dir - PAGE_OFFSET)@h
+        ori     r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
+        mtspr   SPRN_SPRG_PGDIR, r4
        /* enable MMU and jump to start_secondary */
        li      r4,MSR_KERNEL
@@ -942,6 +945,9 @@ start_here:
        li      r3,0
        stw     r3, RTAS_SP(r4)         /* 0 => not in RTAS */
 #endif
+        lis     r4, (swapper_pg_dir - PAGE_OFFSET)@h
+        ori     r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
+        mtspr   SPRN_SPRG_PGDIR, r4
        /* stack */
        lis     r1,init_thread_union@ha
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index 9b8631533e02..b33bafb8fcea 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -190,29 +190,22 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
        bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED);
        ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED);
-        if (bcs || ccd || count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
+        if (bcs || ccd) {
-                bool comma = false;
                seq_buf_printf(&s, "Mitigation: ");
-                if (bcs) {
+                if (bcs)
                        seq_buf_printf(&s, "Indirect branch serialisation (kernel only)");
-                        comma = true;
-                }
-                if (ccd) {
+                if (bcs && ccd)
-                        if (comma)
-                                seq_buf_printf(&s, ", ");
-                        seq_buf_printf(&s, "Indirect branch cache disabled");
-                        comma = true;
-                }
-                if (comma)
                        seq_buf_printf(&s, ", ");
-                seq_buf_printf(&s, "Software count cache flush");
+                if (ccd)
+                        seq_buf_printf(&s, "Indirect branch cache disabled");
+        } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
+                seq_buf_printf(&s, "Mitigation: Software count cache flush");
                if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
-                        seq_buf_printf(&s, "(hardware accelerated)");
+                        seq_buf_printf(&s, " (hardware accelerated)");
        } else if (btb_flush_enabled) {
                seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
        } else {
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index a4ed9edfd5f0..1f324c28705b 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -92,7 +92,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
         * At this point, r4,r5 contain our sec/nsec values.
         */
-        lwa     r6,WTOM_CLOCK_SEC(r3)
+        ld      r6,WTOM_CLOCK_SEC(r3)
        lwa     r9,WTOM_CLOCK_NSEC(r3)
        /* We now have our result in r6,r9. We create a fake dependency
@@ -125,7 +125,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
        bne     cr6,75f
        /* CLOCK_MONOTONIC_COARSE */
-        lwa     r6,WTOM_CLOCK_SEC(r3)
+        ld      r6,WTOM_CLOCK_SEC(r3)
        lwa     r9,WTOM_CLOCK_NSEC(r3)
        /* check if counter has updated */
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 1f13494efb2b..a6c491f18a04 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -70,12 +70,12 @@ _GLOBAL(hash_page)
        lis     r0,KERNELBASE@h         /* check if kernel address */
        cmplw   0,r4,r0
        ori     r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
-        mfspr   r5, SPRN_SPRG_PGDIR     /* virt page-table root */
+        mfspr   r5, SPRN_SPRG_PGDIR     /* phys page-table root */
        blt+    112f                    /* assume user more likely */
-        lis     r5,swapper_pg_dir@ha    /* if kernel address, use */
+        lis     r5, (swapper_pg_dir - PAGE_OFFSET)@ha   /* if kernel address, use */
-        addi    r5,r5,swapper_pg_dir@l  /* kernel page table */
+        addi    r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l        /* kernel page table */
        rlwimi  r3,r9,32-12,29,29       /* MSR_PR -> _PAGE_USER */
-112:    tophys(r5, r5)
+112:
 #ifndef CONFIG_PTE_64BIT
        rlwimi  r5,r4,12,20,29          /* insert top 10 bits of address */
        lwz     r8,0(r5)                /* get pmd entry */
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 315a67b8896b..90154df8f125 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -13,8 +13,9 @@
 */
 #include <linux/types.h>
-#include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <linux/errno.h>
+#include <linux/limits.h>
 #include <asm/asm.h>
 #include "ctype.h"
 #include "string.h"
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 6461a16b4559..e4ba467a9fc6 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -103,9 +103,13 @@ static int hv_cpu_init(unsigned int cpu)
        u64 msr_vp_index;
        struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
        void **input_arg;
+        struct page *pg;
        input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
-        *input_arg = page_address(alloc_page(GFP_KERNEL));
+        pg = alloc_page(GFP_KERNEL);
+        if (unlikely(!pg))
+                return -ENOMEM;
+        *input_arg = page_address(pg);
        hv_get_vp_index(msr_vp_index);
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 3417110574c1..31c379c1da41 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _CPU_DEVICE_ID
+#ifndef _ASM_X86_CPU_DEVICE_ID
-#define _CPU_DEVICE_ID 1
+#define _ASM_X86_CPU_DEVICE_ID
 /*
 * Declare drivers belonging to specific x86 CPUs
@@ -9,8 +9,6 @@
 #include <linux/mod_devicetable.h>
-extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 /*
 * Match specific microcode revisions.
 *
@@ -22,21 +20,22 @@ extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 */
 struct x86_cpu_desc {
-        __u8    x86_family;
+        u8      x86_family;
-        __u8    x86_vendor;
+        u8      x86_vendor;
-        __u8    x86_model;
+        u8      x86_model;
-        __u8    x86_stepping;
+        u8      x86_stepping;
-        __u32   x86_microcode_rev;
+        u32     x86_microcode_rev;
 };
-#define INTEL_CPU_DESC(mod, step, rev) {                        \
+#define INTEL_CPU_DESC(model, stepping, revision) {             \
-        .x86_family = 6,                                        \
+        .x86_family             = 6,                            \
-        .x86_vendor = X86_VENDOR_INTEL,                         \
+        .x86_vendor             = X86_VENDOR_INTEL,             \
-        .x86_model = mod,                                       \
+        .x86_model              = (model),                      \
-        .x86_stepping = step,                                   \
+        .x86_stepping           = (stepping),                   \
-        .x86_microcode_rev = rev,                               \
+        .x86_microcode_rev      = (revision),                   \
 }
+extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table);
-#endif
+#endif /* _ASM_X86_CPU_DEVICE_ID */
diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h
index aaedd73ea2c6..df700a6cc869 100644
--- a/arch/x86/include/asm/processor-cyrix.h
+++ b/arch/x86/include/asm/processor-cyrix.h
@@ -3,19 +3,6 @@
 * NSC/Cyrix CPU indexed register access. Must be inlined instead of
 * macros to ensure correct access ordering
 * Access order is always 0x22 (=offset), 0x23 (=value)
- *
- * When using the old macros a line like
- *   setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
- * gets expanded to:
- *  do {
- *    outb((CX86_CCR2), 0x22);
- *    outb((({
- *        outb((CX86_CCR2), 0x22);
- *        inb(0x23);
- *    }) | 0x88), 0x23);
- *  } while (0);
- *
- * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23).
 */
 static inline u8 getCx86(u8 reg)
@@ -29,11 +16,3 @@ static inline void setCx86(u8 reg, u8 data)
        outb(reg, 0x22);
        outb(data, 0x23);
 }
-#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); })
-#define setCx86_old(reg, data) do { \
-        outb((reg), 0x22); \
-        outb((data), 0x23); \
-} while (0)
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 58176b56354e..294ed4392a0e 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt) "AGP: " fmt
 #include <linux/kernel.h>
+#include <linux/kcore.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
@@ -57,7 +58,7 @@ int fallback_aper_force __initdata;
 int fix_aperture __initdata = 1;
-#ifdef CONFIG_PROC_VMCORE
+#if defined(CONFIG_PROC_VMCORE) || defined(CONFIG_PROC_KCORE)
 /*
 * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
 * use the same range because it will remain configured in the northbridge.
@@ -66,20 +67,25 @@ int fix_aperture __initdata = 1;
 */
 static unsigned long aperture_pfn_start, aperture_page_count;
-static int gart_oldmem_pfn_is_ram(unsigned long pfn)
+static int gart_mem_pfn_is_ram(unsigned long pfn)
 {
        return likely((pfn < aperture_pfn_start) ||
                      (pfn >= aperture_pfn_start + aperture_page_count));
 }
-static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+static void __init exclude_from_core(u64 aper_base, u32 aper_order)
 {
        aperture_pfn_start = aper_base >> PAGE_SHIFT;
        aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
-        WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+#ifdef CONFIG_PROC_VMCORE
+        WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram));
+#endif
+#ifdef CONFIG_PROC_KCORE
+        WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram));
+#endif
 }
 #else
-static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+static void exclude_from_core(u64 aper_base, u32 aper_order)
 {
 }
 #endif
@@ -474,7 +480,7 @@ out:
                         * may have allocated the range over its e820 RAM
                         * and fixed up the northbridge
                         */
-                        exclude_from_vmcore(last_aper_base, last_aper_order);
+                        exclude_from_core(last_aper_base, last_aper_order);
                        return 1;
                }
@@ -520,7 +526,7 @@ out:
         * overlap with the first kernel's memory. We can't access the
         * range through vmcore even though it should be part of the dump.
         */
-        exclude_from_vmcore(aper_alloc, aper_order);
+        exclude_from_core(aper_alloc, aper_order);
        /* Fix up the north bridges */
        for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index d12226f60168..1d9b8aaea06c 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -124,7 +124,7 @@ static void set_cx86_reorder(void)
        setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
        /* Load/Store Serialize to mem access disable (=reorder it) */
-        setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80);
+        setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80);
        /* set load/store serialize from 1GB to 4GB */
        ccr3 |= 0xe0;
        setCx86(CX86_CCR3, ccr3);
@@ -135,11 +135,11 @@ static void set_cx86_memwb(void)
        pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
        /* CCR2 bit 2: unlock NW bit */
-        setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04);
+        setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04);
        /* set 'Not Write-through' */
        write_cr0(read_cr0() | X86_CR0_NW);
        /* CCR2 bit 2: lock NW bit and set WT1 */
-        setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14);
+        setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14);
 }
 /*
@@ -153,14 +153,14 @@ static void geode_configure(void)
        local_irq_save(flags);
        /* Suspend on halt power saving and enable #SUSP pin */
-        setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88);
+        setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
        ccr3 = getCx86(CX86_CCR3);
        setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);       /* enable MAPEN */
        /* FPU fast, DTE cache, Mem bypass */
-        setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38);
+        setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38);
        setCx86(CX86_CCR3, ccr3);                       /* disable MAPEN */
        set_cx86_memwb();
@@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
                /* GXm supports extended cpuid levels 'ala' AMD */
                if (c->cpuid_level == 2) {
                        /* Enable cxMMX extensions (GX1 Datasheet 54) */
-                        setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1);
+                        setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);
                        /*
                         * GXm : 0x30 ... 0x5f GXm  datasheet 51
@@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
                if (dir1 > 7) {
                        dir0_msn++;  /* M II */
                        /* Enable MMX extensions (App note 108) */
-                        setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1);
+                        setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1);
                } else {
                        /* A 6x86MX - it has the bug. */
                        set_cpu_bug(c, X86_BUG_COMA);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 97f9ada9ceda..5260185cbf7b 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -608,6 +608,8 @@ static int microcode_reload_late(void)
        if (ret > 0)
                microcode_check();
+        pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
        return ret;
 }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dfd3aca82c61..fb32925a2e62 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -905,6 +905,8 @@ int __init hpet_enable(void)
                return 0;
        hpet_set_mapping();
+        if (!hpet_virt_address)
+                return 0;
        /*
         * Read the period and check for a sane value:
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index ff9bfd40429e..d73083021002 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -354,6 +354,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 #endif
        default:
                WARN_ON_ONCE(1);
+                return -EINVAL;
        }
        /*
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 3482460d984d..1bfe5c6e6cfe 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -598,8 +598,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
                        mpf_base = base;
                        mpf_found = true;
-                        pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n",
+                        pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n",
-                                base, base + sizeof(*mpf) - 1, mpf);
+                                base, base + sizeof(*mpf) - 1);
                        memblock_reserve(base, sizeof(*mpf));
                        if (mpf->physptr)
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 9baca3e054be..e7925d668b68 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -94,7 +94,7 @@ static unsigned do_csum(const unsigned char *buff, unsigned len)
                                    : "m" (*(unsigned long *)buff), 
                                    "r" (zero),  "0" (result));
                                --count; 
-                                        buff += 8;
+                                buff += 8;
                        }
                        result = add32_with_carry(result>>32,
                                                  result&0xffffffff); 
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 4fee5c3003ed..139b28a01ce4 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -77,7 +77,7 @@ static void __init pti_print_if_secure(const char *reason)
                pr_info("%s\n", reason);
 }
-enum pti_mode {
+static enum pti_mode {
        PTI_AUTO = 0,
        PTI_FORCE_OFF,
        PTI_FORCE_ON
@@ -602,7 +602,7 @@ static void pti_clone_kernel_text(void)
        set_memory_global(start, (end_global - start) >> PAGE_SHIFT);
 }
-void pti_set_kernel_image_nonglobal(void)
+static void pti_set_kernel_image_nonglobal(void)
 {
        /*
         * The identity map is created with PMDs, regardless of the
diff --git a/block/bio.c b/block/bio.c
index 71a78d9fb8b7..b64cedc7f87c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -849,20 +849,14 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
        size = bio_add_page(bio, bv->bv_page, len,
                                bv->bv_offset + iter->iov_offset);
        if (size == len) {
-                struct page *page;
+                if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
-                int i;
+                        struct page *page;
+                        int i;
+                        mp_bvec_for_each_page(page, bv, i)
+                                get_page(page);
+                }
-                /*
-                 * For the normal O_DIRECT case, we could skip grabbing this
-                 * reference and then not have to put them again when IO
-                 * completes. But this breaks some in-kernel users, like
-                 * splicing to/from a loop device, where we release the pipe
-                 * pages unconditionally. If we can fix that case, we can
-                 * get rid of the get here and the need to call
-                 * bio_release_pages() at IO completion time.
-                 */
-                mp_bvec_for_each_page(page, bv, i)
-                        get_page(page);
                iov_iter_advance(iter, size);
                return 0;
        }
@@ -925,10 +919,12 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 * This takes either an iterator pointing to user memory, or one pointing to
 * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
 * map them into the kernel. On IO completion, the caller should put those
- * pages. For now, when adding kernel pages, we still grab a reference to the
+ * pages. If we're adding kernel pages, and the caller told us it's safe to
- * page. This isn't strictly needed for the common case, but some call paths
+ * do so, we just have to add the pages to the bio directly. We don't grab an
- * end up releasing pages from eg a pipe and we can't easily control these.
+ * extra reference to those pages (the user should already have that), and we
- * See comment in __bio_iov_bvec_add_pages().
+ * don't put the page on IO completion. The caller needs to check if the bio is
+ * flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be
+ * released.
 *
 * The function tries, but does not guarantee, to pin as many pages as
 * fit into the bio, or are requested in *iter, whatever is smaller. If
@@ -940,6 +936,13 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
        const bool is_bvec = iov_iter_is_bvec(iter);
        unsigned short orig_vcnt = bio->bi_vcnt;
+        /*
+         * If this is a BVEC iter, then the pages are kernel pages. Don't
+         * release them on IO completion, if the caller asked us to.
+         */
+        if (is_bvec && iov_iter_bvec_no_ref(iter))
+                bio_set_flag(bio, BIO_NO_PAGE_REF);
        do {
                int ret;
@@ -1696,7 +1699,8 @@ static void bio_dirty_fn(struct work_struct *work)
                next = bio->bi_private;
                bio_set_pages_dirty(bio);
-                bio_release_pages(bio);
+                if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+                        bio_release_pages(bio);
                bio_put(bio);
        }
 }
@@ -1713,7 +1717,8 @@ void bio_check_pages_dirty(struct bio *bio)
                        goto defer;
        }
-        bio_release_pages(bio);
+        if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+                bio_release_pages(bio);
        bio_put(bio);
        return;
 defer:
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 77f37ef8ef06..617a2b3f7582 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1736,8 +1736,8 @@ out:
 /**
 * blkcg_schedule_throttle - this task needs to check for throttling
- * @q - the request queue IO was submitted on
+ * @q: the request queue IO was submitted on
- * @use_memdelay - do we charge this to memory delay for PSI
+ * @use_memdelay: do we charge this to memory delay for PSI
 *
 * This is called by the IO controller when we know there's delay accumulated
 * for the blkg for this task.  We do not pass the blkg because there are places
@@ -1769,8 +1769,9 @@ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
 /**
 * blkcg_add_delay - add delay to this blkg
- * @now - the current time in nanoseconds
+ * @blkg: blkg of interest
- * @delta - how many nanoseconds of delay to add
+ * @now: the current time in nanoseconds
+ * @delta: how many nanoseconds of delay to add
 *
 * Charge @delta to the blkg's current delay accumulation.  This is used to
 * throttle tasks if an IO controller thinks we need more throttling.
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 2620baa1f699..507212d75ee2 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -75,6 +75,7 @@
 #include <linux/blk-mq.h>
 #include "blk-rq-qos.h"
 #include "blk-stat.h"
+#include "blk.h"
 #define DEFAULT_SCALE_COOKIE 1000000U
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a9c181603cbd..70b210a308c4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -782,7 +782,6 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
        if (kick_requeue_list)
                blk_mq_kick_requeue_list(q);
 }
-EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
@@ -1093,8 +1092,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
        bool ret;
        if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
-                if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+                blk_mq_sched_mark_restart_hctx(hctx);
-                        set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
                /*
                 * It's possible that a tag was freed in the window between the
@@ -2857,7 +2855,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
        /*
         * Default to classic polling
         */
-        q->poll_nsec = -1;
+        q->poll_nsec = BLK_MQ_POLL_CLASSIC;
        blk_mq_init_cpu_queues(q, set->nr_hw_queues);
        blk_mq_add_queue_tag_set(set, q);
@@ -3392,7 +3390,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
 {
        struct request *rq;
-        if (q->poll_nsec == -1)
+        if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
                return false;
        if (!blk_qc_t_is_internal(cookie))
diff --git a/block/blk-mq.h b/block/blk-mq.h
index c11353a3749d..0ed8e5a8729f 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -41,6 +41,8 @@ void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
+void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
+                                bool kick_requeue_list);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 59685918167e..422327089e0f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -360,8 +360,8 @@ static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
 {
        int val;
-        if (q->poll_nsec == -1)
+        if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
-                val = -1;
+                val = BLK_MQ_POLL_CLASSIC;
        else
                val = q->poll_nsec / 1000;
@@ -380,10 +380,12 @@ static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
        if (err < 0)
                return err;
-        if (val == -1)
+        if (val == BLK_MQ_POLL_CLASSIC)
-                q->poll_nsec = -1;
+                q->poll_nsec = BLK_MQ_POLL_CLASSIC;
-        else
+        else if (val >= 0)
                q->poll_nsec = val * 1000;
+        else
+                return -EINVAL;
        return count;
 }
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 78db97687f26..c4b06cc075f9 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -800,6 +800,7 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
        match.hrv = hrv;
        dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb);
+        put_device(dev);
        return !!dev;
 }
 EXPORT_SYMBOL(acpi_dev_present);
diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig
index 57410f9c5d44..c52c738e554a 100644
--- a/drivers/auxdisplay/Kconfig
+++ b/drivers/auxdisplay/Kconfig
@@ -164,9 +164,7 @@ config ARM_CHARLCD
          line and the Linux version on the second line, but that's
          still useful.
-endif # AUXDISPLAY
+menuconfig PARPORT_PANEL
-menuconfig PANEL
        tristate "Parallel port LCD/Keypad Panel support"
        depends on PARPORT
        select CHARLCD
@@ -178,7 +176,7 @@ menuconfig PANEL
          compiled as a module, or linked into the kernel and started at boot.
          If you don't understand what all this is about, say N.
-if PANEL
+if PARPORT_PANEL
 config PANEL_PARPORT
        int "Default parallel port number (0=LPT1)"
@@ -419,8 +417,11 @@ config PANEL_LCD_PIN_BL
          Default for the 'BL' pin in custom profile is '0' (uncontrolled).
+endif # PARPORT_PANEL
 config PANEL_CHANGE_MESSAGE
        bool "Change LCD initialization message ?"
+        depends on CHARLCD
        default "n"
        ---help---
          This allows you to replace the boot message indicating the kernel version
@@ -444,7 +445,34 @@ config PANEL_BOOT_MESSAGE
          An empty message will only clear the display at driver init time. Any other
          printf()-formatted message is valid with newline and escape codes.
-endif # PANEL
+choice
+        prompt "Backlight initial state"
+        default CHARLCD_BL_FLASH
+        config CHARLCD_BL_OFF
+                bool "Off"
+                help
+                  Backlight is initially turned off
+        config CHARLCD_BL_ON
+                bool "On"
+                help
+                  Backlight is initially turned on
+        config CHARLCD_BL_FLASH
+                bool "Flash"
+                help
+                  Backlight is flashed briefly on init
+endchoice
+endif # AUXDISPLAY
+config PANEL
+        tristate "Parallel port LCD/Keypad Panel support (OLD OPTION)"
+        depends on PARPORT
+        select AUXDISPLAY
+        select PARPORT_PANEL
 config CHARLCD
        tristate "Character LCD core support" if COMPILE_TEST
diff --git a/drivers/auxdisplay/Makefile b/drivers/auxdisplay/Makefile
index 7ac6776ca3f6..cf54b5efb07e 100644
--- a/drivers/auxdisplay/Makefile
+++ b/drivers/auxdisplay/Makefile
@@ -10,4 +10,4 @@ obj-$(CONFIG_CFAG12864B)	+= cfag12864b.o cfag12864bfb.o
 obj-$(CONFIG_IMG_ASCII_LCD)     += img-ascii-lcd.o
 obj-$(CONFIG_HD44780)           += hd44780.o
 obj-$(CONFIG_HT16K33)           += ht16k33.o
-obj-$(CONFIG_PANEL)             += panel.o
+obj-$(CONFIG_PARPORT_PANEL)     += panel.o
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index 60e0b772673f..92745efefb54 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -91,7 +91,7 @@ struct charlcd_priv {
        unsigned long long drvdata[0];
 };
-#define to_priv(p)      container_of(p, struct charlcd_priv, lcd)
+#define charlcd_to_priv(p)      container_of(p, struct charlcd_priv, lcd)
 /* Device single-open policy control */
 static atomic_t charlcd_available = ATOMIC_INIT(1);
@@ -105,7 +105,7 @@ static void long_sleep(int ms)
 /* turn the backlight on or off */
 static void charlcd_backlight(struct charlcd *lcd, int on)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        if (!lcd->ops->backlight)
                return;
@@ -134,7 +134,7 @@ static void charlcd_bl_off(struct work_struct *work)
 /* turn the backlight on for a little while */
 void charlcd_poke(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        if (!lcd->ops->backlight)
                return;
@@ -152,7 +152,7 @@ EXPORT_SYMBOL_GPL(charlcd_poke);
 static void charlcd_gotoxy(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        unsigned int addr;
        /*
@@ -170,7 +170,7 @@ static void charlcd_gotoxy(struct charlcd *lcd)
 static void charlcd_home(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        priv->addr.x = 0;
        priv->addr.y = 0;
@@ -179,7 +179,7 @@ static void charlcd_home(struct charlcd *lcd)
 static void charlcd_print(struct charlcd *lcd, char c)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        if (priv->addr.x < lcd->bwidth) {
                if (lcd->char_conv)
@@ -211,7 +211,7 @@ static void charlcd_clear_fast(struct charlcd *lcd)
 /* clears the display and resets X/Y */
 static void charlcd_clear_display(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        lcd->ops->write_cmd(lcd, LCD_CMD_DISPLAY_CLEAR);
        priv->addr.x = 0;
@@ -223,7 +223,7 @@ static void charlcd_clear_display(struct charlcd *lcd)
 static int charlcd_init_display(struct charlcd *lcd)
 {
        void (*write_cmd_raw)(struct charlcd *lcd, int cmd);
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        u8 init;
        if (lcd->ifwidth != 4 && lcd->ifwidth != 8)
@@ -369,7 +369,7 @@ static bool parse_xy(const char *s, unsigned long *x, unsigned long *y)
 static inline int handle_lcd_special_code(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        /* LCD special codes */
@@ -580,7 +580,7 @@ static inline int handle_lcd_special_code(struct charlcd *lcd)
 static void charlcd_write_char(struct charlcd *lcd, char c)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        /* first, we'll test if we're in escape mode */
        if ((c != '\n') && priv->esc_seq.len >= 0) {
@@ -705,7 +705,7 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf,
 static int charlcd_open(struct inode *inode, struct file *file)
 {
-        struct charlcd_priv *priv = to_priv(the_charlcd);
+        struct charlcd_priv *priv = charlcd_to_priv(the_charlcd);
        int ret;
        ret = -EBUSY;
@@ -763,10 +763,24 @@ static void charlcd_puts(struct charlcd *lcd, const char *s)
        }
 }
+#ifdef CONFIG_PANEL_BOOT_MESSAGE
+#define LCD_INIT_TEXT CONFIG_PANEL_BOOT_MESSAGE
+#else
+#define LCD_INIT_TEXT "Linux-" UTS_RELEASE "\n"
+#endif
+#ifdef CONFIG_CHARLCD_BL_ON
+#define LCD_INIT_BL "\x1b[L+"
+#elif defined(CONFIG_CHARLCD_BL_FLASH)
+#define LCD_INIT_BL "\x1b[L*"
+#else
+#define LCD_INIT_BL "\x1b[L-"
+#endif
 /* initialize the LCD driver */
 static int charlcd_init(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        int ret;
        if (lcd->ops->backlight) {
@@ -784,13 +798,8 @@ static int charlcd_init(struct charlcd *lcd)
                return ret;
        /* display a short message */
-#ifdef CONFIG_PANEL_CHANGE_MESSAGE
+        charlcd_puts(lcd, "\x1b[Lc\x1b[Lb" LCD_INIT_BL LCD_INIT_TEXT);
-#ifdef CONFIG_PANEL_BOOT_MESSAGE
-        charlcd_puts(lcd, "\x1b[Lc\x1b[Lb\x1b[L*" CONFIG_PANEL_BOOT_MESSAGE);
-#endif
-#else
-        charlcd_puts(lcd, "\x1b[Lc\x1b[Lb\x1b[L*Linux-" UTS_RELEASE "\n");
-#endif
        /* clear the display on the next device opening */
        priv->must_clear = true;
        charlcd_home(lcd);
@@ -818,6 +827,12 @@ struct charlcd *charlcd_alloc(unsigned int drvdata_size)
 }
 EXPORT_SYMBOL_GPL(charlcd_alloc);
+void charlcd_free(struct charlcd *lcd)
+{
+        kfree(charlcd_to_priv(lcd));
+}
+EXPORT_SYMBOL_GPL(charlcd_free);
 static int panel_notify_sys(struct notifier_block *this, unsigned long code,
                            void *unused)
 {
@@ -866,7 +881,7 @@ EXPORT_SYMBOL_GPL(charlcd_register);
 int charlcd_unregister(struct charlcd *lcd)
 {
-        struct charlcd_priv *priv = to_priv(lcd);
+        struct charlcd_priv *priv = charlcd_to_priv(lcd);
        unregister_reboot_notifier(&panel_notifier);
        charlcd_puts(lcd, "\x0cLCD driver unloaded.\x1b[Lc\x1b[Lb\x1b[L-");
diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c
index 9ad93ea42fdc..ab15b64707ad 100644
--- a/drivers/auxdisplay/hd44780.c
+++ b/drivers/auxdisplay/hd44780.c
@@ -271,7 +271,7 @@ static int hd44780_probe(struct platform_device *pdev)
        return 0;
 fail:
-        kfree(lcd);
+        charlcd_free(lcd);
        return ret;
 }
@@ -280,6 +280,8 @@ static int hd44780_remove(struct platform_device *pdev)
        struct charlcd *lcd = platform_get_drvdata(pdev);
        charlcd_unregister(lcd);
+        charlcd_free(lcd);
        return 0;
 }
diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c
index 21b9b2f2470a..e06de63497cf 100644
--- a/drivers/auxdisplay/panel.c
+++ b/drivers/auxdisplay/panel.c
@@ -1620,7 +1620,7 @@ err_lcd_unreg:
        if (lcd.enabled)
                charlcd_unregister(lcd.charlcd);
 err_unreg_device:
-        kfree(lcd.charlcd);
+        charlcd_free(lcd.charlcd);
        lcd.charlcd = NULL;
        parport_unregister_device(pprt);
        pprt = NULL;
@@ -1647,7 +1647,7 @@ static void panel_detach(struct parport *port)
        if (lcd.enabled) {
                charlcd_unregister(lcd.charlcd);
                lcd.initialized = false;
-                kfree(lcd.charlcd);
+                charlcd_free(lcd.charlcd);
                lcd.charlcd = NULL;
        }
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 76c9969b7124..96a6dc9d305c 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1469,12 +1469,12 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
        if (IS_ERR(gpd_data))
                return PTR_ERR(gpd_data);
-        genpd_lock(genpd);
        ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
        if (ret)
                goto out;
+        genpd_lock(genpd);
        dev_pm_domain_set(dev, &genpd->domain);
        genpd->device_count++;
@@ -1482,9 +1482,8 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
        list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
- out:
        genpd_unlock(genpd);
+ out:
        if (ret)
                genpd_free_dev_data(dev, gpd_data);
        else
@@ -1533,15 +1532,15 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
        genpd->device_count--;
        genpd->max_off_time_changed = true;
-        if (genpd->detach_dev)
-                genpd->detach_dev(genpd, dev);
        dev_pm_domain_set(dev, NULL);
        list_del_init(&pdd->list_node);
        genpd_unlock(genpd);
+        if (genpd->detach_dev)
+                genpd->detach_dev(genpd, dev);
        genpd_free_dev_data(dev, gpd_data);
        return 0;
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 1fad9291f6aa..7fc5a18e02ad 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -472,7 +472,7 @@ static int software_node_read_string_array(const struct fwnode_handle *fwnode,
                                                val, nval);
 }
-struct fwnode_handle *
+static struct fwnode_handle *
 software_node_get_parent(const struct fwnode_handle *fwnode)
 {
        struct software_node *swnode = to_software_node(fwnode);
@@ -481,7 +481,7 @@ software_node_get_parent(const struct fwnode_handle *fwnode)
                        NULL;
 }
-struct fwnode_handle *
+static struct fwnode_handle *
 software_node_get_next_child(const struct fwnode_handle *fwnode,
                             struct fwnode_handle *child)
 {
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1e6edd568214..bf1c61cab8eb 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -656,7 +656,7 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
                        return -EBADF;
                l = f->f_mapping->host->i_bdev->bd_disk->private_data;
-                if (l->lo_state == Lo_unbound) {
+                if (l->lo_state != Lo_bound) {
                        return -EINVAL;
                }
                f = l->lo_backing_file;
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 96670eefaeb2..377a694dc228 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -749,8 +749,12 @@ static int pcd_detect(void)
                return 0;
        printk("%s: No CD-ROM drive found\n", name);
-        for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
+        for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+                blk_cleanup_queue(cd->disk->queue);
+                cd->disk->queue = NULL;
+                blk_mq_free_tag_set(&cd->tag_set);
                put_disk(cd->disk);
+        }
        pi_unregister_driver(par_drv);
        return -1;
 }
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index e92e7a8eeeb2..103b617cdc31 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -761,8 +761,12 @@ static int pf_detect(void)
                return 0;
        printk("%s: No ATAPI disk detected\n", name);
-        for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
+        for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+                blk_cleanup_queue(pf->disk->queue);
+                pf->disk->queue = NULL;
+                blk_mq_free_tag_set(&pf->tag_set);
                put_disk(pf->disk);
+        }
        pi_unregister_driver(par_drv);
        return -1;
 }
@@ -1047,13 +1051,15 @@ static void __exit pf_exit(void)
        int unit;
        unregister_blkdev(major, name);
        for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
-                if (!pf->present)
+                if (pf->present)
-                        continue;
+                        del_gendisk(pf->disk);
-                del_gendisk(pf->disk);
                blk_cleanup_queue(pf->disk->queue);
                blk_mq_free_tag_set(&pf->tag_set);
                put_disk(pf->disk);
-                pi_release(pf->pi);
+                if (pf->present)
+                        pi_release(pf->pi);
        }
 }
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4ba967d65cf9..2210c1b9491b 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -833,7 +833,7 @@ static int parse_rbd_opts_token(char *c, void *private)
                pctx->opts->queue_depth = intval;
                break;
        case Opt_alloc_size:
-                if (intval < 1) {
+                if (intval < SECTOR_SIZE) {
                        pr_err("alloc_size out of range\n");
                        return -EINVAL;
                }
@@ -924,23 +924,6 @@ static void rbd_put_client(struct rbd_client *rbdc)
                kref_put(&rbdc->kref, rbd_client_release);
 }
-static int wait_for_latest_osdmap(struct ceph_client *client)
-{
-        u64 newest_epoch;
-        int ret;
-        ret = ceph_monc_get_version(&client->monc, "osdmap", &newest_epoch);
-        if (ret)
-                return ret;
-        if (client->osdc.osdmap->epoch >= newest_epoch)
-                return 0;
-        ceph_osdc_maybe_request_map(&client->osdc);
-        return ceph_monc_wait_osdmap(&client->monc, newest_epoch,
-                                     client->options->mount_timeout);
-}
 /*
 * Get a ceph client with specific addr and configuration, if one does
 * not exist create it.  Either way, ceph_opts is consumed by this
@@ -960,7 +943,8 @@ static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts)
                 * Using an existing client.  Make sure ->pg_pools is up to
                 * date before we look up the pool id in do_rbd_add().
                 */
-                ret = wait_for_latest_osdmap(rbdc->client);
+                ret = ceph_wait_for_latest_osdmap(rbdc->client,
+                                        rbdc->client->options->mount_timeout);
                if (ret) {
                        rbd_warn(NULL, "failed to get latest osdmap: %d", ret);
                        rbd_put_client(rbdc);
@@ -4203,12 +4187,12 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
        q->limits.max_sectors = queue_max_hw_sectors(q);
        blk_queue_max_segments(q, USHRT_MAX);
        blk_queue_max_segment_size(q, UINT_MAX);
-        blk_queue_io_min(q, objset_bytes);
+        blk_queue_io_min(q, rbd_dev->opts->alloc_size);
-        blk_queue_io_opt(q, objset_bytes);
+        blk_queue_io_opt(q, rbd_dev->opts->alloc_size);
        if (rbd_dev->opts->trim) {
                blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-                q->limits.discard_granularity = objset_bytes;
+                q->limits.discard_granularity = rbd_dev->opts->alloc_size;
                blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
                blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
        }
diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c
index a8dd80576c95..857f8c086274 100644
--- a/drivers/clocksource/clps711x-timer.c
+++ b/drivers/clocksource/clps711x-timer.c
@@ -31,16 +31,9 @@ static u64 notrace clps711x_sched_clock_read(void)
        return ~readw(tcd);
 }
-static int __init _clps711x_clksrc_init(struct clk *clock, void __iomem *base)
+static void __init clps711x_clksrc_init(struct clk *clock, void __iomem *base)
 {
-        unsigned long rate;
+        unsigned long rate = clk_get_rate(clock);
-        if (!base)
-                return -ENOMEM;
-        if (IS_ERR(clock))
-                return PTR_ERR(clock);
-        rate = clk_get_rate(clock);
        tcd = base;
@@ -48,8 +41,6 @@ static int __init _clps711x_clksrc_init(struct clk *clock, void __iomem *base)
                              clocksource_mmio_readw_down);
        sched_clock_register(clps711x_sched_clock_read, 16, rate);
-        return 0;
 }
 static irqreturn_t clps711x_timer_interrupt(int irq, void *dev_id)
@@ -67,13 +58,6 @@ static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base,
        struct clock_event_device *clkevt;
        unsigned long rate;
-        if (!irq)
-                return -EINVAL;
-        if (!base)
-                return -ENOMEM;
-        if (IS_ERR(clock))
-                return PTR_ERR(clock);
        clkevt = kzalloc(sizeof(*clkevt), GFP_KERNEL);
        if (!clkevt)
                return -ENOMEM;
@@ -93,31 +77,29 @@ static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base,
                           "clps711x-timer", clkevt);
 }
-void __init clps711x_clksrc_init(void __iomem *tc1_base, void __iomem *tc2_base,
-                                 unsigned int irq)
-{
-        struct clk *tc1 = clk_get_sys("clps711x-timer.0", NULL);
-        struct clk *tc2 = clk_get_sys("clps711x-timer.1", NULL);
-        BUG_ON(_clps711x_clksrc_init(tc1, tc1_base));
-        BUG_ON(_clps711x_clkevt_init(tc2, tc2_base, irq));
-}
-#ifdef CONFIG_TIMER_OF
 static int __init clps711x_timer_init(struct device_node *np)
 {
        unsigned int irq = irq_of_parse_and_map(np, 0);
        struct clk *clock = of_clk_get(np, 0);
        void __iomem *base = of_iomap(np, 0);
+        if (!base)
+                return -ENOMEM;
+        if (!irq)
+                return -EINVAL;
+        if (IS_ERR(clock))
+                return PTR_ERR(clock);
        switch (of_alias_get_id(np, "timer")) {
        case CLPS711X_CLKSRC_CLOCKSOURCE:
-                return _clps711x_clksrc_init(clock, base);
+                clps711x_clksrc_init(clock, base);
+                break;
        case CLPS711X_CLKSRC_CLOCKEVENT:
                return _clps711x_clkevt_init(clock, base, irq);
        default:
                return -EINVAL;
        }
+        return 0;
 }
 TIMER_OF_DECLARE(clps711x, "cirrus,ep7209-timer", clps711x_timer_init);
-#endif
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 54f8a331b53a..37671a5d4ed9 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -67,7 +67,7 @@ static irqreturn_t gic_compare_interrupt(int irq, void *dev_id)
        return IRQ_HANDLED;
 }
-struct irqaction gic_compare_irqaction = {
+static struct irqaction gic_compare_irqaction = {
        .handler = gic_compare_interrupt,
        .percpu_dev_id = &gic_clockevent_device,
        .flags = IRQF_PERCPU | IRQF_TIMER,
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 43f4d5c4d6fa..f987027ca566 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -71,7 +71,7 @@ static u64 tc_get_cycles32(struct clocksource *cs)
        return readl_relaxed(tcaddr + ATMEL_TC_REG(0, CV));
 }
-void tc_clksrc_suspend(struct clocksource *cs)
+static void tc_clksrc_suspend(struct clocksource *cs)
 {
        int i;
@@ -86,7 +86,7 @@ void tc_clksrc_suspend(struct clocksource *cs)
        bmr_cache = readl(tcaddr + ATMEL_TC_BMR);
 }
-void tc_clksrc_resume(struct clocksource *cs)
+static void tc_clksrc_resume(struct clocksource *cs)
 {
        int i;
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index e8163693e936..5e6038fbf115 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -58,7 +58,7 @@ static u64 riscv_sched_clock(void)
 static DEFINE_PER_CPU(struct clocksource, riscv_clocksource) = {
        .name           = "riscv_clocksource",
        .rating         = 300,
-        .mask           = CLOCKSOURCE_MASK(BITS_PER_LONG),
+        .mask           = CLOCKSOURCE_MASK(64),
        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
        .read           = riscv_clocksource_rdtime,
 };
@@ -120,8 +120,7 @@ static int __init riscv_timer_init_dt(struct device_node *n)
                return error;
        }
-        sched_clock_register(riscv_sched_clock,
+        sched_clock_register(riscv_sched_clock, 64, riscv_timebase);
-                        BITS_PER_LONG, riscv_timebase);
        error = cpuhp_setup_state(CPUHP_AP_RISCV_TIMER_STARTING,
                         "clockevents/riscv/timer:starting",
diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c
index c364027638e1..3352da6ed61f 100644
--- a/drivers/clocksource/timer-ti-dm.c
+++ b/drivers/clocksource/timer-ti-dm.c
@@ -586,8 +586,8 @@ static int omap_dm_timer_set_load(struct omap_dm_timer *timer, int autoreload,
 }
 /* Optimized set_load which removes costly spin wait in timer_start */
-int omap_dm_timer_set_load_start(struct omap_dm_timer *timer, int autoreload,
+static int omap_dm_timer_set_load_start(struct omap_dm_timer *timer,
-                            unsigned int load)
+                                        int autoreload, unsigned int load)
 {
        u32 l;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index bfa9062ce6b9..16fcb56c232b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -700,6 +700,8 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
        struct amdgpu_vm_bo_base *bo_base, *tmp;
        int r = 0;
+        vm->bulk_moveable &= list_empty(&vm->evicted);
        list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
                struct amdgpu_bo *bo = bo_base->bo;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 600259b4e291..2fe8397241ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -742,7 +742,7 @@ static int gmc_v9_0_allocate_vm_inv_eng(struct amdgpu_device *adev)
                }
                ring->vm_inv_eng = inv_eng - 1;
-                change_bit(inv_eng - 1, (unsigned long *)(&vm_inv_engs[vmhub]));
+                vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
                dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
                         ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 0573eab0e190..f35e4ab55b27 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -20,6 +20,7 @@
 #include "regs-vp.h"
 #include <linux/kernel.h>
+#include <linux/ktime.h>
 #include <linux/spinlock.h>
 #include <linux/wait.h>
 #include <linux/i2c.h>
@@ -352,15 +353,62 @@ static void mixer_cfg_vp_blend(struct mixer_context *ctx, unsigned int alpha)
        mixer_reg_write(ctx, MXR_VIDEO_CFG, val);
 }
-static void mixer_vsync_set_update(struct mixer_context *ctx, bool enable)
+static bool mixer_is_synced(struct mixer_context *ctx)
 {
-        /* block update on vsync */
+        u32 base, shadow;
-        mixer_reg_writemask(ctx, MXR_STATUS, enable ?
-                        MXR_STATUS_SYNC_ENABLE : 0, MXR_STATUS_SYNC_ENABLE);
+        if (ctx->mxr_ver == MXR_VER_16_0_33_0 ||
+            ctx->mxr_ver == MXR_VER_128_0_0_184)
+                return !(mixer_reg_read(ctx, MXR_CFG) &
+                         MXR_CFG_LAYER_UPDATE_COUNT_MASK);
+        if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags) &&
+            vp_reg_read(ctx, VP_SHADOW_UPDATE))
+                return false;
+        base = mixer_reg_read(ctx, MXR_CFG);
+        shadow = mixer_reg_read(ctx, MXR_CFG_S);
+        if (base != shadow)
+                return false;
+        base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(0));
+        shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(0));
+        if (base != shadow)
+                return false;
+        base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(1));
+        shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(1));
+        if (base != shadow)
+                return false;
+        return true;
+}
+static int mixer_wait_for_sync(struct mixer_context *ctx)
+{
+        ktime_t timeout = ktime_add_us(ktime_get(), 100000);
+        while (!mixer_is_synced(ctx)) {
+                usleep_range(1000, 2000);
+                if (ktime_compare(ktime_get(), timeout) > 0)
+                        return -ETIMEDOUT;
+        }
+        return 0;
+}
+static void mixer_disable_sync(struct mixer_context *ctx)
+{
+        mixer_reg_writemask(ctx, MXR_STATUS, 0, MXR_STATUS_SYNC_ENABLE);
+}
+static void mixer_enable_sync(struct mixer_context *ctx)
+{
+        if (ctx->mxr_ver == MXR_VER_16_0_33_0 ||
+            ctx->mxr_ver == MXR_VER_128_0_0_184)
+                mixer_reg_writemask(ctx, MXR_CFG, ~0, MXR_CFG_LAYER_UPDATE);
+        mixer_reg_writemask(ctx, MXR_STATUS, ~0, MXR_STATUS_SYNC_ENABLE);
        if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags))
-                vp_reg_write(ctx, VP_SHADOW_UPDATE, enable ?
+                vp_reg_write(ctx, VP_SHADOW_UPDATE, VP_SHADOW_UPDATE_ENABLE);
-                        VP_SHADOW_UPDATE_ENABLE : 0);
 }
 static void mixer_cfg_scan(struct mixer_context *ctx, int width, int height)
@@ -498,7 +546,6 @@ static void vp_video_buffer(struct mixer_context *ctx,
        spin_lock_irqsave(&ctx->reg_slock, flags);
-        vp_reg_write(ctx, VP_SHADOW_UPDATE, 1);
        /* interlace or progressive scan mode */
        val = (test_bit(MXR_BIT_INTERLACE, &ctx->flags) ? ~0 : 0);
        vp_reg_writemask(ctx, VP_MODE, val, VP_MODE_LINE_SKIP);
@@ -553,11 +600,6 @@ static void vp_video_buffer(struct mixer_context *ctx,
        vp_regs_dump(ctx);
 }
-static void mixer_layer_update(struct mixer_context *ctx)
-{
-        mixer_reg_writemask(ctx, MXR_CFG, ~0, MXR_CFG_LAYER_UPDATE);
-}
 static void mixer_graph_buffer(struct mixer_context *ctx,
                               struct exynos_drm_plane *plane)
 {
@@ -640,11 +682,6 @@ static void mixer_graph_buffer(struct mixer_context *ctx,
        mixer_cfg_layer(ctx, win, priority, true);
        mixer_cfg_gfx_blend(ctx, win, pixel_alpha, state->base.alpha);
-        /* layer update mandatory for mixer 16.0.33.0 */
-        if (ctx->mxr_ver == MXR_VER_16_0_33_0 ||
-                ctx->mxr_ver == MXR_VER_128_0_0_184)
-                mixer_layer_update(ctx);
        spin_unlock_irqrestore(&ctx->reg_slock, flags);
        mixer_regs_dump(ctx);
@@ -709,7 +746,7 @@ static void mixer_win_reset(struct mixer_context *ctx)
 static irqreturn_t mixer_irq_handler(int irq, void *arg)
 {
        struct mixer_context *ctx = arg;
-        u32 val, base, shadow;
+        u32 val;
        spin_lock(&ctx->reg_slock);
@@ -723,26 +760,9 @@ static irqreturn_t mixer_irq_handler(int irq, void *arg)
                val &= ~MXR_INT_STATUS_VSYNC;
                /* interlace scan need to check shadow register */
-                if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+                if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)
-                        if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags) &&
+                    && !mixer_is_synced(ctx))
-                            vp_reg_read(ctx, VP_SHADOW_UPDATE))
+                        goto out;
-                                goto out;
-                        base = mixer_reg_read(ctx, MXR_CFG);
-                        shadow = mixer_reg_read(ctx, MXR_CFG_S);
-                        if (base != shadow)
-                                goto out;
-                        base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(0));
-                        shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(0));
-                        if (base != shadow)
-                                goto out;
-                        base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(1));
-                        shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(1));
-                        if (base != shadow)
-                                goto out;
-                }
                drm_crtc_handle_vblank(&ctx->crtc->base);
        }
@@ -917,12 +937,14 @@ static void mixer_disable_vblank(struct exynos_drm_crtc *crtc)
 static void mixer_atomic_begin(struct exynos_drm_crtc *crtc)
 {
-        struct mixer_context *mixer_ctx = crtc->ctx;
+        struct mixer_context *ctx = crtc->ctx;
-        if (!test_bit(MXR_BIT_POWERED, &mixer_ctx->flags))
+        if (!test_bit(MXR_BIT_POWERED, &ctx->flags))
                return;
-        mixer_vsync_set_update(mixer_ctx, false);
+        if (mixer_wait_for_sync(ctx))
+                dev_err(ctx->dev, "timeout waiting for VSYNC\n");
+        mixer_disable_sync(ctx);
 }
 static void mixer_update_plane(struct exynos_drm_crtc *crtc,
@@ -964,7 +986,7 @@ static void mixer_atomic_flush(struct exynos_drm_crtc *crtc)
        if (!test_bit(MXR_BIT_POWERED, &mixer_ctx->flags))
                return;
-        mixer_vsync_set_update(mixer_ctx, true);
+        mixer_enable_sync(mixer_ctx);
        exynos_crtc_handle_event(crtc);
 }
@@ -979,7 +1001,7 @@ static void mixer_enable(struct exynos_drm_crtc *crtc)
        exynos_drm_pipe_clk_enable(crtc, true);
-        mixer_vsync_set_update(ctx, false);
+        mixer_disable_sync(ctx);
        mixer_reg_writemask(ctx, MXR_STATUS, ~0, MXR_STATUS_SOFT_RESET);
@@ -992,7 +1014,7 @@ static void mixer_enable(struct exynos_drm_crtc *crtc)
        mixer_commit(ctx);
-        mixer_vsync_set_update(ctx, true);
+        mixer_enable_sync(ctx);
        set_bit(MXR_BIT_POWERED, &ctx->flags);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 30d516e975c6..8558e81fdc2a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1734,8 +1734,13 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
         * pages from.
         */
        if (!obj->base.filp) {
-                i915_gem_object_put(obj);
+                addr = -ENXIO;
-                return -ENXIO;
+                goto err;
+        }
+        if (range_overflows(args->offset, args->size, (u64)obj->base.size)) {
+                addr = -EINVAL;
+                goto err;
        }
        addr = vm_mmap(obj->base.filp, 0, args->size,
@@ -1749,8 +1754,8 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
                struct vm_area_struct *vma;
                if (down_write_killable(&mm->mmap_sem)) {
-                        i915_gem_object_put(obj);
+                        addr = -EINTR;
-                        return -EINTR;
+                        goto err;
                }
                vma = find_vma(mm, addr);
                if (vma && __vma_matches(vma, obj->base.filp, addr, args->size))
@@ -1768,12 +1773,10 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
        i915_gem_object_put(obj);
        args->addr_ptr = (u64)addr;
        return 0;
 err:
        i915_gem_object_put(obj);
        return addr;
 }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9a65341fec09..aa6791255252 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1721,7 +1721,7 @@ error_msg(struct i915_gpu_state *error, unsigned long engines, const char *msg)
                        i915_error_generate_code(error, engines));
        if (engines) {
                /* Just show the first executing process, more is confusing */
-                i = ffs(engines);
+                i = __ffs(engines);
                len += scnprintf(error->error_msg + len,
                                 sizeof(error->error_msg) - len,
                                 ", in %s [%d]",
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index b508d8a735e0..4364f42cac6b 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1673,6 +1673,7 @@ init_vbt_missing_defaults(struct drm_i915_private *dev_priv)
                info->supports_dvi = (port != PORT_A && port != PORT_E);
                info->supports_hdmi = info->supports_dvi;
                info->supports_dp = (port != PORT_E);
+                info->supports_edp = (port == PORT_A);
        }
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 88a52f6b39fe..7dfbbbc1beea 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -181,7 +181,7 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf,
        }
        ret = pm_runtime_get_sync(drm->dev);
-        if (IS_ERR_VALUE(ret) && ret != -EACCES)
+        if (ret < 0 && ret != -EACCES)
                return ret;
        ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
        pm_runtime_put_autosuspend(drm->dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index aa9fec80492d..40c47d6a7d78 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -100,12 +100,10 @@ static void
 nouveau_dmem_free(struct hmm_devmem *devmem, struct page *page)
 {
        struct nouveau_dmem_chunk *chunk;
-        struct nouveau_drm *drm;
        unsigned long idx;
        chunk = (void *)hmm_devmem_page_get_drvdata(page);
        idx = page_to_pfn(page) - chunk->pfn_first;
-        drm = chunk->drm;
        /*
         * FIXME:
@@ -456,11 +454,6 @@ nouveau_dmem_resume(struct nouveau_drm *drm)
                /* FIXME handle pin failure */
                WARN_ON(ret);
        }
-        list_for_each_entry (chunk, &drm->dmem->chunk_empty, list) {
-                ret = nouveau_bo_pin(chunk->bo, TTM_PL_FLAG_VRAM, false);
-                /* FIXME handle pin failure */
-                WARN_ON(ret);
-        }
        mutex_unlock(&drm->dmem->mutex);
 }
@@ -479,9 +472,6 @@ nouveau_dmem_suspend(struct nouveau_drm *drm)
        list_for_each_entry (chunk, &drm->dmem->chunk_full, list) {
                nouveau_bo_unpin(chunk->bo);
        }
-        list_for_each_entry (chunk, &drm->dmem->chunk_empty, list) {
-                nouveau_bo_unpin(chunk->bo);
-        }
        mutex_unlock(&drm->dmem->mutex);
 }
@@ -623,7 +613,7 @@ nouveau_dmem_init(struct nouveau_drm *drm)
         */
        drm->dmem->devmem = hmm_devmem_add(&nouveau_dmem_devmem_ops,
                                           device, size);
-        if (drm->dmem->devmem == NULL) {
+        if (IS_ERR(drm->dmem->devmem)) {
                kfree(drm->dmem);
                drm->dmem = NULL;
                return;
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index d5a23295dd80..bb7b58407039 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -224,7 +224,7 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev,
        *offset = drm_vma_node_offset_addr(&gobj->base.vma_node);
 out:
-        drm_gem_object_put(&gobj->base);
+        drm_gem_object_put_unlocked(&gobj->base);
 unlock:
        mutex_unlock(&udl->gem_lock);
        return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index b913a56f3426..2a9112515f46 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -564,11 +564,9 @@ static int vmw_fb_set_par(struct fb_info *info)
                0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
                DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC)
        };
-        struct drm_display_mode *old_mode;
        struct drm_display_mode *mode;
        int ret;
-        old_mode = par->set_mode;
        mode = drm_mode_duplicate(vmw_priv->dev, &new_mode);
        if (!mode) {
                DRM_ERROR("Could not create new fb mode.\n");
@@ -579,11 +577,7 @@ static int vmw_fb_set_par(struct fb_info *info)
        mode->vdisplay = var->yres;
        vmw_guess_mode_timing(mode);
-        if (old_mode && drm_mode_equal(old_mode, mode)) {
+        if (!vmw_kms_validate_mode_vram(vmw_priv,
-                drm_mode_destroy(vmw_priv->dev, mode);
-                mode = old_mode;
-                old_mode = NULL;
-        } else if (!vmw_kms_validate_mode_vram(vmw_priv,
                                        mode->hdisplay *
                                        DIV_ROUND_UP(var->bits_per_pixel, 8),
                                        mode->vdisplay)) {
@@ -620,8 +614,8 @@ static int vmw_fb_set_par(struct fb_info *info)
        schedule_delayed_work(&par->local_work, 0);
 out_unlock:
-        if (old_mode)
+        if (par->set_mode)
-                drm_mode_destroy(vmw_priv->dev, old_mode);
+                drm_mode_destroy(vmw_priv->dev, par->set_mode);
        par->set_mode = mode;
        mutex_unlock(&par->bo_mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index b93c558dd86e..7da752ca1c34 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -57,7 +57,7 @@ static int vmw_gmrid_man_get_node(struct ttm_mem_type_manager *man,
        id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL);
        if (id < 0)
-                return id;
+                return (id != -ENOMEM ? 0 : id);
        spin_lock(&gman->lock);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index c5a881172524..337410f40860 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -173,7 +173,12 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
                rcu_read_lock();
                in = __in_dev_get_rcu(upper_dev);
-                local_ipaddr = ntohl(in->ifa_list->ifa_address);
+                if (!in->ifa_list)
+                        local_ipaddr = 0;
+                else
+                        local_ipaddr = ntohl(in->ifa_list->ifa_address);
                rcu_read_unlock();
        } else {
                local_ipaddr = ntohl(ifa->ifa_address);
@@ -185,6 +190,11 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
        case NETDEV_UP:
                /* Fall through */
        case NETDEV_CHANGEADDR:
+                /* Just skip if no need to handle ARP cache */
+                if (!local_ipaddr)
+                        break;
                i40iw_manage_arp_cache(iwdev,
                                       netdev->dev_addr,
                                       &local_ipaddr,
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 782499abcd98..2a0b59a4b6eb 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -804,8 +804,8 @@ void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev)
        unsigned long flags;
        for (i = 0 ; i < dev->num_ports; i++) {
-                cancel_delayed_work(&dev->sriov.alias_guid.ports_guid[i].alias_guid_work);
                det = &sriov->alias_guid.ports_guid[i];
+                cancel_delayed_work_sync(&det->alias_guid_work);
                spin_lock_irqsave(&sriov->alias_guid.ag_work_lock, flags);
                while (!list_empty(&det->cb_list)) {
                        cb_ctx = list_entry(det->cb_list.next,
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index eaa055007f28..9e08df7914aa 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -20,6 +20,7 @@
 enum devx_obj_flags {
        DEVX_OBJ_FLAGS_INDIRECT_MKEY = 1 << 0,
+        DEVX_OBJ_FLAGS_DCT = 1 << 1,
 };
 struct devx_async_data {
@@ -39,7 +40,10 @@ struct devx_obj {
        u32                     dinlen; /* destroy inbox length */
        u32                     dinbox[MLX5_MAX_DESTROY_INBOX_SIZE_DW];
        u32                     flags;
-        struct mlx5_ib_devx_mr  devx_mr;
+        union {
+                struct mlx5_ib_devx_mr  devx_mr;
+                struct mlx5_core_dct    core_dct;
+        };
 };
 struct devx_umem {
@@ -347,7 +351,6 @@ static u64 devx_get_obj_id(const void *in)
                obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_RQ,
                                        MLX5_GET(arm_rq_in, in, srq_number));
                break;
-        case MLX5_CMD_OP_DRAIN_DCT:
        case MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION:
                obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_DCT,
                                        MLX5_GET(drain_dct_in, in, dctn));
@@ -618,7 +621,6 @@ static bool devx_is_obj_modify_cmd(const void *in)
        case MLX5_CMD_OP_2RST_QP:
        case MLX5_CMD_OP_ARM_XRC_SRQ:
        case MLX5_CMD_OP_ARM_RQ:
-        case MLX5_CMD_OP_DRAIN_DCT:
        case MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION:
        case MLX5_CMD_OP_ARM_XRQ:
        case MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY:
@@ -1124,7 +1126,11 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
        if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
                devx_cleanup_mkey(obj);
-        ret = mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out));
+        if (obj->flags & DEVX_OBJ_FLAGS_DCT)
+                ret = mlx5_core_destroy_dct(obj->mdev, &obj->core_dct);
+        else
+                ret = mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out,
+                                    sizeof(out));
        if (ib_is_destroy_retryable(ret, why, uobject))
                return ret;
@@ -1185,9 +1191,17 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
                devx_set_umem_valid(cmd_in);
        }
-        err = mlx5_cmd_exec(dev->mdev, cmd_in,
+        if (opcode == MLX5_CMD_OP_CREATE_DCT) {
-                            cmd_in_len,
+                obj->flags |= DEVX_OBJ_FLAGS_DCT;
-                            cmd_out, cmd_out_len);
+                err = mlx5_core_create_dct(dev->mdev, &obj->core_dct,
+                                           cmd_in, cmd_in_len,
+                                           cmd_out, cmd_out_len);
+        } else {
+                err = mlx5_cmd_exec(dev->mdev, cmd_in,
+                                    cmd_in_len,
+                                    cmd_out, cmd_out_len);
+        }
        if (err)
                goto obj_free;
@@ -1214,7 +1228,11 @@ err_copy:
        if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
                devx_cleanup_mkey(obj);
 obj_destroy:
-        mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out));
+        if (obj->flags & DEVX_OBJ_FLAGS_DCT)
+                mlx5_core_destroy_dct(obj->mdev, &obj->core_dct);
+        else
+                mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out,
+                              sizeof(out));
 obj_free:
        kfree(obj);
        return err;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 994c19d01211..531ff20b32ad 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -415,10 +415,17 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
                *active_speed = IB_SPEED_EDR;
                break;
        case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2):
+                *active_width = IB_WIDTH_2X;
+                *active_speed = IB_SPEED_EDR;
+                break;
        case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR):
                *active_width = IB_WIDTH_1X;
                *active_speed = IB_SPEED_HDR;
                break;
+        case MLX5E_PROT_MASK(MLX5E_CAUI_4_100GBASE_CR4_KR4):
+                *active_width = IB_WIDTH_4X;
+                *active_speed = IB_SPEED_EDR;
+                break;
        case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2):
                *active_width = IB_WIDTH_2X;
                *active_speed = IB_SPEED_HDR;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 6b1f0e76900b..7cd006da1dae 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3729,6 +3729,7 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
        } else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
                struct mlx5_ib_modify_qp_resp resp = {};
+                u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {0};
                u32 min_resp_len = offsetof(typeof(resp), dctn) +
                                   sizeof(resp.dctn);
@@ -3747,7 +3748,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
                MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
                err = mlx5_core_create_dct(dev->mdev, &qp->dct.mdct, qp->dct.in,
-                                           MLX5_ST_SZ_BYTES(create_dct_in));
+                                           MLX5_ST_SZ_BYTES(create_dct_in), out,
+                                           sizeof(out));
                if (err)
                        return err;
                resp.dctn = qp->dct.mdct.mqp.qpn;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b319e51c379b..21cb088d6687 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2608,7 +2608,12 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
        /* Everything is mapped - write the right values into s->dma_address */
        for_each_sg(sglist, s, nelems, i) {
-                s->dma_address += address + s->offset;
+                /*
+                 * Add in the remaining piece of the scatter-gather offset that
+                 * was masked out when we were determining the physical address
+                 * via (sg_phys(s) & PAGE_MASK) earlier.
+                 */
+                s->dma_address += address + (s->offset & ~PAGE_MASK);
                s->dma_length   = s->length;
        }
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 87274b54febd..28cb713d728c 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1538,6 +1538,9 @@ static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
        u32 pmen;
        unsigned long flags;
+        if (!cap_plmr(iommu->cap) && !cap_phmr(iommu->cap))
+                return;
        raw_spin_lock_irqsave(&iommu->register_lock, flags);
        pmen = readl(iommu->reg + DMAR_PMEN_REG);
        pmen &= ~DMA_PMEN_EPM;
@@ -5332,7 +5335,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
        ctx_lo = context[0].lo;
-        sdev->did = domain->iommu_did[iommu->seq_id];
+        sdev->did = FLPT_DEFAULT_DID;
        sdev->sid = PCI_DEVID(info->bus, info->devfn);
        if (!(ctx_lo & CONTEXT_PASIDE)) {
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index f8d3ba247523..2de8122e218f 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -207,8 +207,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
                curr_iova = rb_entry(curr, struct iova, node);
        } while (curr && new_pfn <= curr_iova->pfn_hi);
-        if (limit_pfn < size || new_pfn < iovad->start_pfn)
+        if (limit_pfn < size || new_pfn < iovad->start_pfn) {
+                iovad->max32_alloc_size = size;
                goto iova32_full;
+        }
        /* pfn_lo will point to size aligned address if size_aligned is set */
        new->pfn_lo = new_pfn;
@@ -222,7 +224,6 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
        return 0;
 iova32_full:
-        iovad->max32_alloc_size = size;
        spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
        return -ENOMEM;
 }
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index 83364fedbf0a..5e4ca139e4ea 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -275,14 +275,14 @@ out_free:
        return ret;
 }
-int __init brcmstb_l2_edge_intc_of_init(struct device_node *np,
+static int __init brcmstb_l2_edge_intc_of_init(struct device_node *np,
        struct device_node *parent)
 {
        return brcmstb_l2_intc_of_init(np, parent, &l2_edge_intc_init);
 }
 IRQCHIP_DECLARE(brcmstb_l2_intc, "brcm,l2-intc", brcmstb_l2_edge_intc_of_init);
-int __init brcmstb_l2_lvl_intc_of_init(struct device_node *np,
+static int __init brcmstb_l2_lvl_intc_of_init(struct device_node *np,
        struct device_node *parent)
 {
        return brcmstb_l2_intc_of_init(np, parent, &l2_lvl_intc_init);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 2dd1ff0cf558..7577755bdcf4 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1482,7 +1482,7 @@ static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
        ra = container_of(a, struct lpi_range, entry);
        rb = container_of(b, struct lpi_range, entry);
-        return rb->base_id - ra->base_id;
+        return ra->base_id - rb->base_id;
 }
 static void merge_lpi_ranges(void)
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index ba2a37a27a54..fd3110c171ba 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1089,11 +1089,10 @@ static void gic_init_chip(struct gic_chip_data *gic, struct device *dev,
 #endif
 }
-static int gic_init_bases(struct gic_chip_data *gic, int irq_start,
+static int gic_init_bases(struct gic_chip_data *gic,
                          struct fwnode_handle *handle)
 {
-        irq_hw_number_t hwirq_base;
+        int gic_irqs, ret;
-        int gic_irqs, irq_base, ret;
        if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
                /* Frankein-GIC without banked registers... */
@@ -1145,28 +1144,21 @@ static int gic_init_bases(struct gic_chip_data *gic, int irq_start,
        } else {                /* Legacy support */
                /*
                 * For primary GICs, skip over SGIs.
-                 * For secondary GICs, skip over PPIs, too.
+                 * No secondary GIC support whatsoever.
                 */
-                if (gic == &gic_data[0] && (irq_start & 31) > 0) {
+                int irq_base;
-                        hwirq_base = 16;
-                        if (irq_start != -1)
-                                irq_start = (irq_start & ~31) + 16;
-                } else {
-                        hwirq_base = 32;
-                }
-                gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
+                gic_irqs -= 16; /* calculate # of irqs to allocate */
-                irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
+                irq_base = irq_alloc_descs(16, 16, gic_irqs,
                                           numa_node_id());
                if (irq_base < 0) {
-                        WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+                        WARN(1, "Cannot allocate irq_descs @ IRQ16, assuming pre-allocated\n");
-                             irq_start);
+                        irq_base = 16;
-                        irq_base = irq_start;
                }
                gic->domain = irq_domain_add_legacy(NULL, gic_irqs, irq_base,
-                                        hwirq_base, &gic_irq_domain_ops, gic);
+                                                    16, &gic_irq_domain_ops, gic);
        }
        if (WARN_ON(!gic->domain)) {
@@ -1195,7 +1187,6 @@ error:
 }
 static int __init __gic_init_bases(struct gic_chip_data *gic,
-                                   int irq_start,
                                   struct fwnode_handle *handle)
 {
        char *name;
@@ -1231,32 +1222,28 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
                gic_init_chip(gic, NULL, name, false);
        }
-        ret = gic_init_bases(gic, irq_start, handle);
+        ret = gic_init_bases(gic, handle);
        if (ret)
                kfree(name);
        return ret;
 }
-void __init gic_init(unsigned int gic_nr, int irq_start,
+void __init gic_init(void __iomem *dist_base, void __iomem *cpu_base)
-                     void __iomem *dist_base, void __iomem *cpu_base)
 {
        struct gic_chip_data *gic;
-        if (WARN_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR))
-                return;
        /*
         * Non-DT/ACPI systems won't run a hypervisor, so let's not
         * bother with these...
         */
        static_branch_disable(&supports_deactivate_key);
-        gic = &gic_data[gic_nr];
+        gic = &gic_data[0];
        gic->raw_dist_base = dist_base;
        gic->raw_cpu_base = cpu_base;
-        __gic_init_bases(gic, irq_start, NULL);
+        __gic_init_bases(gic, NULL);
 }
 static void gic_teardown(struct gic_chip_data *gic)
@@ -1399,7 +1386,7 @@ int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq)
        if (ret)
                return ret;
-        ret = gic_init_bases(*gic, -1, &dev->of_node->fwnode);
+        ret = gic_init_bases(*gic, &dev->of_node->fwnode);
        if (ret) {
                gic_teardown(*gic);
                return ret;
@@ -1459,7 +1446,7 @@ gic_of_init(struct device_node *node, struct device_node *parent)
        if (gic_cnt == 0 && !gic_check_eoimode(node, &gic->raw_cpu_base))
                static_branch_disable(&supports_deactivate_key);
-        ret = __gic_init_bases(gic, -1, &node->fwnode);
+        ret = __gic_init_bases(gic, &node->fwnode);
        if (ret) {
                gic_teardown(gic);
                return ret;
@@ -1650,7 +1637,7 @@ static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
                return -ENOMEM;
        }
-        ret = __gic_init_bases(gic, -1, domain_handle);
+        ret = __gic_init_bases(gic, domain_handle);
        if (ret) {
                pr_err("Failed to initialise GIC\n");
                irq_domain_free_fwnode(domain_handle);
diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c
index d1098f4da6a4..88df3d00052c 100644
--- a/drivers/irqchip/irq-imx-irqsteer.c
+++ b/drivers/irqchip/irq-imx-irqsteer.c
@@ -169,8 +169,12 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
        raw_spin_lock_init(&data->lock);
-        of_property_read_u32(np, "fsl,num-irqs", &irqs_num);
+        ret = of_property_read_u32(np, "fsl,num-irqs", &irqs_num);
-        of_property_read_u32(np, "fsl,channel", &data->channel);
+        if (ret)
+                return ret;
+        ret = of_property_read_u32(np, "fsl,channel", &data->channel);
+        if (ret)
+                return ret;
        /*
         * There is one output irq for each group of 64 inputs.
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 567b29c47608..98b6e1d4b1a6 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -161,6 +161,9 @@ static void mbigen_write_msg(struct msi_desc *desc, struct msi_msg *msg)
        void __iomem *base = d->chip_data;
        u32 val;
+        if (!msg->address_lo && !msg->address_hi)
+                return;
+ 
        base += get_mbigen_vec_reg(d->hwirq);
        val = readl_relaxed(base);
diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c
index 3496b61a312a..8eed478f3b7e 100644
--- a/drivers/irqchip/irq-mmp.c
+++ b/drivers/irqchip/irq-mmp.c
@@ -179,7 +179,7 @@ static int mmp_irq_domain_xlate(struct irq_domain *d, struct device_node *node,
        return 0;
 }
-const struct irq_domain_ops mmp_irq_domain_ops = {
+static const struct irq_domain_ops mmp_irq_domain_ops = {
        .map            = mmp_irq_domain_map,
        .xlate          = mmp_irq_domain_xlate,
 };
diff --git a/drivers/irqchip/irq-mvebu-sei.c b/drivers/irqchip/irq-mvebu-sei.c
index add4c9c934c8..18832ccc8ff8 100644
--- a/drivers/irqchip/irq-mvebu-sei.c
+++ b/drivers/irqchip/irq-mvebu-sei.c
@@ -478,7 +478,7 @@ dispose_irq:
        return ret;
 }
-struct mvebu_sei_caps mvebu_sei_ap806_caps = {
+static struct mvebu_sei_caps mvebu_sei_ap806_caps = {
        .ap_range = {
                .first = 0,
                .size = 21,
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index a93296b9b45d..7bd1d4cb2e19 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -716,7 +716,6 @@ stm32_exti_chip_data *stm32_exti_chip_init(struct stm32_exti_host_data *h_data,
        const struct stm32_exti_bank *stm32_bank;
        struct stm32_exti_chip_data *chip_data;
        void __iomem *base = h_data->base;
-        u32 irqs_mask;
        stm32_bank = h_data->drv_data->exti_banks[bank_idx];
        chip_data = &h_data->chips_data[bank_idx];
@@ -725,21 +724,12 @@ stm32_exti_chip_data *stm32_exti_chip_init(struct stm32_exti_host_data *h_data,
        raw_spin_lock_init(&chip_data->rlock);
-        /* Determine number of irqs supported */
-        writel_relaxed(~0UL, base + stm32_bank->rtsr_ofst);
-        irqs_mask = readl_relaxed(base + stm32_bank->rtsr_ofst);
        /*
         * This IP has no reset, so after hot reboot we should
         * clear registers to avoid residue
         */
        writel_relaxed(0, base + stm32_bank->imr_ofst);
        writel_relaxed(0, base + stm32_bank->emr_ofst);
-        writel_relaxed(0, base + stm32_bank->rtsr_ofst);
-        writel_relaxed(0, base + stm32_bank->ftsr_ofst);
-        writel_relaxed(~0UL, base + stm32_bank->rpr_ofst);
-        if (stm32_bank->fpr_ofst != UNDEF_REG)
-                writel_relaxed(~0UL, base + stm32_bank->fpr_ofst);
        pr_info("%pOF: bank%d\n", h_data->node, bank_idx);
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 3525236ed8d9..19c84214a7ea 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -179,6 +179,12 @@ static void cs_do_release(struct kref *ref)
        /* We also need to update CI for internal queues */
        if (cs->submitted) {
+                int cs_cnt = atomic_dec_return(&hdev->cs_active_cnt);
+                WARN_ONCE((cs_cnt < 0),
+                        "hl%d: error in CS active cnt %d\n",
+                        hdev->id, cs_cnt);
                hl_int_hw_queue_update_ci(cs);
                spin_lock(&hdev->hw_queues_mirror_lock);
diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index a53c12aff6ad..974a87789bd8 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/drivers/misc/habanalabs/debugfs.c
@@ -232,6 +232,7 @@ static int vm_show(struct seq_file *s, void *data)
        struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
        enum vm_type_t *vm_type;
        bool once = true;
+        u64 j;
        int i;
        if (!dev_entry->hdev->mmu_enable)
@@ -260,7 +261,7 @@ static int vm_show(struct seq_file *s, void *data)
                        } else {
                                phys_pg_pack = hnode->ptr;
                                seq_printf(s,
-                                        "    0x%-14llx      %-10u       %-4u\n",
+                                        "    0x%-14llx      %-10llu       %-4u\n",
                                        hnode->vaddr, phys_pg_pack->total_size,
                                        phys_pg_pack->handle);
                        }
@@ -282,9 +283,9 @@ static int vm_show(struct seq_file *s, void *data)
                                                phys_pg_pack->page_size);
                        seq_puts(s, "   physical address\n");
                        seq_puts(s, "---------------------\n");
-                        for (i = 0 ; i < phys_pg_pack->npages ; i++) {
+                        for (j = 0 ; j < phys_pg_pack->npages ; j++) {
                                seq_printf(s, "    0x%-14llx\n",
-                                                phys_pg_pack->pages[i]);
+                                                phys_pg_pack->pages[j]);
                        }
                }
                spin_unlock(&vm->idr_lock);
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index de46aa6ed154..77d51be66c7e 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -11,6 +11,8 @@
 #include <linux/sched/signal.h>
 #include <linux/hwmon.h>
+#define HL_PLDM_PENDING_RESET_PER_SEC   (HL_PENDING_RESET_PER_SEC * 10)
 bool hl_device_disabled_or_in_reset(struct hl_device *hdev)
 {
        if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
@@ -216,6 +218,7 @@ static int device_early_init(struct hl_device *hdev)
        spin_lock_init(&hdev->hw_queues_mirror_lock);
        atomic_set(&hdev->in_reset, 0);
        atomic_set(&hdev->fd_open_cnt, 0);
+        atomic_set(&hdev->cs_active_cnt, 0);
        return 0;
@@ -413,6 +416,27 @@ int hl_device_suspend(struct hl_device *hdev)
        pci_save_state(hdev->pdev);
+        /* Block future CS/VM/JOB completion operations */
+        rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+        if (rc) {
+                dev_err(hdev->dev, "Can't suspend while in reset\n");
+                return -EIO;
+        }
+        /* This blocks all other stuff that is not blocked by in_reset */
+        hdev->disabled = true;
+        /*
+         * Flush anyone that is inside the critical section of enqueue
+         * jobs to the H/W
+         */
+        hdev->asic_funcs->hw_queues_lock(hdev);
+        hdev->asic_funcs->hw_queues_unlock(hdev);
+        /* Flush processes that are sending message to CPU */
+        mutex_lock(&hdev->send_cpu_message_lock);
+        mutex_unlock(&hdev->send_cpu_message_lock);
        rc = hdev->asic_funcs->suspend(hdev);
        if (rc)
                dev_err(hdev->dev,
@@ -440,21 +464,38 @@ int hl_device_resume(struct hl_device *hdev)
        pci_set_power_state(hdev->pdev, PCI_D0);
        pci_restore_state(hdev->pdev);
-        rc = pci_enable_device(hdev->pdev);
+        rc = pci_enable_device_mem(hdev->pdev);
        if (rc) {
                dev_err(hdev->dev,
                        "Failed to enable PCI device in resume\n");
                return rc;
        }
+        pci_set_master(hdev->pdev);
        rc = hdev->asic_funcs->resume(hdev);
        if (rc) {
-                dev_err(hdev->dev,
+                dev_err(hdev->dev, "Failed to resume device after suspend\n");
-                        "Failed to enable PCI access from device CPU\n");
+                goto disable_device;
-                return rc;
+        }
+        hdev->disabled = false;
+        atomic_set(&hdev->in_reset, 0);
+        rc = hl_device_reset(hdev, true, false);
+        if (rc) {
+                dev_err(hdev->dev, "Failed to reset device during resume\n");
+                goto disable_device;
        }
        return 0;
+disable_device:
+        pci_clear_master(hdev->pdev);
+        pci_disable_device(hdev->pdev);
+        return rc;
 }
 static void hl_device_hard_reset_pending(struct work_struct *work)
@@ -462,9 +503,16 @@ static void hl_device_hard_reset_pending(struct work_struct *work)
        struct hl_device_reset_work *device_reset_work =
                container_of(work, struct hl_device_reset_work, reset_work);
        struct hl_device *hdev = device_reset_work->hdev;
-        u16 pending_cnt = HL_PENDING_RESET_PER_SEC;
+        u16 pending_total, pending_cnt;
        struct task_struct *task = NULL;
+        if (hdev->pldm)
+                pending_total = HL_PLDM_PENDING_RESET_PER_SEC;
+        else
+                pending_total = HL_PENDING_RESET_PER_SEC;
+        pending_cnt = pending_total;
        /* Flush all processes that are inside hl_open */
        mutex_lock(&hdev->fd_open_cnt_lock);
@@ -489,6 +537,19 @@ static void hl_device_hard_reset_pending(struct work_struct *work)
                }
        }
+        pending_cnt = pending_total;
+        while ((atomic_read(&hdev->fd_open_cnt)) && (pending_cnt)) {
+                pending_cnt--;
+                ssleep(1);
+        }
+        if (atomic_read(&hdev->fd_open_cnt))
+                dev_crit(hdev->dev,
+                        "Going to hard reset with open user contexts\n");
        mutex_unlock(&hdev->fd_open_cnt_lock);
        hl_device_reset(hdev, true, true);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 238dd57c541b..ea979ebd62fb 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -1201,15 +1201,6 @@ static int goya_stop_external_queues(struct hl_device *hdev)
        return retval;
 }
-static void goya_resume_external_queues(struct hl_device *hdev)
-{
-        WREG32(mmDMA_QM_0_GLBL_CFG1, 0);
-        WREG32(mmDMA_QM_1_GLBL_CFG1, 0);
-        WREG32(mmDMA_QM_2_GLBL_CFG1, 0);
-        WREG32(mmDMA_QM_3_GLBL_CFG1, 0);
-        WREG32(mmDMA_QM_4_GLBL_CFG1, 0);
-}
 /*
 * goya_init_cpu_queues - Initialize PQ/CQ/EQ of CPU
 *
@@ -2178,36 +2169,6 @@ static int goya_stop_internal_queues(struct hl_device *hdev)
        return retval;
 }
-static void goya_resume_internal_queues(struct hl_device *hdev)
-{
-        WREG32(mmMME_QM_GLBL_CFG1, 0);
-        WREG32(mmMME_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC0_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC0_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC1_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC1_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC2_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC2_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC3_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC3_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC4_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC4_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC5_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC5_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC6_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC6_CMDQ_GLBL_CFG1, 0);
-        WREG32(mmTPC7_QM_GLBL_CFG1, 0);
-        WREG32(mmTPC7_CMDQ_GLBL_CFG1, 0);
-}
 static void goya_dma_stall(struct hl_device *hdev)
 {
        WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT);
@@ -2905,20 +2866,6 @@ int goya_suspend(struct hl_device *hdev)
 {
        int rc;
-        rc = goya_stop_internal_queues(hdev);
-        if (rc) {
-                dev_err(hdev->dev, "failed to stop internal queues\n");
-                return rc;
-        }
-        rc = goya_stop_external_queues(hdev);
-        if (rc) {
-                dev_err(hdev->dev, "failed to stop external queues\n");
-                return rc;
-        }
        rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
        if (rc)
                dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
@@ -2928,15 +2875,7 @@ int goya_suspend(struct hl_device *hdev)
 int goya_resume(struct hl_device *hdev)
 {
-        int rc;
+        return goya_init_iatu(hdev);
-        goya_resume_external_queues(hdev);
-        goya_resume_internal_queues(hdev);
-        rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS);
-        if (rc)
-                dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
-        return rc;
 }
 static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
@@ -3070,7 +3009,7 @@ void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id,
        *dma_handle = hdev->asic_prop.sram_base_address;
-        base = hdev->pcie_bar[SRAM_CFG_BAR_ID];
+        base = (void *) hdev->pcie_bar[SRAM_CFG_BAR_ID];
        switch (queue_id) {
        case GOYA_QUEUE_ID_MME:
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index a7c95e9f9b9a..a8ee52c880cd 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -793,11 +793,11 @@ struct hl_vm_hash_node {
 * struct hl_vm_phys_pg_pack - physical page pack.
 * @vm_type: describes the type of the virtual area descriptor.
 * @pages: the physical page array.
+ * @npages: num physical pages in the pack.
+ * @total_size: total size of all the pages in this list.
 * @mapping_cnt: number of shared mappings.
 * @asid: the context related to this list.
- * @npages: num physical pages in the pack.
 * @page_size: size of each page in the pack.
- * @total_size: total size of all the pages in this list.
 * @flags: HL_MEM_* flags related to this list.
 * @handle: the provided handle related to this list.
 * @offset: offset from the first page.
@@ -807,11 +807,11 @@ struct hl_vm_hash_node {
 struct hl_vm_phys_pg_pack {
        enum vm_type_t          vm_type; /* must be first */
        u64                     *pages;
+        u64                     npages;
+        u64                     total_size;
        atomic_t                mapping_cnt;
        u32                     asid;
-        u32                     npages;
        u32                     page_size;
-        u32                     total_size;
        u32                     flags;
        u32                     handle;
        u32                     offset;
@@ -1056,13 +1056,15 @@ struct hl_device_reset_work {
 * @cb_pool_lock: protects the CB pool.
 * @user_ctx: current user context executing.
 * @dram_used_mem: current DRAM memory consumption.
- * @in_reset: is device in reset flow.
- * @curr_pll_profile: current PLL profile.
- * @fd_open_cnt: number of open user processes.
 * @timeout_jiffies: device CS timeout value.
 * @max_power: the max power of the device, as configured by the sysadmin. This
 *             value is saved so in case of hard-reset, KMD will restore this
 *             value and update the F/W after the re-initialization
+ * @in_reset: is device in reset flow.
+ * @curr_pll_profile: current PLL profile.
+ * @fd_open_cnt: number of open user processes.
+ * @cs_active_cnt: number of active command submissions on this device (active
+ *                 means already in H/W queues)
 * @major: habanalabs KMD major.
 * @high_pll: high PLL profile frequency.
 * @soft_reset_cnt: number of soft reset since KMD loading.
@@ -1128,11 +1130,12 @@ struct hl_device {
        struct hl_ctx                   *user_ctx;
        atomic64_t                      dram_used_mem;
+        u64                             timeout_jiffies;
+        u64                             max_power;
        atomic_t                        in_reset;
        atomic_t                        curr_pll_profile;
        atomic_t                        fd_open_cnt;
-        u64                             timeout_jiffies;
+        atomic_t                        cs_active_cnt;
-        u64                             max_power;
        u32                             major;
        u32                             high_pll;
        u32                             soft_reset_cnt;
diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c
index 67bece26417c..ef3bb6951360 100644
--- a/drivers/misc/habanalabs/hw_queue.c
+++ b/drivers/misc/habanalabs/hw_queue.c
@@ -370,12 +370,13 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
                spin_unlock(&hdev->hw_queues_mirror_lock);
        }
-        list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) {
+        atomic_inc(&hdev->cs_active_cnt);
+        list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
                if (job->ext_queue)
                        ext_hw_queue_schedule_job(job);
                else
                        int_hw_queue_schedule_job(job);
-        }
        cs->submitted = true;
diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c
index 3a12fd1a5274..ce1fda40a8b8 100644
--- a/drivers/misc/habanalabs/memory.c
+++ b/drivers/misc/habanalabs/memory.c
@@ -56,9 +56,9 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
        struct hl_device *hdev = ctx->hdev;
        struct hl_vm *vm = &hdev->vm;
        struct hl_vm_phys_pg_pack *phys_pg_pack;
-        u64 paddr = 0;
+        u64 paddr = 0, total_size, num_pgs, i;
-        u32 total_size, num_pgs, num_curr_pgs, page_size, page_shift;
+        u32 num_curr_pgs, page_size, page_shift;
-        int handle, rc, i;
+        int handle, rc;
        bool contiguous;
        num_curr_pgs = 0;
@@ -73,7 +73,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
                paddr = (u64) gen_pool_alloc(vm->dram_pg_pool, total_size);
                if (!paddr) {
                        dev_err(hdev->dev,
-                                "failed to allocate %u huge contiguous pages\n",
+                                "failed to allocate %llu huge contiguous pages\n",
                                num_pgs);
                        return -ENOMEM;
                }
@@ -93,7 +93,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
        phys_pg_pack->flags = args->flags;
        phys_pg_pack->contiguous = contiguous;
-        phys_pg_pack->pages = kcalloc(num_pgs, sizeof(u64), GFP_KERNEL);
+        phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL);
        if (!phys_pg_pack->pages) {
                rc = -ENOMEM;
                goto pages_arr_err;
@@ -148,7 +148,7 @@ page_err:
                        gen_pool_free(vm->dram_pg_pool, phys_pg_pack->pages[i],
                                        page_size);
-        kfree(phys_pg_pack->pages);
+        kvfree(phys_pg_pack->pages);
 pages_arr_err:
        kfree(phys_pg_pack);
 pages_pack_err:
@@ -267,7 +267,7 @@ static void free_phys_pg_pack(struct hl_device *hdev,
                struct hl_vm_phys_pg_pack *phys_pg_pack)
 {
        struct hl_vm *vm = &hdev->vm;
-        int i;
+        u64 i;
        if (!phys_pg_pack->created_from_userptr) {
                if (phys_pg_pack->contiguous) {
@@ -288,7 +288,7 @@ static void free_phys_pg_pack(struct hl_device *hdev,
                }
        }
-        kfree(phys_pg_pack->pages);
+        kvfree(phys_pg_pack->pages);
        kfree(phys_pg_pack);
 }
@@ -519,7 +519,7 @@ static inline int add_va_block(struct hl_device *hdev,
 * - Return the start address of the virtual block
 */
 static u64 get_va_block(struct hl_device *hdev,
-                struct hl_va_range *va_range, u32 size, u64 hint_addr,
+                struct hl_va_range *va_range, u64 size, u64 hint_addr,
                bool is_userptr)
 {
        struct hl_vm_va_block *va_block, *new_va_block = NULL;
@@ -577,7 +577,8 @@ static u64 get_va_block(struct hl_device *hdev,
        }
        if (!new_va_block) {
-                dev_err(hdev->dev, "no available va block for size %u\n", size);
+                dev_err(hdev->dev, "no available va block for size %llu\n",
+                                size);
                goto out;
        }
@@ -648,8 +649,8 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
        struct hl_vm_phys_pg_pack *phys_pg_pack;
        struct scatterlist *sg;
        dma_addr_t dma_addr;
-        u64 page_mask;
+        u64 page_mask, total_npages;
-        u32 npages, total_npages, page_size = PAGE_SIZE;
+        u32 npages, page_size = PAGE_SIZE;
        bool first = true, is_huge_page_opt = true;
        int rc, i, j;
@@ -691,7 +692,8 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
        page_mask = ~(((u64) page_size) - 1);
-        phys_pg_pack->pages = kcalloc(total_npages, sizeof(u64), GFP_KERNEL);
+        phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64),
+                                                GFP_KERNEL);
        if (!phys_pg_pack->pages) {
                rc = -ENOMEM;
                goto page_pack_arr_mem_err;
@@ -750,9 +752,9 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr,
                struct hl_vm_phys_pg_pack *phys_pg_pack)
 {
        struct hl_device *hdev = ctx->hdev;
-        u64 next_vaddr = vaddr, paddr;
+        u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i;
        u32 page_size = phys_pg_pack->page_size;
-        int i, rc = 0, mapped_pg_cnt = 0;
+        int rc = 0;
        for (i = 0 ; i < phys_pg_pack->npages ; i++) {
                paddr = phys_pg_pack->pages[i];
@@ -764,7 +766,7 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr,
                rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size);
                if (rc) {
                        dev_err(hdev->dev,
-                                "map failed for handle %u, npages: %d, mapped: %d",
+                                "map failed for handle %u, npages: %llu, mapped: %llu",
                                phys_pg_pack->handle, phys_pg_pack->npages,
                                mapped_pg_cnt);
                        goto err;
@@ -985,10 +987,10 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr)
        struct hl_vm_hash_node *hnode = NULL;
        struct hl_userptr *userptr = NULL;
        enum vm_type_t *vm_type;
-        u64 next_vaddr;
+        u64 next_vaddr, i;
        u32 page_size;
        bool is_userptr;
-        int i, rc;
+        int rc;
        /* protect from double entrance */
        mutex_lock(&ctx->mem_hash_lock);
diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c
index 2f2e99cb2743..3a5a2cec8305 100644
--- a/drivers/misc/habanalabs/mmu.c
+++ b/drivers/misc/habanalabs/mmu.c
@@ -832,7 +832,7 @@ err:
 int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 {
        struct hl_device *hdev = ctx->hdev;
-        u64 real_virt_addr;
+        u64 real_virt_addr, real_phys_addr;
        u32 real_page_size, npages;
        int i, rc, mapped_cnt = 0;
@@ -857,14 +857,16 @@ int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
        npages = page_size / real_page_size;
        real_virt_addr = virt_addr;
+        real_phys_addr = phys_addr;
        for (i = 0 ; i < npages ; i++) {
-                rc = _hl_mmu_map(ctx, real_virt_addr, phys_addr,
+                rc = _hl_mmu_map(ctx, real_virt_addr, real_phys_addr,
                                real_page_size);
                if (rc)
                        goto err;
                real_virt_addr += real_page_size;
+                real_phys_addr += real_page_size;
                mapped_cnt++;
        }
diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index c712b7deb3a9..82a97866e0cf 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -1044,14 +1044,27 @@ static void alcor_init_mmc(struct alcor_sdmmc_host *host)
        mmc->caps2 = MMC_CAP2_NO_SDIO;
        mmc->ops = &alcor_sdc_ops;
-        /* Hardware cannot do scatter lists */
+        /* The hardware does DMA data transfer of 4096 bytes to/from a single
+         * buffer address. Scatterlists are not supported, but upon DMA
+         * completion (signalled via IRQ), the original vendor driver does
+         * then immediately set up another DMA transfer of the next 4096
+         * bytes.
+         *
+         * This means that we need to handle the I/O in 4096 byte chunks.
+         * Lacking a way to limit the sglist entries to 4096 bytes, we instead
+         * impose that only one segment is provided, with maximum size 4096,
+         * which also happens to be the minimum size. This means that the
+         * single-entry sglist handled by this driver can be handed directly
+         * to the hardware, nice and simple.
+         *
+         * Unfortunately though, that means we only do 4096 bytes I/O per
+         * MMC command. A future improvement would be to make the driver
+         * accept sg lists and entries of any size, and simply iterate
+         * through them 4096 bytes at a time.
+         */
        mmc->max_segs = AU6601_MAX_DMA_SEGMENTS;
        mmc->max_seg_size = AU6601_MAX_DMA_BLOCK_SIZE;
+        mmc->max_req_size = mmc->max_seg_size;
-        mmc->max_blk_size = mmc->max_seg_size;
-        mmc->max_blk_count = mmc->max_segs;
-        mmc->max_req_size = mmc->max_seg_size * mmc->max_segs;
 }
 static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 49e0daf2ef5e..f37003df1e01 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -1117,7 +1117,7 @@ static inline void mmc_davinci_cpufreq_deregister(struct mmc_davinci_host *host)
 {
 }
 #endif
-static void __init init_mmcsd_host(struct mmc_davinci_host *host)
+static void init_mmcsd_host(struct mmc_davinci_host *host)
 {
        mmc_davinci_reset_ctrl(host, 1);
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index d54612257b06..45f7b9b53d48 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -290,11 +290,8 @@ static void mxcmci_swap_buffers(struct mmc_data *data)
        struct scatterlist *sg;
        int i;
-        for_each_sg(data->sg, sg, data->sg_len, i) {
+        for_each_sg(data->sg, sg, data->sg_len, i)
-                void *buf = kmap_atomic(sg_page(sg) + sg->offset);
+                buffer_swap32(sg_virt(sg), sg->length);
-                buffer_swap32(buf, sg->length);
-                kunmap_atomic(buf);
-        }
 }
 #else
 static inline void mxcmci_swap_buffers(struct mmc_data *data) {}
@@ -611,7 +608,6 @@ static int mxcmci_transfer_data(struct mxcmci_host *host)
 {
        struct mmc_data *data = host->req->data;
        struct scatterlist *sg;
-        void *buf;
        int stat, i;
        host->data = data;
@@ -619,18 +615,14 @@ static int mxcmci_transfer_data(struct mxcmci_host *host)
        if (data->flags & MMC_DATA_READ) {
                for_each_sg(data->sg, sg, data->sg_len, i) {
-                        buf = kmap_atomic(sg_page(sg) + sg->offset);
+                        stat = mxcmci_pull(host, sg_virt(sg), sg->length);
-                        stat = mxcmci_pull(host, buf, sg->length);
-                        kunmap(buf);
                        if (stat)
                                return stat;
                        host->datasize += sg->length;
                }
        } else {
                for_each_sg(data->sg, sg, data->sg_len, i) {
-                        buf = kmap_atomic(sg_page(sg) + sg->offset);
+                        stat = mxcmci_push(host, sg_virt(sg), sg->length);
-                        stat = mxcmci_push(host, buf, sg->length);
-                        kunmap(buf);
                        if (stat)
                                return stat;
                        host->datasize += sg->length;
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index c907bf502a12..c1d3f0e38921 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -162,7 +162,7 @@ static void pxamci_dma_irq(void *param);
 static void pxamci_setup_data(struct pxamci_host *host, struct mmc_data *data)
 {
        struct dma_async_tx_descriptor *tx;
-        enum dma_data_direction direction;
+        enum dma_transfer_direction direction;
        struct dma_slave_config config;
        struct dma_chan *chan;
        unsigned int nob = data->blocks;
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 71e13844df6c..8742e27e4e8b 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -641,6 +641,7 @@ int renesas_sdhi_probe(struct platform_device *pdev,
        struct renesas_sdhi *priv;
        struct resource *res;
        int irq, ret, i;
+        u16 ver;
        of_data = of_device_get_match_data(&pdev->dev);
@@ -773,12 +774,17 @@ int renesas_sdhi_probe(struct platform_device *pdev,
        if (ret)
                goto efree;
+        ver = sd_ctrl_read16(host, CTL_VERSION);
+        /* GEN2_SDR104 is first known SDHI to use 32bit block count */
+        if (ver < SDHI_VER_GEN2_SDR104 && mmc_data->max_blk_count > U16_MAX)
+                mmc_data->max_blk_count = U16_MAX;
        ret = tmio_mmc_host_probe(host);
        if (ret < 0)
                goto edisclk;
        /* One Gen2 SDHI incarnation does NOT have a CBSY bit */
-        if (sd_ctrl_read16(host, CTL_VERSION) == SDHI_VER_GEN2_SDR50)
+        if (ver == SDHI_VER_GEN2_SDR50)
                mmc_data->flags &= ~TMIO_MMC_HAVE_CBSY;
        /* Enable tuning iff we have an SCC and a supported mode */
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index b1a66ca3821a..5bbed477c9b1 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -1056,6 +1056,9 @@ static int sdhci_omap_probe(struct platform_device *pdev)
                        mmc->f_max = 48000000;
        }
+        if (!mmc_can_gpio_ro(mmc))
+                mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
        pltfm_host->clk = devm_clk_get(dev, "fck");
        if (IS_ERR(pltfm_host->clk)) {
                ret = PTR_ERR(pltfm_host->clk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 370ca94b6775..b8ba74de9555 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -40,6 +40,9 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
+static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
+                               struct mlx5_core_dct *dct);
 static struct mlx5_core_rsc_common *
 mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
 {
@@ -227,20 +230,49 @@ static void destroy_resource_common(struct mlx5_core_dev *dev,
        wait_for_completion(&qp->common.free);
 }
+static int _mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
+                                  struct mlx5_core_dct *dct, bool need_cleanup)
+{
+        u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
+        u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
+        struct mlx5_core_qp *qp = &dct->mqp;
+        int err;
+        err = mlx5_core_drain_dct(dev, dct);
+        if (err) {
+                if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+                        goto destroy;
+                } else {
+                        mlx5_core_warn(
+                                dev, "failed drain DCT 0x%x with error 0x%x\n",
+                                qp->qpn, err);
+                        return err;
+                }
+        }
+        wait_for_completion(&dct->drained);
+destroy:
+        if (need_cleanup)
+                destroy_resource_common(dev, &dct->mqp);
+        MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
+        MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
+        MLX5_SET(destroy_dct_in, in, uid, qp->uid);
+        err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
+                            (void *)&out, sizeof(out));
+        return err;
+}
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
                         struct mlx5_core_dct *dct,
-                         u32 *in, int inlen)
+                         u32 *in, int inlen,
+                         u32 *out, int outlen)
 {
-        u32 out[MLX5_ST_SZ_DW(create_dct_out)]   = {0};
-        u32 din[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-        u32 dout[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
        struct mlx5_core_qp *qp = &dct->mqp;
        int err;
        init_completion(&dct->drained);
        MLX5_SET(create_dct_in, in, opcode, MLX5_CMD_OP_CREATE_DCT);
-        err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
+        err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
        if (err) {
                mlx5_core_warn(dev, "create DCT failed, ret %d\n", err);
                return err;
@@ -254,11 +286,7 @@ int mlx5_core_create_dct(struct mlx5_core_dev *dev,
        return 0;
 err_cmd:
-        MLX5_SET(destroy_dct_in, din, opcode, MLX5_CMD_OP_DESTROY_DCT);
+        _mlx5_core_destroy_dct(dev, dct, false);
-        MLX5_SET(destroy_dct_in, din, dctn, qp->qpn);
-        MLX5_SET(destroy_dct_in, din, uid, qp->uid);
-        mlx5_cmd_exec(dev, (void *)&in, sizeof(din),
-                      (void *)&out, sizeof(dout));
        return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_create_dct);
@@ -323,29 +351,7 @@ static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
 int mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
                          struct mlx5_core_dct *dct)
 {
-        u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
+        return _mlx5_core_destroy_dct(dev, dct, true);
-        u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-        struct mlx5_core_qp *qp = &dct->mqp;
-        int err;
-        err = mlx5_core_drain_dct(dev, dct);
-        if (err) {
-                if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-                        goto destroy;
-                } else {
-                        mlx5_core_warn(dev, "failed drain DCT 0x%x with error 0x%x\n", qp->qpn, err);
-                        return err;
-                }
-        }
-        wait_for_completion(&dct->drained);
-destroy:
-        destroy_resource_common(dev, &dct->mqp);
-        MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
-        MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
-        MLX5_SET(destroy_dct_in, in, uid, qp->uid);
-        err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-                            (void *)&out, sizeof(out));
-        return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_destroy_dct);
diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c
index 900c7073c46f..71308766e891 100644
--- a/drivers/platform/chrome/cros_ec_debugfs.c
+++ b/drivers/platform/chrome/cros_ec_debugfs.c
@@ -440,7 +440,7 @@ static int cros_ec_debugfs_probe(struct platform_device *pd)
        ret = cros_ec_create_pdinfo(debug_info);
        if (ret)
-                goto remove_debugfs;
+                goto remove_log;
        ec->debug_info = debug_info;
@@ -448,6 +448,8 @@ static int cros_ec_debugfs_probe(struct platform_device *pd)
        return 0;
+remove_log:
+        cros_ec_cleanup_console_log(debug_info);
 remove_debugfs:
        debugfs_remove_recursive(debug_info->dir);
        return ret;
@@ -467,7 +469,8 @@ static int __maybe_unused cros_ec_debugfs_suspend(struct device *dev)
 {
        struct cros_ec_dev *ec = dev_get_drvdata(dev);
-        cancel_delayed_work_sync(&ec->debug_info->log_poll_work);
+        if (ec->debug_info->log_buffer.buf)
+                cancel_delayed_work_sync(&ec->debug_info->log_poll_work);
        return 0;
 }
@@ -476,7 +479,8 @@ static int __maybe_unused cros_ec_debugfs_resume(struct device *dev)
 {
        struct cros_ec_dev *ec = dev_get_drvdata(dev);
-        schedule_delayed_work(&ec->debug_info->log_poll_work, 0);
+        if (ec->debug_info->log_buffer.buf)
+                schedule_delayed_work(&ec->debug_info->log_poll_work, 0);
        return 0;
 }
diff --git a/drivers/platform/chrome/wilco_ec/mailbox.c b/drivers/platform/chrome/wilco_ec/mailbox.c
index f6ff29a11f1a..14355668ddfa 100644
--- a/drivers/platform/chrome/wilco_ec/mailbox.c
+++ b/drivers/platform/chrome/wilco_ec/mailbox.c
@@ -223,11 +223,11 @@ int wilco_ec_mailbox(struct wilco_ec_device *ec, struct wilco_ec_message *msg)
                msg->command, msg->type, msg->flags, msg->response_size,
                msg->request_size);
+        mutex_lock(&ec->mailbox_lock);
        /* Prepare request packet */
        rq = ec->data_buffer;
        wilco_ec_prepare(msg, rq);
-        mutex_lock(&ec->mailbox_lock);
        ret = wilco_ec_transfer(ec, msg, rq);
        mutex_unlock(&ec->mailbox_lock);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 3c3cf89f713f..14bac4966c87 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1801,6 +1801,12 @@ static int hisi_sas_I_T_nexus_reset(struct domain_device *device)
        }
        hisi_sas_dereg_device(hisi_hba, device);
+        if (dev_is_sata(device)) {
+                rc = hisi_sas_softreset_ata_disk(device);
+                if (rc)
+                        return TMF_RESP_FUNC_FAILED;
+        }
        rc = hisi_sas_debug_I_T_nexus_reset(device);
        if ((rc == TMF_RESP_FUNC_COMPLETE) || (rc == -ENODEV))
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 1135e74646e2..8cec5230fe31 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -96,6 +96,7 @@ static int client_reserve = 1;
 static char partition_name[96] = "UNKNOWN";
 static unsigned int partition_number = -1;
 static LIST_HEAD(ibmvscsi_head);
+static DEFINE_SPINLOCK(ibmvscsi_driver_lock);
 static struct scsi_transport_template *ibmvscsi_transport_template;
@@ -2270,7 +2271,9 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
        }
        dev_set_drvdata(&vdev->dev, hostdata);
+        spin_lock(&ibmvscsi_driver_lock);
        list_add_tail(&hostdata->host_list, &ibmvscsi_head);
+        spin_unlock(&ibmvscsi_driver_lock);
        return 0;
      add_srp_port_failed:
@@ -2292,15 +2295,27 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 static int ibmvscsi_remove(struct vio_dev *vdev)
 {
        struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
-        list_del(&hostdata->host_list);
+        unsigned long flags;
-        unmap_persist_bufs(hostdata);
+        srp_remove_host(hostdata->host);
+        scsi_remove_host(hostdata->host);
+        purge_requests(hostdata, DID_ERROR);
+        spin_lock_irqsave(hostdata->host->host_lock, flags);
        release_event_pool(&hostdata->pool, hostdata);
+        spin_unlock_irqrestore(hostdata->host->host_lock, flags);
        ibmvscsi_release_crq_queue(&hostdata->queue, hostdata,
                                        max_events);
        kthread_stop(hostdata->work_thread);
-        srp_remove_host(hostdata->host);
+        unmap_persist_bufs(hostdata);
-        scsi_remove_host(hostdata->host);
+        spin_lock(&ibmvscsi_driver_lock);
+        list_del(&hostdata->host_list);
+        spin_unlock(&ibmvscsi_driver_lock);
        scsi_host_put(hostdata->host);
        return 0;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 420045155ba0..0c700b140ce7 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4991,6 +4991,13 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
                if ((domain & 0xf0) == 0xf0)
                        continue;
+                /* Bypass if not same domain and area of adapter. */
+                if (area && domain && ((area != vha->d_id.b.area) ||
+                    (domain != vha->d_id.b.domain)) &&
+                    (ha->current_topology == ISP_CFG_NL))
+                        continue;
                /* Bypass invalid local loop ID. */
                if (loop_id > LAST_LOCAL_LOOP_ID)
                        continue;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 677f82fdf56f..91f576d743fe 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1517,7 +1517,7 @@ __qla2xxx_eh_generic_reset(char *name, enum nexus_wait_type type,
                goto eh_reset_failed;
        }
        err = 2;
-        if (do_reset(fcport, cmd->device->lun, blk_mq_rq_cpu(cmd->request) + 1)
+        if (do_reset(fcport, cmd->device->lun, 1)
                != QLA_SUCCESS) {
                ql_log(ql_log_warn, vha, 0x800c,
                    "do_reset failed for cmd=%p.\n", cmd);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 20189675677a..601b9f1de267 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -585,10 +585,17 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
        if (!blk_rq_is_scsi(req)) {
                WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
                cmd->flags &= ~SCMD_INITIALIZED;
-                destroy_rcu_head(&cmd->rcu);
        }
        /*
+         * Calling rcu_barrier() is not necessary here because the
+         * SCSI error handler guarantees that the function called by
+         * call_rcu() has been called before scsi_end_request() is
+         * called.
+         */
+        destroy_rcu_head(&cmd->rcu);
+        /*
         * In the MQ case the command gets freed by __blk_mq_end_request,
         * so we have to do all cleanup that depends on it earlier.
         *
@@ -2541,8 +2548,10 @@ void scsi_device_resume(struct scsi_device *sdev)
         * device deleted during suspend)
         */
        mutex_lock(&sdev->state_mutex);
-        sdev->quiesced_by = NULL;
+        if (sdev->quiesced_by) {
-        blk_clear_pm_only(sdev->request_queue);
+                sdev->quiesced_by = NULL;
+                blk_clear_pm_only(sdev->request_queue);
+        }
        if (sdev->sdev_state == SDEV_QUIESCE)
                scsi_device_set_state(sdev, SDEV_RUNNING);
        mutex_unlock(&sdev->state_mutex);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 0508831d6fb9..0a82e93566dc 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2200,6 +2200,8 @@ void iscsi_remove_session(struct iscsi_cls_session *session)
        scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE);
        /* flush running scans then delete devices */
        flush_work(&session->scan_work);
+        /* flush running unbind operations */
+        flush_work(&session->unbind_work);
        __iscsi_unbind_session(&session->unbind_work);
        /* hw iscsi may not have removed all connections from session */
diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c
index 720760cd493f..ba39647a690c 100644
--- a/drivers/thermal/broadcom/bcm2835_thermal.c
+++ b/drivers/thermal/broadcom/bcm2835_thermal.c
@@ -119,8 +119,7 @@ static const struct debugfs_reg32 bcm2835_thermal_regs[] = {
 static void bcm2835_thermal_debugfs(struct platform_device *pdev)
 {
-        struct thermal_zone_device *tz = platform_get_drvdata(pdev);
+        struct bcm2835_thermal_data *data = platform_get_drvdata(pdev);
-        struct bcm2835_thermal_data *data = tz->devdata;
        struct debugfs_regset32 *regset;
        data->debugfsdir = debugfs_create_dir("bcm2835_thermal", NULL);
@@ -266,7 +265,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
        data->tz = tz;
-        platform_set_drvdata(pdev, tz);
+        platform_set_drvdata(pdev, data);
        /*
         * Thermal_zone doesn't enable hwmon as default,
@@ -290,8 +289,8 @@ err_clk:
 static int bcm2835_thermal_remove(struct platform_device *pdev)
 {
-        struct thermal_zone_device *tz = platform_get_drvdata(pdev);
+        struct bcm2835_thermal_data *data = platform_get_drvdata(pdev);
-        struct bcm2835_thermal_data *data = tz->devdata;
+        struct thermal_zone_device *tz = data->tz;
        debugfs_remove_recursive(data->debugfsdir);
        thermal_zone_of_sensor_unregister(&pdev->dev, tz);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6fff16113628..f7c1f49ec87f 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -536,12 +536,11 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
                               struct thermal_zone_device *tz, u32 power,
                               unsigned long *state)
 {
-        unsigned int cur_freq, target_freq;
+        unsigned int target_freq;
        u32 last_load, normalised_power;
        struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
        struct cpufreq_policy *policy = cpufreq_cdev->policy;
-        cur_freq = cpufreq_quick_get(policy->cpu);
        power = power > 0 ? power : 0;
        last_load = cpufreq_cdev->last_load ?: 1;
        normalised_power = (power * 100) / last_load;
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 61ca7ce3624e..5f3ed24e26ec 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -22,6 +22,13 @@ enum int3400_thermal_uuid {
        INT3400_THERMAL_PASSIVE_1,
        INT3400_THERMAL_ACTIVE,
        INT3400_THERMAL_CRITICAL,
+        INT3400_THERMAL_ADAPTIVE_PERFORMANCE,
+        INT3400_THERMAL_EMERGENCY_CALL_MODE,
+        INT3400_THERMAL_PASSIVE_2,
+        INT3400_THERMAL_POWER_BOSS,
+        INT3400_THERMAL_VIRTUAL_SENSOR,
+        INT3400_THERMAL_COOLING_MODE,
+        INT3400_THERMAL_HARDWARE_DUTY_CYCLING,
        INT3400_THERMAL_MAXIMUM_UUID,
 };
@@ -29,6 +36,13 @@ static char *int3400_thermal_uuids[INT3400_THERMAL_MAXIMUM_UUID] = {
        "42A441D6-AE6A-462b-A84B-4A8CE79027D3",
        "3A95C389-E4B8-4629-A526-C52C88626BAE",
        "97C68AE7-15FA-499c-B8C9-5DA81D606E0A",
+        "63BE270F-1C11-48FD-A6F7-3AF253FF3E2D",
+        "5349962F-71E6-431D-9AE8-0A635B710AEE",
+        "9E04115A-AE87-4D1C-9500-0F3E340BFE75",
+        "F5A35014-C209-46A4-993A-EB56DE7530A1",
+        "6ED722A7-9240-48A5-B479-31EEF723D7CF",
+        "16CAF1B7-DD38-40ED-B1C1-1B8A1913D531",
+        "BE84BABF-C4D4-403D-B495-3128FD44dAC1",
 };
 struct int3400_thermal_priv {
@@ -299,10 +313,9 @@ static int int3400_thermal_probe(struct platform_device *pdev)
        platform_set_drvdata(pdev, priv);
-        if (priv->uuid_bitmap & 1 << INT3400_THERMAL_PASSIVE_1) {
+        int3400_thermal_ops.get_mode = int3400_thermal_get_mode;
-                int3400_thermal_ops.get_mode = int3400_thermal_get_mode;
+        int3400_thermal_ops.set_mode = int3400_thermal_set_mode;
-                int3400_thermal_ops.set_mode = int3400_thermal_set_mode;
-        }
        priv->thermal = thermal_zone_device_register("INT3400 Thermal", 0, 0,
                                                priv, &int3400_thermal_ops,
                                                &int3400_thermal_params, 0, 0);
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index 7571f7c2e7c9..ac7256b5f020 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -101,7 +101,7 @@ struct powerclamp_worker_data {
        bool clamping;
 };
-static struct powerclamp_worker_data * __percpu worker_data;
+static struct powerclamp_worker_data __percpu *worker_data;
 static struct thermal_cooling_device *cooling_dev;
 static unsigned long *cpu_clamping_mask;  /* bit map for tracking per cpu
                                           * clamping kthread worker
@@ -494,7 +494,7 @@ static void start_power_clamp_worker(unsigned long cpu)
        struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
        struct kthread_worker *worker;
-        worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inject/%ld", cpu);
+        worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inj/%ld", cpu);
        if (IS_ERR(worker))
                return;
diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
index 5c07a61447d3..e4ea7f6aef20 100644
--- a/drivers/thermal/mtk_thermal.c
+++ b/drivers/thermal/mtk_thermal.c
@@ -199,6 +199,9 @@ enum {
 #define MT7622_TS1      0
 #define MT7622_NUM_CONTROLLER           1
+/* The maximum number of banks */
+#define MAX_NUM_ZONES           8
 /* The calibration coefficient of sensor  */
 #define MT7622_CALIBRATION      165
@@ -249,7 +252,7 @@ struct mtk_thermal_data {
        const int num_controller;
        const int *controller_offset;
        bool need_switch_bank;
-        struct thermal_bank_cfg bank_data[];
+        struct thermal_bank_cfg bank_data[MAX_NUM_ZONES];
 };
 struct mtk_thermal {
@@ -268,7 +271,7 @@ struct mtk_thermal {
        s32 vts[MAX_NUM_VTS];
        const struct mtk_thermal_data *conf;
-        struct mtk_thermal_bank banks[];
+        struct mtk_thermal_bank banks[MAX_NUM_ZONES];
 };
 /* MT8183 thermal sensor data */
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index 48eef552cba4..fc9399d9c082 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -666,7 +666,7 @@ static int exynos_get_temp(void *p, int *temp)
        struct exynos_tmu_data *data = p;
        int value, ret = 0;
-        if (!data || !data->tmu_read || !data->enabled)
+        if (!data || !data->tmu_read)
                return -EINVAL;
        else if (!data->enabled)
                /*
diff --git a/fs/block_dev.c b/fs/block_dev.c
index e9faa52bb489..78d3257435c0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -336,12 +336,14 @@ static void blkdev_bio_end_io(struct bio *bio)
        if (should_dirty) {
                bio_check_pages_dirty(bio);
        } else {
-                struct bio_vec *bvec;
+                if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
-                int i;
+                        struct bvec_iter_all iter_all;
-                struct bvec_iter_all iter_all;
+                        struct bio_vec *bvec;
+                        int i;
-                bio_for_each_segment_all(bvec, bio, i, iter_all)
+                        bio_for_each_segment_all(bvec, bio, i, iter_all)
-                        put_page(bvec->bv_page);
+                                put_page(bvec->bv_page);
+                }
                bio_put(bio);
        }
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 217276b8b942..f9b71c12cc9f 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1008,7 +1008,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
        unsigned int xid;
        int rc;
-        if (remap_flags & ~REMAP_FILE_ADVISORY)
+        if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
                return -EINVAL;
        cifs_dbg(FYI, "clone range\n");
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 142164ef1f05..5c0298b9998f 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION   "2.18"
+#define CIFS_VERSION   "2.19"
 #endif                          /* _CIFSFS_H */
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 2a6d20c0ce02..89006e044973 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2632,43 +2632,56 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
        struct TCP_Server_Info *server =
                tlink_tcon(wdata->cfile->tlink)->ses->server;
-        /*
-         * Wait for credits to resend this wdata.
-         * Note: we are attempting to resend the whole wdata not in segments
-         */
        do {
-                rc = server->ops->wait_mtu_credits(server, wdata->bytes, &wsize,
+                if (wdata->cfile->invalidHandle) {
-                                                   &credits);
+                        rc = cifs_reopen_file(wdata->cfile, false);
+                        if (rc == -EAGAIN)
+                                continue;
+                        else if (rc)
+                                break;
+                }
-                if (rc)
-                        goto out;
-                if (wsize < wdata->bytes) {
+                /*
-                        add_credits_and_wake_if(server, &credits, 0);
+                 * Wait for credits to resend this wdata.
-                        msleep(1000);
+                 * Note: we are attempting to resend the whole wdata not in
-                }
+                 * segments
-        } while (wsize < wdata->bytes);
+                 */
+                do {
+                        rc = server->ops->wait_mtu_credits(server, wdata->bytes,
+                                                &wsize, &credits);
+                        if (rc)
+                                goto fail;
+                        if (wsize < wdata->bytes) {
+                                add_credits_and_wake_if(server, &credits, 0);
+                                msleep(1000);
+                        }
+                } while (wsize < wdata->bytes);
+                wdata->credits = credits;
-        wdata->credits = credits;
+                rc = adjust_credits(server, &wdata->credits, wdata->bytes);
-        rc = -EAGAIN;
-        while (rc == -EAGAIN) {
+                if (!rc) {
-                rc = 0;
+                        if (wdata->cfile->invalidHandle)
-                if (wdata->cfile->invalidHandle)
+                                rc = -EAGAIN;
-                        rc = cifs_reopen_file(wdata->cfile, false);
+                        else
-                if (!rc)
+                                rc = server->ops->async_writev(wdata,
-                        rc = server->ops->async_writev(wdata,
                                        cifs_uncached_writedata_release);
-        }
+                }
-        if (!rc) {
+                /* If the write was successfully sent, we are done */
-                list_add_tail(&wdata->list, wdata_list);
+                if (!rc) {
-                return 0;
+                        list_add_tail(&wdata->list, wdata_list);
-        }
+                        return 0;
+                }
-        add_credits_and_wake_if(server, &wdata->credits, 0);
+                /* Roll back credits and retry if needed */
-out:
+                add_credits_and_wake_if(server, &wdata->credits, 0);
-        kref_put(&wdata->refcount, cifs_uncached_writedata_release);
+        } while (rc == -EAGAIN);
+fail:
+        kref_put(&wdata->refcount, cifs_uncached_writedata_release);
        return rc;
 }
@@ -2896,12 +2909,12 @@ restart_loop:
                                                wdata->bytes, &tmp_from,
                                                ctx->cfile, cifs_sb, &tmp_list,
                                                ctx);
+                                        kref_put(&wdata->refcount,
+                                                cifs_uncached_writedata_release);
                                }
                                list_splice(&tmp_list, &ctx->list);
-                                kref_put(&wdata->refcount,
-                                         cifs_uncached_writedata_release);
                                goto restart_loop;
                        }
                }
@@ -3348,44 +3361,55 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata,
        struct TCP_Server_Info *server =
                tlink_tcon(rdata->cfile->tlink)->ses->server;
-        /*
-         * Wait for credits to resend this rdata.
-         * Note: we are attempting to resend the whole rdata not in segments
-         */
        do {
-                rc = server->ops->wait_mtu_credits(server, rdata->bytes,
+                if (rdata->cfile->invalidHandle) {
+                        rc = cifs_reopen_file(rdata->cfile, true);
+                        if (rc == -EAGAIN)
+                                continue;
+                        else if (rc)
+                                break;
+                }
+                /*
+                 * Wait for credits to resend this rdata.
+                 * Note: we are attempting to resend the whole rdata not in
+                 * segments
+                 */
+                do {
+                        rc = server->ops->wait_mtu_credits(server, rdata->bytes,
                                                &rsize, &credits);
-                if (rc)
+                        if (rc)
-                        goto out;
+                                goto fail;
-                if (rsize < rdata->bytes) {
+                        if (rsize < rdata->bytes) {
-                        add_credits_and_wake_if(server, &credits, 0);
+                                add_credits_and_wake_if(server, &credits, 0);
-                        msleep(1000);
+                                msleep(1000);
-                }
+                        }
-        } while (rsize < rdata->bytes);
+                } while (rsize < rdata->bytes);
+                rdata->credits = credits;
-        rdata->credits = credits;
+                rc = adjust_credits(server, &rdata->credits, rdata->bytes);
-        rc = -EAGAIN;
+                if (!rc) {
-        while (rc == -EAGAIN) {
+                        if (rdata->cfile->invalidHandle)
-                rc = 0;
+                                rc = -EAGAIN;
-                if (rdata->cfile->invalidHandle)
+                        else
-                        rc = cifs_reopen_file(rdata->cfile, true);
+                                rc = server->ops->async_readv(rdata);
-                if (!rc)
+                }
-                        rc = server->ops->async_readv(rdata);
-        }
-        if (!rc) {
+                /* If the read was successfully sent, we are done */
-                /* Add to aio pending list */
+                if (!rc) {
-                list_add_tail(&rdata->list, rdata_list);
+                        /* Add to aio pending list */
-                return 0;
+                        list_add_tail(&rdata->list, rdata_list);
-        }
+                        return 0;
+                }
-        add_credits_and_wake_if(server, &rdata->credits, 0);
+                /* Roll back credits and retry if needed */
-out:
+                add_credits_and_wake_if(server, &rdata->credits, 0);
-        kref_put(&rdata->refcount,
+        } while (rc == -EAGAIN);
-                cifs_uncached_readdata_release);
+fail:
+        kref_put(&rdata->refcount, cifs_uncached_readdata_release);
        return rc;
 }
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 924269cec135..e32c264e3adb 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -1036,7 +1036,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
        {STATUS_UNFINISHED_CONTEXT_DELETED, -EIO,
        "STATUS_UNFINISHED_CONTEXT_DELETED"},
        {STATUS_NO_TGT_REPLY, -EIO, "STATUS_NO_TGT_REPLY"},
-        {STATUS_OBJECTID_NOT_FOUND, -EIO, "STATUS_OBJECTID_NOT_FOUND"},
+        /* Note that ENOATTTR and ENODATA are the same errno */
+        {STATUS_OBJECTID_NOT_FOUND, -ENODATA, "STATUS_OBJECTID_NOT_FOUND"},
        {STATUS_NO_IP_ADDRESSES, -EIO, "STATUS_NO_IP_ADDRESSES"},
        {STATUS_WRONG_CREDENTIAL_HANDLE, -EIO,
        "STATUS_WRONG_CREDENTIAL_HANDLE"},
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index c399e09b76e6..21ac19ff19cb 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1628,9 +1628,16 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
        iov[1].iov_base = unc_path;
        iov[1].iov_len = unc_path_len;
-        /* 3.11 tcon req must be signed if not encrypted. See MS-SMB2 3.2.4.1.1 */
+        /*
+         * 3.11 tcon req must be signed if not encrypted. See MS-SMB2 3.2.4.1.1
+         * unless it is guest or anonymous user. See MS-SMB2 3.2.5.3.1
+         * (Samba servers don't always set the flag so also check if null user)
+         */
        if ((ses->server->dialect == SMB311_PROT_ID) &&
-            !smb3_encryption_required(tcon))
+            !smb3_encryption_required(tcon) &&
+            !(ses->session_flags &
+                    (SMB2_SESSION_FLAG_IS_GUEST|SMB2_SESSION_FLAG_IS_NULL)) &&
+            ((ses->user_name != NULL) || (ses->sectype == Kerberos)))
                req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
        memset(&rqst, 0, sizeof(struct smb_rqst));
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index fa226de48ef3..99c4d799c24b 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -549,19 +549,19 @@ DECLARE_EVENT_CLASS(smb3_tcon_class,
                __field(unsigned int, xid)
                __field(__u32, tid)
                __field(__u64, sesid)
-                __field(const char *,  unc_name)
+                __string(name, unc_name)
                __field(int, rc)
        ),
        TP_fast_assign(
                __entry->xid = xid;
                __entry->tid = tid;
                __entry->sesid = sesid;
-                __entry->unc_name = unc_name;
+                __assign_str(name, unc_name);
                __entry->rc = rc;
        ),
        TP_printk("xid=%u sid=0x%llx tid=0x%x unc_name=%s rc=%d",
                __entry->xid, __entry->sesid, __entry->tid,
-                __entry->unc_name, __entry->rc)
+                __get_str(name), __entry->rc)
 )
 #define DEFINE_SMB3_TCON_EVENT(name)          \
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a1ac7e9245ec..75a5309f2231 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -384,7 +384,7 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
 {
        struct ext4_inode_info *ei = EXT4_I(inode);
-        if (ext4_handle_valid(handle)) {
+        if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) {
                ei->i_sync_tid = handle->h_transaction->t_tid;
                if (datasync)
                        ei->i_datasync_tid = handle->h_transaction->t_tid;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 69d65d49837b..98ec11f69cd4 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -125,7 +125,7 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
        struct super_block *sb = inode->i_sb;
        int blockmask = sb->s_blocksize - 1;
-        if (pos >= i_size_read(inode))
+        if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
                return 0;
        if ((pos | iov_iter_alignment(from)) & blockmask)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index c2225f0d31b5..2024d3fa5504 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -1222,6 +1222,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
        ext4_lblk_t offsets[4], offsets2[4];
        Indirect chain[4], chain2[4];
        Indirect *partial, *partial2;
+        Indirect *p = NULL, *p2 = NULL;
        ext4_lblk_t max_block;
        __le32 nr = 0, nr2 = 0;
        int n = 0, n2 = 0;
@@ -1263,7 +1264,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
                }
-                partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+                partial = p = ext4_find_shared(inode, n, offsets, chain, &nr);
                if (nr) {
                        if (partial == chain) {
                                /* Shared branch grows from the inode */
@@ -1288,13 +1289,11 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
                                partial->p + 1,
                                (__le32 *)partial->bh->b_data+addr_per_block,
                                (chain+n-1) - partial);
-                        BUFFER_TRACE(partial->bh, "call brelse");
-                        brelse(partial->bh);
                        partial--;
                }
 end_range:
-                partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+                partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
                if (nr2) {
                        if (partial2 == chain2) {
                                /*
@@ -1324,16 +1323,14 @@ end_range:
                                           (__le32 *)partial2->bh->b_data,
                                           partial2->p,
                                           (chain2+n2-1) - partial2);
-                        BUFFER_TRACE(partial2->bh, "call brelse");
-                        brelse(partial2->bh);
                        partial2--;
                }
                goto do_indirects;
        }
        /* Punch happened within the same level (n == n2) */
-        partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+        partial = p = ext4_find_shared(inode, n, offsets, chain, &nr);
-        partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+        partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
        /* Free top, but only if partial2 isn't its subtree. */
        if (nr) {
@@ -1390,11 +1387,7 @@ end_range:
                                           partial->p + 1,
                                           partial2->p,
                                           (chain+n-1) - partial);
-                        BUFFER_TRACE(partial->bh, "call brelse");
+                        goto cleanup;
-                        brelse(partial->bh);
-                        BUFFER_TRACE(partial2->bh, "call brelse");
-                        brelse(partial2->bh);
-                        return 0;
                }
                /*
@@ -1409,8 +1402,6 @@ end_range:
                                           partial->p + 1,
                                           (__le32 *)partial->bh->b_data+addr_per_block,
                                           (chain+n-1) - partial);
-                        BUFFER_TRACE(partial->bh, "call brelse");
-                        brelse(partial->bh);
                        partial--;
                }
                if (partial2 > chain2 && depth2 <= depth) {
@@ -1418,11 +1409,21 @@ end_range:
                                           (__le32 *)partial2->bh->b_data,
                                           partial2->p,
                                           (chain2+n2-1) - partial2);
-                        BUFFER_TRACE(partial2->bh, "call brelse");
-                        brelse(partial2->bh);
                        partial2--;
                }
        }
+cleanup:
+        while (p && p > chain) {
+                BUFFER_TRACE(p->bh, "call brelse");
+                brelse(p->bh);
+                p--;
+        }
+        while (p2 && p2 > chain2) {
+                BUFFER_TRACE(p2->bh, "call brelse");
+                brelse(p2->bh);
+                p2--;
+        }
        return 0;
 do_indirects:
@@ -1430,7 +1431,7 @@ do_indirects:
        switch (offsets[0]) {
        default:
                if (++n >= n2)
-                        return 0;
+                        break;
                nr = i_data[EXT4_IND_BLOCK];
                if (nr) {
                        ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
@@ -1439,7 +1440,7 @@ do_indirects:
                /* fall through */
        case EXT4_IND_BLOCK:
                if (++n >= n2)
-                        return 0;
+                        break;
                nr = i_data[EXT4_DIND_BLOCK];
                if (nr) {
                        ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
@@ -1448,7 +1449,7 @@ do_indirects:
                /* fall through */
        case EXT4_DIND_BLOCK:
                if (++n >= n2)
-                        return 0;
+                        break;
                nr = i_data[EXT4_TIND_BLOCK];
                if (nr) {
                        ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
@@ -1458,5 +1459,5 @@ do_indirects:
        case EXT4_TIND_BLOCK:
                ;
        }
-        return 0;
+        goto cleanup;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b54b261ded36..b32a57bc5d5d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -6080,36 +6080,6 @@ out:
        return;
 }
-#if 0
-/*
- * Bind an inode's backing buffer_head into this transaction, to prevent
- * it from being flushed to disk early.  Unlike
- * ext4_reserve_inode_write, this leaves behind no bh reference and
- * returns no iloc structure, so the caller needs to repeat the iloc
- * lookup to mark the inode dirty later.
- */
-static int ext4_pin_inode(handle_t *handle, struct inode *inode)
-{
-        struct ext4_iloc iloc;
-        int err = 0;
-        if (handle) {
-                err = ext4_get_inode_loc(inode, &iloc);
-                if (!err) {
-                        BUFFER_TRACE(iloc.bh, "get_write_access");
-                        err = jbd2_journal_get_write_access(handle, iloc.bh);
-                        if (!err)
-                                err = ext4_handle_dirty_metadata(handle,
-                                                                 NULL,
-                                                                 iloc.bh);
-                        brelse(iloc.bh);
-                }
-        }
-        ext4_std_error(inode->i_sb, err);
-        return err;
-}
-#endif
 int ext4_change_inode_journal_flag(struct inode *inode, int val)
 {
        journal_t *journal;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 3c4f8bb59f8a..bab3da4f1e0d 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1000,6 +1000,13 @@ resizefs_out:
                if (!blk_queue_discard(q))
                        return -EOPNOTSUPP;
+                /*
+                 * We haven't replayed the journal, so we cannot use our
+                 * block-bitmap-guided storage zapping commands.
+                 */
+                if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb))
+                        return -EROFS;
                if (copy_from_user(&range, (struct fstrim_range __user *)arg,
                    sizeof(range)))
                        return -EFAULT;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 3d9b18505c0c..e7ae26e36c9c 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -932,11 +932,18 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
        memcpy(n_group_desc, o_group_desc,
               EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
        n_group_desc[gdb_num] = gdb_bh;
+        BUFFER_TRACE(gdb_bh, "get_write_access");
+        err = ext4_journal_get_write_access(handle, gdb_bh);
+        if (err) {
+                kvfree(n_group_desc);
+                brelse(gdb_bh);
+                return err;
+        }
        EXT4_SB(sb)->s_group_desc = n_group_desc;
        EXT4_SB(sb)->s_gdb_count++;
        kvfree(o_group_desc);
-        BUFFER_TRACE(gdb_bh, "get_write_access");
-        err = ext4_journal_get_write_access(handle, gdb_bh);
        return err;
 }
@@ -2073,6 +2080,10 @@ out:
                free_flex_gd(flex_gd);
        if (resize_inode != NULL)
                iput(resize_inode);
-        ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count);
+        if (err)
+                ext4_warning(sb, "error (%d) occurred during "
+                             "file system resize", err);
+        ext4_msg(sb, KERN_INFO, "resized filesystem to %llu",
+                 ext4_blocks_count(es));
        return err;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f5b828bf1299..6ed4eb81e674 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -430,6 +430,12 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
        spin_unlock(&sbi->s_md_lock);
 }
+static bool system_going_down(void)
+{
+        return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
+                || system_state == SYSTEM_RESTART;
+}
 /* Deal with the reporting of failure conditions on a filesystem such as
 * inconsistencies detected or read IO failures.
 *
@@ -460,7 +466,12 @@ static void ext4_handle_error(struct super_block *sb)
                if (journal)
                        jbd2_journal_abort(journal, -EIO);
        }
-        if (test_opt(sb, ERRORS_RO)) {
+        /*
+         * We force ERRORS_RO behavior when system is rebooting. Otherwise we
+         * could panic during 'reboot -f' as the underlying device got already
+         * disabled.
+         */
+        if (test_opt(sb, ERRORS_RO) || system_going_down()) {
                ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
                /*
                 * Make sure updated value of ->s_mount_flags will be visible
@@ -468,8 +479,7 @@ static void ext4_handle_error(struct super_block *sb)
                 */
                smp_wmb();
                sb->s_flags |= SB_RDONLY;
-        }
+        } else if (test_opt(sb, ERRORS_PANIC)) {
-        if (test_opt(sb, ERRORS_PANIC)) {
                if (EXT4_SB(sb)->s_journal &&
                  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
                        return;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index c88088d92613..6aaa30580a2b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -189,17 +189,28 @@ struct sqe_submit {
        bool                            needs_fixed_file;
 };
+/*
+ * First field must be the file pointer in all the
+ * iocb unions! See also 'struct kiocb' in <linux/fs.h>
+ */
 struct io_poll_iocb {
        struct file                     *file;
        struct wait_queue_head          *head;
        __poll_t                        events;
-        bool                            woken;
+        bool                            done;
        bool                            canceled;
        struct wait_queue_entry         wait;
 };
+/*
+ * NOTE! Each of the iocb union members has the file pointer
+ * as the first entry in their struct definition. So you can
+ * access the file pointer through any of the sub-structs,
+ * or directly as just 'ki_filp' in this struct.
+ */
 struct io_kiocb {
        union {
+                struct file             *file;
                struct kiocb            rw;
                struct io_poll_iocb     poll;
        };
@@ -214,6 +225,7 @@ struct io_kiocb {
 #define REQ_F_IOPOLL_COMPLETED  2       /* polled IO has completed */
 #define REQ_F_FIXED_FILE        4       /* ctx owns file */
 #define REQ_F_SEQ_PREV          8       /* sequential with previous */
+#define REQ_F_PREPPED           16      /* prep already done */
        u64                     user_data;
        u64                     error;
@@ -355,20 +367,25 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
        }
 }
-static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
+{
+        if (waitqueue_active(&ctx->wait))
+                wake_up(&ctx->wait);
+        if (waitqueue_active(&ctx->sqo_wait))
+                wake_up(&ctx->sqo_wait);
+}
+static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data,
                                long res, unsigned ev_flags)
 {
        unsigned long flags;
        spin_lock_irqsave(&ctx->completion_lock, flags);
-        io_cqring_fill_event(ctx, ki_user_data, res, ev_flags);
+        io_cqring_fill_event(ctx, user_data, res, ev_flags);
        io_commit_cqring(ctx);
        spin_unlock_irqrestore(&ctx->completion_lock, flags);
-        if (waitqueue_active(&ctx->wait))
+        io_cqring_ev_posted(ctx);
-                wake_up(&ctx->wait);
-        if (waitqueue_active(&ctx->sqo_wait))
-                wake_up(&ctx->sqo_wait);
 }
 static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
@@ -382,13 +399,14 @@ static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
 static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
                                   struct io_submit_state *state)
 {
+        gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
        struct io_kiocb *req;
        if (!percpu_ref_tryget(&ctx->refs))
                return NULL;
        if (!state) {
-                req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
+                req = kmem_cache_alloc(req_cachep, gfp);
                if (unlikely(!req))
                        goto out;
        } else if (!state->free_reqs) {
@@ -396,10 +414,18 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
                int ret;
                sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs));
-                ret = kmem_cache_alloc_bulk(req_cachep, __GFP_NOWARN, sz,
+                ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs);
-                                                state->reqs);
-                if (unlikely(ret <= 0))
+                /*
-                        goto out;
+                 * Bulk alloc is all-or-nothing. If we fail to get a batch,
+                 * retry single alloc to be on the safe side.
+                 */
+                if (unlikely(ret <= 0)) {
+                        state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
+                        if (!state->reqs[0])
+                                goto out;
+                        ret = 1;
+                }
                state->free_reqs = ret - 1;
                state->cur_req = 1;
                req = state->reqs[0];
@@ -411,7 +437,8 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
        req->ctx = ctx;
        req->flags = 0;
-        refcount_set(&req->refs, 0);
+        /* one is dropped after submission, the other at completion */
+        refcount_set(&req->refs, 2);
        return req;
 out:
        io_ring_drop_ctx_refs(ctx, 1);
@@ -429,10 +456,16 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
 static void io_free_req(struct io_kiocb *req)
 {
-        if (!refcount_read(&req->refs) || refcount_dec_and_test(&req->refs)) {
+        if (req->file && !(req->flags & REQ_F_FIXED_FILE))
-                io_ring_drop_ctx_refs(req->ctx, 1);
+                fput(req->file);
-                kmem_cache_free(req_cachep, req);
+        io_ring_drop_ctx_refs(req->ctx, 1);
-        }
+        kmem_cache_free(req_cachep, req);
+}
+static void io_put_req(struct io_kiocb *req)
+{
+        if (refcount_dec_and_test(&req->refs))
+                io_free_req(req);
 }
 /*
@@ -442,44 +475,34 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
                               struct list_head *done)
 {
        void *reqs[IO_IOPOLL_BATCH];
-        int file_count, to_free;
-        struct file *file = NULL;
        struct io_kiocb *req;
+        int to_free;
-        file_count = to_free = 0;
+        to_free = 0;
        while (!list_empty(done)) {
                req = list_first_entry(done, struct io_kiocb, list);
                list_del(&req->list);
                io_cqring_fill_event(ctx, req->user_data, req->error, 0);
-                reqs[to_free++] = req;
                (*nr_events)++;
-                /*
+                if (refcount_dec_and_test(&req->refs)) {
-                 * Batched puts of the same file, to avoid dirtying the
+                        /* If we're not using fixed files, we have to pair the
-                 * file usage count multiple times, if avoidable.
+                         * completion part with the file put. Use regular
-                 */
+                         * completions for those, only batch free for fixed
-                if (!(req->flags & REQ_F_FIXED_FILE)) {
+                         * file.
-                        if (!file) {
+                         */
-                                file = req->rw.ki_filp;
+                        if (req->flags & REQ_F_FIXED_FILE) {
-                                file_count = 1;
+                                reqs[to_free++] = req;
-                        } else if (file == req->rw.ki_filp) {
+                                if (to_free == ARRAY_SIZE(reqs))
-                                file_count++;
+                                        io_free_req_many(ctx, reqs, &to_free);
                        } else {
-                                fput_many(file, file_count);
+                                io_free_req(req);
-                                file = req->rw.ki_filp;
-                                file_count = 1;
                        }
                }
-                if (to_free == ARRAY_SIZE(reqs))
-                        io_free_req_many(ctx, reqs, &to_free);
        }
-        io_commit_cqring(ctx);
-        if (file)
+        io_commit_cqring(ctx);
-                fput_many(file, file_count);
        io_free_req_many(ctx, reqs, &to_free);
 }
@@ -602,21 +625,14 @@ static void kiocb_end_write(struct kiocb *kiocb)
        }
 }
-static void io_fput(struct io_kiocb *req)
-{
-        if (!(req->flags & REQ_F_FIXED_FILE))
-                fput(req->rw.ki_filp);
-}
 static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 {
        struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
        kiocb_end_write(kiocb);
-        io_fput(req);
        io_cqring_add_event(req->ctx, req->user_data, res, 0);
-        io_free_req(req);
+        io_put_req(req);
 }
 static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
@@ -731,31 +747,18 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
        const struct io_uring_sqe *sqe = s->sqe;
        struct io_ring_ctx *ctx = req->ctx;
        struct kiocb *kiocb = &req->rw;
-        unsigned ioprio, flags;
+        unsigned ioprio;
-        int fd, ret;
+        int ret;
+        if (!req->file)
+                return -EBADF;
        /* For -EAGAIN retry, everything is already prepped */
-        if (kiocb->ki_filp)
+        if (req->flags & REQ_F_PREPPED)
                return 0;
-        flags = READ_ONCE(sqe->flags);
+        if (force_nonblock && !io_file_supports_async(req->file))
-        fd = READ_ONCE(sqe->fd);
+                force_nonblock = false;
-        if (flags & IOSQE_FIXED_FILE) {
-                if (unlikely(!ctx->user_files ||
-                    (unsigned) fd >= ctx->nr_user_files))
-                        return -EBADF;
-                kiocb->ki_filp = ctx->user_files[fd];
-                req->flags |= REQ_F_FIXED_FILE;
-        } else {
-                if (s->needs_fixed_file)
-                        return -EBADF;
-                kiocb->ki_filp = io_file_get(state, fd);
-                if (unlikely(!kiocb->ki_filp))
-                        return -EBADF;
-                if (force_nonblock && !io_file_supports_async(kiocb->ki_filp))
-                        force_nonblock = false;
-        }
        kiocb->ki_pos = READ_ONCE(sqe->off);
        kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
        kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
@@ -764,7 +767,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
        if (ioprio) {
                ret = ioprio_check_cap(ioprio);
                if (ret)
-                        goto out_fput;
+                        return ret;
                kiocb->ki_ioprio = ioprio;
        } else
@@ -772,38 +775,26 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
        ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
        if (unlikely(ret))
-                goto out_fput;
+                return ret;
        if (force_nonblock) {
                kiocb->ki_flags |= IOCB_NOWAIT;
                req->flags |= REQ_F_FORCE_NONBLOCK;
        }
        if (ctx->flags & IORING_SETUP_IOPOLL) {
-                ret = -EOPNOTSUPP;
                if (!(kiocb->ki_flags & IOCB_DIRECT) ||
                    !kiocb->ki_filp->f_op->iopoll)
-                        goto out_fput;
+                        return -EOPNOTSUPP;
                req->error = 0;
                kiocb->ki_flags |= IOCB_HIPRI;
                kiocb->ki_complete = io_complete_rw_iopoll;
        } else {
-                if (kiocb->ki_flags & IOCB_HIPRI) {
+                if (kiocb->ki_flags & IOCB_HIPRI)
-                        ret = -EINVAL;
+                        return -EINVAL;
-                        goto out_fput;
-                }
                kiocb->ki_complete = io_complete_rw;
        }
+        req->flags |= REQ_F_PREPPED;
        return 0;
-out_fput:
-        if (!(flags & IOSQE_FIXED_FILE)) {
-                /*
-                 * in case of error, we didn't use this file reference. drop it.
-                 */
-                if (state)
-                        state->used_refs--;
-                io_file_put(state, kiocb->ki_filp);
-        }
-        return ret;
 }
 static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
@@ -864,6 +855,9 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
        iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
        if (offset)
                iov_iter_advance(iter, offset);
+        /* don't drop a reference to these pages */
+        iter->type |= ITER_BVEC_FLAG_NO_REF;
        return 0;
 }
@@ -887,7 +881,7 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
        opcode = READ_ONCE(sqe->opcode);
        if (opcode == IORING_OP_READ_FIXED ||
            opcode == IORING_OP_WRITE_FIXED) {
-                ssize_t ret = io_import_fixed(ctx, rw, sqe, iter);
+                int ret = io_import_fixed(ctx, rw, sqe, iter);
                *iovec = NULL;
                return ret;
        }
@@ -945,31 +939,29 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
        async_list->io_end = io_end;
 }
-static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
+static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
-                       bool force_nonblock, struct io_submit_state *state)
+                   bool force_nonblock, struct io_submit_state *state)
 {
        struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
        struct kiocb *kiocb = &req->rw;
        struct iov_iter iter;
        struct file *file;
        size_t iov_count;
-        ssize_t ret;
+        int ret;
        ret = io_prep_rw(req, s, force_nonblock, state);
        if (ret)
                return ret;
        file = kiocb->ki_filp;
-        ret = -EBADF;
        if (unlikely(!(file->f_mode & FMODE_READ)))
-                goto out_fput;
+                return -EBADF;
-        ret = -EINVAL;
        if (unlikely(!file->f_op->read_iter))
-                goto out_fput;
+                return -EINVAL;
        ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
        if (ret)
-                goto out_fput;
+                return ret;
        iov_count = iov_iter_count(&iter);
        ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count);
@@ -991,38 +983,32 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
                }
        }
        kfree(iovec);
-out_fput:
-        /* Hold on to the file for -EAGAIN */
-        if (unlikely(ret && ret != -EAGAIN))
-                io_fput(req);
        return ret;
 }
-static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
+static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
-                        bool force_nonblock, struct io_submit_state *state)
+                    bool force_nonblock, struct io_submit_state *state)
 {
        struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
        struct kiocb *kiocb = &req->rw;
        struct iov_iter iter;
        struct file *file;
        size_t iov_count;
-        ssize_t ret;
+        int ret;
        ret = io_prep_rw(req, s, force_nonblock, state);
        if (ret)
                return ret;
-        ret = -EBADF;
        file = kiocb->ki_filp;
        if (unlikely(!(file->f_mode & FMODE_WRITE)))
-                goto out_fput;
+                return -EBADF;
-        ret = -EINVAL;
        if (unlikely(!file->f_op->write_iter))
-                goto out_fput;
+                return -EINVAL;
        ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
        if (ret)
-                goto out_fput;
+                return ret;
        iov_count = iov_iter_count(&iter);
@@ -1054,10 +1040,6 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
        }
 out_free:
        kfree(iovec);
-out_fput:
-        /* Hold on to the file for -EAGAIN */
-        if (unlikely(ret && ret != -EAGAIN))
-                io_fput(req);
        return ret;
 }
@@ -1072,29 +1054,19 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
        if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
                return -EINVAL;
-        /*
-         * Twilight zone - it's possible that someone issued an opcode that
-         * has a file attached, then got -EAGAIN on submission, and changed
-         * the sqe before we retried it from async context. Avoid dropping
-         * a file reference for this malicious case, and flag the error.
-         */
-        if (req->rw.ki_filp) {
-                err = -EBADF;
-                io_fput(req);
-        }
        io_cqring_add_event(ctx, user_data, err, 0);
-        io_free_req(req);
+        io_put_req(req);
        return 0;
 }
 static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
        struct io_ring_ctx *ctx = req->ctx;
-        unsigned flags;
-        int fd;
-        /* Prep already done */
+        if (!req->file)
-        if (req->rw.ki_filp)
+                return -EBADF;
+        /* Prep already done (EAGAIN retry) */
+        if (req->flags & REQ_F_PREPPED)
                return 0;
        if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
@@ -1102,20 +1074,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
        if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
                return -EINVAL;
-        fd = READ_ONCE(sqe->fd);
+        req->flags |= REQ_F_PREPPED;
-        flags = READ_ONCE(sqe->flags);
-        if (flags & IOSQE_FIXED_FILE) {
-                if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files))
-                        return -EBADF;
-                req->rw.ki_filp = ctx->user_files[fd];
-                req->flags |= REQ_F_FIXED_FILE;
-        } else {
-                req->rw.ki_filp = fget(fd);
-                if (unlikely(!req->rw.ki_filp))
-                        return -EBADF;
-        }
        return 0;
 }
@@ -1144,9 +1103,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
                                end > 0 ? end : LLONG_MAX,
                                fsync_flags & IORING_FSYNC_DATASYNC);
-        io_fput(req);
        io_cqring_add_event(req->ctx, sqe->user_data, ret, 0);
-        io_free_req(req);
+        io_put_req(req);
        return 0;
 }
@@ -1204,15 +1162,16 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe)
        spin_unlock_irq(&ctx->completion_lock);
        io_cqring_add_event(req->ctx, sqe->user_data, ret, 0);
-        io_free_req(req);
+        io_put_req(req);
        return 0;
 }
-static void io_poll_complete(struct io_kiocb *req, __poll_t mask)
+static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req,
+                             __poll_t mask)
 {
-        io_cqring_add_event(req->ctx, req->user_data, mangle_poll(mask), 0);
+        req->poll.done = true;
-        io_fput(req);
+        io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask), 0);
-        io_free_req(req);
+        io_commit_cqring(ctx);
 }
 static void io_poll_complete_work(struct work_struct *work)
@@ -1240,9 +1199,11 @@ static void io_poll_complete_work(struct work_struct *work)
                return;
        }
        list_del_init(&req->list);
+        io_poll_complete(ctx, req, mask);
        spin_unlock_irq(&ctx->completion_lock);
-        io_poll_complete(req, mask);
+        io_cqring_ev_posted(ctx);
+        io_put_req(req);
 }
 static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
@@ -1253,29 +1214,25 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
        struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
        struct io_ring_ctx *ctx = req->ctx;
        __poll_t mask = key_to_poll(key);
+        unsigned long flags;
-        poll->woken = true;
        /* for instances that support it check for an event match first: */
-        if (mask) {
+        if (mask && !(mask & poll->events))
-                unsigned long flags;
+                return 0;
-                if (!(mask & poll->events))
+        list_del_init(&poll->wait.entry);
-                        return 0;
-                /* try to complete the iocb inline if we can: */
+        if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
-                if (spin_trylock_irqsave(&ctx->completion_lock, flags)) {
+                list_del(&req->list);
-                        list_del(&req->list);
+                io_poll_complete(ctx, req, mask);
-                        spin_unlock_irqrestore(&ctx->completion_lock, flags);
+                spin_unlock_irqrestore(&ctx->completion_lock, flags);
-                        list_del_init(&poll->wait.entry);
+                io_cqring_ev_posted(ctx);
-                        io_poll_complete(req, mask);
+                io_put_req(req);
-                        return 1;
+        } else {
-                }
+                queue_work(ctx->sqo_wq, &req->work);
        }
-        list_del_init(&poll->wait.entry);
-        queue_work(ctx->sqo_wq, &req->work);
        return 1;
 }
@@ -1305,36 +1262,23 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
        struct io_poll_iocb *poll = &req->poll;
        struct io_ring_ctx *ctx = req->ctx;
        struct io_poll_table ipt;
-        unsigned flags;
+        bool cancel = false;
        __poll_t mask;
        u16 events;
-        int fd;
        if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
                return -EINVAL;
        if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index)
                return -EINVAL;
+        if (!poll->file)
+                return -EBADF;
        INIT_WORK(&req->work, io_poll_complete_work);
        events = READ_ONCE(sqe->poll_events);
        poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
-        flags = READ_ONCE(sqe->flags);
-        fd = READ_ONCE(sqe->fd);
-        if (flags & IOSQE_FIXED_FILE) {
-                if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files))
-                        return -EBADF;
-                poll->file = ctx->user_files[fd];
-                req->flags |= REQ_F_FIXED_FILE;
-        } else {
-                poll->file = fget(fd);
-        }
-        if (unlikely(!poll->file))
-                return -EBADF;
        poll->head = NULL;
-        poll->woken = false;
+        poll->done = false;
        poll->canceled = false;
        ipt.pt._qproc = io_poll_queue_proc;
@@ -1346,56 +1290,44 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
        INIT_LIST_HEAD(&poll->wait.entry);
        init_waitqueue_func_entry(&poll->wait, io_poll_wake);
-        /* one for removal from waitqueue, one for this function */
-        refcount_set(&req->refs, 2);
        mask = vfs_poll(poll->file, &ipt.pt) & poll->events;
-        if (unlikely(!poll->head)) {
-                /* we did not manage to set up a waitqueue, done */
-                goto out;
-        }
        spin_lock_irq(&ctx->completion_lock);
-        spin_lock(&poll->head->lock);
+        if (likely(poll->head)) {
-        if (poll->woken) {
+                spin_lock(&poll->head->lock);
-                /* wake_up context handles the rest */
+                if (unlikely(list_empty(&poll->wait.entry))) {
-                mask = 0;
+                        if (ipt.error)
+                                cancel = true;
+                        ipt.error = 0;
+                        mask = 0;
+                }
+                if (mask || ipt.error)
+                        list_del_init(&poll->wait.entry);
+                else if (cancel)
+                        WRITE_ONCE(poll->canceled, true);
+                else if (!poll->done) /* actually waiting for an event */
+                        list_add_tail(&req->list, &ctx->cancel_list);
+                spin_unlock(&poll->head->lock);
+        }
+        if (mask) { /* no async, we'd stolen it */
+                req->error = mangle_poll(mask);
                ipt.error = 0;
-        } else if (mask || ipt.error) {
+                io_poll_complete(ctx, req, mask);
-                /* if we get an error or a mask we are done */
-                WARN_ON_ONCE(list_empty(&poll->wait.entry));
-                list_del_init(&poll->wait.entry);
-        } else {
-                /* actually waiting for an event */
-                list_add_tail(&req->list, &ctx->cancel_list);
        }
-        spin_unlock(&poll->head->lock);
        spin_unlock_irq(&ctx->completion_lock);
-out:
+        if (mask) {
-        if (unlikely(ipt.error)) {
+                io_cqring_ev_posted(ctx);
-                if (!(flags & IOSQE_FIXED_FILE))
+                io_put_req(req);
-                        fput(poll->file);
-                /*
-                 * Drop one of our refs to this req, __io_submit_sqe() will
-                 * drop the other one since we're returning an error.
-                 */
-                io_free_req(req);
-                return ipt.error;
        }
+        return ipt.error;
-        if (mask)
-                io_poll_complete(req, mask);
-        io_free_req(req);
-        return 0;
 }
 static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
                           const struct sqe_submit *s, bool force_nonblock,
                           struct io_submit_state *state)
 {
-        ssize_t ret;
+        int ret, opcode;
-        int opcode;
        if (unlikely(s->index >= ctx->sq_entries))
                return -EINVAL;
@@ -1524,10 +1456,13 @@ restart:
                                        break;
                                cond_resched();
                        } while (1);
+                        /* drop submission reference */
+                        io_put_req(req);
                }
                if (ret) {
                        io_cqring_add_event(ctx, sqe->user_data, ret, 0);
-                        io_free_req(req);
+                        io_put_req(req);
                }
                /* async context always use a copy of the sqe */
@@ -1614,11 +1549,55 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req)
        return ret;
 }
+static bool io_op_needs_file(const struct io_uring_sqe *sqe)
+{
+        int op = READ_ONCE(sqe->opcode);
+        switch (op) {
+        case IORING_OP_NOP:
+        case IORING_OP_POLL_REMOVE:
+                return false;
+        default:
+                return true;
+        }
+}
+static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
+                           struct io_submit_state *state, struct io_kiocb *req)
+{
+        unsigned flags;
+        int fd;
+        flags = READ_ONCE(s->sqe->flags);
+        fd = READ_ONCE(s->sqe->fd);
+        if (!io_op_needs_file(s->sqe)) {
+                req->file = NULL;
+                return 0;
+        }
+        if (flags & IOSQE_FIXED_FILE) {
+                if (unlikely(!ctx->user_files ||
+                    (unsigned) fd >= ctx->nr_user_files))
+                        return -EBADF;
+                req->file = ctx->user_files[fd];
+                req->flags |= REQ_F_FIXED_FILE;
+        } else {
+                if (s->needs_fixed_file)
+                        return -EBADF;
+                req->file = io_file_get(state, fd);
+                if (unlikely(!req->file))
+                        return -EBADF;
+        }
+        return 0;
+}
 static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
                         struct io_submit_state *state)
 {
        struct io_kiocb *req;
-        ssize_t ret;
+        int ret;
        /* enforce forwards compatibility on users */
        if (unlikely(s->sqe->flags & ~IOSQE_FIXED_FILE))
@@ -1628,7 +1607,9 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
        if (unlikely(!req))
                return -EAGAIN;
-        req->rw.ki_filp = NULL;
+        ret = io_req_set_file(ctx, s, state, req);
+        if (unlikely(ret))
+                goto out;
        ret = __io_submit_sqe(ctx, req, s, true, state);
        if (ret == -EAGAIN) {
@@ -1649,11 +1630,23 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
                                INIT_WORK(&req->work, io_sq_wq_submit_work);
                                queue_work(ctx->sqo_wq, &req->work);
                        }
-                        ret = 0;
+                        /*
+                         * Queued up for async execution, worker will release
+                         * submit reference when the iocb is actually
+                         * submitted.
+                         */
+                        return 0;
                }
        }
+out:
+        /* drop submission reference */
+        io_put_req(req);
+        /* and drop final reference, if we failed */
        if (ret)
-                io_free_req(req);
+                io_put_req(req);
        return ret;
 }
diff --git a/fs/iomap.c b/fs/iomap.c
index 97cb9d486a7d..abdd18e404f8 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1589,12 +1589,14 @@ static void iomap_dio_bio_end_io(struct bio *bio)
        if (should_dirty) {
                bio_check_pages_dirty(bio);
        } else {
-                struct bio_vec *bvec;
+                if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
-                int i;
+                        struct bvec_iter_all iter_all;
-                struct bvec_iter_all iter_all;
+                        struct bio_vec *bvec;
+                        int i;
-                bio_for_each_segment_all(bvec, bio, i, iter_all)
+                        bio_for_each_segment_all(bvec, bio, i, iter_all)
-                        put_page(bvec->bv_page);
+                                put_page(bvec->bv_page);
+                }
                bio_put(bio);
        }
 }
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 56992b32c6bb..a90bb19dcfa2 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -208,6 +208,7 @@ static int copy_fid_to_user(struct fanotify_event *event, char __user *buf)
 {
        struct fanotify_event_info_fid info = { };
        struct file_handle handle = { };
+        unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh;
        size_t fh_len = event->fh_len;
        size_t len = fanotify_event_info_len(event);
@@ -233,7 +234,16 @@ static int copy_fid_to_user(struct fanotify_event *event, char __user *buf)
        buf += sizeof(handle);
        len -= sizeof(handle);
-        if (copy_to_user(buf, fanotify_event_fh(event), fh_len))
+        /*
+         * For an inline fh, copy through stack to exclude the copy from
+         * usercopy hardening protections.
+         */
+        fh = fanotify_event_fh(event);
+        if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
+                memcpy(bounce, fh, fh_len);
+                fh = bounce;
+        }
+        if (copy_to_user(buf, fh, fh_len))
                return -EFAULT;
        /* Pad with 0's */
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e2901fbb9f76..7b53598c8804 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -519,8 +519,10 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
        fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
        if (!fsn_mark)
                return -ENOENT;
-        else if (create)
+        else if (create) {
-                return -EEXIST;
+                ret = -EEXIST;
+                goto out;
+        }
        i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
@@ -548,6 +550,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
        /* return the wd */
        ret = i_mark->wd;
+out:
        /* match the get from fsnotify_find_mark() */
        fsnotify_put_mark(fsn_mark);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index bbcc185062bb..d29d869abec1 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -54,6 +54,28 @@ static LIST_HEAD(kclist_head);
 static DECLARE_RWSEM(kclist_lock);
 static int kcore_need_update = 1;
+/*
+ * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
+ * Same as oldmem_pfn_is_ram in vmcore
+ */
+static int (*mem_pfn_is_ram)(unsigned long pfn);
+int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn))
+{
+        if (mem_pfn_is_ram)
+                return -EBUSY;
+        mem_pfn_is_ram = fn;
+        return 0;
+}
+static int pfn_is_ram(unsigned long pfn)
+{
+        if (mem_pfn_is_ram)
+                return mem_pfn_is_ram(pfn);
+        else
+                return 1;
+}
 /* This doesn't grab kclist_lock, so it should only be used at init time. */
 void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
                       int type)
@@ -465,6 +487,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
                                goto out;
                        }
                        m = NULL;       /* skip the list anchor */
+                } else if (!pfn_is_ram(__pa(start) >> PAGE_SHIFT)) {
+                        if (clear_user(buffer, tsz)) {
+                                ret = -EFAULT;
+                                goto out;
+                        }
                } else if (m->type == KCORE_VMALLOC) {
                        vread(buf, (char *)start, tsz);
                        /* we have to zero-fill user buffer even if no read */
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index ae796e10f68b..e7276932e433 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1242,8 +1242,10 @@ set_size:
                truncate_setsize(inode, newsize);
                down_write(&iinfo->i_data_sem);
                udf_clear_extent_cache(inode);
-                udf_truncate_extents(inode);
+                err = udf_truncate_extents(inode);
                up_write(&iinfo->i_data_sem);
+                if (err)
+                        return err;
        }
 update_time:
        inode->i_mtime = inode->i_ctime = current_time(inode);
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index b647f0bd150c..63a47f1e1d52 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -199,7 +199,7 @@ static void udf_update_alloc_ext_desc(struct inode *inode,
 * for making file shorter. For making file longer, udf_extend_file() has to
 * be used.
 */
-void udf_truncate_extents(struct inode *inode)
+int udf_truncate_extents(struct inode *inode)
 {
        struct extent_position epos;
        struct kernel_lb_addr eloc, neloc = {};
@@ -224,7 +224,7 @@ void udf_truncate_extents(struct inode *inode)
        if (etype == -1) {
                /* We should extend the file? */
                WARN_ON(byte_offset);
-                return;
+                return 0;
        }
        epos.offset -= adsize;
        extent_trunc(inode, &epos, &eloc, etype, elen, byte_offset);
@@ -260,6 +260,9 @@ void udf_truncate_extents(struct inode *inode)
                        epos.block = eloc;
                        epos.bh = udf_tread(sb,
                                        udf_get_lb_pblock(sb, &eloc, 0));
+                        /* Error reading indirect block? */
+                        if (!epos.bh)
+                                return -EIO;
                        if (elen)
                                indirect_ext_len =
                                        (elen + sb->s_blocksize - 1) >>
@@ -283,4 +286,5 @@ void udf_truncate_extents(struct inode *inode)
        iinfo->i_lenExtents = inode->i_size;
        brelse(epos.bh);
+        return 0;
 }
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index ee246769dee4..d89ef71887fc 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -235,7 +235,7 @@ extern struct inode *udf_new_inode(struct inode *, umode_t);
 /* truncate.c */
 extern void udf_truncate_tail_extent(struct inode *);
 extern void udf_discard_prealloc(struct inode *);
-extern void udf_truncate_extents(struct inode *);
+extern int udf_truncate_extents(struct inode *);
 /* balloc.c */
 extern void udf_free_blocks(struct super_block *, struct inode *,
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b0c814bcc7e3..cb2aa7ecafff 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -57,7 +57,6 @@ struct blk_mq_hw_ctx {
        unsigned int            queue_num;
        atomic_t                nr_active;
-        unsigned int            nr_expired;
        struct hlist_node       cpuhp_dead;
        struct kobject          kobj;
@@ -300,8 +299,6 @@ void blk_mq_end_request(struct request *rq, blk_status_t error);
 void __blk_mq_end_request(struct request *rq, blk_status_t error);
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
-void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
-                                bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 bool blk_mq_complete_request(struct request *rq);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d66bf5f32610..791fee35df88 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -215,6 +215,7 @@ struct bio {
 /*
 * bio flags
 */
+#define BIO_NO_PAGE_REF 0       /* don't put release vec pages */
 #define BIO_SEG_VALID   1       /* bi_phys_segments valid */
 #define BIO_CLONED      2       /* doesn't own data */
 #define BIO_BOUNCED     3       /* bio is a bounce bio */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0de92b29f589..5c58a3b2bf00 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -50,6 +50,9 @@ struct blk_stat_callback;
 /* Must be consistent with blk_mq_poll_stats_bkt() */
 #define BLK_MQ_POLL_STATS_BKTS 16
+/* Doing classic polling */
+#define BLK_MQ_POLL_CLASSIC -1
 /*
 * Maximum number of blkcg policies allowed to be registered concurrently.
 * Defined here to simplify include dependency.
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index a420c07904bc..337d5049ff93 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -294,6 +294,8 @@ extern void ceph_destroy_client(struct ceph_client *client);
 extern int __ceph_open_session(struct ceph_client *client,
                               unsigned long started);
 extern int ceph_open_session(struct ceph_client *client);
+int ceph_wait_for_latest_osdmap(struct ceph_client *client,
+                                unsigned long timeout);
 /* pagevec.c */
 extern void ceph_release_page_vector(struct page **pages, int num_pages);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index d6160d479b14..7ae8de5ad0f2 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -195,7 +195,7 @@ struct irq_data {
 * IRQD_LEVEL                   - Interrupt is level triggered
 * IRQD_WAKEUP_STATE            - Interrupt is configured for wakeup
 *                                from suspend
- * IRDQ_MOVE_PCNTXT             - Interrupt can be moved in process
+ * IRQD_MOVE_PCNTXT             - Interrupt can be moved in process
 *                                context
 * IRQD_IRQ_DISABLED            - Disabled state of the interrupt
 * IRQD_IRQ_MASKED              - Masked state of the interrupt
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 626179077bb0..0f049b384ccd 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -158,8 +158,7 @@ int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq);
 * Legacy platforms not converted to DT yet must use this to init
 * their GIC
 */
-void gic_init(unsigned int nr, int start,
+void gic_init(void __iomem *dist , void __iomem *cpu);
-              void __iomem *dist , void __iomem *cpu);
 int gicv2m_init(struct fwnode_handle *parent_handle,
                struct irq_domain *parent);
diff --git a/include/linux/kcore.h b/include/linux/kcore.h
index 8c3f8c14eeaa..c843f4a9c512 100644
--- a/include/linux/kcore.h
+++ b/include/linux/kcore.h
@@ -44,6 +44,8 @@ void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
        m->vaddr = (unsigned long)vaddr;
        kclist_add(m, addr, sz, KCORE_REMAP);
 }
+extern int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn));
 #else
 static inline
 void kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index b26ea9077384..0343c81d4c5f 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -557,7 +557,8 @@ static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev,
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
                         struct mlx5_core_dct *qp,
-                         u32 *in, int inlen);
+                         u32 *in, int inlen,
+                         u32 *out, int outlen);
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
                        struct mlx5_core_qp *qp,
                        u32 *in,
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 14d558146aea..20f3e3f029b9 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -330,7 +330,7 @@ static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr)
 /*
 * This one is special, since it doesn't actually clear the bit, rather it
 * sets the corresponding bit in the ->cleared mask instead. Paired with
- * the caller doing sbitmap_batch_clear() if a given index is full, which
+ * the caller doing sbitmap_deferred_clear() if a given index is full, which
 * will clear the previously freed entries in the corresponding ->word.
 */
 static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr)
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 87477e1640f9..f184af1999a8 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -23,14 +23,23 @@ struct kvec {
 };
 enum iter_type {
-        ITER_IOVEC = 0,
+        /* set if ITER_BVEC doesn't hold a bv_page ref */
-        ITER_KVEC = 2,
+        ITER_BVEC_FLAG_NO_REF = 2,
-        ITER_BVEC = 4,
-        ITER_PIPE = 8,
+        /* iter types */
-        ITER_DISCARD = 16,
+        ITER_IOVEC = 4,
+        ITER_KVEC = 8,
+        ITER_BVEC = 16,
+        ITER_PIPE = 32,
+        ITER_DISCARD = 64,
 };
 struct iov_iter {
+        /*
+         * Bit 0 is the read/write bit, set if we're writing.
+         * Bit 1 is the BVEC_FLAG_NO_REF bit, set if type is a bvec and
+         * the caller isn't expecting to drop a page reference when done.
+         */
        unsigned int type;
        size_t iov_offset;
        size_t count;
@@ -84,6 +93,11 @@ static inline unsigned char iov_iter_rw(const struct iov_iter *i)
        return i->type & (READ | WRITE);
 }
+static inline bool iov_iter_bvec_no_ref(const struct iov_iter *i)
+{
+        return (i->type & ITER_BVEC_FLAG_NO_REF) != 0;
+}
 /*
 * Total number of bytes covered by an iovec.
 *
diff --git a/include/misc/charlcd.h b/include/misc/charlcd.h
index 23f61850f363..1832402324ce 100644
--- a/include/misc/charlcd.h
+++ b/include/misc/charlcd.h
@@ -35,6 +35,7 @@ struct charlcd_ops {
 };
 struct charlcd *charlcd_alloc(unsigned int drvdata_size);
+void charlcd_free(struct charlcd *lcd);
 int charlcd_register(struct charlcd *lcd);
 int charlcd_unregister(struct charlcd *lcd);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1032a16bd186..72d06e302e99 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7189,6 +7189,7 @@ static void perf_event_mmap_output(struct perf_event *event,
        struct perf_output_handle handle;
        struct perf_sample_data sample;
        int size = mmap_event->event_id.header.size;
+        u32 type = mmap_event->event_id.header.type;
        int ret;
        if (!perf_event_mmap_match(event, data))
@@ -7232,6 +7233,7 @@ static void perf_event_mmap_output(struct perf_event *event,
        perf_output_end(&handle);
 out:
        mmap_event->event_id.header.size = size;
+        mmap_event->event_id.header.type = type;
 }
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
diff --git a/kernel/futex.c b/kernel/futex.c
index c3b73b0311bc..9e40cf7be606 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3436,6 +3436,10 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int p
 {
        u32 uval, uninitialized_var(nval), mval;
+        /* Futex address must be 32bit aligned */
+        if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
+                return -1;
 retry:
        if (get_user(uval, uaddr))
                return -1;
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 5d5378ea0afe..f808c6a97dcc 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -84,8 +84,6 @@ EXPORT_SYMBOL(devm_request_threaded_irq);
 *      @dev: device to request interrupt for
 *      @irq: Interrupt line to allocate
 *      @handler: Function to be called when the IRQ occurs
- *      @thread_fn: function to be called in a threaded interrupt context. NULL
- *                  for devices which handle everything in @handler
 *      @irqflags: Interrupt type flags
 *      @devname: An ascii name for the claiming device, dev_name(dev) if NULL
 *      @dev_id: A cookie passed back to the handler function
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9ec34a2a6638..1401afa0d58a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -196,6 +196,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
        case IRQ_SET_MASK_OK:
        case IRQ_SET_MASK_OK_DONE:
                cpumask_copy(desc->irq_common_data.affinity, mask);
+                /* fall through */
        case IRQ_SET_MASK_OK_NOCOPY:
                irq_validate_effective_affinity(data);
                irq_set_thread_affinity(desc);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ead464a0f2e5..4778c48a7fda 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6998,7 +6998,7 @@ static int __maybe_unused cpu_period_quota_parse(char *buf,
 {
        char tok[21];   /* U64_MAX */
-        if (!sscanf(buf, "%s %llu", tok, periodp))
+        if (sscanf(buf, "%20s %llu", tok, periodp) < 1)
                return -EINVAL;
        *periodp *= NSEC_PER_USEC;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 2efe629425be..5c41ea367422 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -48,10 +48,10 @@ struct sugov_cpu {
        bool                    iowait_boost_pending;
        unsigned int            iowait_boost;
-        unsigned int            iowait_boost_max;
        u64                     last_update;
        unsigned long           bw_dl;
+        unsigned long           min;
        unsigned long           max;
        /* The field below is for single-CPU policies only: */
@@ -303,8 +303,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
        if (delta_ns <= TICK_NSEC)
                return false;
-        sg_cpu->iowait_boost = set_iowait_boost
+        sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
-                ? sg_cpu->sg_policy->policy->min : 0;
        sg_cpu->iowait_boost_pending = set_iowait_boost;
        return true;
@@ -344,14 +343,13 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
        /* Double the boost at each request */
        if (sg_cpu->iowait_boost) {
-                sg_cpu->iowait_boost <<= 1;
+                sg_cpu->iowait_boost =
-                if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
+                        min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE);
-                        sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
                return;
        }
        /* First wakeup after IO: start with minimum boost */
-        sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+        sg_cpu->iowait_boost = sg_cpu->min;
 }
 /**
@@ -373,47 +371,38 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
 * This mechanism is designed to boost high frequently IO waiting tasks, while
 * being more conservative on tasks which does sporadic IO operations.
 */
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
-                               unsigned long *util, unsigned long *max)
+                                        unsigned long util, unsigned long max)
 {
-        unsigned int boost_util, boost_max;
+        unsigned long boost;
        /* No boost currently required */
        if (!sg_cpu->iowait_boost)
-                return;
+                return util;
        /* Reset boost if the CPU appears to have been idle enough */
        if (sugov_iowait_reset(sg_cpu, time, false))
-                return;
+                return util;
-        /*
+        if (!sg_cpu->iowait_boost_pending) {
-         * An IO waiting task has just woken up:
-         * allow to further double the boost value
-         */
-        if (sg_cpu->iowait_boost_pending) {
-                sg_cpu->iowait_boost_pending = false;
-        } else {
                /*
-                 * Otherwise: reduce the boost value and disable it when we
+                 * No boost pending; reduce the boost value.
-                 * reach the minimum.
                 */
                sg_cpu->iowait_boost >>= 1;
-                if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
+                if (sg_cpu->iowait_boost < sg_cpu->min) {
                        sg_cpu->iowait_boost = 0;
-                        return;
+                        return util;
                }
        }
+        sg_cpu->iowait_boost_pending = false;
        /*
-         * Apply the current boost value: a CPU is boosted only if its current
+         * @util is already in capacity scale; convert iowait_boost
-         * utilization is smaller then the current IO boost level.
+         * into the same scale so we can compare.
         */
-        boost_util = sg_cpu->iowait_boost;
+        boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT;
-        boost_max = sg_cpu->iowait_boost_max;
+        return max(boost, util);
-        if (*util * boost_max < *max * boost_util) {
-                *util = boost_util;
-                *max = boost_max;
-        }
 }
 #ifdef CONFIG_NO_HZ_COMMON
@@ -460,7 +449,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
        util = sugov_get_util(sg_cpu);
        max = sg_cpu->max;
-        sugov_iowait_apply(sg_cpu, time, &util, &max);
+        util = sugov_iowait_apply(sg_cpu, time, util, max);
        next_f = get_next_freq(sg_policy, util, max);
        /*
         * Do not reduce the frequency if the CPU has not been idle
@@ -500,7 +489,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
                j_util = sugov_get_util(j_sg_cpu);
                j_max = j_sg_cpu->max;
-                sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
+                j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);
                if (j_util * max > j_max * util) {
                        util = j_util;
@@ -837,7 +826,9 @@ static int sugov_start(struct cpufreq_policy *policy)
                memset(sg_cpu, 0, sizeof(*sg_cpu));
                sg_cpu->cpu                     = cpu;
                sg_cpu->sg_policy               = sg_policy;
-                sg_cpu->iowait_boost_max        = policy->cpuinfo.max_freq;
+                sg_cpu->min                     =
+                        (SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
+                        policy->cpuinfo.max_freq;
        }
        for_each_cpu(cpu, policy->cpus) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ea74d43924b2..fdab7eb6f351 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8060,6 +8060,18 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 }
 /*
+ * Check whether a rq has a misfit task and if it looks like we can actually
+ * help that task: we can migrate the task to a CPU of higher capacity, or
+ * the task's current CPU is heavily pressured.
+ */
+static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
+{
+        return rq->misfit_task_load &&
+                (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+                 check_cpu_capacity(rq, sd));
+}
+/*
 * Group imbalance indicates (and tries to solve) the problem where balancing
 * groups is inadequate due to ->cpus_allowed constraints.
 *
@@ -9586,35 +9598,21 @@ static void nohz_balancer_kick(struct rq *rq)
        if (time_before(now, nohz.next_balance))
                goto out;
-        if (rq->nr_running >= 2 || rq->misfit_task_load) {
+        if (rq->nr_running >= 2) {
                flags = NOHZ_KICK_MASK;
                goto out;
        }
        rcu_read_lock();
-        sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
-        if (sds) {
-                /*
-                 * If there is an imbalance between LLC domains (IOW we could
-                 * increase the overall cache use), we need some less-loaded LLC
-                 * domain to pull some load. Likewise, we may need to spread
-                 * load within the current LLC domain (e.g. packed SMT cores but
-                 * other CPUs are idle). We can't really know from here how busy
-                 * the others are - so just get a nohz balance going if it looks
-                 * like this LLC domain has tasks we could move.
-                 */
-                nr_busy = atomic_read(&sds->nr_busy_cpus);
-                if (nr_busy > 1) {
-                        flags = NOHZ_KICK_MASK;
-                        goto unlock;
-                }
-        }
        sd = rcu_dereference(rq->sd);
        if (sd) {
-                if ((rq->cfs.h_nr_running >= 1) &&
+                /*
-                    check_cpu_capacity(rq, sd)) {
+                 * If there's a CFS task and the current CPU has reduced
+                 * capacity; kick the ILB to see if there's a better CPU to run
+                 * on.
+                 */
+                if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) {
                        flags = NOHZ_KICK_MASK;
                        goto unlock;
                }
@@ -9622,6 +9620,11 @@ static void nohz_balancer_kick(struct rq *rq)
        sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
        if (sd) {
+                /*
+                 * When ASYM_PACKING; see if there's a more preferred CPU
+                 * currently idle; in which case, kick the ILB to move tasks
+                 * around.
+                 */
                for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
                        if (sched_asym_prefer(i, cpu)) {
                                flags = NOHZ_KICK_MASK;
@@ -9629,6 +9632,45 @@ static void nohz_balancer_kick(struct rq *rq)
                        }
                }
        }
+        sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu));
+        if (sd) {
+                /*
+                 * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU
+                 * to run the misfit task on.
+                 */
+                if (check_misfit_status(rq, sd)) {
+                        flags = NOHZ_KICK_MASK;
+                        goto unlock;
+                }
+                /*
+                 * For asymmetric systems, we do not want to nicely balance
+                 * cache use, instead we want to embrace asymmetry and only
+                 * ensure tasks have enough CPU capacity.
+                 *
+                 * Skip the LLC logic because it's not relevant in that case.
+                 */
+                goto unlock;
+        }
+        sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
+        if (sds) {
+                /*
+                 * If there is an imbalance between LLC domains (IOW we could
+                 * increase the overall cache use), we need some less-loaded LLC
+                 * domain to pull some load. Likewise, we may need to spread
+                 * load within the current LLC domain (e.g. packed SMT cores but
+                 * other CPUs are idle). We can't really know from here how busy
+                 * the others are - so just get a nohz balance going if it looks
+                 * like this LLC domain has tasks we could move.
+                 */
+                nr_busy = atomic_read(&sds->nr_busy_cpus);
+                if (nr_busy > 1) {
+                        flags = NOHZ_KICK_MASK;
+                        goto unlock;
+                }
+        }
 unlock:
        rcu_read_unlock();
 out:
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index dc1b6f1929f9..ac9c03dd6c7d 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -89,7 +89,7 @@ struct clocksource * __init __weak clocksource_default_clock(void)
        return &clocksource_jiffies;
 }
-struct clocksource refined_jiffies;
+static struct clocksource refined_jiffies;
 int register_refined_jiffies(long cycles_per_second)
 {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 8fbfda94a67b..403c9bd90413 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -42,9 +42,9 @@ int __read_mostly watchdog_user_enabled = 1;
 int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
 int __read_mostly soft_watchdog_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
-int __read_mostly nmi_watchdog_available;
+static int __read_mostly nmi_watchdog_available;
-struct cpumask watchdog_allowed_mask __read_mostly;
+static struct cpumask watchdog_allowed_mask __read_mostly;
 struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4026d1871407..ddee541ea97a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4266,7 +4266,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
        INIT_LIST_HEAD(&wq->list);
        if (alloc_and_link_pwqs(wq) < 0)
-                goto err_free_wq;
+                goto err_unreg_lockdep;
        if (wq_online && init_rescuer(wq) < 0)
                goto err_destroy;
@@ -4292,9 +4292,10 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
        return wq;
-err_free_wq:
+err_unreg_lockdep:
        wq_unregister_lockdep(wq);
        wq_free_lockdep(wq);
+err_free_wq:
        free_workqueue_attrs(wq->unbound_attrs);
        kfree(wq);
        return NULL;
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 9cab80207ced..79eac465ec65 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -738,7 +738,6 @@ int __ceph_open_session(struct ceph_client *client, unsigned long started)
 }
 EXPORT_SYMBOL(__ceph_open_session);
 int ceph_open_session(struct ceph_client *client)
 {
        int ret;
@@ -754,6 +753,23 @@ int ceph_open_session(struct ceph_client *client)
 }
 EXPORT_SYMBOL(ceph_open_session);
+int ceph_wait_for_latest_osdmap(struct ceph_client *client,
+                                unsigned long timeout)
+{
+        u64 newest_epoch;
+        int ret;
+        ret = ceph_monc_get_version(&client->monc, "osdmap", &newest_epoch);
+        if (ret)
+                return ret;
+        if (client->osdc.osdmap->epoch >= newest_epoch)
+                return 0;
+        ceph_osdc_maybe_request_map(&client->osdc);
+        return ceph_monc_wait_osdmap(&client->monc, newest_epoch, timeout);
+}
+EXPORT_SYMBOL(ceph_wait_for_latest_osdmap);
 static int __init init_ceph_lib(void)
 {
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 18deb3d889c4..a53e4fbb6319 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -922,6 +922,15 @@ int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
        mutex_unlock(&monc->mutex);
        ret = wait_generic_request(req);
+        if (!ret)
+                /*
+                 * Make sure we have the osdmap that includes the blacklist
+                 * entry.  This is needed to ensure that the OSDs pick up the
+                 * new blacklist before processing any future requests from
+                 * this client.
+                 */
+                ret = ceph_wait_for_latest_osdmap(monc->client, 0);
 out:
        put_generic_request(req);
        return ret;
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 6b576e588725..daecdfb15a9c 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -828,9 +828,11 @@ void policydb_destroy(struct policydb *p)
        hashtab_map(p->range_tr, range_tr_destroy, NULL);
        hashtab_destroy(p->range_tr);
-        for (i = 0; i < p->p_types.nprim; i++)
+        if (p->type_attr_map_array) {
-                ebitmap_destroy(&p->type_attr_map_array[i]);
+                for (i = 0; i < p->p_types.nprim; i++)
-        kvfree(p->type_attr_map_array);
+                        ebitmap_destroy(&p->type_attr_map_array[i]);
+                kvfree(p->type_attr_map_array);
+        }
        ebitmap_destroy(&p->filename_trans_ttypes);
        ebitmap_destroy(&p->policycaps);
@@ -2496,10 +2498,13 @@ int policydb_read(struct policydb *p, void *fp)
        if (!p->type_attr_map_array)
                goto bad;
+        /* just in case ebitmap_init() becomes more than just a memset(0): */
+        for (i = 0; i < p->p_types.nprim; i++)
+                ebitmap_init(&p->type_attr_map_array[i]);
        for (i = 0; i < p->p_types.nprim; i++) {
                struct ebitmap *e = &p->type_attr_map_array[i];
-                ebitmap_init(e);
                if (p->policyvers >= POLICYDB_VERSION_AVTAB) {
                        rc = ebitmap_read(e, fp);
                        if (rc)
diff --git a/sound/drivers/opl3/opl3_voice.h b/sound/drivers/opl3/opl3_voice.h
index 5b02bd49fde4..4e4ecc21760b 100644
--- a/sound/drivers/opl3/opl3_voice.h
+++ b/sound/drivers/opl3/opl3_voice.h
@@ -41,7 +41,7 @@ void snd_opl3_timer_func(struct timer_list *t);
 /* Prototypes for opl3_drums.c */
 void snd_opl3_load_drums(struct snd_opl3 *opl3);
-void snd_opl3_drum_switch(struct snd_opl3 *opl3, int note, int on_off, int vel, struct snd_midi_channel *chan);
+void snd_opl3_drum_switch(struct snd_opl3 *opl3, int note, int vel, int on_off, struct snd_midi_channel *chan);
 /* Prototypes for opl3_oss.c */
 #if IS_ENABLED(CONFIG_SND_SEQUENCER_OSS)
diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c
index 220e61926ea4..513291ba0ab0 100644
--- a/sound/firewire/motu/motu.c
+++ b/sound/firewire/motu/motu.c
@@ -36,7 +36,7 @@ static void name_card(struct snd_motu *motu)
        fw_csr_iterator_init(&it, motu->unit->directory);
        while (fw_csr_iterator_next(&it, &key, &val)) {
                switch (key) {
-                case CSR_VERSION:
+                case CSR_MODEL:
                        version = val;
                        break;
                }
@@ -46,7 +46,7 @@ static void name_card(struct snd_motu *motu)
        strcpy(motu->card->shortname, motu->spec->name);
        strcpy(motu->card->mixername, motu->spec->name);
        snprintf(motu->card->longname, sizeof(motu->card->longname),
-                 "MOTU %s (version:%d), GUID %08x%08x at %s, S%d",
+                 "MOTU %s (version:%06x), GUID %08x%08x at %s, S%d",
                 motu->spec->name, version,
                 fw_dev->config_rom[3], fw_dev->config_rom[4],
                 dev_name(&motu->unit->device), 100 << fw_dev->max_speed);
@@ -237,20 +237,20 @@ static const struct snd_motu_spec motu_audio_express = {
 #define SND_MOTU_DEV_ENTRY(model, data)                 \
 {                                                       \
        .match_flags    = IEEE1394_MATCH_VENDOR_ID |    \
-                          IEEE1394_MATCH_MODEL_ID |     \
+                          IEEE1394_MATCH_SPECIFIER_ID | \
-                          IEEE1394_MATCH_SPECIFIER_ID,  \
+                          IEEE1394_MATCH_VERSION,       \
        .vendor_id      = OUI_MOTU,                     \
-        .model_id       = model,                        \
        .specifier_id   = OUI_MOTU,                     \
+        .version        = model,                        \
        .driver_data    = (kernel_ulong_t)data,         \
 }
 static const struct ieee1394_device_id motu_id_table[] = {
-        SND_MOTU_DEV_ENTRY(0x101800, &motu_828mk2),
+        SND_MOTU_DEV_ENTRY(0x000003, &motu_828mk2),
-        SND_MOTU_DEV_ENTRY(0x107800, &snd_motu_spec_traveler),
+        SND_MOTU_DEV_ENTRY(0x000009, &snd_motu_spec_traveler),
-        SND_MOTU_DEV_ENTRY(0x106800, &motu_828mk3),     /* FireWire only. */
+        SND_MOTU_DEV_ENTRY(0x000015, &motu_828mk3),     /* FireWire only. */
-        SND_MOTU_DEV_ENTRY(0x100800, &motu_828mk3),     /* Hybrid. */
+        SND_MOTU_DEV_ENTRY(0x000035, &motu_828mk3),     /* Hybrid. */
-        SND_MOTU_DEV_ENTRY(0x104800, &motu_audio_express),
+        SND_MOTU_DEV_ENTRY(0x000033, &motu_audio_express),
        { }
 };
 MODULE_DEVICE_TABLE(ieee1394, motu_id_table);
diff --git a/sound/isa/sb/sb8.c b/sound/isa/sb/sb8.c
index aa2a83eb81a9..dc27a480c2d9 100644
--- a/sound/isa/sb/sb8.c
+++ b/sound/isa/sb/sb8.c
@@ -111,6 +111,10 @@ static int snd_sb8_probe(struct device *pdev, unsigned int dev)
        /* block the 0x388 port to avoid PnP conflicts */
        acard->fm_res = request_region(0x388, 4, "SoundBlaster FM");
+        if (!acard->fm_res) {
+                err = -EBUSY;
+                goto _err;
+        }
        if (port[dev] != SNDRV_AUTO_PORT) {
                if ((err = snd_sbdsp_create(card, port[dev], irq[dev],
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index ea876b0b02b9..dc0084dc8550 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -1952,6 +1952,11 @@ static int snd_echo_create(struct snd_card *card,
        }
        chip->dsp_registers = (volatile u32 __iomem *)
                ioremap_nocache(chip->dsp_registers_phys, sz);
+        if (!chip->dsp_registers) {
+                dev_err(chip->card->dev, "ioremap failed\n");
+                snd_echo_free(chip);
+                return -ENOMEM;
+        }
        if (request_irq(pci->irq, snd_echo_interrupt, IRQF_SHARED,
                        KBUILD_MODNAME, chip)) {
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 5f2005098a60..ec0b8595eb4d 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2939,6 +2939,20 @@ static int hda_codec_runtime_resume(struct device *dev)
 #endif /* CONFIG_PM */
 #ifdef CONFIG_PM_SLEEP
+static int hda_codec_force_resume(struct device *dev)
+{
+        int ret;
+        /* The get/put pair below enforces the runtime resume even if the
+         * device hasn't been used at suspend time.  This trick is needed to
+         * update the jack state change during the sleep.
+         */
+        pm_runtime_get_noresume(dev);
+        ret = pm_runtime_force_resume(dev);
+        pm_runtime_put(dev);
+        return ret;
+}
 static int hda_codec_pm_suspend(struct device *dev)
 {
        dev->power.power_state = PMSG_SUSPEND;
@@ -2948,7 +2962,7 @@ static int hda_codec_pm_suspend(struct device *dev)
 static int hda_codec_pm_resume(struct device *dev)
 {
        dev->power.power_state = PMSG_RESUME;
-        return pm_runtime_force_resume(dev);
+        return hda_codec_force_resume(dev);
 }
 static int hda_codec_pm_freeze(struct device *dev)
@@ -2960,13 +2974,13 @@ static int hda_codec_pm_freeze(struct device *dev)
 static int hda_codec_pm_thaw(struct device *dev)
 {
        dev->power.power_state = PMSG_THAW;
-        return pm_runtime_force_resume(dev);
+        return hda_codec_force_resume(dev);
 }
 static int hda_codec_pm_restore(struct device *dev)
 {
        dev->power.power_state = PMSG_RESTORE;
-        return pm_runtime_force_resume(dev);
+        return hda_codec_force_resume(dev);
 }
 #endif /* CONFIG_PM_SLEEP */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e5c49003e75f..ece256a3b48f 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -947,7 +947,7 @@ static void __azx_runtime_suspend(struct azx *chip)
        display_power(chip, false);
 }
-static void __azx_runtime_resume(struct azx *chip)
+static void __azx_runtime_resume(struct azx *chip, bool from_rt)
 {
        struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
        struct hdac_bus *bus = azx_bus(chip);
@@ -964,7 +964,7 @@ static void __azx_runtime_resume(struct azx *chip)
        azx_init_pci(chip);
        hda_intel_init_chip(chip, true);
-        if (status) {
+        if (status && from_rt) {
                list_for_each_codec(codec, &chip->bus)
                        if (status & (1 << codec->addr))
                                schedule_delayed_work(&codec->jackpoll_work,
@@ -1016,7 +1016,7 @@ static int azx_resume(struct device *dev)
                        chip->msi = 0;
        if (azx_acquire_irq(chip, 1) < 0)
                return -EIO;
-        __azx_runtime_resume(chip);
+        __azx_runtime_resume(chip, false);
        snd_power_change_state(card, SNDRV_CTL_POWER_D0);
        trace_azx_resume(chip);
@@ -1081,7 +1081,7 @@ static int azx_runtime_resume(struct device *dev)
        chip = card->private_data;
        if (!azx_has_pm_runtime(chip))
                return 0;
-        __azx_runtime_resume(chip);
+        __azx_runtime_resume(chip, true);
        /* disable controller Wake Up event*/
        azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
@@ -2144,10 +2144,12 @@ static struct snd_pci_quirk power_save_blacklist[] = {
        SND_PCI_QUIRK(0x8086, 0x2057, "Intel NUC5i7RYB", 0),
        /* https://bugzilla.redhat.com/show_bug.cgi?id=1520902 */
        SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0),
-        /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
-        SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
        /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
        SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0),
+        /* https://bugzilla.redhat.com/show_bug.cgi?id=1689623 */
+        SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0),
+        /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
+        SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
        {}
 };
 #endif /* CONFIG_PM */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 384719d5c44e..191830d4fa40 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5687,6 +5687,7 @@ enum {
        ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE,
        ALC225_FIXUP_WYSE_AUTO_MUTE,
        ALC225_FIXUP_WYSE_DISABLE_MIC_VREF,
+        ALC286_FIXUP_ACER_AIO_HEADSET_MIC,
 };
 static const struct hda_fixup alc269_fixups[] = {
@@ -6685,6 +6686,16 @@ static const struct hda_fixup alc269_fixups[] = {
                .chained = true,
                .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
        },
+        [ALC286_FIXUP_ACER_AIO_HEADSET_MIC] = {
+                .type = HDA_FIXUP_VERBS,
+                .v.verbs = (const struct hda_verb[]) {
+                        { 0x20, AC_VERB_SET_COEF_INDEX, 0x4f },
+                        { 0x20, AC_VERB_SET_PROC_COEF, 0x5029 },
+                        { }
+                },
+                .chained = true,
+                .chain_id = ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE
+        },
 };
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -6701,9 +6712,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
        SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
        SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
        SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
-        SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
+        SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
-        SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
+        SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
-        SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
+        SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
        SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC),
        SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
        SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index dae1584cf017..4703d218663a 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -17,5 +17,7 @@
 #define __ARCH_WANT_RENAMEAT
 #define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_TIME32_SYSCALLS
 #include <asm-generic/unistd.h>
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 8ef80d65a474..d2be5a06c339 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -401,41 +401,31 @@ static int do_show(int argc, char **argv)
 static int do_dump(int argc, char **argv)
 {
-        unsigned int finfo_rec_size, linfo_rec_size, jited_linfo_rec_size;
+        struct bpf_prog_info_linear *info_linear;
-        void *func_info = NULL, *linfo = NULL, *jited_linfo = NULL;
-        unsigned int nr_finfo, nr_linfo = 0, nr_jited_linfo = 0;
        struct bpf_prog_linfo *prog_linfo = NULL;
-        unsigned long *func_ksyms = NULL;
+        enum {DUMP_JITED, DUMP_XLATED} mode;
-        struct bpf_prog_info info = {};
-        unsigned int *func_lens = NULL;
        const char *disasm_opt = NULL;
-        unsigned int nr_func_ksyms;
+        struct bpf_prog_info *info;
-        unsigned int nr_func_lens;
        struct dump_data dd = {};
-        __u32 len = sizeof(info);
+        void *func_info = NULL;
        struct btf *btf = NULL;
-        unsigned int buf_size;
        char *filepath = NULL;
        bool opcodes = false;
        bool visual = false;
        char func_sig[1024];
        unsigned char *buf;
        bool linum = false;
-        __u32 *member_len;
+        __u32 member_len;
-        __u64 *member_ptr;
+        __u64 arrays;
        ssize_t n;
-        int err;
        int fd;
        if (is_prefix(*argv, "jited")) {
                if (disasm_init())
                        return -1;
+                mode = DUMP_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;
+                mode = DUMP_XLATED;
-                member_ptr = &info.xlated_prog_insns;
        } else {
                p_err("expected 'xlated' or 'jited', got: %s", *argv);
                return -1;
@@ -474,175 +464,50 @@ static int do_dump(int argc, char **argv)
                return -1;
        }
-        err = bpf_obj_get_info_by_fd(fd, &info, &len);
+        if (mode == DUMP_JITED)
-        if (err) {
+                arrays = 1UL << BPF_PROG_INFO_JITED_INSNS;
-                p_err("can't get prog info: %s", strerror(errno));
+        else
-                return -1;
+                arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS;
-        }
-        if (!*member_len) {
-                p_info("no instructions returned");
-                close(fd);
-                return 0;
-        }
-        buf_size = *member_len;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+        arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+        arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
-        buf = malloc(buf_size);
+        info_linear = bpf_program__get_prog_info_linear(fd, arrays);
-        if (!buf) {
+        close(fd);
-                p_err("mem alloc failed");
+        if (IS_ERR_OR_NULL(info_linear)) {
-                close(fd);
+                p_err("can't get prog info: %s", strerror(errno));
                return -1;
        }
-        nr_func_ksyms = info.nr_jited_ksyms;
+        info = &info_linear->info;
-        if (nr_func_ksyms) {
+        if (mode == DUMP_JITED) {
-                func_ksyms = malloc(nr_func_ksyms * sizeof(__u64));
+                if (info->jited_prog_len == 0) {
-                if (!func_ksyms) {
+                        p_info("no instructions returned");
-                        p_err("mem alloc failed");
-                        close(fd);
-                        goto err_free;
-                }
-        }
-        nr_func_lens = info.nr_jited_func_lens;
-        if (nr_func_lens) {
-                func_lens = malloc(nr_func_lens * sizeof(__u32));
-                if (!func_lens) {
-                        p_err("mem alloc failed");
-                        close(fd);
                        goto err_free;
                }
-        }
+                buf = (unsigned char *)(info->jited_prog_insns);
+                member_len = info->jited_prog_len;
-        nr_finfo = info.nr_func_info;
+        } else {        /* DUMP_XLATED */
-        finfo_rec_size = info.func_info_rec_size;
+                if (info->xlated_prog_len == 0) {
-        if (nr_finfo && finfo_rec_size) {
+                        p_err("error retrieving insn dump: kernel.kptr_restrict set?");
-                func_info = malloc(nr_finfo * finfo_rec_size);
-                if (!func_info) {
-                        p_err("mem alloc failed");
-                        close(fd);
                        goto err_free;
                }
+                buf = (unsigned char *)info->xlated_prog_insns;
+                member_len = info->xlated_prog_len;
        }
-        linfo_rec_size = info.line_info_rec_size;
+        if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) {
-        if (info.nr_line_info && linfo_rec_size && info.btf_id) {
-                nr_linfo = info.nr_line_info;
-                linfo = malloc(nr_linfo * linfo_rec_size);
-                if (!linfo) {
-                        p_err("mem alloc failed");
-                        close(fd);
-                        goto err_free;
-                }
-        }
-        jited_linfo_rec_size = info.jited_line_info_rec_size;
-        if (info.nr_jited_line_info &&
-            jited_linfo_rec_size &&
-            info.nr_jited_ksyms &&
-            info.nr_jited_func_lens &&
-            info.btf_id) {
-                nr_jited_linfo = info.nr_jited_line_info;
-                jited_linfo = malloc(nr_jited_linfo * jited_linfo_rec_size);
-                if (!jited_linfo) {
-                        p_err("mem alloc failed");
-                        close(fd);
-                        goto err_free;
-                }
-        }
-        memset(&info, 0, sizeof(info));
-        *member_ptr = ptr_to_u64(buf);
-        *member_len = buf_size;
-        info.jited_ksyms = ptr_to_u64(func_ksyms);
-        info.nr_jited_ksyms = nr_func_ksyms;
-        info.jited_func_lens = ptr_to_u64(func_lens);
-        info.nr_jited_func_lens = nr_func_lens;
-        info.nr_func_info = nr_finfo;
-        info.func_info_rec_size = finfo_rec_size;
-        info.func_info = ptr_to_u64(func_info);
-        info.nr_line_info = nr_linfo;
-        info.line_info_rec_size = linfo_rec_size;
-        info.line_info = ptr_to_u64(linfo);
-        info.nr_jited_line_info = nr_jited_linfo;
-        info.jited_line_info_rec_size = jited_linfo_rec_size;
-        info.jited_line_info = ptr_to_u64(jited_linfo);
-        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 (info.nr_jited_ksyms > nr_func_ksyms) {
-                p_err("too many addresses returned");
-                goto err_free;
-        }
-        if (info.nr_jited_func_lens > nr_func_lens) {
-                p_err("too many values returned");
-                goto err_free;
-        }
-        if (info.nr_func_info != nr_finfo) {
-                p_err("incorrect nr_func_info %d vs. expected %d",
-                      info.nr_func_info, nr_finfo);
-                goto err_free;
-        }
-        if (info.func_info_rec_size != finfo_rec_size) {
-                p_err("incorrect func_info_rec_size %d vs. expected %d",
-                      info.func_info_rec_size, finfo_rec_size);
-                goto err_free;
-        }
-        if (linfo && info.nr_line_info != nr_linfo) {
-                p_err("incorrect nr_line_info %u vs. expected %u",
-                      info.nr_line_info, nr_linfo);
-                goto err_free;
-        }
-        if (info.line_info_rec_size != linfo_rec_size) {
-                p_err("incorrect line_info_rec_size %u vs. expected %u",
-                      info.line_info_rec_size, linfo_rec_size);
-                goto err_free;
-        }
-        if (jited_linfo && info.nr_jited_line_info != nr_jited_linfo) {
-                p_err("incorrect nr_jited_line_info %u vs. expected %u",
-                      info.nr_jited_line_info, nr_jited_linfo);
-                goto err_free;
-        }
-        if (info.jited_line_info_rec_size != jited_linfo_rec_size) {
-                p_err("incorrect jited_line_info_rec_size %u vs. expected %u",
-                      info.jited_line_info_rec_size, jited_linfo_rec_size);
-                goto err_free;
-        }
-        if ((member_len == &info.jited_prog_len &&
-             info.jited_prog_insns == 0) ||
-            (member_len == &info.xlated_prog_len &&
-             info.xlated_prog_insns == 0)) {
-                p_err("error retrieving insn dump: kernel.kptr_restrict set?");
-                goto err_free;
-        }
-        if (info.btf_id && btf__get_from_id(info.btf_id, &btf)) {
                p_err("failed to get btf");
                goto err_free;
        }
-        if (nr_linfo) {
+        func_info = (void *)info->func_info;
-                prog_linfo = bpf_prog_linfo__new(&info);
+        if (info->nr_line_info) {
+                prog_linfo = bpf_prog_linfo__new(info);
                if (!prog_linfo)
                        p_info("error in processing bpf_line_info.  continue without it.");
        }
@@ -655,9 +520,9 @@ static int do_dump(int argc, char **argv)
                        goto err_free;
                }
-                n = write(fd, buf, *member_len);
+                n = write(fd, buf, member_len);
                close(fd);
-                if (n != *member_len) {
+                if (n != member_len) {
                        p_err("error writing output file: %s",
                              n < 0 ? strerror(errno) : "short write");
                        goto err_free;
@@ -665,19 +530,19 @@ static int do_dump(int argc, char **argv)
                if (json_output)
                        jsonw_null(json_wtr);
-        } else if (member_len == &info.jited_prog_len) {
+        } else if (mode == DUMP_JITED) {
                const char *name = NULL;
-                if (info.ifindex) {
+                if (info->ifindex) {
-                        name = ifindex_to_bfd_params(info.ifindex,
+                        name = ifindex_to_bfd_params(info->ifindex,
-                                                     info.netns_dev,
+                                                     info->netns_dev,
-                                                     info.netns_ino,
+                                                     info->netns_ino,
                                                     &disasm_opt);
                        if (!name)
                                goto err_free;
                }
-                if (info.nr_jited_func_lens && info.jited_func_lens) {
+                if (info->nr_jited_func_lens && info->jited_func_lens) {
                        struct kernel_sym *sym = NULL;
                        struct bpf_func_info *record;
                        char sym_name[SYM_MAX_NAME];
@@ -685,17 +550,16 @@ static int do_dump(int argc, char **argv)
                        __u64 *ksyms = NULL;
                        __u32 *lens;
                        __u32 i;
+                        if (info->nr_jited_ksyms) {
-                        if (info.nr_jited_ksyms) {
                                kernel_syms_load(&dd);
-                                ksyms = (__u64 *) info.jited_ksyms;
+                                ksyms = (__u64 *) info->jited_ksyms;
                        }
                        if (json_output)
                                jsonw_start_array(json_wtr);
-                        lens = (__u32 *) info.jited_func_lens;
+                        lens = (__u32 *) info->jited_func_lens;
-                        for (i = 0; i < info.nr_jited_func_lens; i++) {
+                        for (i = 0; i < info->nr_jited_func_lens; i++) {
                                if (ksyms) {
                                        sym = kernel_syms_search(&dd, ksyms[i]);
                                        if (sym)
@@ -707,7 +571,7 @@ static int do_dump(int argc, char **argv)
                                }
                                if (func_info) {
-                                        record = func_info + i * finfo_rec_size;
+                                        record = func_info + i * info->func_info_rec_size;
                                        btf_dumper_type_only(btf, record->type_id,
                                                             func_sig,
                                                             sizeof(func_sig));
@@ -744,49 +608,37 @@ static int do_dump(int argc, char **argv)
                        if (json_output)
                                jsonw_end_array(json_wtr);
                } else {
-                        disasm_print_insn(buf, *member_len, opcodes, name,
+                        disasm_print_insn(buf, member_len, opcodes, name,
                                          disasm_opt, btf, NULL, 0, 0, false);
                }
        } else if (visual) {
                if (json_output)
                        jsonw_null(json_wtr);
                else
-                        dump_xlated_cfg(buf, *member_len);
+                        dump_xlated_cfg(buf, member_len);
        } else {
                kernel_syms_load(&dd);
-                dd.nr_jited_ksyms = info.nr_jited_ksyms;
+                dd.nr_jited_ksyms = info->nr_jited_ksyms;
-                dd.jited_ksyms = (__u64 *) info.jited_ksyms;
+                dd.jited_ksyms = (__u64 *) info->jited_ksyms;
                dd.btf = btf;
                dd.func_info = func_info;
-                dd.finfo_rec_size = finfo_rec_size;
+                dd.finfo_rec_size = info->func_info_rec_size;
                dd.prog_linfo = prog_linfo;
                if (json_output)
-                        dump_xlated_json(&dd, buf, *member_len, opcodes,
+                        dump_xlated_json(&dd, buf, member_len, opcodes,
                                         linum);
                else
-                        dump_xlated_plain(&dd, buf, *member_len, opcodes,
+                        dump_xlated_plain(&dd, buf, member_len, opcodes,
                                          linum);
                kernel_syms_destroy(&dd);
        }
-        free(buf);
+        free(info_linear);
-        free(func_ksyms);
-        free(func_lens);
-        free(func_info);
-        free(linfo);
-        free(jited_linfo);
-        bpf_prog_linfo__free(prog_linfo);
        return 0;
 err_free:
-        free(buf);
+        free(info_linear);
-        free(func_ksyms);
-        free(func_lens);
-        free(func_info);
-        free(linfo);
-        free(jited_linfo);
-        bpf_prog_linfo__free(prog_linfo);
        return -1;
 }
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 61e46d54a67c..8d3864b061f3 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -66,7 +66,8 @@ FEATURE_TESTS_BASIC :=                  \
        sched_getcpu                    \
        sdt                             \
        setns                           \
-        libaio
+        libaio                          \
+        disassembler-four-args
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests
@@ -118,7 +119,8 @@ FEATURE_DISPLAY ?=              \
         lzma                   \
         get_cpuid              \
         bpf                    \
-         libaio
+         libaio                 \
+         disassembler-four-args
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index e903b86b742f..7853e6d91090 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -178,6 +178,10 @@
 # include "test-reallocarray.c"
 #undef main
+#define main main_test_disassembler_four_args
+# include "test-disassembler-four-args.c"
+#undef main
 int main(int argc, char *argv[])
 {
        main_test_libpython();
@@ -219,6 +223,7 @@ int main(int argc, char *argv[])
        main_test_setns();
        main_test_libaio();
        main_test_reallocarray();
+        main_test_disassembler_four_args();
        return 0;
 }
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index d90127298f12..12cdf611d217 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -38,8 +38,10 @@ __SYSCALL(__NR_io_destroy, sys_io_destroy)
 __SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
 #define __NR_io_cancel 3
 __SYSCALL(__NR_io_cancel, sys_io_cancel)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_io_getevents 4
-__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents)
+#endif
 /* fs/xattr.c */
 #define __NR_setxattr 5
@@ -179,7 +181,7 @@ __SYSCALL(__NR_fchownat, sys_fchownat)
 #define __NR_fchown 55
 __SYSCALL(__NR_fchown, sys_fchown)
 #define __NR_openat 56
-__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+__SYSCALL(__NR_openat, sys_openat)
 #define __NR_close 57
 __SYSCALL(__NR_close, sys_close)
 #define __NR_vhangup 58
@@ -222,10 +224,12 @@ __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
 __SYSCALL(__NR3264_sendfile, sys_sendfile64)
 /* fs/select.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_pselect6 72
-__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32)
 #define __NR_ppoll 73
-__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32)
+#endif
 /* fs/signalfd.c */
 #define __NR_signalfd4 74
@@ -269,16 +273,20 @@ __SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
 /* fs/timerfd.c */
 #define __NR_timerfd_create 85
 __SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_timerfd_settime 86
-__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \
-          compat_sys_timerfd_settime)
+          sys_timerfd_settime)
 #define __NR_timerfd_gettime 87
-__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \
-          compat_sys_timerfd_gettime)
+          sys_timerfd_gettime)
+#endif
 /* fs/utimes.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_utimensat 88
-__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat)
+#endif
 /* kernel/acct.c */
 #define __NR_acct 89
@@ -309,8 +317,10 @@ __SYSCALL(__NR_set_tid_address, sys_set_tid_address)
 __SYSCALL(__NR_unshare, sys_unshare)
 /* kernel/futex.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_futex 98
-__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+__SC_3264(__NR_futex, sys_futex_time32, sys_futex)
+#endif
 #define __NR_set_robust_list 99
 __SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
          compat_sys_set_robust_list)
@@ -319,8 +329,10 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
          compat_sys_get_robust_list)
 /* kernel/hrtimer.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_nanosleep 101
-__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep)
+#endif
 /* kernel/itimer.c */
 #define __NR_getitimer 102
@@ -341,23 +353,29 @@ __SYSCALL(__NR_delete_module, sys_delete_module)
 /* kernel/posix-timers.c */
 #define __NR_timer_create 107
 __SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_timer_gettime 108
-__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime)
+#endif
 #define __NR_timer_getoverrun 109
 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_timer_settime 110
-__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime)
+#endif
 #define __NR_timer_delete 111
 __SYSCALL(__NR_timer_delete, sys_timer_delete)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_clock_settime 112
-__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime)
 #define __NR_clock_gettime 113
-__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime)
 #define __NR_clock_getres 114
-__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres)
 #define __NR_clock_nanosleep 115
-__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \
-          compat_sys_clock_nanosleep)
+          sys_clock_nanosleep)
+#endif
 /* kernel/printk.c */
 #define __NR_syslog 116
@@ -388,9 +406,11 @@ __SYSCALL(__NR_sched_yield, sys_sched_yield)
 __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
 #define __NR_sched_get_priority_min 126
 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_sched_rr_get_interval 127
-__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \
-          compat_sys_sched_rr_get_interval)
+          sys_sched_rr_get_interval)
+#endif
 /* kernel/signal.c */
 #define __NR_restart_syscall 128
@@ -411,9 +431,11 @@ __SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
 __SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
 #define __NR_rt_sigpending 136
 __SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_rt_sigtimedwait 137
-__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \
-          compat_sys_rt_sigtimedwait)
+          sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32)
+#endif
 #define __NR_rt_sigqueueinfo 138
 __SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
          compat_sys_rt_sigqueueinfo)
@@ -467,10 +489,15 @@ __SYSCALL(__NR_uname, sys_newuname)
 __SYSCALL(__NR_sethostname, sys_sethostname)
 #define __NR_setdomainname 162
 __SYSCALL(__NR_setdomainname, sys_setdomainname)
+#ifdef __ARCH_WANT_SET_GET_RLIMIT
+/* getrlimit and setrlimit are superseded with prlimit64 */
 #define __NR_getrlimit 163
 __SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
 #define __NR_setrlimit 164
 __SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#endif
 #define __NR_getrusage 165
 __SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
 #define __NR_umask 166
@@ -481,12 +508,14 @@ __SYSCALL(__NR_prctl, sys_prctl)
 __SYSCALL(__NR_getcpu, sys_getcpu)
 /* kernel/time.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_gettimeofday 169
 __SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
 #define __NR_settimeofday 170
 __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
 #define __NR_adjtimex 171
-__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
+#endif
 /* kernel/timer.c */
 #define __NR_getpid 172
@@ -511,11 +540,13 @@ __SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
 __SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
 #define __NR_mq_unlink 181
 __SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_mq_timedsend 182
-__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend)
 #define __NR_mq_timedreceive 183
-__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \
-          compat_sys_mq_timedreceive)
+          sys_mq_timedreceive)
+#endif
 #define __NR_mq_notify 184
 __SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
 #define __NR_mq_getsetattr 185
@@ -536,8 +567,10 @@ __SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
 __SYSCALL(__NR_semget, sys_semget)
 #define __NR_semctl 191
 __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_semtimedop 192
-__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32)
+#endif
 #define __NR_semop 193
 __SYSCALL(__NR_semop, sys_semop)
@@ -658,8 +691,10 @@ __SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
 __SYSCALL(__NR_perf_event_open, sys_perf_event_open)
 #define __NR_accept4 242
 __SYSCALL(__NR_accept4, sys_accept4)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_recvmmsg 243
-__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32)
+#endif
 /*
 * Architectures may provide up to 16 syscalls of their own
@@ -667,8 +702,10 @@ __SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
 */
 #define __NR_arch_specific_syscall 244
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_wait4 260
 __SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#endif
 #define __NR_prlimit64 261
 __SYSCALL(__NR_prlimit64, sys_prlimit64)
 #define __NR_fanotify_init 262
@@ -678,10 +715,11 @@ __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
 #define __NR_name_to_handle_at         264
 __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
 #define __NR_open_by_handle_at         265
-__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
-          compat_sys_open_by_handle_at)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_clock_adjtime 266
-__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime)
+#endif
 #define __NR_syncfs 267
 __SYSCALL(__NR_syncfs, sys_syncfs)
 #define __NR_setns 268
@@ -734,15 +772,60 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_io_pgetevents 292
-__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents)
+#endif
 #define __NR_rseq 293
 __SYSCALL(__NR_rseq, sys_rseq)
 #define __NR_kexec_file_load 294
 __SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
+/* 295 through 402 are unassigned to sync up with generic numbers, don't use */
+#if __BITS_PER_LONG == 32
+#define __NR_clock_gettime64 403
+__SYSCALL(__NR_clock_gettime64, sys_clock_gettime)
+#define __NR_clock_settime64 404
+__SYSCALL(__NR_clock_settime64, sys_clock_settime)
+#define __NR_clock_adjtime64 405
+__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime)
+#define __NR_clock_getres_time64 406
+__SYSCALL(__NR_clock_getres_time64, sys_clock_getres)
+#define __NR_clock_nanosleep_time64 407
+__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep)
+#define __NR_timer_gettime64 408
+__SYSCALL(__NR_timer_gettime64, sys_timer_gettime)
+#define __NR_timer_settime64 409
+__SYSCALL(__NR_timer_settime64, sys_timer_settime)
+#define __NR_timerfd_gettime64 410
+__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime)
+#define __NR_timerfd_settime64 411
+__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime)
+#define __NR_utimensat_time64 412
+__SYSCALL(__NR_utimensat_time64, sys_utimensat)
+#define __NR_pselect6_time64 413
+__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64)
+#define __NR_ppoll_time64 414
+__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64)
+#define __NR_io_pgetevents_time64 416
+__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+#define __NR_recvmmsg_time64 417
+__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64)
+#define __NR_mq_timedsend_time64 418
+__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend)
+#define __NR_mq_timedreceive_time64 419
+__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive)
+#define __NR_semtimedop_time64 420
+__SYSCALL(__NR_semtimedop_time64, sys_semtimedop)
+#define __NR_rt_sigtimedwait_time64 421
+__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64)
+#define __NR_futex_time64 422
+__SYSCALL(__NR_futex_time64, sys_futex)
+#define __NR_sched_rr_get_interval_time64 423
+__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#endif
 #undef __NR_syscalls
-#define __NR_syscalls 295
+#define __NR_syscalls 424
 /*
 * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index a55cb8b10165..e7ad9d350a28 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -292,10 +292,11 @@ struct sockaddr_in {
 #define IN_LOOPBACK(a)          ((((long int) (a)) & 0xff000000) == 0x7f000000)
 /* Defines for Multicast INADDR */
-#define INADDR_UNSPEC_GROUP     0xe0000000U     /* 224.0.0.0   */
+#define INADDR_UNSPEC_GROUP             0xe0000000U     /* 224.0.0.0   */
-#define INADDR_ALLHOSTS_GROUP   0xe0000001U     /* 224.0.0.1   */
+#define INADDR_ALLHOSTS_GROUP           0xe0000001U     /* 224.0.0.1   */
-#define INADDR_ALLRTRS_GROUP    0xe0000002U     /* 224.0.0.2 */
+#define INADDR_ALLRTRS_GROUP            0xe0000002U     /* 224.0.0.2 */
-#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU     /* 224.0.0.255 */
+#define INADDR_ALLSNOOPERS_GROUP        0xe000006aU     /* 224.0.0.106 */
+#define INADDR_MAX_LOCAL_GROUP          0xe00000ffU     /* 224.0.0.255 */
 #endif
 /* <asm/byteorder.h> contains the htonl type stuff.. */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d5b830d60601..e6ad87512519 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -112,6 +112,11 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...)
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+        return (__u64) (unsigned long) ptr;
+}
 struct bpf_capabilities {
        /* v4.14: kernel support for program & map names. */
        __u32 name:1;
@@ -622,7 +627,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
        bool strict = !(flags & MAPS_RELAX_COMPAT);
        int i, map_idx, map_def_sz, nr_maps = 0;
        Elf_Scn *scn;
-        Elf_Data *data;
+        Elf_Data *data = NULL;
        Elf_Data *symbols = obj->efile.symbols;
        if (obj->efile.maps_shndx < 0)
@@ -2999,3 +3004,249 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
        ring_buffer_write_tail(header, data_tail);
        return ret;
 }
+struct bpf_prog_info_array_desc {
+        int     array_offset;   /* e.g. offset of jited_prog_insns */
+        int     count_offset;   /* e.g. offset of jited_prog_len */
+        int     size_offset;    /* > 0: offset of rec size,
+                                 * < 0: fix size of -size_offset
+                                 */
+};
+static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = {
+        [BPF_PROG_INFO_JITED_INSNS] = {
+                offsetof(struct bpf_prog_info, jited_prog_insns),
+                offsetof(struct bpf_prog_info, jited_prog_len),
+                -1,
+        },
+        [BPF_PROG_INFO_XLATED_INSNS] = {
+                offsetof(struct bpf_prog_info, xlated_prog_insns),
+                offsetof(struct bpf_prog_info, xlated_prog_len),
+                -1,
+        },
+        [BPF_PROG_INFO_MAP_IDS] = {
+                offsetof(struct bpf_prog_info, map_ids),
+                offsetof(struct bpf_prog_info, nr_map_ids),
+                -(int)sizeof(__u32),
+        },
+        [BPF_PROG_INFO_JITED_KSYMS] = {
+                offsetof(struct bpf_prog_info, jited_ksyms),
+                offsetof(struct bpf_prog_info, nr_jited_ksyms),
+                -(int)sizeof(__u64),
+        },
+        [BPF_PROG_INFO_JITED_FUNC_LENS] = {
+                offsetof(struct bpf_prog_info, jited_func_lens),
+                offsetof(struct bpf_prog_info, nr_jited_func_lens),
+                -(int)sizeof(__u32),
+        },
+        [BPF_PROG_INFO_FUNC_INFO] = {
+                offsetof(struct bpf_prog_info, func_info),
+                offsetof(struct bpf_prog_info, nr_func_info),
+                offsetof(struct bpf_prog_info, func_info_rec_size),
+        },
+        [BPF_PROG_INFO_LINE_INFO] = {
+                offsetof(struct bpf_prog_info, line_info),
+                offsetof(struct bpf_prog_info, nr_line_info),
+                offsetof(struct bpf_prog_info, line_info_rec_size),
+        },
+        [BPF_PROG_INFO_JITED_LINE_INFO] = {
+                offsetof(struct bpf_prog_info, jited_line_info),
+                offsetof(struct bpf_prog_info, nr_jited_line_info),
+                offsetof(struct bpf_prog_info, jited_line_info_rec_size),
+        },
+        [BPF_PROG_INFO_PROG_TAGS] = {
+                offsetof(struct bpf_prog_info, prog_tags),
+                offsetof(struct bpf_prog_info, nr_prog_tags),
+                -(int)sizeof(__u8) * BPF_TAG_SIZE,
+        },
+};
+static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset)
+{
+        __u32 *array = (__u32 *)info;
+        if (offset >= 0)
+                return array[offset / sizeof(__u32)];
+        return -(int)offset;
+}
+static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset)
+{
+        __u64 *array = (__u64 *)info;
+        if (offset >= 0)
+                return array[offset / sizeof(__u64)];
+        return -(int)offset;
+}
+static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset,
+                                         __u32 val)
+{
+        __u32 *array = (__u32 *)info;
+        if (offset >= 0)
+                array[offset / sizeof(__u32)] = val;
+}
+static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset,
+                                         __u64 val)
+{
+        __u64 *array = (__u64 *)info;
+        if (offset >= 0)
+                array[offset / sizeof(__u64)] = val;
+}
+struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays)
+{
+        struct bpf_prog_info_linear *info_linear;
+        struct bpf_prog_info info = {};
+        __u32 info_len = sizeof(info);
+        __u32 data_len = 0;
+        int i, err;
+        void *ptr;
+        if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
+                return ERR_PTR(-EINVAL);
+        /* step 1: get array dimensions */
+        err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+        if (err) {
+                pr_debug("can't get prog info: %s", strerror(errno));
+                return ERR_PTR(-EFAULT);
+        }
+        /* step 2: calculate total size of all arrays */
+        for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+                bool include_array = (arrays & (1UL << i)) > 0;
+                struct bpf_prog_info_array_desc *desc;
+                __u32 count, size;
+                desc = bpf_prog_info_array_desc + i;
+                /* kernel is too old to support this field */
+                if (info_len < desc->array_offset + sizeof(__u32) ||
+                    info_len < desc->count_offset + sizeof(__u32) ||
+                    (desc->size_offset > 0 && info_len < desc->size_offset))
+                        include_array = false;
+                if (!include_array) {
+                        arrays &= ~(1UL << i);  /* clear the bit */
+                        continue;
+                }
+                count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+                size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+                data_len += count * size;
+        }
+        /* step 3: allocate continuous memory */
+        data_len = roundup(data_len, sizeof(__u64));
+        info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
+        if (!info_linear)
+                return ERR_PTR(-ENOMEM);
+        /* step 4: fill data to info_linear->info */
+        info_linear->arrays = arrays;
+        memset(&info_linear->info, 0, sizeof(info));
+        ptr = info_linear->data;
+        for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+                struct bpf_prog_info_array_desc *desc;
+                __u32 count, size;
+                if ((arrays & (1UL << i)) == 0)
+                        continue;
+                desc  = bpf_prog_info_array_desc + i;
+                count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+                size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+                bpf_prog_info_set_offset_u32(&info_linear->info,
+                                             desc->count_offset, count);
+                bpf_prog_info_set_offset_u32(&info_linear->info,
+                                             desc->size_offset, size);
+                bpf_prog_info_set_offset_u64(&info_linear->info,
+                                             desc->array_offset,
+                                             ptr_to_u64(ptr));
+                ptr += count * size;
+        }
+        /* step 5: call syscall again to get required arrays */
+        err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len);
+        if (err) {
+                pr_debug("can't get prog info: %s", strerror(errno));
+                free(info_linear);
+                return ERR_PTR(-EFAULT);
+        }
+        /* step 6: verify the data */
+        for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+                struct bpf_prog_info_array_desc *desc;
+                __u32 v1, v2;
+                if ((arrays & (1UL << i)) == 0)
+                        continue;
+                desc = bpf_prog_info_array_desc + i;
+                v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+                v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+                                                   desc->count_offset);
+                if (v1 != v2)
+                        pr_warning("%s: mismatch in element count\n", __func__);
+                v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+                v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+                                                   desc->size_offset);
+                if (v1 != v2)
+                        pr_warning("%s: mismatch in rec size\n", __func__);
+        }
+        /* step 7: update info_len and data_len */
+        info_linear->info_len = sizeof(struct bpf_prog_info);
+        info_linear->data_len = data_len;
+        return info_linear;
+}
+void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear)
+{
+        int i;
+        for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+                struct bpf_prog_info_array_desc *desc;
+                __u64 addr, offs;
+                if ((info_linear->arrays & (1UL << i)) == 0)
+                        continue;
+                desc = bpf_prog_info_array_desc + i;
+                addr = bpf_prog_info_read_offset_u64(&info_linear->info,
+                                                     desc->array_offset);
+                offs = addr - ptr_to_u64(info_linear->data);
+                bpf_prog_info_set_offset_u64(&info_linear->info,
+                                             desc->array_offset, offs);
+        }
+}
+void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
+{
+        int i;
+        for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+                struct bpf_prog_info_array_desc *desc;
+                __u64 addr, offs;
+                if ((info_linear->arrays & (1UL << i)) == 0)
+                        continue;
+                desc = bpf_prog_info_array_desc + i;
+                offs = bpf_prog_info_read_offset_u64(&info_linear->info,
+                                                     desc->array_offset);
+                addr = offs + ptr_to_u64(info_linear->data);
+                bpf_prog_info_set_offset_u64(&info_linear->info,
+                                             desc->array_offset, addr);
+        }
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b4652aa1a58a..c70785cc8ef5 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,7 @@
 #ifndef __LIBBPF_LIBBPF_H
 #define __LIBBPF_LIBBPF_H
+#include <stdarg.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <stdbool.h>
@@ -377,6 +378,69 @@ LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
 LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
                                 enum bpf_prog_type prog_type, __u32 ifindex);
+/*
+ * Get bpf_prog_info in continuous memory
+ *
+ * struct bpf_prog_info has multiple arrays. The user has option to choose
+ * arrays to fetch from kernel. The following APIs provide an uniform way to
+ * fetch these data. All arrays in bpf_prog_info are stored in a single
+ * continuous memory region. This makes it easy to store the info in a
+ * file.
+ *
+ * Before writing bpf_prog_info_linear to files, it is necessary to
+ * translate pointers in bpf_prog_info to offsets. Helper functions
+ * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr()
+ * are introduced to switch between pointers and offsets.
+ *
+ * Examples:
+ *   # To fetch map_ids and prog_tags:
+ *   __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) |
+ *           (1UL << BPF_PROG_INFO_PROG_TAGS);
+ *   struct bpf_prog_info_linear *info_linear =
+ *           bpf_program__get_prog_info_linear(fd, arrays);
+ *
+ *   # To save data in file
+ *   bpf_program__bpil_addr_to_offs(info_linear);
+ *   write(f, info_linear, sizeof(*info_linear) + info_linear->data_len);
+ *
+ *   # To read data from file
+ *   read(f, info_linear, <proper_size>);
+ *   bpf_program__bpil_offs_to_addr(info_linear);
+ */
+enum bpf_prog_info_array {
+        BPF_PROG_INFO_FIRST_ARRAY = 0,
+        BPF_PROG_INFO_JITED_INSNS = 0,
+        BPF_PROG_INFO_XLATED_INSNS,
+        BPF_PROG_INFO_MAP_IDS,
+        BPF_PROG_INFO_JITED_KSYMS,
+        BPF_PROG_INFO_JITED_FUNC_LENS,
+        BPF_PROG_INFO_FUNC_INFO,
+        BPF_PROG_INFO_LINE_INFO,
+        BPF_PROG_INFO_JITED_LINE_INFO,
+        BPF_PROG_INFO_PROG_TAGS,
+        BPF_PROG_INFO_LAST_ARRAY,
+};
+struct bpf_prog_info_linear {
+        /* size of struct bpf_prog_info, when the tool is compiled */
+        __u32                   info_len;
+        /* total bytes allocated for data, round up to 8 bytes */
+        __u32                   data_len;
+        /* which arrays are included in data */
+        __u64                   arrays;
+        struct bpf_prog_info    info;
+        __u8                    data[];
+};
+LIBBPF_API struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays);
+LIBBPF_API void
+bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
+LIBBPF_API void
+bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 778a26702a70..f3ce50500cf2 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -153,4 +153,7 @@ LIBBPF_0.0.2 {
                xsk_socket__delete;
                xsk_umem__fd;
                xsk_socket__fd;
+                bpf_program__get_prog_info_linear;
+                bpf_program__bpil_addr_to_offs;
+                bpf_program__bpil_offs_to_addr;
 } LIBBPF_0.0.1;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 0414a0d52262..5dde107083c6 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2184,9 +2184,10 @@ static void cleanup(struct objtool_file *file)
        elf_close(file->elf);
 }
+static struct objtool_file file;
 int check(const char *_objname, bool orc)
 {
-        struct objtool_file file;
        int ret, warnings = 0;
        objname = _objname;
diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt
index f6fc6507ba55..3766886c4bca 100644
--- a/tools/perf/Documentation/Build.txt
+++ b/tools/perf/Documentation/Build.txt
@@ -47,3 +47,27 @@ Those objects are then used in final linking:
 NOTE this description is omitting other libraries involved, only
     focusing on build framework outcomes
+3) Build with ASan or UBSan
+==========================
+  $ cd tools/perf
+  $ make DESTDIR=/usr
+  $ make DESTDIR=/usr install
+AddressSanitizer (or ASan) is a GCC feature that detects memory corruption bugs
+such as buffer overflows and memory leaks.
+  $ cd tools/perf
+  $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address'
+  $ ASAN_OPTIONS=log_path=asan.log ./perf record -a
+ASan outputs all detected issues into a log file named 'asan.log.<pid>'.
+UndefinedBehaviorSanitizer (or UBSan) is a fast undefined behavior detector
+supported by GCC. UBSan detects undefined behaviors of programs at runtime.
+  $ cd tools/perf
+  $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=undefined'
+  $ UBSAN_OPTIONS=print_stacktrace=1 ./perf record -a
+If UBSan detects any problem at runtime, it outputs a “runtime error:” message.
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 86f3dcc15f83..462b3cde0675 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -114,7 +114,7 @@ Given a $HOME/.perfconfig like this:
        [report]
                # Defaults
-                sort-order = comm,dso,symbol
+                sort_order = comm,dso,symbol
                percent-limit = 0
                queue-size = 0
                children = true
@@ -584,6 +584,20 @@ llvm.*::
        llvm.opts::
                Options passed to llc.
+samples.*::
+        samples.context::
+                Define how many ns worth of time to show
+                around samples in perf report sample context browser.
+scripts.*::
+        Any option defines a script that is added to the scripts menu
+        in the interactive perf browser and whose output is displayed.
+        The name of the option is the name, the value is a script command line.
+        The script gets the same options passed as a full perf script,
+        in particular -i perfdata file, --cpu, --tid
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8f0c2be34848..8fe4dffcadd0 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -495,6 +495,10 @@ overhead. You can still switch them on with:
  --switch-output --no-no-buildid  --no-no-buildid-cache
+--switch-max-files=N::
+When rotating perf.data with --switch-output, only keep N files.
 --dry-run::
 Parse options then exit. --dry-run can be used to detect errors in cmdline
 options.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 1a27bfe05039..f441baa794ce 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -105,6 +105,8 @@ OPTIONS
        guest machine
        - sample: Number of sample
        - period: Raw number of event count of sample
+        - time: Separate the samples by time stamp with the resolution specified by
+        --time-quantum (default 100ms). Specify with overhead and before it.
        By default, comm, dso and symbol keys are used.
        (i.e. --sort comm,dso,symbol)
@@ -459,6 +461,10 @@ include::itrace.txt[]
 --socket-filter::
        Only report the samples on the processor socket that match with this filter
+--samples=N::
+        Save N individual samples for each histogram entry to show context in perf
+        report tui browser.
 --raw-trace::
        When displaying traceevent output, do not use print fmt or plugins.
@@ -477,6 +483,9 @@ include::itrace.txt[]
        Please note that not all mmaps are stored, options affecting which ones
        are include 'perf record --data', for instance.
+--ns::
+        Show time stamps in nanoseconds.
 --stats::
        Display overall events statistics without any further processing.
        (like the one at the end of the perf report -D command)
@@ -494,6 +503,10 @@ include::itrace.txt[]
        The period/hits keywords set the base the percentage is computed
        on - the samples period or the number of samples (hits).
+--time-quantum::
+        Configure time quantum for time sort key. Default 100ms.
+        Accepts s, us, ms, ns units.
 include::callchain-overhead-calculation.txt[]
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2e19fd7ffe35..9b0d04dd2a61 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -380,6 +380,9 @@ include::itrace.txt[]
        Set the maximum number of program blocks to print with brstackasm for
        each sample.
+--reltime::
+        Print time stamps relative to trace start.
 --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.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4bc2085e5197..39c05f89104e 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -72,9 +72,8 @@ report::
 --all-cpus::
        system-wide collection from all CPUs (default if no target is specified)
-c::
+--no-scale::
--scale::
+        Don't scale/normalize counter values
-        scale/normalize counter values
 -d::
 --detailed::
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 849599f39c5e..869965d629ce 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -15,6 +15,7 @@ To see callchains in a more compact form: perf report -g folded
 Show individual samples with: perf script
 Limit to show entries above 5% only: perf report --percent-limit 5
 Profiling branch (mis)predictions with: perf record -b / perf report
+To show assembler sample contexts use perf record -b / perf script -F +brstackinsn --xed
 Treat branches as callchains: perf report --branch-history
 To count events in every 1000 msec: perf stat -I 1000
 Print event counts in CSV format with: perf stat -x,
@@ -34,3 +35,9 @@ Show current config key-value pairs: perf config --list
 Show user configuration overrides: perf config --user --list
 To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
 To report cacheline events from previous recording: perf c2c report
+To browse sample contexts use perf report --sample 10 and select in context menu
+To separate samples by time use perf report --sort time,overhead,sym
+To set sample time separation other than 100ms with --sort time use --time-quantum
+Add -I to perf report to sample register values visible in perf report context.
+To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context
+To show context switches in perf report sample context add --switch-events to perf record.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0f11d5891301..fe3f97e342fa 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -227,6 +227,8 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -713,7 +715,7 @@ else
 endif
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd
+  EXTLIBS += -lbfd -lopcodes
 else
  # we are on a system that requires -liberty and (maybe) -lz
  # to link against -lbfd; test each case individually here
@@ -724,12 +726,15 @@ else
  $(call feature_check,libbfd-liberty-z)
  ifeq ($(feature-libbfd-liberty), 1)
-    EXTLIBS += -lbfd -liberty
+    EXTLIBS += -lbfd -lopcodes -liberty
+    FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl
  else
    ifeq ($(feature-libbfd-liberty-z), 1)
-      EXTLIBS += -lbfd -liberty -lz
+      EXTLIBS += -lbfd -lopcodes -liberty -lz
+      FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl
    endif
  endif
+  $(call feature_check,disassembler-four-args)
 endif
 ifdef NO_DEMANGLE
@@ -808,6 +813,10 @@ ifdef HAVE_KVM_STAT_SUPPORT
    CFLAGS += -DHAVE_KVM_STAT_SUPPORT
 endif
+ifeq ($(feature-disassembler-four-args), 1)
+    CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
+endif
 ifeq (${IS_64_BIT}, 1)
  ifndef NO_PERF_READ_VDSO32
    $(call feature_check,compile-32)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..2ae92fddb6d5 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,8 @@
 332     common  statx                   __x64_sys_statx
 333     common  io_pgetevents           __x64_sys_io_pgetevents
 334     common  rseq                    __x64_sys_rseq
+# don't use numbers 387 through 423, add new calls after the last
+# 'common' entry
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -361,7 +363,7 @@
 520     x32     execve                  __x32_compat_sys_execve/ptregs
 521     x32     ptrace                  __x32_compat_sys_ptrace
 522     x32     rt_sigpending           __x32_compat_sys_rt_sigpending
-523     x32     rt_sigtimedwait         __x32_compat_sys_rt_sigtimedwait
+523     x32     rt_sigtimedwait         __x32_compat_sys_rt_sigtimedwait_time64
 524     x32     rt_sigqueueinfo         __x32_compat_sys_rt_sigqueueinfo
 525     x32     sigaltstack             __x32_compat_sys_sigaltstack
 526     x32     timer_create            __x32_compat_sys_timer_create
@@ -375,7 +377,7 @@
 534     x32     preadv                  __x32_compat_sys_preadv64
 535     x32     pwritev                 __x32_compat_sys_pwritev64
 536     x32     rt_tgsigqueueinfo       __x32_compat_sys_rt_tgsigqueueinfo
-537     x32     recvmmsg                __x32_compat_sys_recvmmsg
+537     x32     recvmmsg                __x32_compat_sys_recvmmsg_time64
 538     x32     sendmmsg                __x32_compat_sys_sendmmsg
 539     x32     process_vm_readv        __x32_compat_sys_process_vm_readv
 540     x32     process_vm_writev       __x32_compat_sys_process_vm_writev
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 7aab0be5fc5f..47f9c56e744f 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -14,5 +14,6 @@ perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_AUXTRACE) += auxtrace.o
+perf-$(CONFIG_AUXTRACE) += archinsn.o
 perf-$(CONFIG_AUXTRACE) += intel-pt.o
 perf-$(CONFIG_AUXTRACE) += intel-bts.o
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
new file mode 100644
index 000000000000..4237bb2e7fa2
--- /dev/null
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "perf.h"
+#include "archinsn.h"
+#include "util/intel-pt-decoder/insn.h"
+#include "machine.h"
+#include "thread.h"
+#include "symbol.h"
+void arch_fetch_insn(struct perf_sample *sample,
+                     struct thread *thread,
+                     struct machine *machine)
+{
+        struct insn insn;
+        int len;
+        bool is64bit = false;
+        if (!sample->ip)
+                return;
+        len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit);
+        if (len <= 0)
+                return;
+        insn_init(&insn, sample->insn, len, is64bit);
+        insn_get_length(&insn);
+        if (insn_complete(&insn) && insn.length <= len)
+                sample->insn_len = insn.length;
+}
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 0c0a6e824934..2af067859966 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -224,7 +224,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu)
        pthread_attr_t thread_attr, *attrp = NULL;
        cpu_set_t cpuset;
        unsigned int i, j;
-        int ret;
+        int ret = 0;
        if (!noaffinity)
                pthread_attr_init(&thread_attr);
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 5a11534e96a0..fe85448abd45 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -293,7 +293,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu)
        pthread_attr_t thread_attr, *attrp = NULL;
        cpu_set_t cpuset;
        unsigned int i, j;
-        int ret, events = EPOLLIN;
+        int ret = 0, events = EPOLLIN;
        if (oneshot)
                events |= EPOLLONESHOT;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index c9f98d00c0e9..a8394b4f1167 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -119,7 +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, details_flag);
+                        metricgroup__print(true, true, s, raw_dump, details_flag);
                        free(s);
                }
        }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3f7f3100336..4e2d953d4bc5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,6 +62,9 @@ struct switch_output {
        unsigned long    time;
        const char      *str;
        bool             set;
+        char             **filenames;
+        int              num_files;
+        int              cur_file;
 };
 struct record {
@@ -392,7 +395,7 @@ static int record__process_auxtrace(struct perf_tool *tool,
        size_t padding;
        u8 pad[8] = {0};
-        if (!perf_data__is_pipe(data)) {
+        if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) {
                off_t file_offset;
                int fd = perf_data__fd(data);
                int err;
@@ -837,6 +840,8 @@ static void record__init_features(struct record *rec)
        if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
                perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+        perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
        perf_header__clear_feat(&session->header, HEADER_STAT);
 }
@@ -890,6 +895,7 @@ record__switch_output(struct record *rec, bool at_exit)
 {
        struct perf_data *data = &rec->data;
        int fd, err;
+        char *new_filename;
        /* Same Size:      "2015122520103046"*/
        char timestamp[] = "InvalidTimestamp";
@@ -910,7 +916,7 @@ record__switch_output(struct record *rec, bool at_exit)
        fd = perf_data__switch(data, timestamp,
                                    rec->session->header.data_offset,
-                                    at_exit);
+                                    at_exit, &new_filename);
        if (fd >= 0 && !at_exit) {
                rec->bytes_written = 0;
                rec->session->header.data_size = 0;
@@ -920,6 +926,21 @@ record__switch_output(struct record *rec, bool at_exit)
                fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
                        data->path, timestamp);
+        if (rec->switch_output.num_files) {
+                int n = rec->switch_output.cur_file + 1;
+                if (n >= rec->switch_output.num_files)
+                        n = 0;
+                rec->switch_output.cur_file = n;
+                if (rec->switch_output.filenames[n]) {
+                        remove(rec->switch_output.filenames[n]);
+                        free(rec->switch_output.filenames[n]);
+                }
+                rec->switch_output.filenames[n] = new_filename;
+        } else {
+                free(new_filename);
+        }
        /* Output tracking events */
        if (!at_exit) {
                record__synthesize(rec, false);
@@ -1093,7 +1114,7 @@ static int record__synthesize(struct record *rec, bool tail)
                return err;
        }
-        err = perf_event__synthesize_bpf_events(tool, process_synthesized_event,
+        err = perf_event__synthesize_bpf_events(session, process_synthesized_event,
                                                machine, opts);
        if (err < 0)
                pr_warning("Couldn't synthesize bpf events.\n");
@@ -1116,6 +1137,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
        struct perf_data *data = &rec->data;
        struct perf_session *session;
        bool disabled = false, draining = false;
+        struct perf_evlist *sb_evlist = NULL;
        int fd;
        atexit(record__sig_exit);
@@ -1216,6 +1238,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                goto out_child;
        }
+        if (!opts->no_bpf_event)
+                bpf_event__add_sb_event(&sb_evlist, &session->header.env);
+        if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) {
+                pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+                opts->no_bpf_event = true;
+        }
        err = record__synthesize(rec, false);
        if (err < 0)
                goto out_child;
@@ -1466,6 +1496,9 @@ out_child:
 out_delete_session:
        perf_session__delete(session);
+        if (!opts->no_bpf_event)
+                perf_evlist__stop_sb_thread(sb_evlist);
        return status;
 }
@@ -1870,7 +1903,7 @@ static struct option __record_options[] = {
        OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
                    "synthesize non-sample events at the end of output"),
        OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
-        OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"),
+        OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"),
        OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
                    "Fail if the specified frequency can't be used"),
        OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
@@ -1968,9 +2001,11 @@ static struct option __record_options[] = {
        OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
                    "Record timestamp boundary (time of first/last samples)"),
        OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
-                          &record.switch_output.set, "signal,size,time",
+                          &record.switch_output.set, "signal or size[BKMG] or time[smhd]",
-                          "Switch output when receive SIGUSR2 or cross size,time threshold",
+                          "Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold",
                          "signal"),
+        OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files,
+                   "Limit number of switch output generated files"),
        OPT_BOOLEAN(0, "dry-run", &dry_run,
                    "Parse options then exit"),
 #ifdef HAVE_AIO_SUPPORT
@@ -2057,6 +2092,13 @@ int cmd_record(int argc, const char **argv)
                alarm(rec->switch_output.time);
        }
+        if (rec->switch_output.num_files) {
+                rec->switch_output.filenames = calloc(sizeof(char *),
+                                                      rec->switch_output.num_files);
+                if (!rec->switch_output.filenames)
+                        return -EINVAL;
+        }
        /*
         * Allow aliases to facilitate the lookup of symbols for address
         * filters. Refer to auxtrace_parse_filters().
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ee93c18a6685..4054eb1f98ac 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -47,9 +47,11 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
+#include "sane_ctype.h"
 #include <signal.h>
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
+#include <linux/time64.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
@@ -926,6 +928,43 @@ report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
        return parse_callchain_report_opt(arg);
 }
+static int
+parse_time_quantum(const struct option *opt, const char *arg,
+                   int unset __maybe_unused)
+{
+        unsigned long *time_q = opt->value;
+        char *end;
+        *time_q = strtoul(arg, &end, 0);
+        if (end == arg)
+                goto parse_err;
+        if (*time_q == 0) {
+                pr_err("time quantum cannot be 0");
+                return -1;
+        }
+        while (isspace(*end))
+                end++;
+        if (*end == 0)
+                return 0;
+        if (!strcmp(end, "s")) {
+                *time_q *= NSEC_PER_SEC;
+                return 0;
+        }
+        if (!strcmp(end, "ms")) {
+                *time_q *= NSEC_PER_MSEC;
+                return 0;
+        }
+        if (!strcmp(end, "us")) {
+                *time_q *= NSEC_PER_USEC;
+                return 0;
+        }
+        if (!strcmp(end, "ns"))
+                return 0;
+parse_err:
+        pr_err("Cannot parse time quantum `%s'\n", arg);
+        return -1;
+}
 int
 report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
                                const char *arg, int unset __maybe_unused)
@@ -1044,10 +1083,9 @@ int cmd_report(int argc, const char **argv)
        OPT_BOOLEAN(0, "header-only", &report.header_only,
                    "Show only data header."),
        OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-                   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+                   sort_help("sort by key(s):")),
-                   " Please refer the man page for the complete list."),
        OPT_STRING('F', "fields", &field_order, "key[,keys...]",
-                   "output field(s): overhead, period, sample plus all of sort keys"),
+                   sort_help("output field(s): overhead period sample ")),
        OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization,
                    "Show sample percentage for different cpu modes"),
        OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -1120,6 +1158,8 @@ int cmd_report(int argc, const char **argv)
        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
                    "Enable kernel symbol demangling"),
        OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+        OPT_INTEGER(0, "samples", &symbol_conf.res_sample,
+                    "Number of samples to save per histogram entry for individual browsing"),
        OPT_CALLBACK(0, "percent-limit", &report, "percent",
                     "Don't show entries under that percent", parse_percent_limit),
        OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
@@ -1147,6 +1187,10 @@ int cmd_report(int argc, const char **argv)
        OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period",
                     "Set percent type local/global-period/hits",
                     annotate_parse_percent_type),
+        OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"),
+        OPT_CALLBACK(0, "time-quantum", &symbol_conf.time_quantum, "time (ms|us|ns|s)",
+                     "Set time quantum for time sort key (default 100ms)",
+                     parse_time_quantum),
        OPT_END()
        };
        struct perf_data data = {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 53f78cf3113f..61cfd8f70989 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -29,10 +29,12 @@
 #include "util/time-utils.h"
 #include "util/path.h"
 #include "print_binary.h"
+#include "archinsn.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <sys/utsname.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
 #include "util/dump-insn.h"
@@ -51,6 +53,8 @@
 static char const               *script_name;
 static char const               *generate_script_lang;
+static bool                     reltime;
+static u64                      initial_time;
 static bool                     debug_mode;
 static u64                      last_timestamp;
 static u64                      nr_unordered;
@@ -58,11 +62,11 @@ static bool			no_callchain;
 static bool                     latency_format;
 static bool                     system_wide;
 static bool                     print_flags;
-static bool                     nanosecs;
 static const char               *cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config  stat_config;
 static int                      max_blocks;
+static bool                     native_arch;
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
@@ -684,15 +688,21 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
        }
        if (PRINT_FIELD(TIME)) {
-                nsecs = sample->time;
+                u64 t = sample->time;
+                if (reltime) {
+                        if (!initial_time)
+                                initial_time = sample->time;
+                        t = sample->time - initial_time;
+                }
+                nsecs = t;
                secs = nsecs / NSEC_PER_SEC;
                nsecs -= secs * NSEC_PER_SEC;
-                if (nanosecs)
+                if (symbol_conf.nanosecs)
                        printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
                else {
                        char sample_time[32];
-                        timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
+                        timestamp__scnprintf_usec(t, sample_time, sizeof(sample_time));
                        printed += fprintf(fp, "%12s: ", sample_time);
                }
        }
@@ -1227,6 +1237,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
        return len + dlen;
 }
+__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused,
+                            struct thread *thread __maybe_unused,
+                            struct machine *machine __maybe_unused)
+{
+}
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
                                     struct perf_event_attr *attr,
                                     struct thread *thread,
@@ -1234,9 +1250,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 {
        int printed = 0;
+        if (sample->insn_len == 0 && native_arch)
+                arch_fetch_insn(sample, thread, machine);
        if (PRINT_FIELD(INSNLEN))
                printed += fprintf(fp, " ilen: %d", sample->insn_len);
-        if (PRINT_FIELD(INSN)) {
+        if (PRINT_FIELD(INSN) && sample->insn_len) {
                int i;
                printed += fprintf(fp, " insn:");
@@ -1922,6 +1941,13 @@ static int cleanup_scripting(void)
        return scripting_ops ? scripting_ops->stop_script() : 0;
 }
+static bool filter_cpu(struct perf_sample *sample)
+{
+        if (cpu_list)
+                return !test_bit(sample->cpu, cpu_bitmap);
+        return false;
+}
 static int process_sample_event(struct perf_tool *tool,
                                union perf_event *event,
                                struct perf_sample *sample,
@@ -1956,7 +1982,7 @@ static int process_sample_event(struct perf_tool *tool,
        if (al.filtered)
                goto out_put;
-        if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+        if (filter_cpu(sample))
                goto out_put;
        if (scripting_ops)
@@ -2041,9 +2067,11 @@ static int process_comm_event(struct perf_tool *tool,
                sample->tid = event->comm.tid;
                sample->pid = event->comm.pid;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
+                perf_sample__fprintf_start(sample, thread, evsel,
                                   PERF_RECORD_COMM, stdout);
-        perf_event__fprintf(event, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        ret = 0;
 out:
        thread__put(thread);
@@ -2077,9 +2105,11 @@ static int process_namespaces_event(struct perf_tool *tool,
                sample->tid = event->namespaces.tid;
                sample->pid = event->namespaces.pid;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_NAMESPACES, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_NAMESPACES, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        ret = 0;
 out:
        thread__put(thread);
@@ -2111,9 +2141,11 @@ static int process_fork_event(struct perf_tool *tool,
                sample->tid = event->fork.tid;
                sample->pid = event->fork.pid;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_FORK, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_FORK, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        thread__put(thread);
        return 0;
@@ -2141,9 +2173,11 @@ static int process_exit_event(struct perf_tool *tool,
                sample->tid = event->fork.tid;
                sample->pid = event->fork.pid;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_EXIT, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_EXIT, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        if (perf_event__process_exit(tool, event, sample, machine) < 0)
                err = -1;
@@ -2177,9 +2211,11 @@ static int process_mmap_event(struct perf_tool *tool,
                sample->tid = event->mmap.tid;
                sample->pid = event->mmap.pid;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_MMAP, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_MMAP, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        thread__put(thread);
        return 0;
 }
@@ -2209,9 +2245,11 @@ static int process_mmap2_event(struct perf_tool *tool,
                sample->tid = event->mmap2.tid;
                sample->pid = event->mmap2.pid;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_MMAP2, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_MMAP2, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        thread__put(thread);
        return 0;
 }
@@ -2236,9 +2274,11 @@ static int process_switch_event(struct perf_tool *tool,
                return -1;
        }
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_SWITCH, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_SWITCH, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        thread__put(thread);
        return 0;
 }
@@ -2259,9 +2299,11 @@ process_lost_event(struct perf_tool *tool,
        if (thread == NULL)
                return -1;
-        perf_sample__fprintf_start(sample, thread, evsel,
+        if (!filter_cpu(sample)) {
-                                   PERF_RECORD_LOST, stdout);
+                perf_sample__fprintf_start(sample, thread, evsel,
-        perf_event__fprintf(event, stdout);
+                                           PERF_RECORD_LOST, stdout);
+                perf_event__fprintf(event, stdout);
+        }
        thread__put(thread);
        return 0;
 }
@@ -2948,7 +2990,8 @@ static int check_ev_match(char *dir_name, char *scriptname,
 * will list all statically runnable scripts, select one, execute it and
 * show the output in a perf browser.
 */
-int find_scripts(char **scripts_array, char **scripts_path_array)
+int find_scripts(char **scripts_array, char **scripts_path_array, int num,
+                 int pathlen)
 {
        struct dirent *script_dirent, *lang_dirent;
        char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
@@ -2993,7 +3036,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
                        /* Skip those real time scripts: xxxtop.p[yl] */
                        if (strstr(script_dirent->d_name, "top."))
                                continue;
-                        sprintf(scripts_path_array[i], "%s/%s", lang_path,
+                        if (i >= num)
+                                break;
+                        snprintf(scripts_path_array[i], pathlen, "%s/%s",
+                                lang_path,
                                script_dirent->d_name);
                        temp = strchr(script_dirent->d_name, '.');
                        snprintf(scripts_array[i],
@@ -3232,7 +3278,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
 {
        parse_output_fields(NULL, "+insn,-event,-period", 0);
        itrace_parse_synth_opts(opt, "i0ns", 0);
-        nanosecs = true;
+        symbol_conf.nanosecs = true;
        return 0;
 }
@@ -3250,7 +3296,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused,
 {
        parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
        itrace_parse_synth_opts(opt, "cewp", 0);
-        nanosecs = true;
+        symbol_conf.nanosecs = true;
        return 0;
 }
@@ -3260,7 +3306,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused,
 {
        parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
        itrace_parse_synth_opts(opt, "crewp", 0);
-        nanosecs = true;
+        symbol_conf.nanosecs = true;
        return 0;
 }
@@ -3277,6 +3323,7 @@ int cmd_script(int argc, const char **argv)
                .set = false,
                .default_no_sample = true,
        };
+        struct utsname uts;
        char *script_path = NULL;
        const char **__argv;
        int i, j, err = 0;
@@ -3374,6 +3421,7 @@ int cmd_script(int argc, const char **argv)
                     "Set the maximum stack depth when parsing the callchain, "
                     "anything beyond the specified depth will be ignored. "
                     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
+        OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"),
        OPT_BOOLEAN('I', "show-info", &show_full_info,
                    "display extended information from perf.data file"),
        OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
@@ -3395,7 +3443,7 @@ int cmd_script(int argc, const char **argv)
        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"),
-        OPT_BOOLEAN(0, "ns", &nanosecs,
+        OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs,
                    "Use 9 decimal places when displaying time"),
        OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
                            "Instruction Tracing options\n" ITRACE_HELP,
@@ -3448,6 +3496,11 @@ int cmd_script(int argc, const char **argv)
                }
        }
+        if (script.time_str && reltime) {
+                fprintf(stderr, "Don't combine --reltime with --time\n");
+                return -1;
+        }
        if (itrace_synth_opts.callchain &&
            itrace_synth_opts.callchain_sz > scripting_max_stack)
                scripting_max_stack = itrace_synth_opts.callchain_sz;
@@ -3615,6 +3668,12 @@ int cmd_script(int argc, const char **argv)
        if (symbol__init(&session->header.env) < 0)
                goto out_delete;
+        uname(&uts);
+        if (!strcmp(uts.machine, session->header.env.arch) ||
+            (!strcmp(uts.machine, "x86_64") &&
+             !strcmp(session->header.env.arch, "i386")))
+                native_arch = true;
        script.session = session;
        script__setup_sample_type(&script);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7b8f09b0b8bf..49ee3c2033ec 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -718,7 +718,8 @@ static struct option stat_options[] = {
                    "system-wide collection from all CPUs"),
        OPT_BOOLEAN('g', "group", &group,
                    "put the counters into a counter group"),
-        OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+        OPT_BOOLEAN(0, "scale", &stat_config.scale,
+                    "Use --no-scale to disable counter scaling for multiplexing"),
        OPT_INCR('v', "verbose", &verbose,
                    "be more verbose (show counter open errors, etc)"),
        OPT_INTEGER('r', "repeat", &stat_config.run_count,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 231a90daa958..1999d6533d12 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1189,30 +1189,26 @@ static int __cmd_top(struct perf_top *top)
        pthread_t thread, thread_process;
        int ret;
-        top->session = perf_session__new(NULL, false, NULL);
-        if (top->session == NULL)
-                return -1;
        if (!top->annotation_opts.objdump_path) {
                ret = perf_env__lookup_objdump(&top->session->header.env,
                                               &top->annotation_opts.objdump_path);
                if (ret)
-                        goto out_delete;
+                        return ret;
        }
        ret = callchain_param__setup_sample_type(&callchain_param);
        if (ret)
-                goto out_delete;
+                return ret;
        if (perf_session__register_idle_thread(top->session) < 0)
-                goto out_delete;
+                return ret;
        if (top->nr_threads_synthesize > 1)
                perf_set_multithreaded();
        init_process_thread(top);
-        ret = perf_event__synthesize_bpf_events(&top->tool, perf_event__process,
+        ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
                                                &top->session->machines.host,
                                                &top->record_opts);
        if (ret < 0)
@@ -1227,13 +1223,18 @@ static int __cmd_top(struct perf_top *top)
        if (perf_hpp_list.socket) {
                ret = perf_env__read_cpu_topology_map(&perf_env);
-                if (ret < 0)
+                if (ret < 0) {
-                        goto out_err_cpu_topo;
+                        char errbuf[BUFSIZ];
+                        const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
+                        ui__error("Could not read the CPU topology map: %s\n", err);
+                        return ret;
+                }
        }
        ret = perf_top__start_counters(top);
        if (ret)
-                goto out_delete;
+                return ret;
        top->session->evlist = top->evlist;
        perf_session__set_id_hdr_size(top->session);
@@ -1252,7 +1253,7 @@ static int __cmd_top(struct perf_top *top)
        ret = -1;
        if (pthread_create(&thread_process, NULL, process_thread, top)) {
                ui__error("Could not create process thread.\n");
-                goto out_delete;
+                return ret;
        }
        if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
@@ -1296,19 +1297,7 @@ out_join:
 out_join_thread:
        pthread_cond_signal(&top->qe.cond);
        pthread_join(thread_process, NULL);
-out_delete:
-        perf_session__delete(top->session);
-        top->session = NULL;
        return ret;
-out_err_cpu_topo: {
-        char errbuf[BUFSIZ];
-        const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
-        ui__error("Could not read the CPU topology map: %s\n", err);
-        goto out_delete;
-}
 }
 static int
@@ -1480,6 +1469,7 @@ int cmd_top(int argc, const char **argv)
                    "Display raw encoding of assembly instructions (default)"),
        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
                    "Enable kernel symbol demangling"),
+        OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"),
        OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path",
                    "objdump binary to use for disassembly and annotations"),
        OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style",
@@ -1511,6 +1501,7 @@ int cmd_top(int argc, const char **argv)
                        "number of thread to run event synthesize"),
        OPT_END()
        };
+        struct perf_evlist *sb_evlist = NULL;
        const char * const top_usage[] = {
                "perf top [<options>]",
                NULL
@@ -1628,8 +1619,9 @@ int cmd_top(int argc, const char **argv)
        annotation_config__init();
        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-        if (symbol__init(NULL) < 0)
+        status = symbol__init(NULL);
-                return -1;
+        if (status < 0)
+                goto out_delete_evlist;
        sort__setup_elide(stdout);
@@ -1639,10 +1631,28 @@ int cmd_top(int argc, const char **argv)
                signal(SIGWINCH, winch_sig);
        }
+        top.session = perf_session__new(NULL, false, NULL);
+        if (top.session == NULL) {
+                status = -1;
+                goto out_delete_evlist;
+        }
+        if (!top.record_opts.no_bpf_event)
+                bpf_event__add_sb_event(&sb_evlist, &perf_env);
+        if (perf_evlist__start_sb_thread(sb_evlist, target)) {
+                pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+                opts->no_bpf_event = true;
+        }
        status = __cmd_top(&top);
+        if (!opts->no_bpf_event)
+                perf_evlist__stop_sb_thread(sb_evlist);
 out_delete_evlist:
        perf_evlist__delete(top.evlist);
+        perf_session__delete(top.session);
        return status;
 }
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 05745f3ce912..999fe9170122 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -40,5 +40,6 @@ int cmd_mem(int argc, const char **argv);
 int cmd_data(int argc, const char **argv);
 int cmd_ftrace(int argc, const char **argv);
-int find_scripts(char **scripts_array, char **scripts_path_array);
+int find_scripts(char **scripts_array, char **scripts_path_array, int num,
+                 int pathlen);
 #endif
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index a11cb006f968..72df4b6fa36f 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -298,6 +298,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
                use_pager = 1;
        commit_pager_choice();
+        perf_env__init(&perf_env);
        perf_env__set_cmdline(&perf_env, argc, argv);
        status = p->fn(argc, argv);
        perf_config__exit();
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b120e547ddc7..c59743def8d3 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -66,7 +66,7 @@ struct record_opts {
        bool         ignore_missing_thread;
        bool         strict_freq;
        bool         sample_id;
-        bool         bpf_event;
+        bool         no_bpf_event;
        unsigned int freq;
        unsigned int mmap_pages;
        unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json
index 704302c3e67d..9dc2f6b70354 100644
--- a/tools/perf/pmu-events/arch/powerpc/power8/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json
@@ -348,18 +348,6 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x517082",
-    "EventName": "PM_CO_DISP_FAIL",
-    "BriefDescription": "CO dispatch failed due to all CO machines being busy",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x527084",
-    "EventName": "PM_CO_TM_SC_FOOTPRINT",
-    "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3)",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x3608a",
    "EventName": "PM_CO_USAGE",
    "BriefDescription": "Continuous 16 cycle(2to1) window where this signals rotates thru sampling each L2 CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running",
@@ -1578,36 +1566,12 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x617082",
-    "EventName": "PM_ISIDE_DISP",
-    "BriefDescription": "All i-side dispatch attempts",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x627084",
-    "EventName": "PM_ISIDE_DISP_FAIL",
-    "BriefDescription": "All i-side dispatch attempts that failed due to a addr collision with another machine",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x627086",
-    "EventName": "PM_ISIDE_DISP_FAIL_OTHER",
-    "BriefDescription": "All i-side dispatch attempts that failed due to a reason other than addrs collision",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x4608e",
    "EventName": "PM_ISIDE_L2MEMACC",
    "BriefDescription": "valid when first beat of data comes in for an i-side fetch where data came from mem(or L4)",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x44608e",
-    "EventName": "PM_ISIDE_MRU_TOUCH",
-    "BriefDescription": "Iside L2 MRU touch",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x30ac",
    "EventName": "PM_ISU_REF_FX0",
    "BriefDescription": "FX0 ISU reject",
@@ -1734,222 +1698,36 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x417080",
-    "EventName": "PM_L2_CASTOUT_MOD",
-    "BriefDescription": "L2 Castouts - Modified (M, Mu, Me)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x417082",
-    "EventName": "PM_L2_CASTOUT_SHR",
-    "BriefDescription": "L2 Castouts - Shared (T, Te, Si, S)",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x27084",
    "EventName": "PM_L2_CHIP_PUMP",
    "BriefDescription": "RC requests that were local on chip pump attempts",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x427086",
-    "EventName": "PM_L2_DC_INV",
-    "BriefDescription": "Dcache invalidates from L2",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x44608c",
-    "EventName": "PM_L2_DISP_ALL_L2MISS",
-    "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2miss",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x27086",
    "EventName": "PM_L2_GROUP_PUMP",
    "BriefDescription": "RC requests that were on Node Pump attempts",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x626084",
-    "EventName": "PM_L2_GRP_GUESS_CORRECT",
-    "BriefDescription": "L2 guess grp and guess was correct (data intra-6chip AND ^on-chip)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x626086",
-    "EventName": "PM_L2_GRP_GUESS_WRONG",
-    "BriefDescription": "L2 guess grp and guess was not correct (ie data on-chip OR beyond-6chip)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x427084",
-    "EventName": "PM_L2_IC_INV",
-    "BriefDescription": "Icache Invalidates from L2",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x436088",
-    "EventName": "PM_L2_INST",
-    "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x43608a",
-    "EventName": "PM_L2_INST_MISS",
-    "BriefDescription": "All successful i-side dispatches that were an L2miss for this thread (excludes i_l2mru_tch reqs)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x416080",
-    "EventName": "PM_L2_LD",
-    "BriefDescription": "All successful D-side Load dispatches for this thread",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x437088",
-    "EventName": "PM_L2_LD_DISP",
-    "BriefDescription": "All successful load dispatches",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x43708a",
-    "EventName": "PM_L2_LD_HIT",
-    "BriefDescription": "All successful load dispatches that were L2 hits",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x426084",
-    "EventName": "PM_L2_LD_MISS",
-    "BriefDescription": "All successful D-Side Load dispatches that were an L2miss for this thread",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x616080",
-    "EventName": "PM_L2_LOC_GUESS_CORRECT",
-    "BriefDescription": "L2 guess loc and guess was correct (ie data local)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x616082",
-    "EventName": "PM_L2_LOC_GUESS_WRONG",
-    "BriefDescription": "L2 guess loc and guess was not correct (ie data not on chip)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x516080",
-    "EventName": "PM_L2_RCLD_DISP",
-    "BriefDescription": "L2 RC load dispatch attempt",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x516082",
-    "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR",
-    "BriefDescription": "L2 RC load dispatch attempt failed due to address collision with RC/CO/SN/SQ",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x526084",
-    "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER",
-    "BriefDescription": "L2 RC load dispatch attempt failed due to other reasons",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x536088",
-    "EventName": "PM_L2_RCST_DISP",
-    "BriefDescription": "L2 RC store dispatch attempt",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x53608a",
-    "EventName": "PM_L2_RCST_DISP_FAIL_ADDR",
-    "BriefDescription": "L2 RC store dispatch attempt failed due to address collision with RC/CO/SN/SQ",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x54608c",
-    "EventName": "PM_L2_RCST_DISP_FAIL_OTHER",
-    "BriefDescription": "L2 RC store dispatch attempt failed due to other reasons",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x537088",
-    "EventName": "PM_L2_RC_ST_DONE",
-    "BriefDescription": "RC did st to line that was Tx or Sx",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x63708a",
-    "EventName": "PM_L2_RTY_LD",
-    "BriefDescription": "RC retries on PB for any load from core",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x3708a",
    "EventName": "PM_L2_RTY_ST",
    "BriefDescription": "RC retries on PB for any store from core",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x54708c",
-    "EventName": "PM_L2_SN_M_RD_DONE",
-    "BriefDescription": "SNP dispatched for a read and was M",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x54708e",
-    "EventName": "PM_L2_SN_M_WR_DONE",
-    "BriefDescription": "SNP dispatched for a write and was M",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x53708a",
-    "EventName": "PM_L2_SN_SX_I_DONE",
-    "BriefDescription": "SNP dispatched and went from Sx or Tx to Ix",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x17080",
    "EventName": "PM_L2_ST",
    "BriefDescription": "All successful D-side store dispatches for this thread",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x44708c",
-    "EventName": "PM_L2_ST_DISP",
-    "BriefDescription": "All successful store dispatches",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x44708e",
-    "EventName": "PM_L2_ST_HIT",
-    "BriefDescription": "All successful store dispatches that were L2Hits",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x17082",
    "EventName": "PM_L2_ST_MISS",
    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 Miss",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x636088",
-    "EventName": "PM_L2_SYS_GUESS_CORRECT",
-    "BriefDescription": "L2 guess sys and guess was correct (ie data beyond-6chip)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x63608a",
-    "EventName": "PM_L2_SYS_GUESS_WRONG",
-    "BriefDescription": "L2 guess sys and guess was not correct (ie data ^beyond-6chip)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x617080",
-    "EventName": "PM_L2_SYS_PUMP",
-    "BriefDescription": "RC requests that were system pump attempts",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x1e05e",
    "EventName": "PM_L2_TM_REQ_ABORT",
    "BriefDescription": "TM abort",
@@ -1962,36 +1740,12 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x23808a",
-    "EventName": "PM_L3_CINJ",
-    "BriefDescription": "l3 ci of cache inject",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x128084",
-    "EventName": "PM_L3_CI_HIT",
-    "BriefDescription": "L3 Castins Hit (total count",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x128086",
-    "EventName": "PM_L3_CI_MISS",
-    "BriefDescription": "L3 castins miss (total count",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x819082",
    "EventName": "PM_L3_CI_USAGE",
    "BriefDescription": "rotating sample of 16 CI or CO actives",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x438088",
-    "EventName": "PM_L3_CO",
-    "BriefDescription": "l3 castout occurring ( does not include casthrough or log writes (cinj/dmaw)",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x83908b",
    "EventName": "PM_L3_CO0_ALLOC",
    "BriefDescription": "lifetime, sample of CO machine 0 valid",
@@ -2010,120 +1764,18 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x238088",
-    "EventName": "PM_L3_CO_LCO",
-    "BriefDescription": "Total L3 castouts occurred on LCO",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x28084",
    "EventName": "PM_L3_CO_MEM",
    "BriefDescription": "L3 CO to memory OR of port 0 and 1 ( lossy)",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0xb19082",
-    "EventName": "PM_L3_GRP_GUESS_CORRECT",
-    "BriefDescription": "Initial scope=group and data from same group (near) (pred successful)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xb3908a",
-    "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH",
-    "BriefDescription": "Initial scope=group but data from local node. Predition too high",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xb39088",
-    "EventName": "PM_L3_GRP_GUESS_WRONG_LOW",
-    "BriefDescription": "Initial scope=group but data from outside group (far or rem). Prediction too Low",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x218080",
-    "EventName": "PM_L3_HIT",
-    "BriefDescription": "L3 Hits",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x138088",
-    "EventName": "PM_L3_L2_CO_HIT",
-    "BriefDescription": "L2 castout hits",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x13808a",
-    "EventName": "PM_L3_L2_CO_MISS",
-    "BriefDescription": "L2 castout miss",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x14808c",
-    "EventName": "PM_L3_LAT_CI_HIT",
-    "BriefDescription": "L3 Lateral Castins Hit",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x14808e",
-    "EventName": "PM_L3_LAT_CI_MISS",
-    "BriefDescription": "L3 Lateral Castins Miss",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x228084",
-    "EventName": "PM_L3_LD_HIT",
-    "BriefDescription": "L3 demand LD Hits",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x228086",
-    "EventName": "PM_L3_LD_MISS",
-    "BriefDescription": "L3 demand LD Miss",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x1e052",
    "EventName": "PM_L3_LD_PREF",
    "BriefDescription": "L3 Load Prefetches",
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0xb19080",
-    "EventName": "PM_L3_LOC_GUESS_CORRECT",
-    "BriefDescription": "initial scope=node/chip and data from local node (local) (pred successful)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xb29086",
-    "EventName": "PM_L3_LOC_GUESS_WRONG",
-    "BriefDescription": "Initial scope=node but data from out side local node (near or far or rem). Prediction too Low",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x218082",
-    "EventName": "PM_L3_MISS",
-    "BriefDescription": "L3 Misses",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x54808c",
-    "EventName": "PM_L3_P0_CO_L31",
-    "BriefDescription": "l3 CO to L3.1 (lco) port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x538088",
-    "EventName": "PM_L3_P0_CO_MEM",
-    "BriefDescription": "l3 CO to memory port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x929084",
-    "EventName": "PM_L3_P0_CO_RTY",
-    "BriefDescription": "L3 CO received retry port 0",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0xa29084",
    "EventName": "PM_L3_P0_GRP_PUMP",
    "BriefDescription": "L3 pf sent with grp scope port 0",
@@ -2148,120 +1800,6 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0xa19080",
-    "EventName": "PM_L3_P0_NODE_PUMP",
-    "BriefDescription": "L3 pf sent with nodal scope port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x919080",
-    "EventName": "PM_L3_P0_PF_RTY",
-    "BriefDescription": "L3 PF received retry port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x939088",
-    "EventName": "PM_L3_P0_SN_HIT",
-    "BriefDescription": "L3 snoop hit port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x118080",
-    "EventName": "PM_L3_P0_SN_INV",
-    "BriefDescription": "Port0 snooper detects someone doing a store to a line thats Sx",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x94908c",
-    "EventName": "PM_L3_P0_SN_MISS",
-    "BriefDescription": "L3 snoop miss port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xa39088",
-    "EventName": "PM_L3_P0_SYS_PUMP",
-    "BriefDescription": "L3 pf sent with sys scope port 0",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x54808e",
-    "EventName": "PM_L3_P1_CO_L31",
-    "BriefDescription": "l3 CO to L3.1 (lco) port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x53808a",
-    "EventName": "PM_L3_P1_CO_MEM",
-    "BriefDescription": "l3 CO to memory port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x929086",
-    "EventName": "PM_L3_P1_CO_RTY",
-    "BriefDescription": "L3 CO received retry port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xa29086",
-    "EventName": "PM_L3_P1_GRP_PUMP",
-    "BriefDescription": "L3 pf sent with grp scope port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x528086",
-    "EventName": "PM_L3_P1_LCO_DATA",
-    "BriefDescription": "lco sent with data port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x518082",
-    "EventName": "PM_L3_P1_LCO_NO_DATA",
-    "BriefDescription": "dataless l3 lco sent port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xa4908e",
-    "EventName": "PM_L3_P1_LCO_RTY",
-    "BriefDescription": "L3 LCO received retry port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xa19082",
-    "EventName": "PM_L3_P1_NODE_PUMP",
-    "BriefDescription": "L3 pf sent with nodal scope port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x919082",
-    "EventName": "PM_L3_P1_PF_RTY",
-    "BriefDescription": "L3 PF received retry port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x93908a",
-    "EventName": "PM_L3_P1_SN_HIT",
-    "BriefDescription": "L3 snoop hit port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x118082",
-    "EventName": "PM_L3_P1_SN_INV",
-    "BriefDescription": "Port1 snooper detects someone doing a store to a line thats Sx",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x94908e",
-    "EventName": "PM_L3_P1_SN_MISS",
-    "BriefDescription": "L3 snoop miss port 1",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xa3908a",
-    "EventName": "PM_L3_P1_SYS_PUMP",
-    "BriefDescription": "L3 pf sent with sys scope port 1",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x84908d",
    "EventName": "PM_L3_PF0_ALLOC",
    "BriefDescription": "lifetime, sample of PF machine 0 valid",
@@ -2274,12 +1812,6 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x428084",
-    "EventName": "PM_L3_PF_HIT_L3",
-    "BriefDescription": "l3 pf hit in l3",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x18080",
    "EventName": "PM_L3_PF_MISS_L3",
    "BriefDescription": "L3 Prefetch missed in L3",
@@ -2370,42 +1902,12 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0xb29084",
-    "EventName": "PM_L3_SYS_GUESS_CORRECT",
-    "BriefDescription": "Initial scope=system and data from outside group (far or rem)(pred successful)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0xb4908c",
-    "EventName": "PM_L3_SYS_GUESS_WRONG",
-    "BriefDescription": "Initial scope=system but data from local or near. Predction too high",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x24808e",
-    "EventName": "PM_L3_TRANS_PF",
-    "BriefDescription": "L3 Transient prefetch",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x18081",
    "EventName": "PM_L3_WI0_ALLOC",
    "BriefDescription": "lifetime, sample of Write Inject machine 0 valid",
    "PublicDescription": "0.0"
  },
  {,
-    "EventCode": "0x418080",
-    "EventName": "PM_L3_WI0_BUSY",
-    "BriefDescription": "lifetime, sample of Write Inject machine 0 valid",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x418082",
-    "EventName": "PM_L3_WI_USAGE",
-    "BriefDescription": "rotating sample of 8 WI actives",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0xc080",
    "EventName": "PM_LD_REF_L1_LSU0",
    "BriefDescription": "LS0 L1 D cache load references counted at finish, gated by reject",
@@ -3312,12 +2814,6 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x328084",
-    "EventName": "PM_NON_TM_RST_SC",
-    "BriefDescription": "non tm snp rst tm sc",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x2001a",
    "EventName": "PM_NTCG_ALL_FIN",
    "BriefDescription": "Cycles after all instructions have finished to group completed",
@@ -3420,24 +2916,6 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x34808e",
-    "EventName": "PM_RD_CLEARING_SC",
-    "BriefDescription": "rd clearing sc",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x34808c",
-    "EventName": "PM_RD_FORMING_SC",
-    "BriefDescription": "rd forming sc",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x428086",
-    "EventName": "PM_RD_HIT_PF",
-    "BriefDescription": "rd machine hit l3 pf machine",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x20004",
    "EventName": "PM_REAL_SRQ_FULL",
    "BriefDescription": "Out of real srq entries",
@@ -3504,18 +2982,6 @@
    "PublicDescription": "TLBIE snoopSnoop TLBIE"
  },
  {,
-    "EventCode": "0x338088",
-    "EventName": "PM_SNP_TM_HIT_M",
-    "BriefDescription": "snp tm st hit m mu",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x33808a",
-    "EventName": "PM_SNP_TM_HIT_T",
-    "BriefDescription": "snp tm_st_hit t tn te",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x4608c",
    "EventName": "PM_SN_USAGE",
    "BriefDescription": "Continuous 16 cycle(2to1) window where this signals rotates thru sampling each L2 SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running",
@@ -3534,12 +3000,6 @@
    "PublicDescription": "STCX executed reported at sent to nest42"
  },
  {,
-    "EventCode": "0x717080",
-    "EventName": "PM_ST_CAUSED_FAIL",
-    "BriefDescription": "Non TM St caused any thread to fail",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x3090",
    "EventName": "PM_SWAP_CANCEL",
    "BriefDescription": "SWAP cancel , rtag not available",
@@ -3624,18 +3084,6 @@
    "PublicDescription": ""
  },
  {,
-    "EventCode": "0x318082",
-    "EventName": "PM_TM_CAM_OVERFLOW",
-    "BriefDescription": "l3 tm cam overflow during L2 co of SC",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x74708c",
-    "EventName": "PM_TM_CAP_OVERFLOW",
-    "BriefDescription": "TM Footprint Capactiy Overflow",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x20ba",
    "EventName": "PM_TM_END_ALL",
    "BriefDescription": "Tm any tend",
@@ -3690,48 +3138,6 @@
    "PublicDescription": "Transactional conflict from LSU, whatever gets reported to texas 42"
  },
  {,
-    "EventCode": "0x727086",
-    "EventName": "PM_TM_FAV_CAUSED_FAIL",
-    "BriefDescription": "TM Load (fav) caused another thread to fail",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x717082",
-    "EventName": "PM_TM_LD_CAUSED_FAIL",
-    "BriefDescription": "Non TM Ld caused any thread to fail",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x727084",
-    "EventName": "PM_TM_LD_CONF",
-    "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x328086",
-    "EventName": "PM_TM_RST_SC",
-    "BriefDescription": "tm snp rst tm sc",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x318080",
-    "EventName": "PM_TM_SC_CO",
-    "BriefDescription": "l3 castout tm Sc line",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x73708a",
-    "EventName": "PM_TM_ST_CAUSED_FAIL",
-    "BriefDescription": "TM Store (fav or non-fav) caused another thread to fail",
-    "PublicDescription": ""
-  },
-  {,
-    "EventCode": "0x737088",
-    "EventName": "PM_TM_ST_CONF",
-    "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)",
-    "PublicDescription": ""
-  },
-  {,
    "EventCode": "0x20bc",
    "EventName": "PM_TM_TBEGIN",
    "BriefDescription": "Tm nested tbegin",
diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json b/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json
new file mode 100644
index 000000000000..93ddfd8053ca
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json
@@ -0,0 +1,12 @@
+[
+  {
+    "EventName": "bp_l1_btb_correct",
+    "EventCode": "0x8a",
+    "BriefDescription": "L1 BTB Correction."
+  },
+  {
+    "EventName": "bp_l2_btb_correct",
+    "EventCode": "0x8b",
+    "BriefDescription": "L2 BTB Correction."
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json
new file mode 100644
index 000000000000..fad4af9142cb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json
@@ -0,0 +1,287 @@
+[
+  {
+    "EventName": "ic_fw32",
+    "EventCode": "0x80",
+    "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)."
+  },
+  {
+    "EventName": "ic_fw32_miss",
+    "EventCode": "0x81",
+    "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag."
+  },
+  {
+    "EventName": "ic_cache_fill_l2",
+    "EventCode": "0x82",
+    "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache."
+  },
+  {
+    "EventName": "ic_cache_fill_sys",
+    "EventCode": "0x83",
+    "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache."
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_hit",
+    "EventCode": "0x84",
+    "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB."
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_miss",
+    "EventCode": "0x85",
+    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs."
+  },
+  {
+    "EventName": "bp_snp_re_sync",
+    "EventCode": "0x86",
+    "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event."
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_any",
+    "EventCode": "0x87",
+    "BriefDescription": "IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).",
+    "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_dq_empty",
+    "EventCode": "0x87",
+    "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.",
+    "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_back_pressure",
+    "EventCode": "0x87",
+    "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.",
+    "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ic_cache_inval.l2_invalidating_probe",
+    "EventCode": "0x8c",
+    "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS).",
+    "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to L2 invalidating probe (external or LS).",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_cache_inval.fill_invalidated",
+    "EventCode": "0x8c",
+    "BriefDescription": "IC line invalidated due to overwriting fill response.",
+    "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to overwriting fill response.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "bp_tlb_rel",
+    "EventCode": "0x99",
+    "BriefDescription": "The number of ITLB reload requests."
+  },
+  {
+    "EventName": "l2_request_g1.rd_blk_l",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_request_g1.rd_blk_x",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_request_g1.ls_rd_blk_c_s",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_request_g1.cacheable_ic_read",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_request_g1.change_to_x",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_request_g1.prefetch_l2",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_request_g1.l2_hw_pf",
+    "EventCode": "0x60",
+    "BriefDescription": "Requests to L2 Group1.",
+    "PublicDescription": "Requests to L2 Group1.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_request_g1.other_requests",
+    "EventCode": "0x60",
+    "BriefDescription": "Events covered by l2_request_g2.",
+    "PublicDescription": "Requests to L2 Group1. Events covered by l2_request_g2.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_request_g2.group1",
+    "EventCode": "0x61",
+    "BriefDescription": "All Group 1 commands not in unit0.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. All Group 1 commands not in unit0.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_request_g2.ls_rd_sized",
+    "EventCode": "0x61",
+    "BriefDescription": "RdSized, RdSized32, RdSized64.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSized, RdSized32, RdSized64.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_request_g2.ls_rd_sized_nc",
+    "EventCode": "0x61",
+    "BriefDescription": "RdSizedNC, RdSized32NC, RdSized64NC.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSizedNC, RdSized32NC, RdSized64NC.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_request_g2.ic_rd_sized",
+    "EventCode": "0x61",
+    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_request_g2.ic_rd_sized_nc",
+    "EventCode": "0x61",
+    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_request_g2.smc_inval",
+    "EventCode": "0x61",
+    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_request_g2.bus_locks_originator",
+    "EventCode": "0x61",
+    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_request_g2.bus_locks_responses",
+    "EventCode": "0x61",
+    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_latency.l2_cycles_waiting_on_fills",
+    "EventCode": "0x62",
+    "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.",
+    "PublicDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_wcb_req.wcb_write",
+    "EventCode": "0x63",
+    "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.",
+    "BriefDescription": "LS to L2 WCB write requests.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_wcb_req.wcb_close",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB close requests.",
+    "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_wcb_req.zero_byte_store",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB zero byte store requests.",
+    "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_wcb_req.cl_zero",
+    "EventCode": "0x63",
+    "PublicDescription": "LS to L2 WCB cache line zeroing requests.",
+    "BriefDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_cs",
+    "EventCode": "0x64",
+    "BriefDescription": "LS ReadBlock C/S Hit.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS ReadBlock C/S Hit.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x",
+    "EventCode": "0x64",
+    "BriefDescription": "LS Read Block L Hit X.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block L Hit X.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s",
+    "EventCode": "0x64",
+    "BriefDescription": "LsRdBlkL Hit Shared.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkL Hit Shared.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_x",
+    "EventCode": "0x64",
+    "BriefDescription": "LsRdBlkX/ChgToX Hit X.  Count RdBlkX finding Shared as a Miss.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkX/ChgToX Hit X.  Count RdBlkX finding Shared as a Miss.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_c",
+    "EventCode": "0x64",
+    "BriefDescription": "LS Read Block C S L X Change to X Miss.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block C S L X Change to X Miss.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_hit_x",
+    "EventCode": "0x64",
+    "BriefDescription": "IC Fill Hit Exclusive Stale.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Exclusive Stale.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_hit_s",
+    "EventCode": "0x64",
+    "BriefDescription": "IC Fill Hit Shared.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Shared.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_miss",
+    "EventCode": "0x64",
+    "BriefDescription": "IC Fill Miss.",
+    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Miss.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_fill_pending.l2_fill_busy",
+    "EventCode": "0x6d",
+    "BriefDescription": "Total cycles spent with one or more fill requests in flight from L2.",
+    "PublicDescription": "Total cycles spent with one or more fill requests in flight from L2.",
+    "UMask": "0x1"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json
new file mode 100644
index 000000000000..7b285b0a7f35
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json
@@ -0,0 +1,134 @@
+[
+  {
+    "EventName": "ex_ret_instr",
+    "EventCode": "0xc0",
+    "BriefDescription": "Retired Instructions."
+  },
+  {
+    "EventName": "ex_ret_cops",
+    "EventCode": "0xc1",
+    "BriefDescription": "Retired Uops.",
+    "PublicDescription": "The number of uOps retired. This includes all processor activity (instructions, exceptions, interrupts, microcode assists, etc.). The number of events logged per cycle can vary from 0 to 4."
+  },
+  {
+    "EventName": "ex_ret_brn",
+    "EventCode": "0xc2",
+    "BriefDescription": "[Retired Branch Instructions.",
+    "PublicDescription": "The number of branch instructions retired. This includes all types of architectural control flow changes, including exceptions and interrupts."
+  },
+  {
+    "EventName": "ex_ret_brn_misp",
+    "EventCode": "0xc3",
+    "BriefDescription": "Retired Branch Instructions Mispredicted.",
+    "PublicDescription": "The number of branch instructions retired, of any type, that were not correctly predicted. This includes those for which prediction is not attempted (far control transfers, exceptions and interrupts)."
+  },
+  {
+    "EventName": "ex_ret_brn_tkn",
+    "EventCode": "0xc4",
+    "BriefDescription": "Retired Taken Branch Instructions.",
+    "PublicDescription": "The number of taken branches that were retired. This includes all types of architectural control flow changes, including exceptions and interrupts."
+  },
+  {
+    "EventName": "ex_ret_brn_tkn_misp",
+    "EventCode": "0xc5",
+    "BriefDescription": "Retired Taken Branch Instructions Mispredicted.",
+    "PublicDescription": "The number of retired taken branch instructions that were mispredicted."
+  },
+  {
+    "EventName": "ex_ret_brn_far",
+    "EventCode": "0xc6",
+    "BriefDescription": "Retired Far Control Transfers.",
+    "PublicDescription": "The number of far control transfers retired including far call/jump/return, IRET, SYSCALL and SYSRET, plus exceptions and interrupts. Far control transfers are not subject to branch prediction."
+  },
+  {
+    "EventName": "ex_ret_brn_resync",
+    "EventCode": "0xc7",
+    "BriefDescription": "Retired Branch Resyncs.",
+    "PublicDescription": "The number of resync branches. These reflect pipeline restarts due to certain microcode assists and events such as writes to the active instruction stream, among other things. Each occurrence reflects a restart penalty similar to a branch mispredict. This is relatively rare."
+  },
+  {
+    "EventName": "ex_ret_near_ret",
+    "EventCode": "0xc8",
+    "BriefDescription": "Retired Near Returns.",
+    "PublicDescription": "The number of near return instructions (RET or RET Iw) retired."
+  },
+  {
+    "EventName": "ex_ret_near_ret_mispred",
+    "EventCode": "0xc9",
+    "BriefDescription": "Retired Near Returns Mispredicted.",
+    "PublicDescription": "The number of near returns retired that were not correctly predicted by the return address predictor. Each such mispredict incurs the same penalty as a mispredicted conditional branch instruction."
+  },
+  {
+    "EventName": "ex_ret_brn_ind_misp",
+    "EventCode": "0xca",
+    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.",
+    "PublicDescription": "Retired Indirect Branch Instructions Mispredicted."
+  },
+  {
+    "EventName": "ex_ret_mmx_fp_instr.sse_instr",
+    "EventCode": "0xcb",
+    "BriefDescription": "SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).",
+    "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ex_ret_mmx_fp_instr.mmx_instr",
+    "EventCode": "0xcb",
+    "BriefDescription": "MMX instructions.",
+    "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. MMX instructions.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ex_ret_mmx_fp_instr.x87_instr",
+    "EventCode": "0xcb",
+    "BriefDescription": "x87 instructions.",
+    "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. x87 instructions.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ex_ret_cond",
+    "EventCode": "0xd1",
+    "BriefDescription": "Retired Conditional Branch Instructions."
+  },
+  {
+    "EventName": "ex_ret_cond_misp",
+    "EventCode": "0xd2",
+    "BriefDescription": "Retired Conditional Branch Instructions Mispredicted."
+  },
+  {
+    "EventName": "ex_div_busy",
+    "EventCode": "0xd3",
+    "BriefDescription": "Div Cycles Busy count."
+  },
+  {
+    "EventName": "ex_div_count",
+    "EventCode": "0xd4",
+    "BriefDescription": "Div Op Count."
+  },
+  {
+    "EventName": "ex_tagged_ibs_ops.ibs_count_rollover",
+    "EventCode": "0x1cf",
+    "BriefDescription": "Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.",
+    "PublicDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret",
+    "EventCode": "0x1cf",
+    "BriefDescription": "Number of Ops tagged by IBS that retired.",
+    "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops",
+    "EventCode": "0x1cf",
+    "BriefDescription": "Number of Ops tagged by IBS.",
+    "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ex_ret_fus_brnch_inst",
+    "EventCode": "0x1d0",
+    "BriefDescription": "The number of fused retired branch instructions retired per cycle. The number of events logged per cycle can vary from 0 to 3."
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json b/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json
new file mode 100644
index 000000000000..ea4711983d1d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json
@@ -0,0 +1,168 @@
+[
+  {
+    "EventName": "fpu_pipe_assignment.dual",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number multi-pipe uOps.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to Pipe 3.",
+    "UMask": "0xf0"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number uOps.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to Pipe 3.",
+    "UMask": "0xf"
+  },
+  {
+    "EventName": "fp_sched_empty",
+    "EventCode": "0x01",
+    "BriefDescription": "This is a speculative event. The number of cycles in which the FPU scheduler is empty. Note that some Ops like FP loads bypass the scheduler."
+  },
+  {
+    "EventName": "fp_retx87_fp_ops.all",
+    "EventCode": "0x02",
+    "BriefDescription": "All Ops.",
+    "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8.",
+    "UMask": "0x7"
+  },
+  {
+    "EventName": "fp_retx87_fp_ops.div_sqr_r_ops",
+    "EventCode": "0x02",
+    "BriefDescription": "Divide and square root Ops.",
+    "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Divide and square root Ops.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_retx87_fp_ops.mul_ops",
+    "EventCode": "0x02",
+    "BriefDescription": "Multiply Ops.",
+    "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Multiply Ops.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_retx87_fp_ops.add_sub_ops",
+    "EventCode": "0x02",
+    "BriefDescription": "Add/subtract Ops.",
+    "PublicDescription": "The number of x87 floating-point Ops that have retired. The number of events logged per cycle can vary from 0 to 8. Add/subtract Ops.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.all",
+    "EventCode": "0x03",
+    "BriefDescription": "All FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.dp_mult_add_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.dp_div_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Double precision divide/square root FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision divide/square root FLOPS.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.dp_mult_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Double precision multiply FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision multiply FLOPS.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.dp_add_sub_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Double precision add/subtract FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Double precision add/subtract FLOPS.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.sp_mult_add_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single precision multiply-add FLOPS. Multiply-add counts as 2 FLOPS.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.sp_div_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Single-precision divide/square root FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision divide/square root FLOPS.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.sp_mult_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Single-precision multiply FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision multiply FLOPS.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.sp_add_sub_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Single-precision add/subtract FLOPS.",
+    "PublicDescription": "This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15. Single-precision add/subtract FLOPS.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.optimized",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of Scalar Ops optimized.",
+    "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of Scalar Ops optimized.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.opt_potential",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of Ops that are candidates for optimization (have Z-bit either set or pass).",
+    "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of Ops that are candidates for optimization (have Z-bit either set or pass).",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops_elim",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of SSE Move Ops eliminated.",
+    "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of SSE Move Ops eliminated.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of SSE Move Ops.",
+    "PublicDescription": "This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number of SSE Move Ops.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.x87_ctrl_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits.",
+    "PublicDescription": "The number of serializing Ops retired. x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.x87_bot_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "x87 bottom-executing uOps retired.",
+    "PublicDescription": "The number of serializing Ops retired. x87 bottom-executing uOps retired.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.sse_ctrl_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.",
+    "PublicDescription": "The number of serializing Ops retired. SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.sse_bot_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "SSE bottom-executing uOps retired.",
+    "PublicDescription": "The number of serializing Ops retired. SSE bottom-executing uOps retired.",
+    "UMask": "0x1"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json b/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json
new file mode 100644
index 000000000000..fa2d60d4def0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json
@@ -0,0 +1,162 @@
+[
+  {
+    "EventName": "ls_locks.bus_lock",
+    "EventCode": "0x25",
+    "BriefDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.",
+    "PublicDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_dispatch.ld_st_dispatch",
+    "EventCode": "0x29",
+    "BriefDescription": "Load-op-Stores.",
+    "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_dispatch.store_dispatch",
+    "EventCode": "0x29",
+    "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_dispatch.ld_dispatch",
+    "EventCode": "0x29",
+    "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_stlf",
+    "EventCode": "0x35",
+    "BriefDescription": "Number of STLF hits."
+  },
+  {
+    "EventName": "ls_dc_accesses",
+    "EventCode": "0x40",
+    "BriefDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event."
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.all",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss or Reload off all sizes.",
+    "PublicDescription": "L1 DTLB Miss or Reload off all sizes.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss of a page of 1G size.",
+    "PublicDescription": "L1 DTLB Miss of a page of 1G size.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss of a page of 2M size.",
+    "PublicDescription": "L1 DTLB Miss of a page of 2M size.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss of a page of 32K size.",
+    "PublicDescription": "L1 DTLB Miss of a page of 32K size.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss of a page of 4K size.",
+    "PublicDescription": "L1 DTLB Miss of a page of 4K size.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Reload of a page of 1G size.",
+    "PublicDescription": "L1 DTLB Reload of a page of 1G size.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Reload of a page of 2M size.",
+    "PublicDescription": "L1 DTLB Reload of a page of 2M size.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Reload of a page of 32K size.",
+    "PublicDescription": "L1 DTLB Reload of a page of 32K size.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Reload of a page of 4K size.",
+    "PublicDescription": "L1 DTLB Reload of a page of 4K size.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_iside",
+    "EventCode": "0x46",
+    "BriefDescription": "Tablewalker allocation.",
+    "PublicDescription": "Tablewalker allocation.",
+    "UMask": "0xc"
+  },
+  {
+    "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_dside",
+    "EventCode": "0x46",
+    "BriefDescription": "Tablewalker allocation.",
+    "PublicDescription": "Tablewalker allocation.",
+    "UMask": "0x3"
+  },
+  {
+    "EventName": "ls_misal_accesses",
+    "EventCode": "0x47",
+    "BriefDescription": "Misaligned loads."
+  },
+  {
+    "EventName": "ls_pref_instr_disp.prefetch_nta",
+    "EventCode": "0x4b",
+    "BriefDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.",
+    "PublicDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_pref_instr_disp.store_prefetch_w",
+    "EventCode": "0x4b",
+    "BriefDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.",
+    "PublicDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_pref_instr_disp.load_prefetch_w",
+    "EventCode": "0x4b",
+    "BriefDescription": "Prefetch, Prefetch_T0_T1_T2.",
+    "PublicDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_inef_sw_pref.mab_mch_cnt",
+    "EventCode": "0x52",
+    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
+    "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit",
+    "EventCode": "0x52",
+    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
+    "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_not_halted_cyc",
+    "EventCode": "0x76",
+    "BriefDescription": "Cycles not in Halt."
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/other.json b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json
new file mode 100644
index 000000000000..b26a00d05a2e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json
@@ -0,0 +1,65 @@
+[
+  {
+    "EventName": "ic_oc_mode_switch.oc_ic_mode_switch",
+    "EventCode": "0x28a",
+    "BriefDescription": "OC to IC mode switch.",
+    "PublicDescription": "OC Mode Switch. OC to IC mode switch.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_oc_mode_switch.ic_oc_mode_switch",
+    "EventCode": "0x28a",
+    "BriefDescription": "IC to OC mode switch.",
+    "PublicDescription": "OC Mode Switch. IC to OC mode switch.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "RETIRE Tokens unavailable.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "AGSQ Tokens unavailable.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "ALU tokens total unavailable.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "ALSQ 3 Tokens unavailable.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "ALSQ 2 Tokens unavailable.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "ALSQ 1 Tokens unavailable.",
+    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.",
+    "UMask": "0x1"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index e05c2c8458fc..d6984a3017e0 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -33,3 +33,4 @@ GenuineIntel-6-25,v2,westmereep-sp,core
 GenuineIntel-6-2F,v2,westmereex,core
 GenuineIntel-6-55-[01234],v1,skylakex,core
 GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core
+AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 390a351d15ea..c3eae1d77d36 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -10,6 +10,8 @@
 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 # more details.
+from __future__ import print_function
 import os
 import sys
 import struct
@@ -199,6 +201,18 @@ import datetime
 from PySide.QtSql import *
+if sys.version_info < (3, 0):
+        def toserverstr(str):
+                return str
+        def toclientstr(str):
+                return str
+else:
+        # Assume UTF-8 server_encoding and client_encoding
+        def toserverstr(str):
+                return bytes(str, "UTF_8")
+        def toclientstr(str):
+                return bytes(str, "UTF_8")
 # Need to access PostgreSQL C library directly to use COPY FROM STDIN
 from ctypes import *
 libpq = CDLL("libpq.so.5")
@@ -234,12 +248,17 @@ perf_db_export_mode = True
 perf_db_export_calls = False
 perf_db_export_callchains = False
+def printerr(*args, **kw_args):
+        print(*args, file=sys.stderr, **kw_args)
+def printdate(*args, **kw_args):
+        print(datetime.datetime.today(), *args, sep=' ', **kw_args)
 def usage():
-        print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]"
+        printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]")
-        print >> sys.stderr, "where:    columns         'all' or 'branches'"
+        printerr("where:        columns         'all' or 'branches'")
-        print >> sys.stderr, "          calls           'calls' => create calls and call_paths table"
+        printerr("              calls           'calls' => create calls and call_paths table")
-        print >> sys.stderr, "          callchains      'callchains' => create call_paths table"
+        printerr("              callchains      'callchains' => create call_paths table")
        raise Exception("Too few arguments")
 if (len(sys.argv) < 2):
@@ -273,7 +292,7 @@ def do_query(q, s):
                return
        raise Exception("Query failed: " + q.lastError().text())
-print datetime.datetime.today(), "Creating database..."
+printdate("Creating database...")
 db = QSqlDatabase.addDatabase('QPSQL')
 query = QSqlQuery(db)
@@ -506,12 +525,12 @@ do_query(query, 'CREATE VIEW samples_view AS '
        ' FROM samples')
-file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0)
+file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0)
-file_trailer = "\377\377"
+file_trailer = b"\377\377"
 def open_output_file(file_name):
        path_name = output_dir_name + "/" + file_name
-        file = open(path_name, "w+")
+        file = open(path_name, "wb+")
        file.write(file_header)
        return file
@@ -526,13 +545,13 @@ def copy_output_file_direct(file, table_name):
 # Use COPY FROM STDIN because security may prevent postgres from accessing the files directly
 def copy_output_file(file, table_name):
-        conn = PQconnectdb("dbname = " + dbname)
+        conn = PQconnectdb(toclientstr("dbname = " + dbname))
        if (PQstatus(conn)):
                raise Exception("COPY FROM STDIN PQconnectdb failed")
        file.write(file_trailer)
        file.seek(0)
        sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')"
-        res = PQexec(conn, sql)
+        res = PQexec(conn, toclientstr(sql))
        if (PQresultStatus(res) != 4):
                raise Exception("COPY FROM STDIN PQexec failed")
        data = file.read(65536)
@@ -566,7 +585,7 @@ if perf_db_export_calls:
        call_file               = open_output_file("call_table.bin")
 def trace_begin():
-        print datetime.datetime.today(), "Writing to intermediate files..."
+        printdate("Writing to intermediate files...")
        # id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
        evsel_table(0, "unknown")
        machine_table(0, 0, "unknown")
@@ -582,7 +601,7 @@ def trace_begin():
 unhandled_count = 0
 def trace_end():
-        print datetime.datetime.today(), "Copying to database..."
+        printdate("Copying to database...")
        copy_output_file(evsel_file,            "selected_events")
        copy_output_file(machine_file,          "machines")
        copy_output_file(thread_file,           "threads")
@@ -597,7 +616,7 @@ def trace_end():
        if perf_db_export_calls:
                copy_output_file(call_file,             "calls")
-        print datetime.datetime.today(), "Removing intermediate files..."
+        printdate("Removing intermediate files...")
        remove_output_file(evsel_file)
        remove_output_file(machine_file)
        remove_output_file(thread_file)
@@ -612,7 +631,7 @@ def trace_end():
        if perf_db_export_calls:
                remove_output_file(call_file)
        os.rmdir(output_dir_name)
-        print datetime.datetime.today(), "Adding primary keys"
+        printdate("Adding primary keys")
        do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
        do_query(query, 'ALTER TABLE machines        ADD PRIMARY KEY (id)')
        do_query(query, 'ALTER TABLE threads         ADD PRIMARY KEY (id)')
@@ -627,7 +646,7 @@ def trace_end():
        if perf_db_export_calls:
                do_query(query, 'ALTER TABLE calls           ADD PRIMARY KEY (id)')
-        print datetime.datetime.today(), "Adding foreign keys"
+        printdate("Adding foreign keys")
        do_query(query, 'ALTER TABLE threads '
                                        'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
                                        'ADD CONSTRAINT processfk  FOREIGN KEY (process_id)   REFERENCES threads    (id)')
@@ -663,8 +682,8 @@ def trace_end():
                do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
        if (unhandled_count):
-                print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+                printdate("Warning: ", unhandled_count, " unhandled events")
-        print datetime.datetime.today(), "Done"
+        printdate("Done")
 def trace_unhandled(event_name, context, event_fields_dict):
        global unhandled_count
@@ -674,12 +693,14 @@ def sched__sched_switch(*x):
        pass
 def evsel_table(evsel_id, evsel_name, *x):
+        evsel_name = toserverstr(evsel_name)
        n = len(evsel_name)
        fmt = "!hiqi" + str(n) + "s"
        value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name)
        evsel_file.write(value)
 def machine_table(machine_id, pid, root_dir, *x):
+        root_dir = toserverstr(root_dir)
        n = len(root_dir)
        fmt = "!hiqiii" + str(n) + "s"
        value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir)
@@ -690,6 +711,7 @@ def thread_table(thread_id, machine_id, process_id, pid, tid, *x):
        thread_file.write(value)
 def comm_table(comm_id, comm_str, *x):
+        comm_str = toserverstr(comm_str)
        n = len(comm_str)
        fmt = "!hiqi" + str(n) + "s"
        value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
@@ -701,6 +723,9 @@ def comm_thread_table(comm_thread_id, comm_id, thread_id, *x):
        comm_thread_file.write(value)
 def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x):
+        short_name = toserverstr(short_name)
+        long_name = toserverstr(long_name)
+        build_id = toserverstr(build_id)
        n1 = len(short_name)
        n2 = len(long_name)
        n3 = len(build_id)
@@ -709,12 +734,14 @@ def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x):
        dso_file.write(value)
 def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x):
+        symbol_name = toserverstr(symbol_name)
        n = len(symbol_name)
        fmt = "!hiqiqiqiqiii" + str(n) + "s"
        value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
        symbol_file.write(value)
 def branch_type_table(branch_type, name, *x):
+        name = toserverstr(name)
        n = len(name)
        fmt = "!hiii" + str(n) + "s"
        value = struct.pack(fmt, 2, 4, branch_type, n, name)
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index eb63e6c7107f..3b71902a5a21 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -10,6 +10,8 @@
 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 # more details.
+from __future__ import print_function
 import os
 import sys
 import struct
@@ -60,11 +62,17 @@ perf_db_export_mode = True
 perf_db_export_calls = False
 perf_db_export_callchains = False
+def printerr(*args, **keyword_args):
+        print(*args, file=sys.stderr, **keyword_args)
+def printdate(*args, **kw_args):
+        print(datetime.datetime.today(), *args, sep=' ', **kw_args)
 def usage():
-        print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"
+        printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]");
-        print >> sys.stderr, "where:    columns         'all' or 'branches'"
+        printerr("where:        columns         'all' or 'branches'");
-        print >> sys.stderr, "          calls           'calls' => create calls and call_paths table"
+        printerr("              calls           'calls' => create calls and call_paths table");
-        print >> sys.stderr, "          callchains      'callchains' => create call_paths table"
+        printerr("              callchains      'callchains' => create call_paths table");
        raise Exception("Too few arguments")
 if (len(sys.argv) < 2):
@@ -100,7 +108,7 @@ def do_query_(q):
                return
        raise Exception("Query failed: " + q.lastError().text())
-print datetime.datetime.today(), "Creating database..."
+printdate("Creating database ...")
 db_exists = False
 try:
@@ -378,7 +386,7 @@ if perf_db_export_calls:
        call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
 def trace_begin():
-        print datetime.datetime.today(), "Writing records..."
+        printdate("Writing records...")
        do_query(query, 'BEGIN TRANSACTION')
        # id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
        evsel_table(0, "unknown")
@@ -397,14 +405,14 @@ unhandled_count = 0
 def trace_end():
        do_query(query, 'END TRANSACTION')
-        print datetime.datetime.today(), "Adding indexes"
+        printdate("Adding indexes")
        if perf_db_export_calls:
                do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
                do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
        if (unhandled_count):
-                print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+                printdate("Warning: ", unhandled_count, " unhandled events")
-        print datetime.datetime.today(), "Done"
+        printdate("Done")
 def trace_unhandled(event_name, context, event_fields_dict):
        global unhandled_count
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index afec9479ca7f..e38518cdcbc3 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -88,11 +88,20 @@
 #                                                                              7fab593ea956 48 89 15 3b 13 22 00                            movq  %rdx, 0x22133b(%rip)
 # 8107675243232  2    ls       22011  22011  hardware interrupt     No         7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+from __future__ import print_function
 import sys
 import weakref
 import threading
 import string
-import cPickle
+try:
+        # Python2
+        import cPickle as pickle
+        # size of pickled integer big enough for record size
+        glb_nsz = 8
+except ImportError:
+        import pickle
+        glb_nsz = 16
 import re
 import os
 from PySide.QtCore import *
@@ -102,6 +111,15 @@ from decimal import *
 from ctypes import *
 from multiprocessing import Process, Array, Value, Event
+# xrange is range in Python3
+try:
+        xrange
+except NameError:
+        xrange = range
+def printerr(*args, **keyword_args):
+        print(*args, file=sys.stderr, **keyword_args)
 # Data formatting helpers
 def tohex(ip):
@@ -1004,10 +1022,6 @@ class ChildDataItemFinder():
 glb_chunk_sz = 10000
-# size of pickled integer big enough for record size
-glb_nsz = 8
 # Background process for SQL data fetcher
 class SQLFetcherProcess():
@@ -1066,7 +1080,7 @@ class SQLFetcherProcess():
                                return True
                        if space >= glb_nsz:
                                # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer
-                                nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL)
+                                nd = pickle.dumps(0, pickle.HIGHEST_PROTOCOL)
                                self.buffer[self.local_head : self.local_head + len(nd)] = nd
                        self.local_head = 0
                if self.local_tail - self.local_head > sz:
@@ -1084,9 +1098,9 @@ class SQLFetcherProcess():
                        self.wait_event.wait()
        def AddToBuffer(self, obj):
-                d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL)
+                d = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL)
                n = len(d)
-                nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL)
+                nd = pickle.dumps(n, pickle.HIGHEST_PROTOCOL)
                sz = n + glb_nsz
                self.WaitForSpace(sz)
                pos = self.local_head
@@ -1198,12 +1212,12 @@ class SQLFetcher(QObject):
                pos = self.local_tail
                if len(self.buffer) - pos < glb_nsz:
                        pos = 0
-                n = cPickle.loads(self.buffer[pos : pos + glb_nsz])
+                n = pickle.loads(self.buffer[pos : pos + glb_nsz])
                if n == 0:
                        pos = 0
-                        n = cPickle.loads(self.buffer[0 : glb_nsz])
+                        n = pickle.loads(self.buffer[0 : glb_nsz])
                pos += glb_nsz
-                obj = cPickle.loads(self.buffer[pos : pos + n])
+                obj = pickle.loads(self.buffer[pos : pos + n])
                self.local_tail = pos + n
                return obj
@@ -2973,7 +2987,7 @@ class DBRef():
 def Main():
        if (len(sys.argv) < 2):
-                print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}"
+                printerr("Usage is: exported-sql-viewer.py {<database name> | --help-only}");
                raise Exception("Too few arguments")
        dbname = sys.argv[1]
@@ -2986,8 +3000,8 @@ def Main():
        is_sqlite3 = False
        try:
-                f = open(dbname)
+                f = open(dbname, "rb")
-                if f.read(15) == "SQLite format 3":
+                if f.read(15) == b'SQLite format 3':
                        is_sqlite3 = True
                f.close()
        except:
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
index cb0a3138fa54..93818054ae20 100644
--- a/tools/perf/tests/attr/test-record-C0
+++ b/tools/perf/tests/attr/test-record-C0
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -C 0 kill >/dev/null 2>&1
+args    = --no-bpf-event -C 0 kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic
index 85a23cf35ba1..b0ca42a5ecc9 100644
--- a/tools/perf/tests/attr/test-record-basic
+++ b/tools/perf/tests/attr/test-record-basic
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = kill >/dev/null 2>&1
+args    = --no-bpf-event kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any
index 81f839e2fad0..1a99b3ce6b89 100644
--- a/tools/perf/tests/attr/test-record-branch-any
+++ b/tools/perf/tests/attr/test-record-branch-any
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -b kill >/dev/null 2>&1
+args    = --no-bpf-event -b kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any
index 357421f4dfce..709768b508c6 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any
+++ b/tools/perf/tests/attr/test-record-branch-filter-any
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j any kill >/dev/null 2>&1
+args    = --no-bpf-event -j any kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call
index dbc55f2ab845..f943221f7825 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any_call
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_call
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j any_call kill >/dev/null 2>&1
+args    = --no-bpf-event -j any_call kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret
index a0824ff8e131..fd4f5b4154a9 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any_ret
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j any_ret kill >/dev/null 2>&1
+args    = --no-bpf-event -j any_ret kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv
index f34d6f120181..4e52d685ebe1 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-hv
+++ b/tools/perf/tests/attr/test-record-branch-filter-hv
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j hv kill >/dev/null 2>&1
+args    = --no-bpf-event -j hv kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call
index b86a35232248..e08c6ab3796e 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-ind_call
+++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j ind_call kill >/dev/null 2>&1
+args    = --no-bpf-event -j ind_call kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k
index d3fbc5e1858a..b4b98f84fc2f 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-k
+++ b/tools/perf/tests/attr/test-record-branch-filter-k
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j k kill >/dev/null 2>&1
+args    = --no-bpf-event -j k kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u
index a318f0dda173..fb9610edbb0d 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-u
+++ b/tools/perf/tests/attr/test-record-branch-filter-u
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -j u kill >/dev/null 2>&1
+args    = --no-bpf-event -j u kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count
index 34f6cc577263..5e9b9019d786 100644
--- a/tools/perf/tests/attr/test-record-count
+++ b/tools/perf/tests/attr/test-record-count
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -c 123 kill >/dev/null 2>&1
+args    = --no-bpf-event -c 123 kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
index a9cf2233b0ce..a99bb13149c2 100644
--- a/tools/perf/tests/attr/test-record-data
+++ b/tools/perf/tests/attr/test-record-data
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -d kill >/dev/null 2>&1
+args    = --no-bpf-event -d kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq
index bf4cb459f0d5..89e29f6b2ae0 100644
--- a/tools/perf/tests/attr/test-record-freq
+++ b/tools/perf/tests/attr/test-record-freq
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -F 100 kill >/dev/null 2>&1
+args    = --no-bpf-event -F 100 kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
index 0b216e69760c..5d8234d50845 100644
--- a/tools/perf/tests/attr/test-record-graph-default
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -g kill >/dev/null 2>&1
+args    = --no-bpf-event -g kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf
index da2fa73bd0a2..ae92061d611d 100644
--- a/tools/perf/tests/attr/test-record-graph-dwarf
+++ b/tools/perf/tests/attr/test-record-graph-dwarf
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --call-graph dwarf -- kill >/dev/null 2>&1
+args    = --no-bpf-event --call-graph dwarf -- kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
index 625d190bb798..5630521c0b0f 100644
--- a/tools/perf/tests/attr/test-record-graph-fp
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --call-graph fp kill >/dev/null 2>&1
+args    = --no-bpf-event --call-graph fp kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index 618ba1c17474..14ee60fd3f41 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --group -e cycles,instructions kill >/dev/null 2>&1
+args    = --no-bpf-event --group -e cycles,instructions kill >/dev/null 2>&1
 ret     = 1
 [event-1:base-record]
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index f0729c454f16..300b9f7e6d69 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
 [event-1:base-record]
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index 48e8bd12fe46..3ffe246e0228 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,instructions}' kill >/dev/null 2>&1
 ret     = 1
 [event-1:base-record]
diff --git a/tools/perf/tests/attr/test-record-no-buffering b/tools/perf/tests/attr/test-record-no-buffering
index aa3956d8fe20..583dcbb078ba 100644
--- a/tools/perf/tests/attr/test-record-no-buffering
+++ b/tools/perf/tests/attr/test-record-no-buffering
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = --no-buffering kill >/dev/null 2>&1
+args    = --no-bpf-event --no-buffering kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 560943decb87..15d1dc162e1c 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -i kill >/dev/null 2>&1
+args    = --no-bpf-event -i kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples
index 8eb73ab639e0..596fbd6d5a2c 100644
--- a/tools/perf/tests/attr/test-record-no-samples
+++ b/tools/perf/tests/attr/test-record-no-samples
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -n kill >/dev/null 2>&1
+args    = --no-bpf-event -n kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period
index 69bc748f0f27..119101154c5e 100644
--- a/tools/perf/tests/attr/test-record-period
+++ b/tools/perf/tests/attr/test-record-period
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -c 100 -P kill >/dev/null 2>&1
+args    = --no-bpf-event -c 100 -P kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw
index a188a614a44c..13a5f7860c78 100644
--- a/tools/perf/tests/attr/test-record-raw
+++ b/tools/perf/tests/attr/test-record-raw
@@ -1,6 +1,6 @@
 [config]
 command = record
-args    = -R kill >/dev/null 2>&1
+args    = --no-bpf-event -R kill >/dev/null 2>&1
 ret     = 1
 [event:base-record]
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 6d598cc071ae..1a9c3becf5ff 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -18,7 +18,7 @@ static void testcase(void)
        int i;
        for (i = 0; i < NR_ITERS; i++) {
-                char proc_name[10];
+                char proc_name[15];
                snprintf(proc_name, sizeof(proc_name), "p:%d\n", i);
                prctl(PR_SET_NAME, proc_name);
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index ea7acf403727..71f60c0f9faa 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -85,5 +85,6 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
        if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
                ret = -1;
+        perf_evsel__delete(evsel);
        return ret;
 }
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 01f0706995a9..9acc1e80b936 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -19,7 +19,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
        const char *p;
        const char **other;
        double val;
-        int ret;
+        int i, ret;
        struct parse_ctx ctx;
        int num_other;
@@ -56,6 +56,9 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
        TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
        TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO"));
        TEST_ASSERT_VAL("find other", other[3] == NULL);
+        for (i = 0; i < num_other; i++)
+                free((void *)other[i]);
        free((void *)other);
        return 0;
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index c531e6deb104..493ecb611540 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -45,7 +45,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int
        if (IS_ERR(evsel)) {
                tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "syscalls", "sys_enter_openat");
                pr_debug("%s\n", errbuf);
-                goto out_thread_map_delete;
+                goto out_cpu_map_delete;
        }
        if (perf_evsel__open(evsel, cpus, threads) < 0) {
@@ -119,6 +119,8 @@ out_close_fd:
        perf_evsel__close_fd(evsel);
 out_evsel_delete:
        perf_evsel__delete(evsel);
+out_cpu_map_delete:
+        cpu_map__put(cpus);
 out_thread_map_delete:
        thread_map__put(threads);
        return err;
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 4f75561424ed..4ad37d8c7d6a 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -611,14 +611,16 @@ void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence)
                browser->top = browser->entries;
                break;
        case SEEK_CUR:
-                browser->top = browser->top + browser->top_idx + offset;
+                browser->top = (char **)browser->top + offset;
                break;
        case SEEK_END:
-                browser->top = browser->top + browser->nr_entries - 1 + offset;
+                browser->top = (char **)browser->entries + browser->nr_entries - 1 + offset;
                break;
        default:
                return;
        }
+        assert((char **)browser->top < (char **)browser->entries + browser->nr_entries);
+        assert((char **)browser->top >= (char **)browser->entries);
 }
 unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
@@ -630,7 +632,9 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
                browser->top = browser->entries;
        pos = (char **)browser->top;
-        while (idx < browser->nr_entries) {
+        while (idx < browser->nr_entries &&
+               row < (unsigned)SLtt_Screen_Rows - 1) {
+                assert(pos < (char **)browser->entries + browser->nr_entries);
                if (!browser->filter || !browser->filter(browser, *pos)) {
                        ui_browser__gotorc(browser, row, 0);
                        browser->write(browser, pos, row);
diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build
index 8fee56b46502..fdf86f7981ca 100644
--- a/tools/perf/ui/browsers/Build
+++ b/tools/perf/ui/browsers/Build
@@ -3,6 +3,7 @@ perf-y += hists.o
 perf-y += map.o
 perf-y += scripts.o
 perf-y += header.o
+perf-y += res_sample.o
 CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST
 CFLAGS_hists.o    += -DENABLE_SLFUTURE_CONST
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 35bdfd8b1e71..98d934a36d86 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -750,7 +750,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
                        continue;
                case 'r':
                        {
-                                script_browse(NULL);
+                                script_browse(NULL, NULL);
                                continue;
                        }
                case 'k':
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index aef800d97ea1..3421ecbdd3f0 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -7,6 +7,7 @@
 #include <string.h>
 #include <linux/rbtree.h>
 #include <sys/ttydefaults.h>
+#include <linux/time64.h>
 #include "../../util/callchain.h"
 #include "../../util/evsel.h"
@@ -30,6 +31,7 @@
 #include "srcline.h"
 #include "string2.h"
 #include "units.h"
+#include "time-utils.h"
 #include "sane_ctype.h"
@@ -1224,6 +1226,8 @@ void hist_browser__init_hpp(void)
                                hist_browser__hpp_color_overhead_guest_us;
        perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
                                hist_browser__hpp_color_overhead_acc;
+        res_sample_init();
 }
 static int hist_browser__show_entry(struct hist_browser *browser,
@@ -2338,9 +2342,12 @@ close_file_and_continue:
 }
 struct popup_action {
+        unsigned long           time;
        struct thread           *thread;
        struct map_symbol       ms;
        int                     socket;
+        struct perf_evsel       *evsel;
+        enum rstype             rstype;
        int (*fn)(struct hist_browser *browser, struct popup_action *act);
 };
@@ -2527,46 +2534,137 @@ static int
 do_run_script(struct hist_browser *browser __maybe_unused,
              struct popup_action *act)
 {
-        char script_opt[64];
+        char *script_opt;
-        memset(script_opt, 0, sizeof(script_opt));
+        int len;
+        int n = 0;
+        len = 100;
+        if (act->thread)
+                len += strlen(thread__comm_str(act->thread));
+        else if (act->ms.sym)
+                len += strlen(act->ms.sym->name);
+        script_opt = malloc(len);
+        if (!script_opt)
+                return -1;
+        script_opt[0] = 0;
        if (act->thread) {
-                scnprintf(script_opt, sizeof(script_opt), " -c %s ",
+                n = scnprintf(script_opt, len, " -c %s ",
                          thread__comm_str(act->thread));
        } else if (act->ms.sym) {
-                scnprintf(script_opt, sizeof(script_opt), " -S %s ",
+                n = scnprintf(script_opt, len, " -S %s ",
                          act->ms.sym->name);
        }
-        script_browse(script_opt);
+        if (act->time) {
+                char start[32], end[32];
+                unsigned long starttime = act->time;
+                unsigned long endtime = act->time + symbol_conf.time_quantum;
+                if (starttime == endtime) { /* Display 1ms as fallback */
+                        starttime -= 1*NSEC_PER_MSEC;
+                        endtime += 1*NSEC_PER_MSEC;
+                }
+                timestamp__scnprintf_usec(starttime, start, sizeof start);
+                timestamp__scnprintf_usec(endtime, end, sizeof end);
+                n += snprintf(script_opt + n, len - n, " --time %s,%s", start, end);
+        }
+        script_browse(script_opt, act->evsel);
+        free(script_opt);
        return 0;
 }
 static int
-add_script_opt(struct hist_browser *browser __maybe_unused,
+do_res_sample_script(struct hist_browser *browser __maybe_unused,
+                     struct popup_action *act)
+{
+        struct hist_entry *he;
+        he = hist_browser__selected_entry(browser);
+        res_sample_browse(he->res_samples, he->num_res, act->evsel, act->rstype);
+        return 0;
+}
+static int
+add_script_opt_2(struct hist_browser *browser __maybe_unused,
               struct popup_action *act, char **optstr,
-               struct thread *thread, struct symbol *sym)
+               struct thread *thread, struct symbol *sym,
+               struct perf_evsel *evsel, const char *tstr)
 {
        if (thread) {
-                if (asprintf(optstr, "Run scripts for samples of thread [%s]",
+                if (asprintf(optstr, "Run scripts for samples of thread [%s]%s",
-                             thread__comm_str(thread)) < 0)
+                             thread__comm_str(thread), tstr) < 0)
                        return 0;
        } else if (sym) {
-                if (asprintf(optstr, "Run scripts for samples of symbol [%s]",
+                if (asprintf(optstr, "Run scripts for samples of symbol [%s]%s",
-                             sym->name) < 0)
+                             sym->name, tstr) < 0)
                        return 0;
        } else {
-                if (asprintf(optstr, "Run scripts for all samples") < 0)
+                if (asprintf(optstr, "Run scripts for all samples%s", tstr) < 0)
                        return 0;
        }
        act->thread = thread;
        act->ms.sym = sym;
+        act->evsel = evsel;
        act->fn = do_run_script;
        return 1;
 }
 static int
+add_script_opt(struct hist_browser *browser,
+               struct popup_action *act, char **optstr,
+               struct thread *thread, struct symbol *sym,
+               struct perf_evsel *evsel)
+{
+        int n, j;
+        struct hist_entry *he;
+        n = add_script_opt_2(browser, act, optstr, thread, sym, evsel, "");
+        he = hist_browser__selected_entry(browser);
+        if (sort_order && strstr(sort_order, "time")) {
+                char tstr[128];
+                optstr++;
+                act++;
+                j = sprintf(tstr, " in ");
+                j += timestamp__scnprintf_usec(he->time, tstr + j,
+                                               sizeof tstr - j);
+                j += sprintf(tstr + j, "-");
+                timestamp__scnprintf_usec(he->time + symbol_conf.time_quantum,
+                                          tstr + j, sizeof tstr - j);
+                n += add_script_opt_2(browser, act, optstr, thread, sym,
+                                          evsel, tstr);
+                act->time = he->time;
+        }
+        return n;
+}
+static int
+add_res_sample_opt(struct hist_browser *browser __maybe_unused,
+                   struct popup_action *act, char **optstr,
+                   struct res_sample *res_sample,
+                   struct perf_evsel *evsel,
+                   enum rstype type)
+{
+        if (!res_sample)
+                return 0;
+        if (asprintf(optstr, "Show context for individual samples %s",
+                type == A_ASM ? "with assembler" :
+                type == A_SOURCE ? "with source" : "") < 0)
+                return 0;
+        act->fn = do_res_sample_script;
+        act->evsel = evsel;
+        act->rstype = type;
+        return 1;
+}
+static int
 do_switch_data(struct hist_browser *browser __maybe_unused,
               struct popup_action *act __maybe_unused)
 {
@@ -3031,7 +3129,7 @@ skip_annotation:
                                nr_options += add_script_opt(browser,
                                                             &actions[nr_options],
                                                             &options[nr_options],
-                                                             thread, NULL);
+                                                             thread, NULL, evsel);
                        }
                        /*
                         * Note that browser->selection != NULL
@@ -3046,11 +3144,24 @@ skip_annotation:
                                nr_options += add_script_opt(browser,
                                                             &actions[nr_options],
                                                             &options[nr_options],
-                                                             NULL, browser->selection->sym);
+                                                             NULL, browser->selection->sym,
+                                                             evsel);
                        }
                }
                nr_options += add_script_opt(browser, &actions[nr_options],
-                                             &options[nr_options], NULL, NULL);
+                                             &options[nr_options], NULL, NULL, evsel);
+                nr_options += add_res_sample_opt(browser, &actions[nr_options],
+                                                 &options[nr_options],
+                                 hist_browser__selected_entry(browser)->res_samples,
+                                 evsel, A_NORMAL);
+                nr_options += add_res_sample_opt(browser, &actions[nr_options],
+                                                 &options[nr_options],
+                                 hist_browser__selected_entry(browser)->res_samples,
+                                 evsel, A_ASM);
+                nr_options += add_res_sample_opt(browser, &actions[nr_options],
+                                                 &options[nr_options],
+                                 hist_browser__selected_entry(browser)->res_samples,
+                                 evsel, A_SOURCE);
                nr_options += add_switch_opt(browser, &actions[nr_options],
                                             &options[nr_options]);
 skip_scripting:
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
new file mode 100644
index 000000000000..c0dd73176d42
--- /dev/null
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Display a menu with individual samples to browse with perf script */
+#include "util.h"
+#include "hist.h"
+#include "evsel.h"
+#include "hists.h"
+#include "sort.h"
+#include "config.h"
+#include "time-utils.h"
+#include <linux/time64.h>
+static u64 context_len = 10 * NSEC_PER_MSEC;
+static int res_sample_config(const char *var, const char *value, void *data __maybe_unused)
+{
+        if (!strcmp(var, "samples.context"))
+                return perf_config_u64(&context_len, var, value);
+        return 0;
+}
+void res_sample_init(void)
+{
+        perf_config(res_sample_config, NULL);
+}
+int res_sample_browse(struct res_sample *res_samples, int num_res,
+                      struct perf_evsel *evsel, enum rstype rstype)
+{
+        char **names;
+        int i, n;
+        int choice;
+        char *cmd;
+        char pbuf[256], tidbuf[32], cpubuf[32];
+        const char *perf = perf_exe(pbuf, sizeof pbuf);
+        char trange[128], tsample[64];
+        struct res_sample *r;
+        char extra_format[256];
+        names = calloc(num_res, sizeof(char *));
+        if (!names)
+                return -1;
+        for (i = 0; i < num_res; i++) {
+                char tbuf[64];
+                timestamp__scnprintf_nsec(res_samples[i].time, tbuf, sizeof tbuf);
+                if (asprintf(&names[i], "%s: CPU %d tid %d", tbuf,
+                             res_samples[i].cpu, res_samples[i].tid) < 0) {
+                        while (--i >= 0)
+                                free(names[i]);
+                        free(names);
+                        return -1;
+                }
+        }
+        choice = ui__popup_menu(num_res, names);
+        for (i = 0; i < num_res; i++)
+                free(names[i]);
+        free(names);
+        if (choice < 0 || choice >= num_res)
+                return -1;
+        r = &res_samples[choice];
+        n = timestamp__scnprintf_nsec(r->time - context_len, trange, sizeof trange);
+        trange[n++] = ',';
+        timestamp__scnprintf_nsec(r->time + context_len, trange + n, sizeof trange - n);
+        timestamp__scnprintf_nsec(r->time, tsample, sizeof tsample);
+        attr_to_script(extra_format, &evsel->attr);
+        if (asprintf(&cmd, "%s script %s%s --time %s %s%s %s%s --ns %s %s %s %s %s | less +/%s",
+                     perf,
+                     input_name ? "-i " : "",
+                     input_name ? input_name : "",
+                     trange,
+                     r->cpu >= 0 ? "--cpu " : "",
+                     r->cpu >= 0 ? (sprintf(cpubuf, "%d", r->cpu), cpubuf) : "",
+                     r->tid ? "--tid " : "",
+                     r->tid ? (sprintf(tidbuf, "%d", r->tid), tidbuf) : "",
+                     extra_format,
+                     rstype == A_ASM ? "-F +insn --xed" :
+                     rstype == A_SOURCE ? "-F +srcline,+srccode" : "",
+                     symbol_conf.inline_name ? "--inline" : "",
+                     "--show-lost-events ",
+                     r->tid ? "--show-switch-events --show-task-events " : "",
+                     tsample) < 0)
+                return -1;
+        run_script(cmd);
+        free(cmd);
+        return 0;
+}
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 90a32ac69e76..27cf3ab88d13 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,34 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <elf.h>
-#include <inttypes.h>
-#include <sys/ttydefaults.h>
-#include <string.h>
 #include "../../util/sort.h"
 #include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/debug.h"
 #include "../../util/symbol.h"
 #include "../browser.h"
-#include "../helpline.h"
 #include "../libslang.h"
+#include "config.h"
-/* 2048 lines should be enough for a script output */
-#define MAX_LINES               2048
-/* 160 bytes for one output line */
-#define AVERAGE_LINE_LEN        160
-struct script_line {
-        struct list_head node;
-        char line[AVERAGE_LINE_LEN];
-};
-struct perf_script_browser {
-        struct ui_browser b;
-        struct list_head entries;
-        const char *script_name;
-        int nr_lines;
-};
 #define SCRIPT_NAMELEN  128
 #define SCRIPT_MAX_NO   64
@@ -40,149 +18,169 @@ struct perf_script_browser {
 */
 #define SCRIPT_FULLPATH_LEN     256
+struct script_config {
+        const char **names;
+        char **paths;
+        int index;
+        const char *perf;
+        char extra_format[256];
+};
+void attr_to_script(char *extra_format, struct perf_event_attr *attr)
+{
+        extra_format[0] = 0;
+        if (attr->read_format & PERF_FORMAT_GROUP)
+                strcat(extra_format, " -F +metric");
+        if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK)
+                strcat(extra_format, " -F +brstackinsn --xed");
+        if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
+                strcat(extra_format, " -F +iregs");
+        if (attr->sample_type & PERF_SAMPLE_REGS_USER)
+                strcat(extra_format, " -F +uregs");
+        if (attr->sample_type & PERF_SAMPLE_PHYS_ADDR)
+                strcat(extra_format, " -F +phys_addr");
+}
+static int add_script_option(const char *name, const char *opt,
+                             struct script_config *c)
+{
+        c->names[c->index] = name;
+        if (asprintf(&c->paths[c->index],
+                     "%s script %s -F +metric %s %s",
+                     c->perf, opt, symbol_conf.inline_name ? " --inline" : "",
+                     c->extra_format) < 0)
+                return -1;
+        c->index++;
+        return 0;
+}
+static int scripts_config(const char *var, const char *value, void *data)
+{
+        struct script_config *c = data;
+        if (!strstarts(var, "scripts."))
+                return -1;
+        if (c->index >= SCRIPT_MAX_NO)
+                return -1;
+        c->names[c->index] = strdup(var + 7);
+        if (!c->names[c->index])
+                return -1;
+        if (asprintf(&c->paths[c->index], "%s %s", value,
+                     c->extra_format) < 0)
+                return -1;
+        c->index++;
+        return 0;
+}
 /*
 * When success, will copy the full path of the selected script
 * into  the buffer pointed by script_name, and return 0.
 * Return -1 on failure.
 */
-static int list_scripts(char *script_name)
+static int list_scripts(char *script_name, bool *custom,
+                        struct perf_evsel *evsel)
 {
-        char *buf, *names[SCRIPT_MAX_NO], *paths[SCRIPT_MAX_NO];
+        char *buf, *paths[SCRIPT_MAX_NO], *names[SCRIPT_MAX_NO];
-        int i, num, choice, ret = -1;
+        int i, num, choice;
+        int ret = 0;
+        int max_std, custom_perf;
+        char pbuf[256];
+        const char *perf = perf_exe(pbuf, sizeof pbuf);
+        struct script_config scriptc = {
+                .names = (const char **)names,
+                .paths = paths,
+                .perf = perf
+        };
+        script_name[0] = 0;
        /* Preset the script name to SCRIPT_NAMELEN */
        buf = malloc(SCRIPT_MAX_NO * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN));
        if (!buf)
-                return ret;
+                return -1;
-        for (i = 0; i < SCRIPT_MAX_NO; i++) {
+        if (evsel)
-                names[i] = buf + i * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN);
+                attr_to_script(scriptc.extra_format, &evsel->attr);
+        add_script_option("Show individual samples", "", &scriptc);
+        add_script_option("Show individual samples with assembler", "-F +insn --xed",
+                          &scriptc);
+        add_script_option("Show individual samples with source", "-F +srcline,+srccode",
+                          &scriptc);
+        perf_config(scripts_config, &scriptc);
+        custom_perf = scriptc.index;
+        add_script_option("Show samples with custom perf script arguments", "", &scriptc);
+        i = scriptc.index;
+        max_std = i;
+        for (; i < SCRIPT_MAX_NO; i++) {
+                names[i] = buf + (i - max_std) * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN);
                paths[i] = names[i] + SCRIPT_NAMELEN;
        }
-        num = find_scripts(names, paths);
+        num = find_scripts(names + max_std, paths + max_std, SCRIPT_MAX_NO - max_std,
-        if (num > 0) {
+                        SCRIPT_FULLPATH_LEN);
-                choice = ui__popup_menu(num, names);
+        if (num < 0)
-                if (choice < num && choice >= 0) {
+                num = 0;
-                        strcpy(script_name, paths[choice]);
+        choice = ui__popup_menu(num + max_std, (char * const *)names);
-                        ret = 0;
+        if (choice < 0) {
-                }
+                ret = -1;
+                goto out;
        }
+        if (choice == custom_perf) {
+                char script_args[50];
+                int key = ui_browser__input_window("perf script command",
+                                "Enter perf script command line (without perf script prefix)",
+                                script_args, "", 0);
+                if (key != K_ENTER)
+                        return -1;
+                sprintf(script_name, "%s script %s", perf, script_args);
+        } else if (choice < num + max_std) {
+                strcpy(script_name, paths[choice]);
+        }
+        *custom = choice >= max_std;
+out:
        free(buf);
+        for (i = 0; i < max_std; i++)
+                free(paths[i]);
        return ret;
 }
-static void script_browser__write(struct ui_browser *browser,
+void run_script(char *cmd)
-                                   void *entry, int row)
 {
-        struct script_line *sline = list_entry(entry, struct script_line, node);
+        pr_debug("Running %s\n", cmd);
-        bool current_entry = ui_browser__is_current_entry(browser, row);
+        SLang_reset_tty();
+        if (system(cmd) < 0)
-        ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+                pr_warning("Cannot run %s\n", cmd);
-                                                       HE_COLORSET_NORMAL);
+        /*
+         * SLang doesn't seem to reset the whole terminal, so be more
-        ui_browser__write_nstring(browser, sline->line, browser->width);
+         * forceful to get back to the original state.
+         */
+        printf("\033[c\033[H\033[J");
+        fflush(stdout);
+        SLang_init_tty(0, 0, 0);
+        SLsmg_refresh();
 }
-static int script_browser__run(struct perf_script_browser *browser)
+int script_browse(const char *script_opt, struct perf_evsel *evsel)
 {
-        int key;
+        char *cmd, script_name[SCRIPT_FULLPATH_LEN];
+        bool custom = false;
-        if (ui_browser__show(&browser->b, browser->script_name,
+        memset(script_name, 0, SCRIPT_FULLPATH_LEN);
-                             "Press ESC to exit") < 0)
+        if (list_scripts(script_name, &custom, evsel))
                return -1;
-        while (1) {
+        if (asprintf(&cmd, "%s%s %s %s%s 2>&1 | less",
-                key = ui_browser__run(&browser->b, 0);
+                        custom ? "perf script -s " : "",
+                        script_name,
-                /* We can add some special key handling here if needed */
+                        script_opt ? script_opt : "",
-                break;
+                        input_name ? "-i " : "",
-        }
+                        input_name ? input_name : "") < 0)
-        ui_browser__hide(&browser->b);
-        return key;
-}
-int script_browse(const char *script_opt)
-{
-        char cmd[SCRIPT_FULLPATH_LEN*2], script_name[SCRIPT_FULLPATH_LEN];
-        char *line = NULL;
-        size_t len = 0;
-        ssize_t retlen;
-        int ret = -1, nr_entries = 0;
-        FILE *fp;
-        void *buf;
-        struct script_line *sline;
-        struct perf_script_browser script = {
-                .b = {
-                        .refresh    = ui_browser__list_head_refresh,
-                        .seek       = ui_browser__list_head_seek,
-                        .write      = script_browser__write,
-                },
-                .script_name = script_name,
-        };
-        INIT_LIST_HEAD(&script.entries);
-        /* Save each line of the output in one struct script_line object. */
-        buf = zalloc((sizeof(*sline)) * MAX_LINES);
-        if (!buf)
                return -1;
-        sline = buf;
-        memset(script_name, 0, SCRIPT_FULLPATH_LEN);
-        if (list_scripts(script_name))
-                goto exit;
-        sprintf(cmd, "perf script -s %s ", script_name);
-        if (script_opt)
+        run_script(cmd);
-                strcat(cmd, script_opt);
+        free(cmd);
-        if (input_name) {
+        return 0;
-                strcat(cmd, " -i ");
-                strcat(cmd, input_name);
-        }
-        strcat(cmd, " 2>&1");
-        fp = popen(cmd, "r");
-        if (!fp)
-                goto exit;
-        while ((retlen = getline(&line, &len, fp)) != -1) {
-                strncpy(sline->line, line, AVERAGE_LINE_LEN);
-                /* If one output line is very large, just cut it short */
-                if (retlen >= AVERAGE_LINE_LEN) {
-                        sline->line[AVERAGE_LINE_LEN - 1] = '\0';
-                        sline->line[AVERAGE_LINE_LEN - 2] = '\n';
-                }
-                list_add_tail(&sline->node, &script.entries);
-                if (script.b.width < retlen)
-                        script.b.width = retlen;
-                if (nr_entries++ >= MAX_LINES - 1)
-                        break;
-                sline++;
-        }
-        if (script.b.width > AVERAGE_LINE_LEN)
-                script.b.width = AVERAGE_LINE_LEN;
-        free(line);
-        pclose(fp);
-        script.nr_lines = nr_entries;
-        script.b.nr_entries = nr_entries;
-        script.b.entries = &script.entries;
-        ret = script_browser__run(&script);
-exit:
-        free(buf);
-        return ret;
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 5f6dbbf5d749..c8b01176c9e1 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -10,6 +10,10 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <libgen.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
 #include "util.h"
 #include "ui/ui.h"
 #include "sort.h"
@@ -24,6 +28,7 @@
 #include "annotate.h"
 #include "evsel.h"
 #include "evlist.h"
+#include "bpf-event.h"
 #include "block-range.h"
 #include "string2.h"
 #include "arch/common.h"
@@ -31,6 +36,7 @@
 #include <pthread.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
+#include <bpf/libbpf.h>
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -1615,6 +1621,9 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
                          "  --vmlinux vmlinux\n", build_id_msg ?: "");
        }
                break;
+        case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
+                scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
+                break;
        default:
                scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
                break;
@@ -1674,6 +1683,156 @@ fallback:
        return 0;
 }
+#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+#define PACKAGE "perf"
+#include <bfd.h>
+#include <dis-asm.h>
+static int symbol__disassemble_bpf(struct symbol *sym,
+                                   struct annotate_args *args)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct annotation_options *opts = args->options;
+        struct bpf_prog_info_linear *info_linear;
+        struct bpf_prog_linfo *prog_linfo = NULL;
+        struct bpf_prog_info_node *info_node;
+        int len = sym->end - sym->start;
+        disassembler_ftype disassemble;
+        struct map *map = args->ms.map;
+        struct disassemble_info info;
+        struct dso *dso = map->dso;
+        int pc = 0, count, sub_id;
+        struct btf *btf = NULL;
+        char tpath[PATH_MAX];
+        size_t buf_size;
+        int nr_skip = 0;
+        int ret = -1;
+        char *buf;
+        bfd *bfdf;
+        FILE *s;
+        if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
+                return -1;
+        pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
+                 sym->name, sym->start, sym->end - sym->start);
+        memset(tpath, 0, sizeof(tpath));
+        perf_exe(tpath, sizeof(tpath));
+        bfdf = bfd_openr(tpath, NULL);
+        assert(bfdf);
+        assert(bfd_check_format(bfdf, bfd_object));
+        s = open_memstream(&buf, &buf_size);
+        if (!s)
+                goto out;
+        init_disassemble_info(&info, s,
+                              (fprintf_ftype) fprintf);
+        info.arch = bfd_get_arch(bfdf);
+        info.mach = bfd_get_mach(bfdf);
+        info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
+                                                 dso->bpf_prog.id);
+        if (!info_node)
+                goto out;
+        info_linear = info_node->info_linear;
+        sub_id = dso->bpf_prog.sub_id;
+        info.buffer = (void *)(info_linear->info.jited_prog_insns);
+        info.buffer_length = info_linear->info.jited_prog_len;
+        if (info_linear->info.nr_line_info)
+                prog_linfo = bpf_prog_linfo__new(&info_linear->info);
+        if (info_linear->info.btf_id) {
+                struct btf_node *node;
+                node = perf_env__find_btf(dso->bpf_prog.env,
+                                          info_linear->info.btf_id);
+                if (node)
+                        btf = btf__new((__u8 *)(node->data),
+                                       node->data_size);
+        }
+        disassemble_init_for_target(&info);
+#ifdef DISASM_FOUR_ARGS_SIGNATURE
+        disassemble = disassembler(info.arch,
+                                   bfd_big_endian(bfdf),
+                                   info.mach,
+                                   bfdf);
+#else
+        disassemble = disassembler(bfdf);
+#endif
+        assert(disassemble);
+        fflush(s);
+        do {
+                const struct bpf_line_info *linfo = NULL;
+                struct disasm_line *dl;
+                size_t prev_buf_size;
+                const char *srcline;
+                u64 addr;
+                addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+                count = disassemble(pc, &info);
+                if (prog_linfo)
+                        linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+                                                                addr, sub_id,
+                                                                nr_skip);
+                if (linfo && btf) {
+                        srcline = btf__name_by_offset(btf, linfo->line_off);
+                        nr_skip++;
+                } else
+                        srcline = NULL;
+                fprintf(s, "\n");
+                prev_buf_size = buf_size;
+                fflush(s);
+                if (!opts->hide_src_code && srcline) {
+                        args->offset = -1;
+                        args->line = strdup(srcline);
+                        args->line_nr = 0;
+                        args->ms.sym  = sym;
+                        dl = disasm_line__new(args);
+                        if (dl) {
+                                annotation_line__add(&dl->al,
+                                                     &notes->src->source);
+                        }
+                }
+                args->offset = pc;
+                args->line = buf + prev_buf_size;
+                args->line_nr = 0;
+                args->ms.sym  = sym;
+                dl = disasm_line__new(args);
+                if (dl)
+                        annotation_line__add(&dl->al, &notes->src->source);
+                pc += count;
+        } while (count > 0 && pc < len);
+        ret = 0;
+out:
+        free(prog_linfo);
+        free(btf);
+        fclose(s);
+        bfd_close(bfdf);
+        return ret;
+}
+#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
+                                   struct annotate_args *args __maybe_unused)
+{
+        return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
+}
+#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
        struct annotation_options *opts = args->options;
@@ -1701,7 +1860,9 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
        pr_debug("annotating [%p] %30s : [%p] %30s\n",
                 dso, dso->long_name, sym, sym->name);
-        if (dso__is_kcore(dso)) {
+        if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+                return symbol__disassemble_bpf(sym, args);
+        } else if (dso__is_kcore(dso)) {
                kce.kcore_filename = symfs_filename;
                kce.addr = map__rip_2objdump(map, sym->start);
                kce.offs = sym->start;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index df34fe483164..5bc0cf655d37 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -369,6 +369,7 @@ enum symbol_disassemble_errno {
        __SYMBOL_ANNOTATE_ERRNO__START          = -10000,
        SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX       = __SYMBOL_ANNOTATE_ERRNO__START,
+        SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
        __SYMBOL_ANNOTATE_ERRNO__END,
 };
diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h
new file mode 100644
index 000000000000..448cbb6b8d7e
--- /dev/null
+++ b/tools/perf/util/archinsn.h
@@ -0,0 +1,12 @@
+#ifndef INSN_H
+#define INSN_H 1
+struct perf_sample;
+struct machine;
+struct thread;
+void arch_fetch_insn(struct perf_sample *sample,
+                     struct thread *thread,
+                     struct machine *machine);
+#endif
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 028c8ec1f62a..2a4a0da35632 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -3,11 +3,17 @@
 #include <stdlib.h>
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/libbpf.h>
 #include <linux/btf.h>
+#include <linux/err.h>
 #include "bpf-event.h"
 #include "debug.h"
 #include "symbol.h"
 #include "machine.h"
+#include "env.h"
+#include "session.h"
+#include "map.h"
+#include "evlist.h"
 #define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
@@ -21,15 +27,122 @@ static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
        return ret;
 }
+static int machine__process_bpf_event_load(struct machine *machine,
+                                           union perf_event *event,
+                                           struct perf_sample *sample __maybe_unused)
+{
+        struct bpf_prog_info_linear *info_linear;
+        struct bpf_prog_info_node *info_node;
+        struct perf_env *env = machine->env;
+        int id = event->bpf_event.id;
+        unsigned int i;
+        /* perf-record, no need to handle bpf-event */
+        if (env == NULL)
+                return 0;
+        info_node = perf_env__find_bpf_prog_info(env, id);
+        if (!info_node)
+                return 0;
+        info_linear = info_node->info_linear;
+        for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) {
+                u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);
+                u64 addr = addrs[i];
+                struct map *map;
+                map = map_groups__find(&machine->kmaps, addr);
+                if (map) {
+                        map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO;
+                        map->dso->bpf_prog.id = id;
+                        map->dso->bpf_prog.sub_id = i;
+                        map->dso->bpf_prog.env = env;
+                }
+        }
+        return 0;
+}
 int machine__process_bpf_event(struct machine *machine __maybe_unused,
                               union perf_event *event,
                               struct perf_sample *sample __maybe_unused)
 {
        if (dump_trace)
                perf_event__fprintf_bpf_event(event, stdout);
+        switch (event->bpf_event.type) {
+        case PERF_BPF_EVENT_PROG_LOAD:
+                return machine__process_bpf_event_load(machine, event, sample);
+        case PERF_BPF_EVENT_PROG_UNLOAD:
+                /*
+                 * Do not free bpf_prog_info and btf of the program here,
+                 * as annotation still need them. They will be freed at
+                 * the end of the session.
+                 */
+                break;
+        default:
+                pr_debug("unexpected bpf_event type of %d\n",
+                         event->bpf_event.type);
+                break;
+        }
        return 0;
 }
+static int perf_env__fetch_btf(struct perf_env *env,
+                               u32 btf_id,
+                               struct btf *btf)
+{
+        struct btf_node *node;
+        u32 data_size;
+        const void *data;
+        data = btf__get_raw_data(btf, &data_size);
+        node = malloc(data_size + sizeof(struct btf_node));
+        if (!node)
+                return -1;
+        node->id = btf_id;
+        node->data_size = data_size;
+        memcpy(node->data, data, data_size);
+        perf_env__insert_btf(env, node);
+        return 0;
+}
+static int synthesize_bpf_prog_name(char *buf, int size,
+                                    struct bpf_prog_info *info,
+                                    struct btf *btf,
+                                    u32 sub_id)
+{
+        u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags);
+        void *func_infos = (void *)(uintptr_t)(info->func_info);
+        u32 sub_prog_cnt = info->nr_jited_ksyms;
+        const struct bpf_func_info *finfo;
+        const char *short_name = NULL;
+        const struct btf_type *t;
+        int name_len;
+        name_len = snprintf(buf, size, "bpf_prog_");
+        name_len += snprintf_hex(buf + name_len, size - name_len,
+                                 prog_tags[sub_id], BPF_TAG_SIZE);
+        if (btf) {
+                finfo = func_infos + sub_id * info->func_info_rec_size;
+                t = btf__type_by_id(btf, finfo->type_id);
+                short_name = btf__name_by_offset(btf, t->name_off);
+        } else if (sub_id == 0 && sub_prog_cnt == 1) {
+                /* no subprog */
+                if (info->name[0])
+                        short_name = info->name;
+        } else
+                short_name = "F";
+        if (short_name)
+                name_len += snprintf(buf + name_len, size - name_len,
+                                     "_%s", short_name);
+        return name_len;
+}
 /*
 * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf
 * program. One PERF_RECORD_BPF_EVENT is generated for the program. And
@@ -40,7 +153,7 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
 *   -1 for failures;
 *   -2 for lack of kernel support.
 */
-static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
+static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
                                               perf_event__handler_t process,
                                               struct machine *machine,
                                               int fd,
@@ -49,102 +162,71 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
 {
        struct ksymbol_event *ksymbol_event = &event->ksymbol_event;
        struct bpf_event *bpf_event = &event->bpf_event;
-        u32 sub_prog_cnt, i, func_info_rec_size = 0;
+        struct bpf_prog_info_linear *info_linear;
-        u8 (*prog_tags)[BPF_TAG_SIZE] = NULL;
+        struct perf_tool *tool = session->tool;
-        struct bpf_prog_info info = { .type = 0, };
+        struct bpf_prog_info_node *info_node;
-        u32 info_len = sizeof(info);
+        struct bpf_prog_info *info;
-        void *func_infos = NULL;
-        u64 *prog_addrs = NULL;
        struct btf *btf = NULL;
-        u32 *prog_lens = NULL;
+        struct perf_env *env;
-        bool has_btf = false;
+        u32 sub_prog_cnt, i;
-        char errbuf[512];
        int err = 0;
+        u64 arrays;
+        /*
+         * for perf-record and perf-report use header.env;
+         * otherwise, use global perf_env.
+         */
+        env = session->data ? &session->header.env : &perf_env;
-        /* Call bpf_obj_get_info_by_fd() to get sizes of arrays */
+        arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS;
-        err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+        arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+        arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+        arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS;
+        arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
-        if (err) {
+        info_linear = bpf_program__get_prog_info_linear(fd, arrays);
-                pr_debug("%s: failed to get BPF program info: %s, aborting\n",
+        if (IS_ERR_OR_NULL(info_linear)) {
-                         __func__, str_error_r(errno, errbuf, sizeof(errbuf)));
+                info_linear = NULL;
+                pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
                return -1;
        }
-        if (info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+        if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
                pr_debug("%s: the kernel is too old, aborting\n", __func__);
                return -2;
        }
+        info = &info_linear->info;
        /* number of ksyms, func_lengths, and tags should match */
-        sub_prog_cnt = info.nr_jited_ksyms;
+        sub_prog_cnt = info->nr_jited_ksyms;
-        if (sub_prog_cnt != info.nr_prog_tags ||
+        if (sub_prog_cnt != info->nr_prog_tags ||
-            sub_prog_cnt != info.nr_jited_func_lens)
+            sub_prog_cnt != info->nr_jited_func_lens)
                return -1;
        /* check BTF func info support */
-        if (info.btf_id && info.nr_func_info && info.func_info_rec_size) {
+        if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
                /* btf func info number should be same as sub_prog_cnt */
-                if (sub_prog_cnt != info.nr_func_info) {
+                if (sub_prog_cnt != info->nr_func_info) {
                        pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
-                        return -1;
+                        err = -1;
-                }
+                        goto out;
-                if (btf__get_from_id(info.btf_id, &btf)) {
-                        pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info.btf_id);
-                        return -1;
                }
-                func_info_rec_size = info.func_info_rec_size;
+                if (btf__get_from_id(info->btf_id, &btf)) {
-                func_infos = calloc(sub_prog_cnt, func_info_rec_size);
+                        pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
-                if (!func_infos) {
+                        err = -1;
-                        pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__);
+                        btf = NULL;
-                        return -1;
+                        goto out;
                }
-                has_btf = true;
+                perf_env__fetch_btf(env, info->btf_id, btf);
-        }
-        /*
-         * We need address, length, and tag for each sub program.
-         * Allocate memory and call bpf_obj_get_info_by_fd() again
-         */
-        prog_addrs = calloc(sub_prog_cnt, sizeof(u64));
-        if (!prog_addrs) {
-                pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__);
-                goto out;
-        }
-        prog_lens = calloc(sub_prog_cnt, sizeof(u32));
-        if (!prog_lens) {
-                pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__);
-                goto out;
-        }
-        prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE);
-        if (!prog_tags) {
-                pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__);
-                goto out;
-        }
-        memset(&info, 0, sizeof(info));
-        info.nr_jited_ksyms = sub_prog_cnt;
-        info.nr_jited_func_lens = sub_prog_cnt;
-        info.nr_prog_tags = sub_prog_cnt;
-        info.jited_ksyms = ptr_to_u64(prog_addrs);
-        info.jited_func_lens = ptr_to_u64(prog_lens);
-        info.prog_tags = ptr_to_u64(prog_tags);
-        info_len = sizeof(info);
-        if (has_btf) {
-                info.nr_func_info = sub_prog_cnt;
-                info.func_info_rec_size = func_info_rec_size;
-                info.func_info = ptr_to_u64(func_infos);
-        }
-        err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
-        if (err) {
-                pr_debug("%s: failed to get BPF program info, aborting\n", __func__);
-                goto out;
        }
        /* Synthesize PERF_RECORD_KSYMBOL */
        for (i = 0; i < sub_prog_cnt; i++) {
-                const struct bpf_func_info *finfo;
+                __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
-                const char *short_name = NULL;
+                __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
-                const struct btf_type *t;
                int name_len;
                *ksymbol_event = (struct ksymbol_event){
@@ -157,26 +239,9 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
                        .ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
                        .flags = 0,
                };
-                name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN,
-                                    "bpf_prog_");
-                name_len += snprintf_hex(ksymbol_event->name + name_len,
-                                         KSYM_NAME_LEN - name_len,
-                                         prog_tags[i], BPF_TAG_SIZE);
-                if (has_btf) {
-                        finfo = func_infos + i * info.func_info_rec_size;
-                        t = btf__type_by_id(btf, finfo->type_id);
-                        short_name = btf__name_by_offset(btf, t->name_off);
-                } else if (i == 0 && sub_prog_cnt == 1) {
-                        /* no subprog */
-                        if (info.name[0])
-                                short_name = info.name;
-                } else
-                        short_name = "F";
-                if (short_name)
-                        name_len += snprintf(ksymbol_event->name + name_len,
-                                             KSYM_NAME_LEN - name_len,
-                                             "_%s", short_name);
+                name_len = synthesize_bpf_prog_name(ksymbol_event->name,
+                                                    KSYM_NAME_LEN, info, btf, i);
                ksymbol_event->header.size += PERF_ALIGN(name_len + 1,
                                                         sizeof(u64));
@@ -186,8 +251,8 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
                                                     machine, process);
        }
-        /* Synthesize PERF_RECORD_BPF_EVENT */
+        if (!opts->no_bpf_event) {
-        if (opts->bpf_event) {
+                /* Synthesize PERF_RECORD_BPF_EVENT */
                *bpf_event = (struct bpf_event){
                        .header = {
                                .type = PERF_RECORD_BPF_EVENT,
@@ -195,25 +260,38 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
                        },
                        .type = PERF_BPF_EVENT_PROG_LOAD,
                        .flags = 0,
-                        .id = info.id,
+                        .id = info->id,
                };
-                memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE);
+                memcpy(bpf_event->tag, info->tag, BPF_TAG_SIZE);
                memset((void *)event + event->header.size, 0, machine->id_hdr_size);
                event->header.size += machine->id_hdr_size;
+                /* save bpf_prog_info to env */
+                info_node = malloc(sizeof(struct bpf_prog_info_node));
+                if (!info_node) {
+                        err = -1;
+                        goto out;
+                }
+                info_node->info_linear = info_linear;
+                perf_env__insert_bpf_prog_info(env, info_node);
+                info_linear = NULL;
+                /*
+                 * process after saving bpf_prog_info to env, so that
+                 * required information is ready for look up
+                 */
                err = perf_tool__process_synth_event(tool, event,
                                                     machine, process);
        }
 out:
-        free(prog_tags);
+        free(info_linear);
-        free(prog_lens);
-        free(prog_addrs);
-        free(func_infos);
        free(btf);
        return err ? -1 : 0;
 }
-int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+int perf_event__synthesize_bpf_events(struct perf_session *session,
                                      perf_event__handler_t process,
                                      struct machine *machine,
                                      struct record_opts *opts)
@@ -247,7 +325,7 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool,
                        continue;
                }
-                err = perf_event__synthesize_one_bpf_prog(tool, process,
+                err = perf_event__synthesize_one_bpf_prog(session, process,
                                                          machine, fd,
                                                          event, opts);
                close(fd);
@@ -261,3 +339,142 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool,
        free(event);
        return err;
 }
+static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
+{
+        struct bpf_prog_info_linear *info_linear;
+        struct bpf_prog_info_node *info_node;
+        struct btf *btf = NULL;
+        u64 arrays;
+        u32 btf_id;
+        int fd;
+        fd = bpf_prog_get_fd_by_id(id);
+        if (fd < 0)
+                return;
+        arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+        arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+        arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS;
+        arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+        arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
+        info_linear = bpf_program__get_prog_info_linear(fd, arrays);
+        if (IS_ERR_OR_NULL(info_linear)) {
+                pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+                goto out;
+        }
+        btf_id = info_linear->info.btf_id;
+        info_node = malloc(sizeof(struct bpf_prog_info_node));
+        if (info_node) {
+                info_node->info_linear = info_linear;
+                perf_env__insert_bpf_prog_info(env, info_node);
+        } else
+                free(info_linear);
+        if (btf_id == 0)
+                goto out;
+        if (btf__get_from_id(btf_id, &btf)) {
+                pr_debug("%s: failed to get BTF of id %u, aborting\n",
+                         __func__, btf_id);
+                goto out;
+        }
+        perf_env__fetch_btf(env, btf_id, btf);
+out:
+        free(btf);
+        close(fd);
+}
+static int bpf_event__sb_cb(union perf_event *event, void *data)
+{
+        struct perf_env *env = data;
+        if (event->header.type != PERF_RECORD_BPF_EVENT)
+                return -1;
+        switch (event->bpf_event.type) {
+        case PERF_BPF_EVENT_PROG_LOAD:
+                perf_env__add_bpf_info(env, event->bpf_event.id);
+        case PERF_BPF_EVENT_PROG_UNLOAD:
+                /*
+                 * Do not free bpf_prog_info and btf of the program here,
+                 * as annotation still need them. They will be freed at
+                 * the end of the session.
+                 */
+                break;
+        default:
+                pr_debug("unexpected bpf_event type of %d\n",
+                         event->bpf_event.type);
+                break;
+        }
+        return 0;
+}
+int bpf_event__add_sb_event(struct perf_evlist **evlist,
+                            struct perf_env *env)
+{
+        struct perf_event_attr attr = {
+                .type             = PERF_TYPE_SOFTWARE,
+                .config           = PERF_COUNT_SW_DUMMY,
+                .sample_id_all    = 1,
+                .watermark        = 1,
+                .bpf_event        = 1,
+                .size      = sizeof(attr), /* to capture ABI version */
+        };
+        /*
+         * Older gcc versions don't support designated initializers, like above,
+         * for unnamed union members, such as the following:
+         */
+        attr.wakeup_watermark = 1;
+        return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
+}
+void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+                                    struct perf_env *env,
+                                    FILE *fp)
+{
+        __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
+        __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
+        char name[KSYM_NAME_LEN];
+        struct btf *btf = NULL;
+        u32 sub_prog_cnt, i;
+        sub_prog_cnt = info->nr_jited_ksyms;
+        if (sub_prog_cnt != info->nr_prog_tags ||
+            sub_prog_cnt != info->nr_jited_func_lens)
+                return;
+        if (info->btf_id) {
+                struct btf_node *node;
+                node = perf_env__find_btf(env, info->btf_id);
+                if (node)
+                        btf = btf__new((__u8 *)(node->data),
+                                       node->data_size);
+        }
+        if (sub_prog_cnt == 1) {
+                synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, 0);
+                fprintf(fp, "# bpf_prog_info %u: %s addr 0x%llx size %u\n",
+                        info->id, name, prog_addrs[0], prog_lens[0]);
+                return;
+        }
+        fprintf(fp, "# bpf_prog_info %u:\n", info->id);
+        for (i = 0; i < sub_prog_cnt; i++) {
+                synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, i);
+                fprintf(fp, "# \tsub_prog %u: %s addr 0x%llx size %u\n",
+                        i, name, prog_addrs[i], prog_lens[i]);
+        }
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 7890067e1a37..04c33b3bfe28 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -3,22 +3,45 @@
 #define __PERF_BPF_EVENT_H
 #include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <pthread.h>
+#include <api/fd/array.h>
 #include "event.h"
+#include <stdio.h>
 struct machine;
 union perf_event;
+struct perf_env;
 struct perf_sample;
-struct perf_tool;
 struct record_opts;
+struct evlist;
+struct target;
+struct bpf_prog_info_node {
+        struct bpf_prog_info_linear     *info_linear;
+        struct rb_node                  rb_node;
+};
+struct btf_node {
+        struct rb_node  rb_node;
+        u32             id;
+        u32             data_size;
+        char            data[];
+};
 #ifdef HAVE_LIBBPF_SUPPORT
 int machine__process_bpf_event(struct machine *machine, union perf_event *event,
                               struct perf_sample *sample);
-int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+int perf_event__synthesize_bpf_events(struct perf_session *session,
                                      perf_event__handler_t process,
                                      struct machine *machine,
                                      struct record_opts *opts);
+int bpf_event__add_sb_event(struct perf_evlist **evlist,
+                                 struct perf_env *env);
+void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+                                    struct perf_env *env,
+                                    FILE *fp);
 #else
 static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
                                             union perf_event *event __maybe_unused,
@@ -27,12 +50,25 @@ static inline int machine__process_bpf_event(struct machine *machine __maybe_unu
        return 0;
 }
-static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __maybe_unused,
+static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused,
                                                    perf_event__handler_t process __maybe_unused,
                                                    struct machine *machine __maybe_unused,
                                                    struct record_opts *opts __maybe_unused)
 {
        return 0;
 }
+static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_unused,
+                                          struct perf_env *env __maybe_unused)
+{
+        return 0;
+}
+static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+                                                  struct perf_env *env __maybe_unused,
+                                                  FILE *fp __maybe_unused)
+{
+}
 #endif // HAVE_LIBBPF_SUPPORT
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff0d17920ed..0c5517a8d0b7 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -185,6 +185,7 @@ char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size)
        return bf;
 }
+/* The caller is responsible to free the returned buffer. */
 char *build_id_cache__origname(const char *sbuild_id)
 {
        char *linkname;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index fa092511c52b..7e3c1b60120c 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -633,11 +633,10 @@ static int collect_config(const char *var, const char *value,
        }
        ret = set_value(item, value);
-        return ret;
 out_free:
        free(key);
-        return -1;
+        return ret;
 }
 int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e098e189f93e..6a64f713710d 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -14,6 +14,7 @@
 #include "data.h"
 #include "util.h"
 #include "debug.h"
+#include "header.h"
 static void close_dir(struct perf_data_file *files, int nr)
 {
@@ -34,12 +35,16 @@ int perf_data__create_dir(struct perf_data *data, int nr)
        struct perf_data_file *files = NULL;
        int i, ret = -1;
+        if (WARN_ON(!data->is_dir))
+                return -EINVAL;
        files = zalloc(nr * sizeof(*files));
        if (!files)
                return -ENOMEM;
-        data->dir.files = files;
+        data->dir.version = PERF_DIR_VERSION;
-        data->dir.nr    = nr;
+        data->dir.files   = files;
+        data->dir.nr      = nr;
        for (i = 0; i < nr; i++) {
                struct perf_data_file *file = &files[i];
@@ -69,6 +74,13 @@ int perf_data__open_dir(struct perf_data *data)
        DIR *dir;
        int nr = 0;
+        if (WARN_ON(!data->is_dir))
+                return -EINVAL;
+        /* The version is provided by DIR_FORMAT feature. */
+        if (WARN_ON(data->dir.version != PERF_DIR_VERSION))
+                return -1;
        dir = opendir(data->path);
        if (!dir)
                return -EINVAL;
@@ -118,6 +130,26 @@ out_err:
        return ret;
 }
+int perf_data__update_dir(struct perf_data *data)
+{
+        int i;
+        if (WARN_ON(!data->is_dir))
+                return -EINVAL;
+        for (i = 0; i < data->dir.nr; i++) {
+                struct perf_data_file *file = &data->dir.files[i];
+                struct stat st;
+                if (fstat(file->fd, &st))
+                        return -1;
+                file->size = st.st_size;
+        }
+        return 0;
+}
 static bool check_pipe(struct perf_data *data)
 {
        struct stat st;
@@ -173,6 +205,16 @@ static int check_backup(struct perf_data *data)
        return 0;
 }
+static bool is_dir(struct perf_data *data)
+{
+        struct stat st;
+        if (stat(data->path, &st))
+                return false;
+        return (st.st_mode & S_IFMT) == S_IFDIR;
+}
 static int open_file_read(struct perf_data *data)
 {
        struct stat st;
@@ -254,6 +296,30 @@ static int open_file_dup(struct perf_data *data)
        return open_file(data);
 }
+static int open_dir(struct perf_data *data)
+{
+        int ret;
+        /*
+         * So far we open only the header, so we can read the data version and
+         * layout.
+         */
+        if (asprintf(&data->file.path, "%s/header", data->path) < 0)
+                return -1;
+        if (perf_data__is_write(data) &&
+            mkdir(data->path, S_IRWXU) < 0)
+                return -1;
+        ret = open_file(data);
+        /* Cleanup whatever we managed to create so far. */
+        if (ret && perf_data__is_write(data))
+                rm_rf_perf_data(data->path);
+        return ret;
+}
 int perf_data__open(struct perf_data *data)
 {
        if (check_pipe(data))
@@ -265,11 +331,18 @@ int perf_data__open(struct perf_data *data)
        if (check_backup(data))
                return -1;
-        return open_file_dup(data);
+        if (perf_data__is_read(data))
+                data->is_dir = is_dir(data);
+        return perf_data__is_dir(data) ?
+               open_dir(data) : open_file_dup(data);
 }
 void perf_data__close(struct perf_data *data)
 {
+        if (perf_data__is_dir(data))
+                perf_data__close_dir(data);
        zfree(&data->file.path);
        close(data->file.fd);
 }
@@ -288,9 +361,9 @@ ssize_t perf_data__write(struct perf_data *data,
 int perf_data__switch(struct perf_data *data,
                           const char *postfix,
-                           size_t pos, bool at_exit)
+                           size_t pos, bool at_exit,
+                           char **new_filepath)
 {
-        char *new_filepath;
        int ret;
        if (check_pipe(data))
@@ -298,15 +371,15 @@ int perf_data__switch(struct perf_data *data,
        if (perf_data__is_read(data))
                return -EINVAL;
-        if (asprintf(&new_filepath, "%s.%s", data->path, postfix) < 0)
+        if (asprintf(new_filepath, "%s.%s", data->path, postfix) < 0)
                return -ENOMEM;
        /*
         * Only fire a warning, don't return error, continue fill
         * original file.
         */
-        if (rename(data->path, new_filepath))
+        if (rename(data->path, *new_filepath))
-                pr_warning("Failed to rename %s to %s\n", data->path, new_filepath);
+                pr_warning("Failed to rename %s to %s\n", data->path, *new_filepath);
        if (!at_exit) {
                close(data->file.fd);
@@ -323,6 +396,22 @@ int perf_data__switch(struct perf_data *data,
        }
        ret = data->file.fd;
 out:
-        free(new_filepath);
        return ret;
 }
+unsigned long perf_data__size(struct perf_data *data)
+{
+        u64 size = data->file.size;
+        int i;
+        if (!data->is_dir)
+                return size;
+        for (i = 0; i < data->dir.nr; i++) {
+                struct perf_data_file *file = &data->dir.files[i];
+                size += file->size;
+        }
+        return size;
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 14b47be2bd69..259868a39019 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -19,10 +19,12 @@ struct perf_data {
        const char              *path;
        struct perf_data_file    file;
        bool                     is_pipe;
+        bool                     is_dir;
        bool                     force;
        enum perf_data_mode      mode;
        struct {
+                u64                      version;
                struct perf_data_file   *files;
                int                      nr;
        } dir;
@@ -43,14 +45,14 @@ static inline int perf_data__is_pipe(struct perf_data *data)
        return data->is_pipe;
 }
-static inline int perf_data__fd(struct perf_data *data)
+static inline bool perf_data__is_dir(struct perf_data *data)
 {
-        return data->file.fd;
+        return data->is_dir;
 }
-static inline unsigned long perf_data__size(struct perf_data *data)
+static inline int perf_data__fd(struct perf_data *data)
 {
-        return data->file.size;
+        return data->file.fd;
 }
 int perf_data__open(struct perf_data *data);
@@ -68,9 +70,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 */
 int perf_data__switch(struct perf_data *data,
                           const char *postfix,
-                           size_t pos, bool at_exit);
+                           size_t pos, bool at_exit, char **new_filepath);
 int perf_data__create_dir(struct perf_data *data, int nr);
 int perf_data__open_dir(struct perf_data *data);
 void perf_data__close_dir(struct perf_data *data);
+int perf_data__update_dir(struct perf_data *data);
+unsigned long perf_data__size(struct perf_data *data);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index ba58ba603b69..e059976d9d93 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -184,6 +184,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
        case DSO_BINARY_TYPE__KALLSYMS:
        case DSO_BINARY_TYPE__GUEST_KALLSYMS:
        case DSO_BINARY_TYPE__JAVA_JIT:
+        case DSO_BINARY_TYPE__BPF_PROG_INFO:
        case DSO_BINARY_TYPE__NOT_FOUND:
                ret = -1;
                break;
@@ -1141,28 +1142,34 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 static void dso__set_basename(struct dso *dso)
 {
-       /*
+        char *base, *lname;
-        * basename() may modify path buffer, so we must pass
+        int tid;
-        * a copy.
-        */
-       char *base, *lname = strdup(dso->long_name);
-       if (!lname)
+        if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
-               return;
+                if (asprintf(&base, "[JIT] tid %d", tid) < 0)
+                        return;
-       /*
+        } else {
-        * basename() may return a pointer to internal
+              /*
-        * storage which is reused in subsequent calls
+               * basename() may modify path buffer, so we must pass
-        * so copy the result.
+               * a copy.
-        */
+               */
-       base = strdup(basename(lname));
+                lname = strdup(dso->long_name);
+                if (!lname)
+                        return;
-       free(lname);
+                /*
+                 * basename() may return a pointer to internal
+                 * storage which is reused in subsequent calls
+                 * so copy the result.
+                 */
+                base = strdup(basename(lname));
-       if (!base)
+                free(lname);
-               return;
-       dso__set_short_name(dso, base, true);
+                if (!base)
+                        return;
+        }
+        dso__set_short_name(dso, base, true);
 }
 int dso__name_len(const struct dso *dso)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index bb417c54c25a..6e3f63781e51 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -14,6 +14,7 @@
 struct machine;
 struct map;
+struct perf_env;
 enum dso_binary_type {
        DSO_BINARY_TYPE__KALLSYMS = 0,
@@ -35,6 +36,7 @@ enum dso_binary_type {
        DSO_BINARY_TYPE__KCORE,
        DSO_BINARY_TYPE__GUEST_KCORE,
        DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+        DSO_BINARY_TYPE__BPF_PROG_INFO,
        DSO_BINARY_TYPE__NOT_FOUND,
 };
@@ -189,6 +191,12 @@ struct dso {
                u64              debug_frame_offset;
                u64              eh_frame_hdr_offset;
        } data;
+        /* bpf prog information */
+        struct {
+                u32             id;
+                u32             sub_id;
+                struct perf_env *env;
+        } bpf_prog;
        union { /* Tool specific area */
                void     *priv;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 4c23779e271a..c6351b557bb0 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -3,15 +3,163 @@
 #include "env.h"
 #include "sane_ctype.h"
 #include "util.h"
+#include "bpf-event.h"
 #include <errno.h>
 #include <sys/utsname.h>
+#include <bpf/libbpf.h>
 struct perf_env perf_env;
+void perf_env__insert_bpf_prog_info(struct perf_env *env,
+                                    struct bpf_prog_info_node *info_node)
+{
+        __u32 prog_id = info_node->info_linear->info.id;
+        struct bpf_prog_info_node *node;
+        struct rb_node *parent = NULL;
+        struct rb_node **p;
+        down_write(&env->bpf_progs.lock);
+        p = &env->bpf_progs.infos.rb_node;
+        while (*p != NULL) {
+                parent = *p;
+                node = rb_entry(parent, struct bpf_prog_info_node, rb_node);
+                if (prog_id < node->info_linear->info.id) {
+                        p = &(*p)->rb_left;
+                } else if (prog_id > node->info_linear->info.id) {
+                        p = &(*p)->rb_right;
+                } else {
+                        pr_debug("duplicated bpf prog info %u\n", prog_id);
+                        goto out;
+                }
+        }
+        rb_link_node(&info_node->rb_node, parent, p);
+        rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
+        env->bpf_progs.infos_cnt++;
+out:
+        up_write(&env->bpf_progs.lock);
+}
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+                                                        __u32 prog_id)
+{
+        struct bpf_prog_info_node *node = NULL;
+        struct rb_node *n;
+        down_read(&env->bpf_progs.lock);
+        n = env->bpf_progs.infos.rb_node;
+        while (n) {
+                node = rb_entry(n, struct bpf_prog_info_node, rb_node);
+                if (prog_id < node->info_linear->info.id)
+                        n = n->rb_left;
+                else if (prog_id > node->info_linear->info.id)
+                        n = n->rb_right;
+                else
+                        break;
+        }
+        up_read(&env->bpf_progs.lock);
+        return node;
+}
+void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
+        struct rb_node *parent = NULL;
+        __u32 btf_id = btf_node->id;
+        struct btf_node *node;
+        struct rb_node **p;
+        down_write(&env->bpf_progs.lock);
+        p = &env->bpf_progs.btfs.rb_node;
+        while (*p != NULL) {
+                parent = *p;
+                node = rb_entry(parent, struct btf_node, rb_node);
+                if (btf_id < node->id) {
+                        p = &(*p)->rb_left;
+                } else if (btf_id > node->id) {
+                        p = &(*p)->rb_right;
+                } else {
+                        pr_debug("duplicated btf %u\n", btf_id);
+                        goto out;
+                }
+        }
+        rb_link_node(&btf_node->rb_node, parent, p);
+        rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
+        env->bpf_progs.btfs_cnt++;
+out:
+        up_write(&env->bpf_progs.lock);
+}
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
+        struct btf_node *node = NULL;
+        struct rb_node *n;
+        down_read(&env->bpf_progs.lock);
+        n = env->bpf_progs.btfs.rb_node;
+        while (n) {
+                node = rb_entry(n, struct btf_node, rb_node);
+                if (btf_id < node->id)
+                        n = n->rb_left;
+                else if (btf_id > node->id)
+                        n = n->rb_right;
+                else
+                        break;
+        }
+        up_read(&env->bpf_progs.lock);
+        return node;
+}
+/* purge data in bpf_progs.infos tree */
+static void perf_env__purge_bpf(struct perf_env *env)
+{
+        struct rb_root *root;
+        struct rb_node *next;
+        down_write(&env->bpf_progs.lock);
+        root = &env->bpf_progs.infos;
+        next = rb_first(root);
+        while (next) {
+                struct bpf_prog_info_node *node;
+                node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+                next = rb_next(&node->rb_node);
+                rb_erase(&node->rb_node, root);
+                free(node);
+        }
+        env->bpf_progs.infos_cnt = 0;
+        root = &env->bpf_progs.btfs;
+        next = rb_first(root);
+        while (next) {
+                struct btf_node *node;
+                node = rb_entry(next, struct btf_node, rb_node);
+                next = rb_next(&node->rb_node);
+                rb_erase(&node->rb_node, root);
+                free(node);
+        }
+        env->bpf_progs.btfs_cnt = 0;
+        up_write(&env->bpf_progs.lock);
+}
 void perf_env__exit(struct perf_env *env)
 {
        int i;
+        perf_env__purge_bpf(env);
        zfree(&env->hostname);
        zfree(&env->os_release);
        zfree(&env->version);
@@ -38,6 +186,13 @@ void perf_env__exit(struct perf_env *env)
        zfree(&env->memory_nodes);
 }
+void perf_env__init(struct perf_env *env)
+{
+        env->bpf_progs.infos = RB_ROOT;
+        env->bpf_progs.btfs = RB_ROOT;
+        init_rwsem(&env->bpf_progs.lock);
+}
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 {
        int i;
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index d01b8355f4ca..4f8e2b485c01 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -3,7 +3,9 @@
 #define __PERF_ENV_H
 #include <linux/types.h>
+#include <linux/rbtree.h>
 #include "cpumap.h"
+#include "rwsem.h"
 struct cpu_topology_map {
        int     socket_id;
@@ -64,8 +66,23 @@ struct perf_env {
        struct memory_node      *memory_nodes;
        unsigned long long       memory_bsize;
        u64                     clockid_res_ns;
+        /*
+         * bpf_info_lock protects bpf rbtrees. This is needed because the
+         * trees are accessed by different threads in perf-top
+         */
+        struct {
+                struct rw_semaphore     lock;
+                struct rb_root          infos;
+                u32                     infos_cnt;
+                struct rb_root          btfs;
+                u32                     btfs_cnt;
+        } bpf_progs;
 };
+struct bpf_prog_info_node;
+struct btf_node;
 extern struct perf_env perf_env;
 void perf_env__exit(struct perf_env *env);
@@ -80,4 +97,11 @@ const char *perf_env__arch(struct perf_env *env);
 const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
+void perf_env__init(struct perf_env *env);
+void perf_env__insert_bpf_prog_info(struct perf_env *env,
+                                    struct bpf_prog_info_node *info_node);
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+                                                        __u32 prog_id);
+void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ed20f4379956..ec78e93085de 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -19,6 +19,7 @@
 #include "debug.h"
 #include "units.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
 #include <signal.h>
 #include <unistd.h>
@@ -1856,3 +1857,121 @@ struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list,
        }
        return leader;
 }
+int perf_evlist__add_sb_event(struct perf_evlist **evlist,
+                              struct perf_event_attr *attr,
+                              perf_evsel__sb_cb_t cb,
+                              void *data)
+{
+        struct perf_evsel *evsel;
+        bool new_evlist = (*evlist) == NULL;
+        if (*evlist == NULL)
+                *evlist = perf_evlist__new();
+        if (*evlist == NULL)
+                return -1;
+        if (!attr->sample_id_all) {
+                pr_warning("enabling sample_id_all for all side band events\n");
+                attr->sample_id_all = 1;
+        }
+        evsel = perf_evsel__new_idx(attr, (*evlist)->nr_entries);
+        if (!evsel)
+                goto out_err;
+        evsel->side_band.cb = cb;
+        evsel->side_band.data = data;
+        perf_evlist__add(*evlist, evsel);
+        return 0;
+out_err:
+        if (new_evlist) {
+                perf_evlist__delete(*evlist);
+                *evlist = NULL;
+        }
+        return -1;
+}
+static void *perf_evlist__poll_thread(void *arg)
+{
+        struct perf_evlist *evlist = arg;
+        bool draining = false;
+        int i;
+        while (draining || !(evlist->thread.done)) {
+                if (draining)
+                        draining = false;
+                else if (evlist->thread.done)
+                        draining = true;
+                if (!draining)
+                        perf_evlist__poll(evlist, 1000);
+                for (i = 0; i < evlist->nr_mmaps; i++) {
+                        struct perf_mmap *map = &evlist->mmap[i];
+                        union perf_event *event;
+                        if (perf_mmap__read_init(map))
+                                continue;
+                        while ((event = perf_mmap__read_event(map)) != NULL) {
+                                struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+                                if (evsel && evsel->side_band.cb)
+                                        evsel->side_band.cb(event, evsel->side_band.data);
+                                else
+                                        pr_warning("cannot locate proper evsel for the side band event\n");
+                                perf_mmap__consume(map);
+                        }
+                        perf_mmap__read_done(map);
+                }
+        }
+        return NULL;
+}
+int perf_evlist__start_sb_thread(struct perf_evlist *evlist,
+                                 struct target *target)
+{
+        struct perf_evsel *counter;
+        if (!evlist)
+                return 0;
+        if (perf_evlist__create_maps(evlist, target))
+                goto out_delete_evlist;
+        evlist__for_each_entry(evlist, counter) {
+                if (perf_evsel__open(counter, evlist->cpus,
+                                     evlist->threads) < 0)
+                        goto out_delete_evlist;
+        }
+        if (perf_evlist__mmap(evlist, UINT_MAX))
+                goto out_delete_evlist;
+        evlist__for_each_entry(evlist, counter) {
+                if (perf_evsel__enable(counter))
+                        goto out_delete_evlist;
+        }
+        evlist->thread.done = 0;
+        if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
+                goto out_delete_evlist;
+        return 0;
+out_delete_evlist:
+        perf_evlist__delete(evlist);
+        evlist = NULL;
+        return -1;
+}
+void perf_evlist__stop_sb_thread(struct perf_evlist *evlist)
+{
+        if (!evlist)
+                return;
+        evlist->thread.done = 1;
+        pthread_join(evlist->thread.th, NULL);
+        perf_evlist__delete(evlist);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 744906dd4887..dcb68f34d2cd 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,10 @@ struct perf_evlist {
                                       struct perf_sample *sample);
        u64             first_sample_time;
        u64             last_sample_time;
+        struct {
+                pthread_t               th;
+                volatile int            done;
+        } thread;
 };
 struct perf_evsel_str_handler {
@@ -87,6 +91,14 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
 int perf_evlist__add_dummy(struct perf_evlist *evlist);
+int perf_evlist__add_sb_event(struct perf_evlist **evlist,
+                              struct perf_event_attr *attr,
+                              perf_evsel__sb_cb_t cb,
+                              void *data);
+int perf_evlist__start_sb_thread(struct perf_evlist *evlist,
+                                 struct target *target);
+void perf_evlist__stop_sb_thread(struct perf_evlist *evlist);
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
                           const char *sys, const char *name, void *handler);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3bbf73e979c0..7835e05f0c0a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1036,7 +1036,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
        attr->mmap2 = track && !perf_missing_features.mmap2;
        attr->comm  = track;
        attr->ksymbol = track && !perf_missing_features.ksymbol;
-        attr->bpf_event = track && opts->bpf_event &&
+        attr->bpf_event = track && !opts->no_bpf_event &&
                !perf_missing_features.bpf_event;
        if (opts->record_namespaces)
@@ -1292,6 +1292,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 {
        assert(list_empty(&evsel->node));
        assert(evsel->evlist == NULL);
+        perf_evsel__free_counts(evsel);
        perf_evsel__free_fd(evsel);
        perf_evsel__free_id(evsel);
        perf_evsel__free_config_terms(evsel);
@@ -1342,10 +1343,9 @@ void perf_counts_values__scale(struct perf_counts_values *count,
                        count->val = 0;
                } else if (count->run < count->ena) {
                        scaled = 1;
-                        count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+                        count->val = (u64)((double) count->val * count->ena / count->run);
                }
-        } else
+        }
-                count->ena = count->run = 0;
        if (pscaled)
                *pscaled = scaled;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cc578e02e08f..0f2c6c93d721 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -73,6 +73,8 @@ struct perf_evsel_config_term {
 struct perf_stat_evsel;
+typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
 /** struct perf_evsel - event selector
 *
 * @evlist - evlist this evsel is in, if it is in one.
@@ -151,6 +153,10 @@ struct perf_evsel {
        bool                    collect_stat;
        bool                    weak_group;
        const char              *pmu_name;
+        struct {
+                perf_evsel__sb_cb_t     *cb;
+                void                    *data;
+        } side_band;
 };
 union u64_swap {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 01b324c275b9..b9e693825873 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -18,6 +18,7 @@
 #include <sys/utsname.h>
 #include <linux/time64.h>
 #include <dirent.h>
+#include <bpf/libbpf.h>
 #include "evlist.h"
 #include "evsel.h"
@@ -40,6 +41,7 @@
 #include "time-utils.h"
 #include "units.h"
 #include "cputopo.h"
+#include "bpf-event.h"
 #include "sane_ctype.h"
@@ -861,6 +863,104 @@ static int write_clockid(struct feat_fd *ff,
                        sizeof(ff->ph->env.clockid_res_ns));
 }
+static int write_dir_format(struct feat_fd *ff,
+                            struct perf_evlist *evlist __maybe_unused)
+{
+        struct perf_session *session;
+        struct perf_data *data;
+        session = container_of(ff->ph, struct perf_session, header);
+        data = session->data;
+        if (WARN_ON(!perf_data__is_dir(data)))
+                return -1;
+        return do_write(ff, &data->dir.version, sizeof(data->dir.version));
+}
+#ifdef HAVE_LIBBPF_SUPPORT
+static int write_bpf_prog_info(struct feat_fd *ff,
+                               struct perf_evlist *evlist __maybe_unused)
+{
+        struct perf_env *env = &ff->ph->env;
+        struct rb_root *root;
+        struct rb_node *next;
+        int ret;
+        down_read(&env->bpf_progs.lock);
+        ret = do_write(ff, &env->bpf_progs.infos_cnt,
+                       sizeof(env->bpf_progs.infos_cnt));
+        if (ret < 0)
+                goto out;
+        root = &env->bpf_progs.infos;
+        next = rb_first(root);
+        while (next) {
+                struct bpf_prog_info_node *node;
+                size_t len;
+                node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+                next = rb_next(&node->rb_node);
+                len = sizeof(struct bpf_prog_info_linear) +
+                        node->info_linear->data_len;
+                /* before writing to file, translate address to offset */
+                bpf_program__bpil_addr_to_offs(node->info_linear);
+                ret = do_write(ff, node->info_linear, len);
+                /*
+                 * translate back to address even when do_write() fails,
+                 * so that this function never changes the data.
+                 */
+                bpf_program__bpil_offs_to_addr(node->info_linear);
+                if (ret < 0)
+                        goto out;
+        }
+out:
+        up_read(&env->bpf_progs.lock);
+        return ret;
+}
+#else // HAVE_LIBBPF_SUPPORT
+static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused,
+                               struct perf_evlist *evlist __maybe_unused)
+{
+        return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+static int write_bpf_btf(struct feat_fd *ff,
+                         struct perf_evlist *evlist __maybe_unused)
+{
+        struct perf_env *env = &ff->ph->env;
+        struct rb_root *root;
+        struct rb_node *next;
+        int ret;
+        down_read(&env->bpf_progs.lock);
+        ret = do_write(ff, &env->bpf_progs.btfs_cnt,
+                       sizeof(env->bpf_progs.btfs_cnt));
+        if (ret < 0)
+                goto out;
+        root = &env->bpf_progs.btfs;
+        next = rb_first(root);
+        while (next) {
+                struct btf_node *node;
+                node = rb_entry(next, struct btf_node, rb_node);
+                next = rb_next(&node->rb_node);
+                ret = do_write(ff, &node->id,
+                               sizeof(u32) * 2 + node->data_size);
+                if (ret < 0)
+                        goto out;
+        }
+out:
+        up_read(&env->bpf_progs.lock);
+        return ret;
+}
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
        struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1341,6 +1441,63 @@ static void print_clockid(struct feat_fd *ff, FILE *fp)
                ff->ph->env.clockid_res_ns * 1000);
 }
+static void print_dir_format(struct feat_fd *ff, FILE *fp)
+{
+        struct perf_session *session;
+        struct perf_data *data;
+        session = container_of(ff->ph, struct perf_session, header);
+        data = session->data;
+        fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version);
+}
+static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
+{
+        struct perf_env *env = &ff->ph->env;
+        struct rb_root *root;
+        struct rb_node *next;
+        down_read(&env->bpf_progs.lock);
+        root = &env->bpf_progs.infos;
+        next = rb_first(root);
+        while (next) {
+                struct bpf_prog_info_node *node;
+                node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+                next = rb_next(&node->rb_node);
+                bpf_event__print_bpf_prog_info(&node->info_linear->info,
+                                               env, fp);
+        }
+        up_read(&env->bpf_progs.lock);
+}
+static void print_bpf_btf(struct feat_fd *ff, FILE *fp)
+{
+        struct perf_env *env = &ff->ph->env;
+        struct rb_root *root;
+        struct rb_node *next;
+        down_read(&env->bpf_progs.lock);
+        root = &env->bpf_progs.btfs;
+        next = rb_first(root);
+        while (next) {
+                struct btf_node *node;
+                node = rb_entry(next, struct btf_node, rb_node);
+                next = rb_next(&node->rb_node);
+                fprintf(fp, "# btf info of id %u\n", node->id);
+        }
+        up_read(&env->bpf_progs.lock);
+}
 static void free_event_desc(struct perf_evsel *events)
 {
        struct perf_evsel *evsel;
@@ -2373,6 +2530,139 @@ static int process_clockid(struct feat_fd *ff,
        return 0;
 }
+static int process_dir_format(struct feat_fd *ff,
+                              void *_data __maybe_unused)
+{
+        struct perf_session *session;
+        struct perf_data *data;
+        session = container_of(ff->ph, struct perf_session, header);
+        data = session->data;
+        if (WARN_ON(!perf_data__is_dir(data)))
+                return -1;
+        return do_read_u64(ff, &data->dir.version);
+}
+#ifdef HAVE_LIBBPF_SUPPORT
+static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
+{
+        struct bpf_prog_info_linear *info_linear;
+        struct bpf_prog_info_node *info_node;
+        struct perf_env *env = &ff->ph->env;
+        u32 count, i;
+        int err = -1;
+        if (ff->ph->needs_swap) {
+                pr_warning("interpreting bpf_prog_info from systems with endianity is not yet supported\n");
+                return 0;
+        }
+        if (do_read_u32(ff, &count))
+                return -1;
+        down_write(&env->bpf_progs.lock);
+        for (i = 0; i < count; ++i) {
+                u32 info_len, data_len;
+                info_linear = NULL;
+                info_node = NULL;
+                if (do_read_u32(ff, &info_len))
+                        goto out;
+                if (do_read_u32(ff, &data_len))
+                        goto out;
+                if (info_len > sizeof(struct bpf_prog_info)) {
+                        pr_warning("detected invalid bpf_prog_info\n");
+                        goto out;
+                }
+                info_linear = malloc(sizeof(struct bpf_prog_info_linear) +
+                                     data_len);
+                if (!info_linear)
+                        goto out;
+                info_linear->info_len = sizeof(struct bpf_prog_info);
+                info_linear->data_len = data_len;
+                if (do_read_u64(ff, (u64 *)(&info_linear->arrays)))
+                        goto out;
+                if (__do_read(ff, &info_linear->info, info_len))
+                        goto out;
+                if (info_len < sizeof(struct bpf_prog_info))
+                        memset(((void *)(&info_linear->info)) + info_len, 0,
+                               sizeof(struct bpf_prog_info) - info_len);
+                if (__do_read(ff, info_linear->data, data_len))
+                        goto out;
+                info_node = malloc(sizeof(struct bpf_prog_info_node));
+                if (!info_node)
+                        goto out;
+                /* after reading from file, translate offset to address */
+                bpf_program__bpil_offs_to_addr(info_linear);
+                info_node->info_linear = info_linear;
+                perf_env__insert_bpf_prog_info(env, info_node);
+        }
+        return 0;
+out:
+        free(info_linear);
+        free(info_node);
+        up_write(&env->bpf_progs.lock);
+        return err;
+}
+#else // HAVE_LIBBPF_SUPPORT
+static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused)
+{
+        return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
+{
+        struct perf_env *env = &ff->ph->env;
+        u32 count, i;
+        if (ff->ph->needs_swap) {
+                pr_warning("interpreting btf from systems with endianity is not yet supported\n");
+                return 0;
+        }
+        if (do_read_u32(ff, &count))
+                return -1;
+        down_write(&env->bpf_progs.lock);
+        for (i = 0; i < count; ++i) {
+                struct btf_node *node;
+                u32 id, data_size;
+                if (do_read_u32(ff, &id))
+                        return -1;
+                if (do_read_u32(ff, &data_size))
+                        return -1;
+                node = malloc(sizeof(struct btf_node) + data_size);
+                if (!node)
+                        return -1;
+                node->id = id;
+                node->data_size = data_size;
+                if (__do_read(ff, node->data, data_size)) {
+                        free(node);
+                        return -1;
+                }
+                perf_env__insert_btf(env, node);
+        }
+        up_write(&env->bpf_progs.lock);
+        return 0;
+}
 struct feature_ops {
        int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
        void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2432,7 +2722,10 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
        FEAT_OPN(CACHE,         cache,          true),
        FEAT_OPR(SAMPLE_TIME,   sample_time,    false),
        FEAT_OPR(MEM_TOPOLOGY,  mem_topology,   true),
-        FEAT_OPR(CLOCKID,       clockid,        false)
+        FEAT_OPR(CLOCKID,       clockid,        false),
+        FEAT_OPN(DIR_FORMAT,    dir_format,     false),
+        FEAT_OPR(BPF_PROG_INFO, bpf_prog_info,  false),
+        FEAT_OPR(BPF_BTF,       bpf_btf,        false),
 };
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 0d553ddca0a3..386da49e1bfa 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,9 @@ enum {
        HEADER_SAMPLE_TIME,
        HEADER_MEM_TOPOLOGY,
        HEADER_CLOCKID,
+        HEADER_DIR_FORMAT,
+        HEADER_BPF_PROG_INFO,
+        HEADER_BPF_BTF,
        HEADER_LAST_FEATURE,
        HEADER_FEAT_BITS        = 256,
 };
@@ -48,6 +51,10 @@ enum perf_header_version {
        PERF_HEADER_VERSION_2,
 };
+enum perf_dir_version {
+        PERF_DIR_VERSION        = 1,
+};
 struct perf_file_section {
        u64 offset;
        u64 size;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f9eb95bf3938..7ace7a10054d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -19,6 +19,7 @@
 #include <math.h>
 #include <inttypes.h>
 #include <sys/param.h>
+#include <linux/time64.h>
 static bool hists__filter_entry_by_dso(struct hists *hists,
                                       struct hist_entry *he);
@@ -192,6 +193,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
        hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
        hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
        hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
+        hists__new_col_len(hists, HISTC_TIME, 12);
        if (h->srcline) {
                len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
@@ -246,6 +248,14 @@ static void he_stat__add_cpumode_period(struct he_stat *he_stat,
        }
 }
+static long hist_time(unsigned long htime)
+{
+        unsigned long time_quantum = symbol_conf.time_quantum;
+        if (time_quantum)
+                return (htime / time_quantum) * time_quantum;
+        return htime;
+}
 static void he_stat__add_period(struct he_stat *he_stat, u64 period,
                                u64 weight)
 {
@@ -426,6 +436,13 @@ static int hist_entry__init(struct hist_entry *he,
                        goto err_rawdata;
        }
+        if (symbol_conf.res_sample) {
+                he->res_samples = calloc(sizeof(struct res_sample),
+                                        symbol_conf.res_sample);
+                if (!he->res_samples)
+                        goto err_srcline;
+        }
        INIT_LIST_HEAD(&he->pairs.node);
        thread__get(he->thread);
        he->hroot_in  = RB_ROOT_CACHED;
@@ -436,6 +453,9 @@ static int hist_entry__init(struct hist_entry *he,
        return 0;
+err_srcline:
+        free(he->srcline);
 err_rawdata:
        free(he->raw_data);
@@ -593,6 +613,32 @@ out:
        return he;
 }
+static unsigned random_max(unsigned high)
+{
+        unsigned thresh = -high % high;
+        for (;;) {
+                unsigned r = random();
+                if (r >= thresh)
+                        return r % high;
+        }
+}
+static void hists__res_sample(struct hist_entry *he, struct perf_sample *sample)
+{
+        struct res_sample *r;
+        int j;
+        if (he->num_res < symbol_conf.res_sample) {
+                j = he->num_res++;
+        } else {
+                j = random_max(symbol_conf.res_sample);
+        }
+        r = &he->res_samples[j];
+        r->time = sample->time;
+        r->cpu = sample->cpu;
+        r->tid = sample->tid;
+}
 static struct hist_entry*
 __hists__add_entry(struct hists *hists,
                   struct addr_location *al,
@@ -635,10 +681,13 @@ __hists__add_entry(struct hists *hists,
                .raw_data = sample->raw_data,
                .raw_size = sample->raw_size,
                .ops = ops,
+                .time = hist_time(sample->time),
        }, *he = hists__findnew_entry(hists, &entry, al, sample_self);
        if (!hists->has_callchains && he && he->callchain_size != 0)
                hists->has_callchains = true;
+        if (he && symbol_conf.res_sample)
+                hists__res_sample(he, sample);
        return he;
 }
@@ -1062,8 +1111,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
        err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
                                        iter->evsel, al, max_stack_depth);
-        if (err)
+        if (err) {
+                map__put(alm);
                return err;
+        }
        err = iter->ops->prepare_entry(iter, al);
        if (err)
@@ -1162,6 +1213,7 @@ void hist_entry__delete(struct hist_entry *he)
                mem_info__zput(he->mem_info);
        }
+        zfree(&he->res_samples);
        zfree(&he->stat_acc);
        free_srcline(he->srcline);
        if (he->srcfile && he->srcfile[0])
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4af27fbab24f..76ff6c6d03b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -31,6 +31,7 @@ enum hist_filter {
 enum hist_column {
        HISTC_SYMBOL,
+        HISTC_TIME,
        HISTC_DSO,
        HISTC_THREAD,
        HISTC_COMM,
@@ -432,9 +433,18 @@ struct hist_browser_timer {
 };
 struct annotation_options;
+struct res_sample;
+enum rstype {
+        A_NORMAL,
+        A_ASM,
+        A_SOURCE
+};
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
+void attr_to_script(char *buf, struct perf_event_attr *attr);
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
                             struct hist_browser_timer *hbt,
                             struct annotation_options *annotation_opts);
@@ -449,7 +459,13 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                  struct perf_env *env,
                                  bool warn_lost_event,
                                  struct annotation_options *annotation_options);
-int script_browse(const char *script_opt);
+int script_browse(const char *script_opt, struct perf_evsel *evsel);
+void run_script(char *cmd);
+int res_sample_browse(struct res_sample *res_samples, int num_res,
+                      struct perf_evsel *evsel, enum rstype rstype);
+void res_sample_init(void);
 #else
 static inline
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
@@ -478,11 +494,22 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
        return 0;
 }
-static inline int script_browse(const char *script_opt __maybe_unused)
+static inline int script_browse(const char *script_opt __maybe_unused,
+                                struct perf_evsel *evsel __maybe_unused)
 {
        return 0;
 }
+static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused,
+                                    int num_res __maybe_unused,
+                                    struct perf_evsel *evsel __maybe_unused,
+                                    enum rstype rstype __maybe_unused)
+{
+        return 0;
+}
+static inline void res_sample_init(void) {}
 #define K_LEFT  -1000
 #define K_RIGHT -2000
 #define K_SWITCH_INPUT_DATA -3000
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index fbeb0c6efaa6..e32628cd20a7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -577,10 +577,25 @@ static void __maps__purge(struct maps *maps)
        }
 }
+static void __maps__purge_names(struct maps *maps)
+{
+        struct rb_root *root = &maps->names;
+        struct rb_node *next = rb_first(root);
+        while (next) {
+                struct map *pos = rb_entry(next, struct map, rb_node_name);
+                next = rb_next(&pos->rb_node_name);
+                rb_erase_init(&pos->rb_node_name, root);
+                map__put(pos);
+        }
+}
 static void maps__exit(struct maps *maps)
 {
        down_write(&maps->lock);
        __maps__purge(maps);
+        __maps__purge_names(maps);
        up_write(&maps->lock);
 }
@@ -917,6 +932,9 @@ static void __maps__remove(struct maps *maps, struct map *map)
 {
        rb_erase_init(&map->rb_node, &maps->entries);
        map__put(map);
+        rb_erase_init(&map->rb_node_name, &maps->names);
+        map__put(map);
 }
 void maps__remove(struct maps *maps, struct map *map)
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index ea523d3b248f..989fed6f43b5 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -270,6 +270,8 @@ static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how,
                "FINAL",
                "ROUND",
                "HALF ",
+                "TOP  ",
+                "TIME ",
        };
        int err;
        bool show_progress = false;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4dcc01b2532c..5ef4939408f2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2271,6 +2271,7 @@ static bool is_event_supported(u8 type, unsigned config)
                perf_evsel__delete(evsel);
        }
+        thread_map__put(tmap);
        return ret;
 }
@@ -2341,6 +2342,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
                                printf("  %-50s [%s]\n", buf, "SDT event");
                                free(buf);
                        }
+                        free(path);
                } else
                        printf("  %-50s [%s]\n", nd->s, "SDT event");
                if (nd2) {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a1b8d9649ca7..198e09ff611e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -160,8 +160,10 @@ static struct map *kernel_get_module_map(const char *module)
        if (module && strchr(module, '/'))
                return dso__new_map(module);
-        if (!module)
+        if (!module) {
-                module = "kernel";
+                pos = machine__kernel_map(host_machine);
+                return map__get(pos);
+        }
        for (pos = maps__first(maps); pos; pos = map__next(pos)) {
                /* short_name is "[module]" */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index db643f3c2b95..b17f1c9bc965 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -132,6 +132,7 @@ struct perf_session *perf_session__new(struct perf_data *data,
        ordered_events__init(&session->ordered_events,
                             ordered_events__deliver_event, NULL);
+        perf_env__init(&session->header.env);
        if (data) {
                if (perf_data__open(data))
                        goto out_delete;
@@ -152,6 +153,10 @@ struct perf_session *perf_session__new(struct perf_data *data,
                        }
                        perf_evlist__init_trace_event_sample_raw(session->evlist);
+                        /* Open the directory data. */
+                        if (data->is_dir && perf_data__open_dir(data))
+                                goto out_delete;
                }
        } else  {
                session->machines.host.env = &perf_env;
@@ -1843,10 +1848,17 @@ fetch_mmaped_event(struct perf_session *session,
 #define NUM_MMAPS 128
 #endif
+struct reader;
+typedef s64 (*reader_cb_t)(struct perf_session *session,
+                           union perf_event *event,
+                           u64 file_offset);
 struct reader {
-        int     fd;
+        int              fd;
-        u64     data_size;
+        u64              data_size;
-        u64     data_offset;
+        u64              data_offset;
+        reader_cb_t      process;
 };
 static int
@@ -1917,7 +1929,7 @@ more:
        size = event->header.size;
        if (size < sizeof(struct perf_event_header) ||
-            (skip = perf_session__process_event(session, event, file_pos)) < 0) {
+            (skip = rd->process(session, event, file_pos)) < 0) {
                pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
                       file_offset + head, event->header.size,
                       event->header.type);
@@ -1943,12 +1955,20 @@ out:
        return err;
 }
+static s64 process_simple(struct perf_session *session,
+                          union perf_event *event,
+                          u64 file_offset)
+{
+        return perf_session__process_event(session, event, file_offset);
+}
 static int __perf_session__process_events(struct perf_session *session)
 {
        struct reader rd = {
                .fd             = perf_data__fd(session->data),
                .data_size      = session->header.data_size,
                .data_offset    = session->header.data_offset,
+                .process        = process_simple,
        };
        struct ordered_events *oe = &session->ordered_events;
        struct perf_tool *tool = session->tool;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d2299e912e59..5d2518e89fc4 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -3,6 +3,7 @@
 #include <inttypes.h>
 #include <regex.h>
 #include <linux/mman.h>
+#include <linux/time64.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -12,9 +13,11 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "strlist.h"
+#include "strbuf.h"
 #include <traceevent/event-parse.h>
 #include "mem-events.h"
 #include "annotate.h"
+#include "time-utils.h"
 #include <linux/kernel.h>
 regex_t         parent_regex;
@@ -654,6 +657,42 @@ struct sort_entry sort_socket = {
        .se_width_idx   = HISTC_SOCKET,
 };
+/* --sort time */
+static int64_t
+sort__time_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        return right->time - left->time;
+}
+static int hist_entry__time_snprintf(struct hist_entry *he, char *bf,
+                                    size_t size, unsigned int width)
+{
+        unsigned long secs;
+        unsigned long long nsecs;
+        char he_time[32];
+        nsecs = he->time;
+        secs = nsecs / NSEC_PER_SEC;
+        nsecs -= secs * NSEC_PER_SEC;
+        if (symbol_conf.nanosecs)
+                snprintf(he_time, sizeof he_time, "%5lu.%09llu: ",
+                         secs, nsecs);
+        else
+                timestamp__scnprintf_usec(he->time, he_time,
+                                          sizeof(he_time));
+        return repsep_snprintf(bf, size, "%-.*s", width, he_time);
+}
+struct sort_entry sort_time = {
+        .se_header      = "Time",
+        .se_cmp         = sort__time_cmp,
+        .se_snprintf    = hist_entry__time_snprintf,
+        .se_width_idx   = HISTC_TIME,
+};
 /* --sort trace */
 static char *get_trace_output(struct hist_entry *he)
@@ -1634,6 +1673,7 @@ static struct sort_dimension common_sort_dimensions[] = {
        DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size),
        DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
        DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
+        DIM(SORT_TIME, "time", sort_time),
 };
 #undef DIM
@@ -3068,3 +3108,54 @@ void reset_output_field(void)
        reset_dimensions();
        perf_hpp__reset_output_field(&perf_hpp_list);
 }
+#define INDENT (3*8 + 1)
+static void add_key(struct strbuf *sb, const char *str, int *llen)
+{
+        if (*llen >= 75) {
+                strbuf_addstr(sb, "\n\t\t\t ");
+                *llen = INDENT;
+        }
+        strbuf_addf(sb, " %s", str);
+        *llen += strlen(str) + 1;
+}
+static void add_sort_string(struct strbuf *sb, struct sort_dimension *s, int n,
+                            int *llen)
+{
+        int i;
+        for (i = 0; i < n; i++)
+                add_key(sb, s[i].name, llen);
+}
+static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int n,
+                                int *llen)
+{
+        int i;
+        for (i = 0; i < n; i++)
+                add_key(sb, s[i].name, llen);
+}
+const char *sort_help(const char *prefix)
+{
+        struct strbuf sb;
+        char *s;
+        int len = strlen(prefix) + INDENT;
+        strbuf_init(&sb, 300);
+        strbuf_addstr(&sb, prefix);
+        add_hpp_sort_string(&sb, hpp_sort_dimensions,
+                            ARRAY_SIZE(hpp_sort_dimensions), &len);
+        add_sort_string(&sb, common_sort_dimensions,
+                            ARRAY_SIZE(common_sort_dimensions), &len);
+        add_sort_string(&sb, bstack_sort_dimensions,
+                            ARRAY_SIZE(bstack_sort_dimensions), &len);
+        add_sort_string(&sb, memory_sort_dimensions,
+                            ARRAY_SIZE(memory_sort_dimensions), &len);
+        s = strbuf_detach(&sb, NULL);
+        strbuf_release(&sb);
+        return s;
+}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 2fbee0b1011c..ce376a73f964 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -47,6 +47,12 @@ extern struct sort_entry sort_srcline;
 extern enum sort_type sort__first_dimension;
 extern const char default_mem_sort_order[];
+struct res_sample {
+        u64 time;
+        int cpu;
+        int tid;
+};
 struct he_stat {
        u64                     period;
        u64                     period_sys;
@@ -135,10 +141,13 @@ struct hist_entry {
        char                    *srcfile;
        struct symbol           *parent;
        struct branch_info      *branch_info;
+        long                    time;
        struct hists            *hists;
        struct mem_info         *mem_info;
        void                    *raw_data;
        u32                     raw_size;
+        int                     num_res;
+        struct res_sample       *res_samples;
        void                    *trace_output;
        struct perf_hpp_list    *hpp_list;
        struct hist_entry       *parent_he;
@@ -231,6 +240,7 @@ enum sort_type {
        SORT_DSO_SIZE,
        SORT_CGROUP_ID,
        SORT_SYM_IPC_NULL,
+        SORT_TIME,
        /* branch stack specific sort keys */
        __SORT_BRANCH_STACK,
@@ -286,6 +296,8 @@ void reset_output_field(void);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
+const char *sort_help(const char *prefix);
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 bool is_strict_order(const char *order);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4d40515307b8..2856cc9d5a31 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -291,10 +291,8 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
                break;
        case AGGR_GLOBAL:
                aggr->val += count->val;
-                if (config->scale) {
+                aggr->ena += count->ena;
-                        aggr->ena += count->ena;
+                aggr->run += count->run;
-                        aggr->run += count->run;
-                }
        case AGGR_UNSET:
        default:
                break;
@@ -442,10 +440,8 @@ int create_perf_stat_counter(struct perf_evsel *evsel,
        struct perf_event_attr *attr = &evsel->attr;
        struct perf_evsel *leader = evsel->leader;
-        if (config->scale) {
+        attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
-                attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+                            PERF_FORMAT_TOTAL_TIME_RUNNING;
-                                    PERF_FORMAT_TOTAL_TIME_RUNNING;
-        }
        /*
         * The event is part of non trivial group, let's enable
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 758bf5f74e6e..5cbad55cd99d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -6,6 +6,7 @@
 #include <string.h>
 #include <linux/kernel.h>
 #include <linux/mman.h>
+#include <linux/time64.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/param.h>
@@ -39,15 +40,18 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 struct symbol_conf symbol_conf = {
+        .nanosecs               = false,
        .use_modules            = true,
        .try_vmlinux_path       = true,
        .demangle               = true,
        .demangle_kernel        = false,
        .cumulate_callchain     = true,
+        .time_quantum           = 100 * NSEC_PER_MSEC, /* 100ms */
        .show_hist_headers      = true,
        .symfs                  = "",
        .event_group            = true,
        .inline_name            = true,
+        .res_sample             = 0,
 };
 static enum dso_binary_type binary_type_symtab[] = {
@@ -1451,6 +1455,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
        case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
                return true;
+        case DSO_BINARY_TYPE__BPF_PROG_INFO:
        case DSO_BINARY_TYPE__NOT_FOUND:
        default:
                return false;
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index fffea68c1203..6c55fa6fccec 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -8,6 +8,7 @@ struct strlist;
 struct intlist;
 struct symbol_conf {
+        bool            nanosecs;
        unsigned short  priv_size;
        bool            try_vmlinux_path,
                        init_annotation,
@@ -55,6 +56,7 @@ struct symbol_conf {
                        *sym_list_str,
                        *col_width_list_str,
                        *bt_stop_list_str;
+        unsigned long   time_quantum;
       struct strlist   *dso_list,
                        *comm_list,
                        *sym_list,
@@ -66,6 +68,7 @@ struct symbol_conf {
        struct intlist  *pid_list,
                        *tid_list;
        const char      *symfs;
+        int             res_sample;
 };
 extern struct symbol_conf symbol_conf;
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 0f53baec660e..20663a460df3 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -453,6 +453,14 @@ int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
        return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
 }
+int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz)
+{
+        u64 sec  = timestamp / NSEC_PER_SEC,
+            nsec = timestamp % NSEC_PER_SEC;
+        return scnprintf(buf, sz, "%" PRIu64 ".%09" PRIu64, sec, nsec);
+}
 int fetch_current_timestamp(char *buf, size_t sz)
 {
        struct timeval tv;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index b923de44e36f..72a42ea1d513 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -30,6 +30,7 @@ int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
                                int *range_size, int *range_num);
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz);
 int fetch_current_timestamp(char *buf, size_t sz);
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9327c0ddc3a5..c3fad065c89c 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -5077,6 +5077,9 @@ int fork_it(char **argv)
                signal(SIGQUIT, SIG_IGN);
                if (waitpid(child_pid, &status, 0) == -1)
                        err(status, "waitpid");
+                if (WIFEXITED(status))
+                        status = WEXITSTATUS(status);
        }
        /*
         * n.b. fork_it() does not check for errors from for_all_cpus()
author	Greg Kroah-Hartman <gregkh@linuxfoundation.org>	2019-03-26 04:17:40 -0400
committer	Greg Kroah-Hartman <gregkh@linuxfoundation.org>	2019-03-26 04:17:40 -0400
commit	80045e14423aaf1d3d51bca0524336f8a624003e (patch)
tree	915319f6d353a2e8c1f69a16502e61d6020f3bc4
parent	5cec2d2e5839f9c0fec319c523a911e0a7fd299f (diff)
parent	7c22278edd0a931c565a8511dfc1bc57ffbb9166 (diff)