From 266d63a7d9d48c6d5dee486378ec0e8c86c4d74a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 11 Feb 2019 12:23:51 +0100 Subject: [PATCH 001/256] x86/cpufeature: Fix various quality problems in the header Thomas noticed that the new arch/x86/include/asm/cpu_device_id.h header is a train-wreck that didn't incorporate review feedback like not using __u8 in kernel-only headers. While at it also fix all the *other* problems this header has: - Use canonical names for the header guards. It's inexplicable why a non-standard guard was used. - Don't define the header guard to 1. Plus annotate the closing #endif as done absolutely every other header. Again, an inexplicable source of noise. - Move the kernel API calls provided by this header next to each other, there's absolutely no reason to have them spread apart in the header. - Align the INTEL_CPU_DESC() macro initializations vertically, this is easier to read and it's also the canonical style. - Actually name the macro arguments properly: instead of 'mod, step, rev', spell out 'model, stepping, revision' - it's not like we have a lack of characters in this header. - Actually make arguments macro-safe - again it's inexplicable why it wasn't done properly to begin with. Quite amazing how many problems a 41 lines header can contain. This kind of code quality is unacceptable, and it slipped through the review net of 2 developers and 2 maintainers, including myself, until Thomas noticed it. :-/ Reported-by: Thomas Gleixner Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpu_device_id.h | 31 ++++++++++++++-------------- 1 file changed, 15 insertions(+), 16 deletions(-) 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 -#define _CPU_DEVICE_ID 1 +#ifndef _ASM_X86_CPU_DEVICE_ID +#define _ASM_X86_CPU_DEVICE_ID /* * Declare drivers belonging to specific x86 CPUs @@ -9,8 +9,6 @@ #include -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_vendor; - __u8 x86_model; - __u8 x86_stepping; - __u32 x86_microcode_rev; + u8 x86_family; + u8 x86_vendor; + u8 x86_model; + u8 x86_stepping; + u32 x86_microcode_rev; }; -#define INTEL_CPU_DESC(mod, step, rev) { \ - .x86_family = 6, \ - .x86_vendor = X86_VENDOR_INTEL, \ - .x86_model = mod, \ - .x86_stepping = step, \ - .x86_microcode_rev = rev, \ +#define INTEL_CPU_DESC(model, stepping, revision) { \ + .x86_family = 6, \ + .x86_vendor = X86_VENDOR_INTEL, \ + .x86_model = (model), \ + .x86_stepping = (stepping), \ + .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 */ From ef4c54c340de47bf167b326f7560c1cc3751d154 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Thu, 24 Jan 2019 15:17:03 +0300 Subject: [PATCH 002/256] ARC: DTB: [scripted] fix node name and address spelling 1. Remove "0x" prefix from unit-address of node names ----------------------->8------------------------ sed -i 's/@0x/@/g' arch/arc/boot/dts/*.dts* ----------------------->8------------------------ 2. Make all hex addresses lowercase: ----------------------->8------------------------ sed -i 's/@\([0-9A-Za-z]*\)/@\L\1/g' arch/arc/boot/dts/*.dts* sed -i 's/0x\([0-9A-Za-z]*\)/0x\L\1/g' arch/arc/boot/dts/*.dts* ----------------------->8------------------------ Inspired by [1] and the like. [1] http://kisskb.ellerman.id.au/kisskb/buildresult/13612017/ Reviewed-by: Rob Herring Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/abilis_tb100.dtsi | 58 ++++++++++++------------- arch/arc/boot/dts/abilis_tb100_dvk.dts | 14 +++--- arch/arc/boot/dts/abilis_tb101.dtsi | 58 ++++++++++++------------- arch/arc/boot/dts/abilis_tb101_dvk.dts | 14 +++--- arch/arc/boot/dts/abilis_tb10x.dtsi | 60 +++++++++++++------------- arch/arc/boot/dts/axc001.dtsi | 6 +-- arch/arc/boot/dts/axc003.dtsi | 16 +++---- arch/arc/boot/dts/axc003_idu.dtsi | 16 +++---- arch/arc/boot/dts/axs10x_mb.dtsi | 22 +++++----- arch/arc/boot/dts/hsdk.dts | 4 +- arch/arc/boot/dts/vdk_axc003.dtsi | 4 +- arch/arc/boot/dts/vdk_axc003_idu.dtsi | 4 +- arch/arc/boot/dts/vdk_axs10x_mb.dtsi | 18 ++++---- 13 files changed, 147 insertions(+), 147 deletions(-) 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..6c23fa063ced 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>; 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>; From 66f7d3709c431d37a0b7f2b59ed00fbf93de1f0d Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 15 Feb 2019 19:17:33 +0300 Subject: [PATCH 003/256] ARC: [plat-hsdk]: Add reset controller handle to manage USB reset DW USB controller on HSDK hangs sometimes after SW reset, so add reset handle to make possible to reset DW USB controller HW. Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/hsdk.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 6c23fa063ced..b62088bf03a8 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -200,6 +200,7 @@ compatible = "snps,hsdk-v1.0-ohci", "generic-ohci"; reg = <0x60000 0x100>; interrupts = <15>; + resets = <&cgu_rst HSDK_USB_RESET>; dma-coherent; }; @@ -207,6 +208,7 @@ compatible = "snps,hsdk-v1.0-ehci", "generic-ehci"; reg = <0x40000 0x100>; interrupts = <15>; + resets = <&cgu_rst HSDK_USB_RESET>; dma-coherent; }; From 5d4ab8d0960e399e85a55e659b11cfc86a03a776 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Tue, 19 Feb 2019 13:52:26 +0300 Subject: [PATCH 004/256] ARC: [plat-hsdk]: Enable AXI DW DMAC support Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/hsdk.dts | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index b62088bf03a8..69bc1c9e8e50 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -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"; @@ -239,6 +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 { From 4d1e7918aae59ef504f5170a4f0c7ae82339fcb2 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Wed, 30 Jan 2019 19:32:43 +0300 Subject: [PATCH 005/256] ARCv2: lib: introduce memcpy optimized for unaligned access Optimise code to use efficient unaligned memory access which is available on ARCv2. This allows us to really simplify memcpy code and speed up the code one and a half times (in case of unaligned source or destination). Don't wire it up yet ! Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/lib/memcpy-archs-unaligned.S | 47 +++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 arch/arc/lib/memcpy-archs-unaligned.S 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 + */ + +#include + +#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) From 76551468833cd5c356b1d9ff4bc9393fcf768a59 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Wed, 30 Jan 2019 19:32:41 +0300 Subject: [PATCH 006/256] ARCv2: Add explcit unaligned access support (and ability to disable too) As of today we enable unaligned access unconditionally on ARCv2. Do this under a Kconfig option to allow disable it for test, benchmarking etc. Also while at it - Select HAVE_EFFICIENT_UNALIGNED_ACCESS - Although gcc defaults to unaligned access (since GNU 2018.03), add the right toggles for enabling or disabling as appropriate - update bootlog to prints both HW feature status (exists, enabled/disabled) and SW status (used / not used). - wire up the relaxed memcpy for unaligned access Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta [vgupta: squashed patches, handle gcc -mno-unaligned-access quick] --- arch/arc/Kconfig | 9 +++++++++ arch/arc/Makefile | 6 ++++++ arch/arc/include/asm/arcregs.h | 1 + arch/arc/include/asm/irqflags-arcv2.h | 8 +++++++- arch/arc/kernel/head.S | 5 +++++ arch/arc/kernel/intc-arcv2.c | 2 +- arch/arc/kernel/setup.c | 27 +++++++++++++++++---------- arch/arc/kernel/troubleshoot.c | 5 ++++- arch/arc/lib/Makefile | 8 +++++++- 9 files changed, 57 insertions(+), 14 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index d750b302d5ab..95fb11a85566 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -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 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/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index a27eafdc8260..0c13317af1d6 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 */ 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/kernel/head.S b/arch/arc/kernel/head.S index 30e090625916..36774348d23b 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 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..2266e4ee4142 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -263,7 +263,7 @@ 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; + int n = 0; FIX_PTR(cpu); @@ -283,16 +283,23 @@ 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)); + n += 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_AVAIL2(cpu->isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS)); - if (i) - n += scnprintf(buf + n, len - n, "\n\t\t: "); +#if defined(__ARC_UNALIGNED__) && !defined(CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS) + /* + * gcc 7.3.1 (GNU 2018.03) onwards generate unaligned access by default + * but -mno-unaligned-access to disable that didn't work until gcc 8.2.1 + * (GNU 2019.03). So landing here implies the interim period, when + * despite Kconfig being off, gcc is generating unaligned accesses which + * could bomb later on. So better to disallow such broken builds + */ + BUILD_BUG_ON_MSG(1, "gcc doesn't support -mno-unaligned-access"); +#endif + + n += scnprintf(buf + n, len - n, "\n\t\t: "); if (cpu->extn_mpy.ver) { if (cpu->extn_mpy.ver <= 0x2) { /* ARCompact */ 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 From fbe025c3eaf5f52060c2820eddb7357363db0d27 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 22 Feb 2019 10:42:44 -0800 Subject: [PATCH 007/256] ARC: perf: bpok condition only exists for ARCompact Signed-off-by: Vineet Gupta --- arch/arc/include/asm/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 */ From edb64bca50cd736c6894cc6081d5263c007ce005 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Mon, 25 Feb 2019 20:16:01 +0300 Subject: [PATCH 008/256] ARC: u-boot args: check that magic number is correct In case of devboards we really often disable bootloader and load Linux image in memory via JTAG. Even if kernel tries to verify uboot_tag and uboot_arg there is sill a chance that we treat some garbage in registers as valid u-boot arguments in JTAG case. E.g. it is enough to have '1' in r0 to treat any value in r2 as a boot command line. So check that magic number passed from u-boot is correct and drop u-boot arguments otherwise. That helps to reduce the possibility of using garbage as u-boot arguments in JTAG case. We can safely check U-boot magic value (0x0) in linux passed via r1 register as U-boot pass it from the beginning. So there is no backward-compatibility issues. Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/kernel/head.S | 1 + arch/arc/kernel/setup.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 36774348d23b..8f6e0447dd17 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -111,6 +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/setup.c b/arch/arc/kernel/setup.c index 2266e4ee4142..ec2fd231ecd9 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; @@ -504,6 +505,8 @@ 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) { @@ -518,6 +521,11 @@ 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); From 0728aeb7ead99a9b0dac2f3c92b3752b4e02ff97 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Mon, 25 Feb 2019 09:45:38 +0000 Subject: [PATCH 009/256] arc: hsdk_defconfig: Enable CONFIG_BLK_DEV_RAM We have now a HSDK device in our kernelci lab, but kernel builded via the hsdk_defconfig lacks ramfs supports, so it cannot boot kernelci jobs yet. So this patch enable CONFIG_BLK_DEV_RAM in hsdk_defconfig. Signed-off-by: Corentin Labbe Acked-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/configs/hsdk_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 87b23b7fb781..aefcf7a4e17a 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 From 00a4ae65cc600b008c80429a4fa37ccee21f139e Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 25 Feb 2019 11:24:05 -0800 Subject: [PATCH 010/256] ARCv2: boot log: refurbish HS core/release identification HS core names and releases have so far been identified based solely on IDENTIFY.ARCVER field. With the future HS releases this will not be sufficient as same ARCVER 0x54 could be an HS38 or HS48. So rewrite the code to use a new BCR to identify the cores properly. Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 2 +- arch/arc/kernel/setup.c | 130 +++++++++++++++++++-------------- 2 files changed, 75 insertions(+), 57 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 0c13317af1d6..36e5d124f5ae 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -313,7 +313,7 @@ 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 { diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index ec2fd231ecd9..6bd466892915 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -45,29 +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"}, - { 0x35, "R4.11"}, + { 0x34, "R4.10"}, + { 0x35, "R4.11"}, #else - { 0x51, "R2.0" }, - { 0x52, "R2.1" }, - { 0x53, "R3.0" }, - { 0x54, "R3.10a" }, + { 0x51, "R2.0" }, + { 0x52, "R2.1" }, + { 0x53, "R3.0" }, #endif - { 0x00, NULL } + { 0x00, NULL } }; -static const struct id_to_str arc_cpu_nm[] = { -#ifdef CONFIG_ISA_ARCOMPACT - { 0x20, "ARC 600" }, - { 0x30, "ARC 770" }, /* 750 identified seperately */ -#else - { 0x40, "ARC EM" }, - { 0x50, "ARC HS38" }, - { 0x54, "ARC HS48" }, -#endif - { 0x00, "Unknown" } +static const struct id_to_str arc_cpu_rel[] = { + /* UARCH.MAJOR, Release */ + { 0, "R3.10a"}, + { 1, "R3.50a"}, + { 0xFF, NULL } }; static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu) @@ -117,31 +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); - - 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; + decode_arc_core(cpu); READ_BCR(ARC_REG_TIMERS_BCR, timer); cpu->extn.timer0 = timer.t0; @@ -199,30 +235,12 @@ 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) { + unsigned int exec_ctrl; - struct bcr_uarch_build_arcv2 uarch; - - /* - * 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 ? */ - cpu->extn.dual_enb = !(exec_ctrl & 1); - - } + READ_BCR(AUX_EXEC_CTRL, exec_ctrl); + cpu->extn.dual_enb = !(exec_ctrl & 1); } } @@ -273,7 +291,7 @@ 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 ")); From 85d6adcbbe6dfc557755543c6c39b497d3032cdc Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 25 Feb 2019 11:56:28 -0800 Subject: [PATCH 011/256] ARC: boot log: cut down on verbosity The syscall ABI has long been fixed, so no need to call that out now. Also, there's no need to print really fine details such as norm, barrel-shifter etc. Those are given in a Linux enabled hardware config. So now we print just 1 line for all optional "instruction" related hardware features | | ISA Extn : atomic ll64 unalign mpy[opt 9] div_rem vs. 2 before | |ISA Extn : atomic ll64 unalign | : mpy[opt 9] div_rem norm barrel-shift swap minmax swape Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 9 ---- arch/arc/kernel/setup.c | 84 +++++++++++++--------------------- 2 files changed, 32 insertions(+), 61 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 36e5d124f5ae..a7d4be87b2f0 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -168,14 +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; @@ -323,7 +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/kernel/setup.c b/arch/arc/kernel/setup.c index 6bd466892915..15da43d2e416 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -188,16 +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); @@ -282,6 +272,7 @@ 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; + char mpy_opt[16]; int n = 0; FIX_PTR(cpu); @@ -302,10 +293,27 @@ 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)); - n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s", + if (cpu->extn_mpy.ver) { + if (is_isa_arcompact()) { + 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; + + scnprintf(mpy_opt, 16, "mpy[opt %d] ", opt); + } + } + + n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC), IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64), - IS_AVAIL2(cpu->isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS)); + IS_AVAIL2(cpu->isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS), + IS_AVAIL1(cpu->extn_mpy.ver, mpy_opt), + IS_AVAIL1(cpu->isa.div_rem, "div_rem ")); + #if defined(__ARC_UNALIGNED__) && !defined(CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS) /* @@ -318,52 +326,29 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) BUILD_BUG_ON_MSG(1, "gcc doesn't support -mno-unaligned-access"); #endif - n += scnprintf(buf + n, len - n, "\n\t\t: "); - - if (cpu->extn_mpy.ver) { - if (cpu->extn_mpy.ver <= 0x2) { /* ARCompact */ - n += scnprintf(buf + n, len - n, "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); - } - } - - n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", - IS_AVAIL1(cpu->isa.div_rem, "div_rem "), - IS_AVAIL1(cpu->extn.norm, "norm "), - IS_AVAIL1(cpu->extn.barrel, "barrel-shift "), - IS_AVAIL1(cpu->extn.swap, "swap "), - IS_AVAIL1(cpu->extn.minmax, "minmax "), - 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()) { - struct bcr_lpb lpb; + if (is_isa_arcv2()) { + struct bcr_lpb lpb; - READ_BCR(ARC_REG_LPB_BUILD, lpb); - if (lpb.ver) { - unsigned int ctl; - ctl = read_aux_reg(ARC_REG_LPB_CTRL); + READ_BCR(ARC_REG_LPB_BUILD, lpb); + if (lpb.ver) { + unsigned int ctl; + ctl = read_aux_reg(ARC_REG_LPB_CTRL); - n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s", - lpb.entries, - IS_DISABLED_RUN(!ctl)); + n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s", + lpb.entries, + IS_DISABLED_RUN(!ctl)); + } } + n += scnprintf(buf + n, len - n, "\n"); } - n += scnprintf(buf + n, len - n, "\n"); return buf; } @@ -416,11 +401,6 @@ 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; } From 7d3a5eb78e3614b025389d2cd89d6d85e91f5549 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 4 Mar 2019 21:02:18 +0100 Subject: [PATCH 012/256] irqchip/imx-irqsteer: Fix of_property_read_u32() error handling gcc points out that irqs_num is not initialized when of_property_read_u32() is an empty stub function: Included from drivers/irqchip/irq-imx-irqsteer.c:7: drivers/irqchip/irq-imx-irqsteer.c: In function 'imx_irqsteer_probe': include/uapi/linux/kernel.h:13:49: error: 'irqs_num' may be used uninitialized in this function [-Werror=maybe-uninitialized] The same can actually happen with CONFIG_OF=y as well, though we don't get a warning then. Add error checking here that lets the code deal with missing or invalid properties as well as avoid the warning. Fixes: 28528fca4908 ("irqchip/imx-irqsteer: Add multi output interrupts support") Signed-off-by: Arnd Bergmann Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-imx-irqsteer.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) 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); - of_property_read_u32(np, "fsl,channel", &data->channel); + ret = of_property_read_u32(np, "fsl,num-irqs", &irqs_num); + 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. From 6dd356d8fc0641a8f0afb6ba457fb9351eea5076 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 5 Mar 2019 09:16:29 -0800 Subject: [PATCH 013/256] ARC: unaligned: relax the check for gcc supporting -mno-unaligned-access Without bleeding edge gcc, kernel builds were tripping everywhere. So current gcc will generate unaligned code despite !CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS but that is something we have to live with. Signed-off-by: Vineet Gupta --- arch/arc/kernel/setup.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 15da43d2e416..a9c88b7e9182 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -314,18 +314,6 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) IS_AVAIL1(cpu->extn_mpy.ver, mpy_opt), IS_AVAIL1(cpu->isa.div_rem, "div_rem ")); - -#if defined(__ARC_UNALIGNED__) && !defined(CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS) - /* - * gcc 7.3.1 (GNU 2018.03) onwards generate unaligned access by default - * but -mno-unaligned-access to disable that didn't work until gcc 8.2.1 - * (GNU 2019.03). So landing here implies the interim period, when - * despite Kconfig being off, gcc is generating unaligned accesses which - * could bomb later on. So better to disallow such broken builds - */ - BUILD_BUG_ON_MSG(1, "gcc doesn't support -mno-unaligned-access"); -#endif - if (cpu->bpu.ver) { n += scnprintf(buf + n, len - n, "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d", From 3032f0c9008088a3effdc2622ce16c3e1bcb13a2 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 7 Mar 2019 13:29:59 -0800 Subject: [PATCH 014/256] ARCv2: spinlock: remove the extra smp_mb before lock, after unlock - ARCv2 LLSC spinlocks have smp_mb() both before and after the LLSC instructions, which is not required per lkmm ACQ/REL semantics. smp_mb() is only needed _after_ lock and _before_ unlock. So remove the extra barriers. The reason they were there was mainly historical. At the time of initial SMP Linux bringup on HS38 cores, I was too conservative, given the fluidity of both hw and sw. The last attempt to ditch the extra barrier showed some hackbench regression which is apparently not the case now (atleast for LLSC case, read on...) - EX based spinlocks (!CONFIG_ARC_HAS_LLSC) still needs the extra smp_mb(), not due to lkmm, but due to some hardware shenanigans. W/o that, hackbench triggers RCU stall splat so extra DMB is retained !LLSC based systems are not realistic Linux sstem anyways so they can afford to be a nit suboptimal ;-) | [ARCLinux]# for i in (seq 1 1 5) ; do hackbench; done | Running with 10 groups 400 process | INFO: task hackbench:158 blocked for more than 10 seconds. | Not tainted 4.20.0-00005-g96b18288a88e-dirty #117 | "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. | hackbench D 0 158 135 0x00000000 | | Stack Trace: | watchdog: BUG: soft lockup - CPU#3 stuck for 59s! [hackbench:469] | Modules linked in: | Path: (null) | CPU: 3 PID: 469 Comm: hackbench Not tainted 4.20.0-00005-g96b18288a88e-dirty | | [ECR ]: 0x00000000 => Check Programmer's Manual | [EFA ]: 0x00000000 | [BLINK ]: do_exit+0x4a6/0x7d0 | [ERET ]: _raw_write_unlock_irq+0x44/0x5c - And while at it, remove the extar smp_mb() from EX based arch_read_trylock() since the spin lock there guarantees a full barrier anyways - For LLSC case, hackbench threads improves with this patch (HAPS @ 50MHz) ---- before ---- | | [ARCLinux]# for i in 1 2 3 4 5; do hackbench 10 thread; done | Running with 10 groups 400 threads | Time: 16.253 | Time: 16.445 | Time: 16.590 | Time: 16.721 | Time: 16.544 ---- after ---- | | [ARCLinux]# for i in 1 2 3 4 5; do hackbench 10 thread; done | Running with 10 groups 400 threads | Time: 15.638 | Time: 15.730 | Time: 15.870 | Time: 15.842 | Time: 15.729 Acked-by: Peter Zijlstra (Intel) Signed-off-by: Vineet Gupta --- arch/arc/include/asm/spinlock.h | 49 ++++++++++----------------------- 1 file changed, 14 insertions(+), 35 deletions(-) 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__; - - smp_mb(); + WRITE_ONCE(lock->slock, __ARCH_SPIN_LOCK_UNLOCKED__); } /* @@ -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__; - - smp_mb(); + WRITE_ONCE(rw->counter, __ARCH_RW_LOCK_UNLOCKED__); } #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 - * after the lock for providing the ACQUIRE semantics. - * However doing the "right" thing was regressing hackbench - * so keeping this, pending further investigation + * Per lkmm, smp_mb() is only required after _lock (and before_unlock) + * for ACQ and REL semantics respectively. However EX based spinlocks + * need the extra smp_mb to workaround a hardware quirk. */ 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 - * arch_spin_lock above + * see pairing version/comment in 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; } From 62c9d2674b31d4c8a674bee86b7edc6da2803aea Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Sat, 2 Mar 2019 09:17:32 +0800 Subject: [PATCH 015/256] inotify: Fix fsnotify_mark refcount leak in inotify_update_existing_watch() Commit 4d97f7d53da7dc83 ("inotify: Add flag IN_MASK_CREATE for inotify_add_watch()") forgot to call fsnotify_put_mark() with IN_MASK_CREATE after fsnotify_find_mark() Fixes: 4d97f7d53da7dc83 ("inotify: Add flag IN_MASK_CREATE for inotify_add_watch()") Signed-off-by: ZhangXiaoxu Signed-off-by: Jan Kara --- fs/notify/inotify/inotify_user.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) 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) - return -EEXIST; + else if (create) { + 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); From d9c1bb2f6a2157b38e8eb63af437cb22701d31ee Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 7 Mar 2019 10:52:33 -0800 Subject: [PATCH 016/256] perf/core: Restore mmap record type correctly On mmap(), perf_events generates a RECORD_MMAP record and then checks which events are interested in this record. There are currently 2 versions of mmap records: RECORD_MMAP and RECORD_MMAP2. MMAP2 is larger. The event configuration controls which version the user level tool accepts. If the event->attr.mmap2=1 field then MMAP2 record is returned. The perf_event_mmap_output() takes care of this. It checks attr->mmap2 and corrects the record fields before putting it in the sampling buffer of the event. At the end the function restores the modified MMAP record fields. The problem is that the function restores the size but not the type. Thus, if a subsequent event only accepts MMAP type, then it would instead receive an MMAP2 record with a size of MMAP record. This patch fixes the problem by restoring the record type on exit. Signed-off-by: Stephane Eranian Acked-by: Peter Zijlstra (Intel) Cc: Andi Kleen Cc: Jiri Olsa Cc: Kan Liang Fixes: 13d7a2410fa6 ("perf: Add attr->mmap2 attribute to an event") Link: http://lkml.kernel.org/r/20190307185233.225521-1-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo --- kernel/events/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 6fb27b564730..514b8e014a2d 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) From 3ab481a1cfe1511b94e142b648e2c5ade9175ed3 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 5 Mar 2019 06:47:45 -0800 Subject: [PATCH 017/256] perf script: Support insn output for normal samples MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit perf script -F +insn was only working for PT traces because the PT instruction decoder was filling in the insn/insn_len sample attributes. Support it for non PT samples too on x86 using the existing x86 instruction decoder. This adds some extra checking to ensure that we don't try to decode instructions when using perf.data from a different architecture. % perf record -a sleep 1 % perf script -F ip,sym,insn --xed ffffffff811704c9 remote_function movl %eax, 0x18(%rbx) ffffffff8100bb50 intel_bts_enable_local retq ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi) ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi) ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi) ffffffff810f1f79 generic_exec_single xor %eax, %eax ffffffff811704c9 remote_function movl %eax, 0x18(%rbx) ffffffff8100bb34 intel_bts_enable_local movl 0x2000(%rax), %edx ffffffff81048610 native_apic_mem_write mov %edi, %edi ... Committer testing: Before: # perf script -F ip,sym,insn --xed | head -5 ffffffffa4068804 native_write_msr addb %al, (%rax) ffffffffa4068804 native_write_msr addb %al, (%rax) ffffffffa4068804 native_write_msr addb %al, (%rax) ffffffffa4068806 native_write_msr addb %al, (%rax) ffffffffa4068806 native_write_msr addb %al, (%rax) # perf script -F ip,sym,insn --xed | grep -v "addb %al, (%rax)" # After: # perf script -F ip,sym,insn --xed | head -5 ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) # perf script -F ip,sym,insn --xed | grep -v "addb %al, (%rax)" | head -5 ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) # More examples: # perf script -F ip,sym,insn --xed | grep -v native_write_msr | head ffffffffa416b90e tick_check_broadcast_expired btq %rax, 0x1a5f42a(%rip) ffffffffa4956bd0 nmi_cpu_backtrace pushq %r13 ffffffffa415b95e __hrtimer_next_event_base movq 0x18(%rax), %rdx ffffffffa4956bf3 nmi_cpu_backtrace popq %r12 ffffffffa4171d5c smp_call_function_single pause ffffffffa4956bdd nmi_cpu_backtrace mov %ebp, %r12d ffffffffa4797e4d menu_select cmp $0x190, %rax ffffffffa4171d5c smp_call_function_single pause ffffffffa405a7d8 nmi_cpu_backtrace_handler callq 0xffffffffa4956bd0 ffffffffa4797f7a menu_select shr $0x3, %rax # Which matches the annotate output modulo resolving callqs: # perf annotate --stdio2 nmi_cpu_backtrace_handler Samples: 4 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 35908, [percent: local period] nmi_cpu_backtrace_handler() /lib/modules/5.0.0+/build/vmlinux Percent Disassembly of section .text: ffffffff8105a7d0 : nmi_cpu_backtrace_handler(): nmi_trigger_cpumask_backtrace(mask, exclude_self, nmi_raise_cpu_backtrace); } static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { 24.45 → callq __fentry__ if (nmi_cpu_backtrace(regs)) mov %rsi,%rdi 75.55 → callq nmi_cpu_backtrace return NMI_HANDLED; movzbl %al,%eax return NMI_DONE; } ← retq # # perf annotate --stdio2 __hrtimer_next_event_base Samples: 4 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 767977, [percent: local period] __hrtimer_next_event_base() /lib/modules/5.0.0+/build/vmlinux Percent Disassembly of section .text: ffffffff8115b910 <__hrtimer_next_event_base>: __hrtimer_next_event_base(): static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { → callq __fentry__ 4a: add $0x1,%r14 77.31 mov 0x18(%rax),%rdx shl $0x6,%r14 sub 0x38(%rbx,%r14,1),%rdx if (expires < expires_next) { cmp %r12,%rdx ↓ jge 68 Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20190305144758.12397-3-andi@firstfloor.org [ Converted fetch_exe() to use the name it ended up having when merged: thread__memcpy() ] [ archinsn.c needs the instruction decoder that is only build when CONFIG_AUXTRACE=y, fix that ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/Build | 1 + tools/perf/arch/x86/util/archinsn.c | 26 ++++++++++++++++++++++++++ tools/perf/builtin-script.c | 21 ++++++++++++++++++++- tools/perf/util/archinsn.h | 12 ++++++++++++ 4 files changed, 59 insertions(+), 1 deletion(-) create mode 100644 tools/perf/arch/x86/util/archinsn.c create mode 100644 tools/perf/util/archinsn.h diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 7aab0be5fc5f..47f9c56e744f 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -14,5 +14,6 @@ perf-$(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/builtin-script.c b/tools/perf/builtin-script.c index 53f78cf3113f..a5080afd361d 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 #include #include #include +#include #include "asm/bug.h" #include "util/mem-events.h" #include "util/dump-insn.h" @@ -63,6 +65,7 @@ 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; @@ -1227,6 +1230,12 @@ 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 +1243,12 @@ 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:"); @@ -3277,6 +3289,7 @@ 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; @@ -3615,6 +3628,12 @@ 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/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 From 52bab8868211b7c504146f6239e101421d4d125b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 5 Mar 2019 06:47:47 -0800 Subject: [PATCH 018/256] perf report: Support output in nanoseconds Upcoming changes add timestamp output in perf report. Add a --ns argument similar to perf script to support nanoseconds resolution when needed. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20190305144758.12397-5-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 3 +++ tools/perf/builtin-report.c | 1 + tools/perf/builtin-script.c | 11 +++++------ tools/perf/util/symbol.c | 1 + tools/perf/util/symbol_conf.h | 1 + 5 files changed, 11 insertions(+), 6 deletions(-) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 1a27bfe05039..51dbc519dbce 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -477,6 +477,9 @@ 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) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ee93c18a6685..515864ba504a 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1147,6 +1147,7 @@ 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_END() }; struct perf_data data = { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a5080afd361d..111787e83784 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -60,7 +60,6 @@ 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; @@ -691,7 +690,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, 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]; @@ -3244,7 +3243,7 @@ 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; } @@ -3262,7 +3261,7 @@ 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; } @@ -3272,7 +3271,7 @@ 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; } @@ -3408,7 +3407,7 @@ 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, diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 758bf5f74e6e..eb873ea1c405 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -39,6 +39,7 @@ int vmlinux_path__nr_entries; char **vmlinux_path; struct symbol_conf symbol_conf = { + .nanosecs = false, .use_modules = true, .try_vmlinux_path = true, .demangle = true, diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index fffea68c1203..095a297c8b47 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, From f8c856cb2c947f4fad0a2dff5e95cdcddb801303 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 5 Mar 2019 06:47:53 -0800 Subject: [PATCH 019/256] perf time-utils: Add utility function to print time stamps in nanoseconds Add a utility function to print nanosecond timestamps. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20190305144758.12397-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/time-utils.c | 8 ++++++++ tools/perf/util/time-utils.h | 1 + 2 files changed, 9 insertions(+) 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); From 2a1292cbd4e5c81edbf815a410fa2072c341db1e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 5 Mar 2019 06:47:48 -0800 Subject: [PATCH 020/256] perf report: Parse time quantum Many workloads change over time. 'perf report' currently aggregates the whole time range reported in perf.data. This patch adds an option for a time quantum to quantisize the perf.data over time. This just adds the option, will be used in follow on patches for a time sort key. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20190305144758.12397-6-andi@firstfloor.org [ Use NSEC_PER_[MU]SEC ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 4 +++ tools/perf/builtin-report.c | 42 ++++++++++++++++++++++++ tools/perf/util/symbol.c | 2 ++ tools/perf/util/symbol_conf.h | 1 + 4 files changed, 49 insertions(+) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 51dbc519dbce..9ec1702bccdd 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -497,6 +497,10 @@ 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/builtin-report.c b/tools/perf/builtin-report.c index 515864ba504a..05c8dd41106c 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -47,9 +47,11 @@ #include #include #include +#include "sane_ctype.h" #include #include #include +#include #include #include #include @@ -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) @@ -1148,6 +1187,9 @@ int cmd_report(int argc, const char **argv) "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/util/symbol.c b/tools/perf/util/symbol.c index eb873ea1c405..6b73a0eeb6a1 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -45,6 +46,7 @@ struct symbol_conf symbol_conf = { .demangle = true, .demangle_kernel = false, .cumulate_callchain = true, + .time_quantum = 100 * NSEC_PER_MSEC, /* 100ms */ .show_hist_headers = true, .symfs = "", .event_group = true, diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index 095a297c8b47..a5684a71b78e 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -56,6 +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, From eaeffeb9838a7c0dec981d258666bfcc0fa6a947 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 4 Mar 2019 15:13:21 +0200 Subject: [PATCH 021/256] perf probe: Fix getting the kernel map Since commit 4d99e4136580 ("perf machine: Workaround missing maps for x86 PTI entry trampolines"), perf tools has been creating more than one kernel map, however 'perf probe' assumed there could be only one. Fix by using machine__kernel_map() to get the main kernel map. Signed-off-by: Adrian Hunter Tested-by: Joseph Qi Acked-by: Masami Hiramatsu Cc: Alexander Shishkin Cc: Andy Lutomirski Cc: Greg Kroah-Hartman Cc: Jiufei Xue Cc: Peter Zijlstra Cc: stable@vger.kernel.org Cc: Xu Yu Fixes: 4d99e4136580 ("perf machine: Workaround missing maps for x86 PTI entry trampolines") Fixes: d83212d5dd67 ("kallsyms, x86: Export addresses of PTI entry trampolines") Link: http://lkml.kernel.org/r/2ed432de-e904-85d2-5c36-5897ddc5b23b@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) 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) - module = "kernel"; + if (!module) { + pos = machine__kernel_map(host_machine); + return map__get(pos); + } for (pos = maps__first(maps); pos; pos = map__next(pos)) { /* short_name is "[module]" */ From 98c07a8f74f85a19aeee2016f5afa0c667fa694d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Li=C5=A1ka?= Date: Wed, 13 Feb 2019 12:19:16 +0100 Subject: [PATCH 022/256] perf vendor events amd: perf PMU events for AMD Family 17h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thi patch adds PMC events for AMD Family 17 CPUs as defined in [1]. It covers events described in section: 2.1.13. Regex pattern in mapfile.csv covers all CPUs of the family. [1] https://support.amd.com/TechDocs/54945_PPR_Family_17h_Models_00h-0Fh.pdf Signed-off-by: Martin Liška Acked-by: Borislav Petkov Cc: Jiri Olsa Cc: Jon Grimm Cc: Martin Jambor Cc: William Cohen Link: https://lkml.kernel.org/r/d65873ca-e402-b198-4fe9-8c4af81258c8@suse.cz Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/amdfam17h/branch.json | 12 + .../pmu-events/arch/x86/amdfam17h/cache.json | 287 ++++++++++++++++++ .../pmu-events/arch/x86/amdfam17h/core.json | 134 ++++++++ .../arch/x86/amdfam17h/floating-point.json | 168 ++++++++++ .../pmu-events/arch/x86/amdfam17h/memory.json | 162 ++++++++++ .../pmu-events/arch/x86/amdfam17h/other.json | 65 ++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + 7 files changed, 829 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/branch.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/core.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/other.json 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 From ec65def1045e4c7817b7f741a86dadae82877a93 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Mar 2019 14:47:35 +0100 Subject: [PATCH 023/256] perf data: Support having perf.data stored as a directory The caller needs to set 'struct perf_data::is_dir flag and the path will be treated as a directory. The 'struct perf_data::file' is initialized and open as 'path/header' file. Add a check to the direcory interface functions to check the is_dir flag. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190308134745.5057-2-jolsa@kernel.org [ Be consistent on how to signal failure, i.e. use -1 and let users check errno ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 49 ++++++++++++++++++++++++++++++++++++++- tools/perf/util/data.h | 6 +++++ tools/perf/util/session.c | 4 ++++ 3 files changed, 58 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index e098e189f93e..18fa8d4614eb 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -34,6 +34,9 @@ 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; @@ -69,6 +72,9 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + if (WARN_ON(!data->is_dir)) + return -EINVAL; + dir = opendir(data->path); if (!dir) return -EINVAL; @@ -173,6 +179,16 @@ 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 +270,30 @@ 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 +305,18 @@ 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); } diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 14b47be2bd69..06aefeda311f 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -19,6 +19,7 @@ struct perf_data { const char *path; struct perf_data_file file; bool is_pipe; + bool is_dir; bool force; enum perf_data_mode mode; @@ -43,6 +44,11 @@ static inline int perf_data__is_pipe(struct perf_data *data) return data->is_pipe; } +static inline bool perf_data__is_dir(struct perf_data *data) +{ + return data->is_dir; +} + static inline int perf_data__fd(struct perf_data *data) { return data->file.fd; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index db643f3c2b95..de777bdc0ed3 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -152,6 +152,10 @@ 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; From cd3dd8dd8ff62374d90cb3f2e54b8c94106c7810 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Mar 2019 14:47:36 +0100 Subject: [PATCH 024/256] perf data: Don't store auxtrace index for directory data file We can't store the auxtrace index when we store into multiple files, because we keep only offset for it, not the file. The auxtrace data will be processed correctly in the 'pipe' mode. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190308134745.5057-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f3f7f3100336..e983c8d71a79 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -392,7 +392,7 @@ 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; From e8be135751f26aa5de63e517d375ecf69e9b20c3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Mar 2019 14:47:37 +0100 Subject: [PATCH 025/256] perf data: Add perf_data__update_dir() function Add perf_data__update_dir() to update the size for every file within the perf.data directory. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190308134745.5057-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 20 ++++++++++++++++++++ tools/perf/util/data.h | 1 + 2 files changed, 21 insertions(+) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 18fa8d4614eb..5d0f26aef77f 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -124,6 +124,26 @@ 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; diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 06aefeda311f..0deeb1af9f54 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -79,4 +79,5 @@ int perf_data__switch(struct perf_data *data, 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); #endif /* __PERF_DATA_H */ From 29583c17b5ce0bc17fdd80da939f8199a03d9668 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Mar 2019 14:47:38 +0100 Subject: [PATCH 026/256] perf data: Make perf_data__size() work over directory Make perf_data__size() return proper size for directory data, summing up all the individual file sizes. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190308134745.5057-5-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/data.c | 17 +++++++++++++++++ tools/perf/util/data.h | 6 +----- 2 files changed, 18 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 5d0f26aef77f..b71c441cafbb 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -393,3 +393,20 @@ 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 0deeb1af9f54..d342469bdfda 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -54,11 +54,6 @@ static inline int perf_data__fd(struct perf_data *data) return data->file.fd; } -static inline unsigned long perf_data__size(struct perf_data *data) -{ - return data->file.size; -} - int perf_data__open(struct perf_data *data); void perf_data__close(struct perf_data *data); ssize_t perf_data__write(struct perf_data *data, @@ -80,4 +75,5 @@ 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 */ From 258031c017c353e899902342a25579fc81a34cc1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Mar 2019 14:47:39 +0100 Subject: [PATCH 027/256] perf header: Add DIR_FORMAT feature to describe directory data The data files layout is described by HEADER_DIR_FORMAT feature. Currently it holds only version number (1): uint64_t version; The current version holds only version value (1) means that data files: - Follow the 'data.*' name format. - Contain raw events data in standard perf format as read from kernel (and need to be sorted) Future versions are expected to describe different data files layout according to special needs. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190308134745.5057-6-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 ++ tools/perf/util/data.c | 10 +++++++-- tools/perf/util/data.h | 1 + tools/perf/util/header.c | 44 ++++++++++++++++++++++++++++++++++++- tools/perf/util/header.h | 5 +++++ 5 files changed, 59 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e983c8d71a79..a468d882e74f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -837,6 +837,8 @@ 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); } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index b71c441cafbb..c6b67efea11a 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) { @@ -41,8 +42,9 @@ int perf_data__create_dir(struct perf_data *data, int nr) if (!files) return -ENOMEM; - data->dir.files = files; - data->dir.nr = nr; + data->dir.version = PERF_DIR_VERSION; + data->dir.files = files; + data->dir.nr = nr; for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; @@ -75,6 +77,10 @@ int perf_data__open_dir(struct perf_data *data) 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; diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index d342469bdfda..6aef8746469f 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -24,6 +24,7 @@ struct perf_data { enum perf_data_mode mode; struct { + u64 version; struct perf_data_file *files; int nr; } dir; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 01b324c275b9..b0683bf4d9f3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -861,6 +861,21 @@ 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)); +} + 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 +1356,17 @@ 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 free_event_desc(struct perf_evsel *events) { struct perf_evsel *evsel; @@ -2373,6 +2399,21 @@ 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); +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2432,7 +2473,8 @@ 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) }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 0d553ddca0a3..6a231340238d 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -39,6 +39,7 @@ enum { HEADER_SAMPLE_TIME, HEADER_MEM_TOPOLOGY, HEADER_CLOCKID, + HEADER_DIR_FORMAT, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -48,6 +49,10 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; +enum perf_dir_version { + PERF_DIR_VERSION = 1, +}; + struct perf_file_section { u64 offset; u64 size; From e51f806198306a8ad7ae6e34d1af0716ef73da80 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Mar 2019 14:47:40 +0100 Subject: [PATCH 028/256] perf session: Add process callback to reader object Adding callback function to reader object so callers can process data in different ways. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190308134745.5057-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index de777bdc0ed3..0ec34227bd60 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1847,10 +1847,17 @@ 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; - u64 data_size; - u64 data_offset; + int fd; + u64 data_size; + u64 data_offset; + reader_cb_t process; }; static int @@ -1921,7 +1928,7 @@ 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); @@ -1947,12 +1954,20 @@ 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; From b41fdc4a7bf9045e4871c5b15905ea732ffd044f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 11 Mar 2019 15:38:10 +0000 Subject: [PATCH 029/256] irqchip/gic: Drop support for secondary GIC in non-DT systems We do not have any in-tree platform with this pathological setup, and only a single system (Cavium's cns3xxx) isn't DT aware. Let's drop the secondary GIC support for now, until we remove the above horror altogether. Signed-off-by: Marc Zyngier --- arch/arm/mach-cns3xxx/core.c | 2 +- drivers/irqchip/irq-gic.c | 45 ++++++++++++--------------------- include/linux/irqchip/arm-gic.h | 3 +-- 3 files changed, 18 insertions(+), 32 deletions(-) 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/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, irq_base, ret; + int gic_irqs, 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) { - hwirq_base = 16; - if (irq_start != -1) - irq_start = (irq_start & ~31) + 16; - } else { - hwirq_base = 32; - } + int irq_base; - 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", - irq_start); - irq_base = irq_start; + WARN(1, "Cannot allocate irq_descs @ IRQ16, assuming pre-allocated\n"); + irq_base = 16; } 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 __iomem *dist_base, void __iomem *cpu_base) +void __init gic_init(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/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 __iomem *dist , void __iomem *cpu); +void gic_init(void __iomem *dist , void __iomem *cpu); int gicv2m_init(struct fwnode_handle *parent_handle, struct irq_domain *parent); From 75065a85a9705ad4c0135f07fd4467d46ff342a3 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 8 Mar 2019 21:56:20 -0800 Subject: [PATCH 030/256] perf report: Use less for scripts output The UI viewer for scripts output has a lot of limitations: limited size, no search or save function, slow, and various other issues. Just use 'less' to display directly on the terminal instead. This won't work in GTK mode, but GTK doesn't support these context menus anyways. If that is ever done could use an terminal for the output. Signed-off-by: Andi Kleen Acked-by: Feng Tang Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190309055628.21617-8-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/scripts.c | 130 ++++--------------------------- 1 file changed, 17 insertions(+), 113 deletions(-) diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 90a32ac69e76..7f36630694bf 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,35 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include #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" -/* 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 /* @@ -73,69 +50,29 @@ static int list_scripts(char *script_name) return ret; } -static void script_browser__write(struct ui_browser *browser, - void *entry, int row) +static void run_script(char *cmd) { - struct script_line *sline = list_entry(entry, struct script_line, node); - bool current_entry = ui_browser__is_current_entry(browser, row); - - ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : - HE_COLORSET_NORMAL); - - ui_browser__write_nstring(browser, sline->line, browser->width); + pr_debug("Running %s\n", cmd); + SLang_reset_tty(); + if (system(cmd) < 0) + pr_warning("Cannot run %s\n", cmd); + /* + * SLang doesn't seem to reset the whole terminal, so be more + * 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 key; - - if (ui_browser__show(&browser->b, browser->script_name, - "Press ESC to exit") < 0) - return -1; - - while (1) { - key = ui_browser__run(&browser->b, 0); - - /* We can add some special key handling here if needed */ - break; - } - - 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; + return -1; sprintf(cmd, "perf script -s %s ", script_name); @@ -147,42 +84,9 @@ int script_browse(const char *script_opt) strcat(cmd, input_name); } - strcat(cmd, " 2>&1"); + strcat(cmd, " 2>&1 | less"); - fp = popen(cmd, "r"); - if (!fp) - goto exit; + run_script(cmd); - 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; + return 0; } From 5f5f67da9781770df0403269bc57d7aae608fecd Mon Sep 17 00:00:00 2001 From: Yifeng Li Date: Tue, 5 Mar 2019 06:00:22 +0800 Subject: [PATCH 031/256] mips: loongson64: lemote-2f: Add IRQF_NO_SUSPEND to "cascade" irqaction. Timekeeping IRQs from CS5536 MFGPT are routed to i8259, which then triggers the "cascade" IRQ on MIPS CPU. Without IRQF_NO_SUSPEND in cascade_irqaction, MFGPT interrupts will be masked in suspend mode, and the machine would be unable to resume once suspended. Previously, MIPS IRQs were not disabled properly, so the original code appeared to work. Commit a3e6c1eff5 ("MIPS: IRQ: Fix disable_irq on CPU IRQs") uncovers the bug. To fix it, add IRQF_NO_SUSPEND to cascade_irqaction. This commit is functionally identical to 0add9c2f1cff ("MIPS: Loongson-3: Add IRQF_NO_SUSPEND to Cascade irqaction"), but it forgot to apply the same fix to Loongson2. Signed-off-by: Yifeng Li Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org Cc: Jiaxun Yang Cc: Huacai Chen Cc: Ralf Baechle Cc: James Hogan Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v3.19+ --- arch/mips/loongson64/lemote-2f/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) From 3f0a53bc6482fb09770982a8447981260ea258dc Mon Sep 17 00:00:00 2001 From: Yasha Cherikovsky Date: Fri, 8 Mar 2019 14:58:51 +0200 Subject: [PATCH 032/256] MIPS: Ensure ELF appended dtb is relocated This fixes booting with the combination of CONFIG_RELOCATABLE=y and CONFIG_MIPS_ELF_APPENDED_DTB=y. Sections that appear after the relocation table are not relocated on system boot (except .bss, which has special handling). With CONFIG_MIPS_ELF_APPENDED_DTB, the dtb is part of the vmlinux ELF, so it must be relocated together with everything else. Fixes: 069fd766271d ("MIPS: Reserve space for relocation table") Signed-off-by: Yasha Cherikovsky Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: Paul Burton Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v4.7+ --- arch/mips/kernel/vmlinux.lds.S | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) 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 From 47c25036b60f27b86ab44b66a8861bcf81cde39b Mon Sep 17 00:00:00 2001 From: Archer Yan Date: Fri, 8 Mar 2019 03:29:19 +0000 Subject: [PATCH 033/256] MIPS: Fix kernel crash for R6 in jump label branch function Insert Branch instruction instead of NOP to make sure assembler don't patch code in forbidden slot. In jump label function, it might be possible to patch Control Transfer Instructions(CTIs) into forbidden slot, which will generate Reserved Instruction exception in MIPS release 6. Signed-off-by: Archer Yan Reviewed-by: Paul Burton [paul.burton@mips.com: - Add MIPS prefix to subject. - Mark for stable from v4.0, which introduced r6 support, onwards.] Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org Cc: stable@vger.kernel.org # v4.0+ --- arch/mips/include/asm/jump_label.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) 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" - "nop\n\t" + asm_volatile_goto("1:\t" B_INSN " 2f\n\t" + "2:\tnop\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" ".popsection\n\t" From beda0e725e5f06aca27eda2434ea9447dad88e36 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Fri, 8 Mar 2019 16:05:15 -0800 Subject: [PATCH 034/256] perf script python: Add Python3 support to exported-sql-viewer.py Support both Python2 and Python3 in the exported-sql-viewer.py script. The use of 'from __future__' implies the minimum supported Python2 version is now v2.6 Signed-off-by: Tony Jones Acked-by: Adrian Hunter Link: http://lkml.kernel.org/r/20190309000518.2438-2-tonyj@suse.de Signed-off-by: Seeteena Thoufeek Signed-off-by: Arnaldo Carvalho de Melo --- .../scripts/python/exported-sql-viewer.py | 42 ++++++++++++------- 1 file changed, 28 insertions(+), 14 deletions(-) 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 { | --help-only}" + printerr("Usage is: exported-sql-viewer.py { | --help-only}"); raise Exception("Too few arguments") dbname = sys.argv[1] @@ -2986,8 +3000,8 @@ def Main(): is_sqlite3 = False try: - f = open(dbname) - if f.read(15) == "SQLite format 3": + f = open(dbname, "rb") + if f.read(15) == b'SQLite format 3': is_sqlite3 = True f.close() except: From 1937b0560c3ea43b1b0f7d3617949ca50de8f8c0 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Fri, 8 Mar 2019 16:05:16 -0800 Subject: [PATCH 035/256] perf script python: Add Python3 support to export-to-postgresql.py Support both Python2 and Python3 in the export-to-postgresql.py script. The use of 'from __future__' implies the minimum supported Python2 version is now v2.6 Signed-off-by: Tony Jones Link: http://lkml.kernel.org/r/20190309000518.2438-3-tonyj@suse.de Signed-off-by: Adrian Hunter Signed-off-by: Seeteena Thoufeek Signed-off-by: Arnaldo Carvalho de Melo --- .../scripts/python/export-to-postgresql.py | 58 +++++++++++++------ 1 file changed, 41 insertions(+), 17 deletions(-) diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 390a351d15ea..00ab972a2eba 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 +248,14 @@ 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 usage(): - print >> sys.stderr, "Usage is: export-to-postgresql.py [] [] []" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-postgresql.py [] [] []") + printerr("where: columns 'all' or 'branches'") + printerr(" calls 'calls' => create calls and call_paths table") + printerr(" callchains 'callchains' => create call_paths table") raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -273,7 +289,7 @@ def do_query(q, s): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +print(datetime.datetime.today(), "Creating database...") db = QSqlDatabase.addDatabase('QPSQL') query = QSqlQuery(db) @@ -506,12 +522,12 @@ do_query(query, 'CREATE VIEW samples_view AS ' ' FROM samples') -file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0) -file_trailer = "\377\377" +file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0) +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 +542,13 @@ 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 +582,7 @@ if perf_db_export_calls: call_file = open_output_file("call_table.bin") def trace_begin(): - print datetime.datetime.today(), "Writing to intermediate files..." + print(datetime.datetime.today(), "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 +598,7 @@ def trace_begin(): unhandled_count = 0 def trace_end(): - print datetime.datetime.today(), "Copying to database..." + print(datetime.datetime.today(), "Copying to database...") copy_output_file(evsel_file, "selected_events") copy_output_file(machine_file, "machines") copy_output_file(thread_file, "threads") @@ -597,7 +613,7 @@ def trace_end(): if perf_db_export_calls: copy_output_file(call_file, "calls") - print datetime.datetime.today(), "Removing intermediate files..." + print(datetime.datetime.today(), "Removing intermediate files...") remove_output_file(evsel_file) remove_output_file(machine_file) remove_output_file(thread_file) @@ -612,7 +628,7 @@ 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" + print(datetime.datetime.today(), "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 +643,7 @@ 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" + print(datetime.datetime.today(), "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 +679,8 @@ 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" - print datetime.datetime.today(), "Done" + print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events") + print(datetime.datetime.today(), "Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count @@ -674,12 +690,14 @@ 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 +708,7 @@ 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 +720,9 @@ 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 +731,14 @@ 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) From ebf6c5c181abe9309788c6241d39602a1ce18723 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Fri, 8 Mar 2019 16:05:17 -0800 Subject: [PATCH 036/256] perf script python: Add Python3 support to export-to-sqlite.py Support both Python2 and Python3 in the export-to-sqlite.py script The use of 'from __future__' implies the minimum supported Python2 version is now v2.6 Signed-off-by: Tony Jones Acked-by: Adrian Hunter Link: http://lkml.kernel.org/r/20190309000518.2438-4-tonyj@suse.de Signed-off-by: Seeteena Thoufeek Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/export-to-sqlite.py | 23 +++++++++++-------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index eb63e6c7107f..3da338243aed 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 +62,14 @@ 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 usage(): - print >> sys.stderr, "Usage is: export-to-sqlite.py [] [] []" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-sqlite.py [] [] []"); + printerr("where: columns 'all' or 'branches'"); + printerr(" calls 'calls' => create calls and call_paths table"); + printerr(" callchains 'callchains' => create call_paths table"); raise Exception("Too few arguments") if (len(sys.argv) < 2): @@ -100,7 +105,7 @@ def do_query_(q): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +print(datetime.datetime.today(), "Creating database ...") db_exists = False try: @@ -378,7 +383,7 @@ if perf_db_export_calls: call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") def trace_begin(): - print datetime.datetime.today(), "Writing records..." + print(datetime.datetime.today(), "Writing records...") do_query(query, 'BEGIN TRANSACTION') # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") @@ -397,14 +402,14 @@ unhandled_count = 0 def trace_end(): do_query(query, 'END TRANSACTION') - print datetime.datetime.today(), "Adding indexes" + print(datetime.datetime.today(), "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" - print datetime.datetime.today(), "Done" + print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events") + print(datetime.datetime.today(), "Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count From 49f93bbf17e6267eb34e0c12a9813f3a8723749e Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Fri, 8 Mar 2019 16:05:18 -0800 Subject: [PATCH 037/256] perf script python: Add printdate function to SQL exporters Introduce a printdate function to eliminate the repetitive use of datetime.datetime.today() in the SQL exporting scripts. Signed-off-by: Tony Jones Acked-by: Adrian Hunter Link: http://lkml.kernel.org/r/20190309000518.2438-5-tonyj@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- .../scripts/python/export-to-postgresql.py | 19 +++++++++++-------- tools/perf/scripts/python/export-to-sqlite.py | 13 ++++++++----- 2 files changed, 19 insertions(+), 13 deletions(-) diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 00ab972a2eba..c3eae1d77d36 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -251,6 +251,9 @@ 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(): printerr("Usage is: export-to-postgresql.py [] [] []") printerr("where: columns 'all' or 'branches'") @@ -289,7 +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) @@ -582,7 +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") @@ -598,7 +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") @@ -613,7 +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) @@ -628,7 +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)') @@ -643,7 +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)') @@ -679,8 +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") - print(datetime.datetime.today(), "Done") + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index 3da338243aed..3b71902a5a21 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -65,6 +65,9 @@ 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(): printerr("Usage is: export-to-sqlite.py [] [] []"); printerr("where: columns 'all' or 'branches'"); @@ -105,7 +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: @@ -383,7 +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") @@ -402,14 +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") - print(datetime.datetime.today(), "Done") + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count From df94bb44b518b1d0c9f4b2e5127441cec13ab75c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Mar 2019 13:20:25 -0300 Subject: [PATCH 038/256] perf tools: Update x86's syscall_64.tbl, no change in tools/perf behaviour To pick the changes in 7948450d4556 ("x86/x32: use time64 versions of sigtimedwait and recvmmsg"), that doesn't cause any change in behaviour in tools/perf/ as it deals just with the x32 entries. This silences this tools/perf build warning: Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Cc: Adrian Hunter Cc: Arnd Bergmann Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-mqpvshayeqidlulx5qpioa59@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) 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 From 1a787fc5ba18ac767e635c58d06a0b46876184e3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Mar 2019 13:30:08 -0300 Subject: [PATCH 039/256] tools headers uapi: Sync copy of asm-generic/unistd.h with the kernel sources To get the changes in: c8ce48f06503 ("asm-generic: Make time32 syscall numbers optional") Silencing these tools/perf build warnings: Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/unistd.h' differs from latest version at 'arch/arm64/include/uapi/asm/unistd.h' diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Test built it under the ubuntu:14.04.4-x-linaro-arm64 cross build environment and looked at the syscall table at /tmp/build/perf/arch/arm64/include/generated/asm/syscalls.c, looks ok. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Arnd Bergmann Cc: Hendrik Brueckner Cc: Jiri Olsa Cc: Kim Phillips Cc: Michael Ellerman Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Thomas Richter Link: https://lkml.kernel.org/n/tip-e4w7ngsmkq48bd6st52ty2kb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/unistd.h | 2 + tools/include/uapi/asm-generic/unistd.h | 149 ++++++++++++++++----- 2 files changed, 118 insertions(+), 33 deletions(-) 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 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, \ - compat_sys_timerfd_settime) +__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \ + sys_timerfd_settime) #define __NR_timerfd_gettime 87 -__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \ - compat_sys_timerfd_gettime) +__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \ + 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, \ - compat_sys_clock_nanosleep) +__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \ + 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, \ - compat_sys_sched_rr_get_interval) +__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \ + 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, \ - compat_sys_rt_sigtimedwait) +__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \ + 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, \ - compat_sys_mq_timedreceive) +__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \ + 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, \ - compat_sys_open_by_handle_at) +__SYSCALL(__NR_open_by_handle_at, 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 From 2fb71043e8894ca78258f7458a2db2eb3a142a22 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Mar 2019 13:39:48 -0300 Subject: [PATCH 040/256] tools headers uapi: Update linux/in.h copy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To get the changes in: 4effd28c1245 ("bridge: join all-snoopers multicast address") That do not generate any changes in tools/ use of this file. Silences this tools/perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Cc: Adrian Hunter Cc: David S. Miller Cc: Jiri Olsa Cc: Linus Lüssing Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-ifpl634035266ho6wxuqgo81@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/in.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) 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_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ -#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ -#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ #endif /* contains the htonl type stuff.. */ From e87e548126cdc66fd4f194b38b59f351b6e5d3e8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:44:52 -0700 Subject: [PATCH 041/256] perf script: Filter COMM/FORK/.. events by CPU The --cpu option only filtered samples. Filter other perf events, such as COMM, FORK, SWITCH by the CPU too. Reported-by: Jiri Olsa Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 71 ++++++++++++++++++++++++------------- 1 file changed, 47 insertions(+), 24 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 111787e83784..b695b20ffc8a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1933,6 +1933,13 @@ 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, @@ -1967,7 +1974,7 @@ 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) @@ -2052,9 +2059,11 @@ 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); @@ -2088,9 +2097,11 @@ 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, - PERF_RECORD_NAMESPACES, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_NAMESPACES, stdout); + perf_event__fprintf(event, stdout); + } ret = 0; out: thread__put(thread); @@ -2122,9 +2133,11 @@ 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, - PERF_RECORD_FORK, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_FORK, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; @@ -2152,9 +2165,11 @@ 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, - PERF_RECORD_EXIT, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_EXIT, stdout); + perf_event__fprintf(event, stdout); + } if (perf_event__process_exit(tool, event, sample, machine) < 0) err = -1; @@ -2188,9 +2203,11 @@ 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, - PERF_RECORD_MMAP, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2220,9 +2237,11 @@ 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, - PERF_RECORD_MMAP2, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_MMAP2, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2247,9 +2266,11 @@ static int process_switch_event(struct perf_tool *tool, return -1; } - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_SWITCH, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_SWITCH, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } @@ -2270,9 +2291,11 @@ process_lost_event(struct perf_tool *tool, if (thread == NULL) return -1; - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_LOST, stdout); - perf_event__fprintf(event, stdout); + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_LOST, stdout); + perf_event__fprintf(event, stdout); + } thread__put(thread); return 0; } From 3723908d05834c76fd5cc9ecd17b0851342e1df4 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:44:54 -0700 Subject: [PATCH 042/256] perf report: Support time sort key Add a time sort key to perf report to display samples for different time quantums separately. This allows easier analysis of workloads that change over time, and also will allow looking at the context of samples. % perf record ... % perf report --sort time,overhead,symbol --time-quantum 1ms --stdio ... 0.67% 277061.87300 [.] _dl_start 0.50% 277061.87300 [.] f1 0.50% 277061.87300 [.] f2 0.33% 277061.87300 [.] main 0.29% 277061.87300 [.] _dl_lookup_symbol_x 0.29% 277061.87300 [.] dl_main 0.29% 277061.87300 [.] do_lookup_x 0.17% 277061.87300 [.] _dl_debug_initialize 0.17% 277061.87300 [.] _dl_init_paths 0.08% 277061.87300 [.] check_match 0.04% 277061.87300 [.] _dl_count_modids 1.33% 277061.87400 [.] f1 1.33% 277061.87400 [.] f2 1.33% 277061.87400 [.] main 1.17% 277061.87500 [.] main 1.08% 277061.87500 [.] f1 1.08% 277061.87500 [.] f2 1.00% 277061.87600 [.] main 0.83% 277061.87600 [.] f1 0.83% 277061.87600 [.] f2 1.00% 277061.87700 [.] main Committer notes: Rename 'time' argument to hist_time() to htime to overcome this in older distros: cc1: warnings being treated as errors util/hist.c: In function 'hist_time': util/hist.c:251: error: declaration of 'time' shadows a global declaration /usr/include/time.h:186: error: shadowed declaration is here Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-4-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 2 ++ tools/perf/util/hist.c | 11 +++++++ tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 39 ++++++++++++++++++++++++ tools/perf/util/sort.h | 2 ++ 5 files changed, 55 insertions(+) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 9ec1702bccdd..546d87221ad8 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) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f9eb95bf3938..34c0f00c68d1 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -19,6 +19,7 @@ #include #include #include +#include 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) { @@ -635,6 +645,7 @@ __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) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 4af27fbab24f..6279eca56409 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, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d2299e912e59..bdd30cab51cb 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -3,6 +3,7 @@ #include #include #include +#include #include "sort.h" #include "hist.h" #include "comm.h" @@ -15,6 +16,7 @@ #include #include "mem-events.h" #include "annotate.h" +#include "time-utils.h" #include regex_t parent_regex; @@ -654,6 +656,42 @@ 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 +1672,7 @@ 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 diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 2fbee0b1011c..19dceb7f6145 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -135,6 +135,7 @@ 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; @@ -231,6 +232,7 @@ enum sort_type { SORT_DSO_SIZE, SORT_CGROUP_ID, SORT_SYM_IPC_NULL, + SORT_TIME, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, From 1d6c49df74b0706af13a7d707638f0db374eaf88 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:44:56 -0700 Subject: [PATCH 043/256] perf report: Support running scripts for current time range When using the time sort key, add new context menus to run scripts for only the currently selected time range. Compute the correct range for the selection add pass it as the --time option to perf script. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-6-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 83 +++++++++++++++++++++++++++++----- 1 file changed, 72 insertions(+), 11 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index aef800d97ea1..f98aeac607dd 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -7,6 +7,7 @@ #include #include #include +#include #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" @@ -2338,6 +2340,7 @@ close_file_and_continue: } struct popup_action { + unsigned long time; struct thread *thread; struct map_symbol ms; int socket; @@ -2527,36 +2530,64 @@ static int do_run_script(struct hist_browser *browser __maybe_unused, struct popup_action *act) { - char script_opt[64]; - memset(script_opt, 0, sizeof(script_opt)); + char *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); } + 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); + free(script_opt); return 0; } static int -add_script_opt(struct hist_browser *browser __maybe_unused, +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, + const char *tstr) { + if (thread) { - if (asprintf(optstr, "Run scripts for samples of thread [%s]", - thread__comm_str(thread)) < 0) + if (asprintf(optstr, "Run scripts for samples of thread [%s]%s", + thread__comm_str(thread), tstr) < 0) return 0; } else if (sym) { - if (asprintf(optstr, "Run scripts for samples of symbol [%s]", - sym->name) < 0) + if (asprintf(optstr, "Run scripts for samples of symbol [%s]%s", + 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; } @@ -2566,6 +2597,36 @@ add_script_opt(struct hist_browser *browser __maybe_unused, return 1; } +static int +add_script_opt(struct hist_browser *browser, + struct popup_action *act, char **optstr, + struct thread *thread, struct symbol *sym) +{ + int n, j; + struct hist_entry *he; + + n = add_script_opt_2(browser, act, optstr, thread, sym, ""); + + 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, + tstr); + act->time = he->time; + } + return n; +} + static int do_switch_data(struct hist_browser *browser __maybe_unused, struct popup_action *act __maybe_unused) From 6f3da20e151f4121548cf598730ae0f9559ae45d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:44:57 -0700 Subject: [PATCH 044/256] perf report: Support builtin perf script in scripts menu The scripts menu traditionally only showed custom perf scripts. Allow to run standard perf script with useful default options too. - Normal perf script - perf script with assembler (needs xed installed) - perf script with source code output (needs debuginfo) - perf script with custom arguments Then we automatically select the right options to display the information in the perf.data file. For example with -b display branch contexts. It's not easily possible to check for xed's existence in advance. perf script usually gives sensible error messages when it's not available. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/annotate.c | 2 +- tools/perf/ui/browsers/hists.c | 23 +++--- tools/perf/ui/browsers/scripts.c | 127 +++++++++++++++++++++++------- tools/perf/util/hist.h | 8 +- 4 files changed, 120 insertions(+), 40 deletions(-) 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 f98aeac607dd..fb4430f8982c 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2344,6 +2344,7 @@ struct popup_action { struct thread *thread; struct map_symbol ms; int socket; + struct perf_evsel *evsel; int (*fn)(struct hist_browser *browser, struct popup_action *act); }; @@ -2566,7 +2567,7 @@ do_run_script(struct hist_browser *browser __maybe_unused, n += snprintf(script_opt + n, len - n, " --time %s,%s", start, end); } - script_browse(script_opt); + script_browse(script_opt, act->evsel); free(script_opt); return 0; } @@ -2575,7 +2576,7 @@ static int add_script_opt_2(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct thread *thread, struct symbol *sym, - const char *tstr) + struct perf_evsel *evsel, const char *tstr) { if (thread) { @@ -2593,6 +2594,7 @@ add_script_opt_2(struct hist_browser *browser __maybe_unused, act->thread = thread; act->ms.sym = sym; + act->evsel = evsel; act->fn = do_run_script; return 1; } @@ -2600,12 +2602,13 @@ add_script_opt_2(struct hist_browser *browser __maybe_unused, static int add_script_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, - struct thread *thread, struct symbol *sym) + 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, ""); + n = add_script_opt_2(browser, act, optstr, thread, sym, evsel, ""); he = hist_browser__selected_entry(browser); if (sort_order && strstr(sort_order, "time")) { @@ -2618,10 +2621,9 @@ add_script_opt(struct hist_browser *browser, sizeof tstr - j); j += sprintf(tstr + j, "-"); timestamp__scnprintf_usec(he->time + symbol_conf.time_quantum, - tstr + j, - sizeof tstr - j); + tstr + j, sizeof tstr - j); n += add_script_opt_2(browser, act, optstr, thread, sym, - tstr); + evsel, tstr); act->time = he->time; } return n; @@ -3092,7 +3094,7 @@ skip_annotation: nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], - thread, NULL); + thread, NULL, evsel); } /* * Note that browser->selection != NULL @@ -3107,11 +3109,12 @@ 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_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 7f36630694bf..9e5f87558af6 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -17,36 +17,111 @@ */ #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; +} + /* * 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]; - int i, num, choice, ret = -1; + char *buf, *paths[SCRIPT_MAX_NO], *names[SCRIPT_MAX_NO]; + 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++) { - names[i] = buf + i * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN); + if (evsel) + 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); + 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); - if (num > 0) { - choice = ui__popup_menu(num, names); - if (choice < num && choice >= 0) { - strcpy(script_name, paths[choice]); - ret = 0; - } + num = find_scripts(names + max_std, paths + max_std); + if (num < 0) + num = 0; + choice = ui__popup_menu(num + max_std, (char * const *)names); + 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; } @@ -66,27 +141,25 @@ static void run_script(char *cmd) SLsmg_refresh(); } -int script_browse(const char *script_opt) +int script_browse(const char *script_opt, struct perf_evsel *evsel) { - char cmd[SCRIPT_FULLPATH_LEN*2], script_name[SCRIPT_FULLPATH_LEN]; + char *cmd, script_name[SCRIPT_FULLPATH_LEN]; + bool custom = false; memset(script_name, 0, SCRIPT_FULLPATH_LEN); - if (list_scripts(script_name)) + if (list_scripts(script_name, &custom, evsel)) return -1; - sprintf(cmd, "perf script -s %s ", script_name); - - if (script_opt) - strcat(cmd, script_opt); - - if (input_name) { - strcat(cmd, " -i "); - strcat(cmd, input_name); - } - - strcat(cmd, " 2>&1 | less"); + if (asprintf(&cmd, "%s%s %s %s%s 2>&1 | less", + custom ? "perf script -s " : "", + script_name, + script_opt ? script_opt : "", + input_name ? "-i " : "", + input_name ? input_name : "") < 0) + return -1; run_script(cmd); + free(cmd); return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 6279eca56409..2113a6639cea 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -436,6 +436,8 @@ struct annotation_options; #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); @@ -450,7 +452,8 @@ 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); #else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, @@ -479,7 +482,8 @@ 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; } From 4968ac8fb7c378e2bc40b7e9bd97768fa8c7aa32 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:44:58 -0700 Subject: [PATCH 045/256] perf report: Implement browsing of individual samples Now 'perf report' can show whole time periods with 'perf script', but the user still has to find individual samples of interest manually. It would be expensive and complicated to search for the right samples in the whole perf file. Typically users only need to look at a small number of samples for useful analysis. Also the full scripts tend to show samples of all CPUs and all threads mixed up, which can be very confusing on larger systems. Add a new --samples option to save a small random number of samples per hist entry. Use a reservoir sample technique to select a representatve number of samples. Then allow browsing the samples using 'perf script' as part of the hist entry context menu. This automatically adds the right filters, so only the thread or cpu of the sample is displayed. Then we use less' search functionality to directly jump the to the time stamp of the selected sample. It uses different menus for assembler and source display. Assembler needs xed installed and source needs debuginfo. Currently it only supports as many samples as fit on the screen due to some limitations in the slang ui code. Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311174605.GA29294@tassilo.jf.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 6 ++ tools/perf/Documentation/perf-report.txt | 4 + tools/perf/builtin-report.c | 2 + tools/perf/ui/browsers/Build | 1 + tools/perf/ui/browsers/hists.c | 47 ++++++++++++ tools/perf/ui/browsers/res_sample.c | 94 ++++++++++++++++++++++++ tools/perf/ui/browsers/scripts.c | 2 +- tools/perf/util/hist.c | 39 ++++++++++ tools/perf/util/hist.h | 22 ++++++ tools/perf/util/sort.h | 8 ++ tools/perf/util/symbol.c | 1 + tools/perf/util/symbol_conf.h | 1 + 12 files changed, 226 insertions(+), 1 deletion(-) create mode 100644 tools/perf/ui/browsers/res_sample.c diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 86f3dcc15f83..2d0fb7613134 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -584,6 +584,12 @@ 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. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 546d87221ad8..f441baa794ce 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -461,6 +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. diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 05c8dd41106c..1921aaa9cece 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1159,6 +1159,8 @@ 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", 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/hists.c b/tools/perf/ui/browsers/hists.c index fb4430f8982c..3421ecbdd3f0 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1226,6 +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, @@ -2345,6 +2347,7 @@ struct popup_action { struct map_symbol ms; int socket; struct perf_evsel *evsel; + enum rstype rstype; int (*fn)(struct hist_browser *browser, struct popup_action *act); }; @@ -2572,6 +2575,17 @@ do_run_script(struct hist_browser *browser __maybe_unused, return 0; } +static int +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, @@ -2629,6 +2643,27 @@ add_script_opt(struct hist_browser *browser, 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) @@ -3115,6 +3150,18 @@ skip_annotation: } nr_options += add_script_opt(browser, &actions[nr_options], &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..884ef2a92c15 --- /dev/null +++ b/tools/perf/ui/browsers/res_sample.c @@ -0,0 +1,94 @@ +// 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 + +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]; + + /* For now since ui__popup_menu doesn't like lists that don't fit */ + num_res = max(min(SLtt_Screen_Rows - 4, num_res), 0); + + 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 9e5f87558af6..cdba58447b85 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -125,7 +125,7 @@ out: return ret; } -static void run_script(char *cmd) +void run_script(char *cmd) { pr_debug("Running %s\n", cmd); SLang_reset_tty(); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 34c0f00c68d1..1f230285d78a 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -436,6 +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; @@ -446,6 +453,9 @@ static int hist_entry__init(struct hist_entry *he, return 0; +err_srcline: + free(he->srcline); + err_rawdata: free(he->raw_data); @@ -603,6 +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, @@ -650,6 +686,8 @@ __hists__add_entry(struct hists *hists, 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; } @@ -1173,6 +1211,7 @@ 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 2113a6639cea..76ff6c6d03b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -433,6 +433,13 @@ 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" @@ -454,6 +461,11 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct annotation_options *annotation_options); 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, @@ -488,6 +500,16 @@ static inline int script_browse(const char *script_opt __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/sort.h b/tools/perf/util/sort.h index 19dceb7f6145..bb9442ab7a0c 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; @@ -140,6 +146,8 @@ struct hist_entry { 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; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 6b73a0eeb6a1..58442ca5e3c4 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -51,6 +51,7 @@ struct symbol_conf symbol_conf = { .symfs = "", .event_group = true, .inline_name = true, + .res_sample = 0, }; static enum dso_binary_type binary_type_symtab[] = { diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index a5684a71b78e..6c55fa6fccec 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -68,6 +68,7 @@ struct symbol_conf { struct intlist *pid_list, *tid_list; const char *symfs; + int res_sample; }; extern struct symbol_conf symbol_conf; From ca52babe033f2a0a535ce7c814e54a44cead1f15 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:44:59 -0700 Subject: [PATCH 046/256] perf tools: Add some new tips describing the new options Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-9-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/tips.txt | 7 +++++++ 1 file changed, 7 insertions(+) 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. From 905e4aff31382c3f9b2014d1361f4a1be4479ba2 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:45:01 -0700 Subject: [PATCH 047/256] perf script: Add array bound checking to list_scripts Don't overflow array when the scripts directory is too large, or the script file name is too long. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 8 ++++++-- tools/perf/builtin.h | 3 ++- tools/perf/ui/browsers/scripts.c | 3 ++- 3 files changed, 10 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b695b20ffc8a..2f93d60c5a17 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2982,7 +2982,8 @@ 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]; @@ -3027,7 +3028,10 @@ 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], 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/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index cdba58447b85..96e5cd3b0eee 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -97,7 +97,8 @@ static int list_scripts(char *script_name, bool *custom, paths[i] = names[i] + SCRIPT_NAMELEN; } - num = find_scripts(names + max_std, paths + max_std); + num = find_scripts(names + max_std, paths + max_std, SCRIPT_MAX_NO - max_std, + SCRIPT_FULLPATH_LEN); if (num < 0) num = 0; choice = ui__popup_menu(num + max_std, (char * const *)names); From 59c24980dffbea2106fe65e64ea77834d657ee9c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:45:02 -0700 Subject: [PATCH 048/256] perf ui browser: Fix ui popup argv browser for many entries Fix the argv ui browser code to correctly display more entries than fit on the screen without crashing. The problem was some type confusion with pointer types in the ->seek function. Do the argv arithmetic correctly with char ** pointers. Also add some asserts to find overruns and limit the display function correctly. Then finally remove a workaround for this in the res sample browser. Committer testing: 1) Resize the x terminal to have just some 5 lines 2) Use 'perf report --samples 1' to activate the sample browser options in the menu 3) Press ENTER, this will cause the crash: # perf report --samples 1 perf: Segmentation fault -------- backtrace -------- perf[0x5a514a] /lib64/libc.so.6(+0x385bf)[0x7f27281b55bf] /lib64/libc.so.6(+0x161a67)[0x7f27282dea67] /lib64/libslang.so.2(SLsmg_write_wrapped_string+0x82)[0x7f272874a0b2] perf(ui_browser__argv_refresh+0x77)[0x5939a7] perf[0x5924cc] perf(ui_browser__run+0x39)[0x593449] perf(ui__popup_menu+0x83)[0x5a5263] perf[0x59f421] perf(perf_evlist__tui_browse_hists+0x3a0)[0x5a3780] perf(cmd_report+0x2746)[0x447136] perf[0x4a95fe] perf(main+0x61c)[0x42dc6c] /lib64/libc.so.6(__libc_start_main+0xf2)[0x7f27281a1412] perf(_start+0x2d)[0x42de9d] # After applying this patch no crash takes place in such situation. Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-12-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browser.c | 10 +++++++--- tools/perf/ui/browsers/res_sample.c | 3 --- 2 files changed, 7 insertions(+), 6 deletions(-) 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/res_sample.c b/tools/perf/ui/browsers/res_sample.c index 884ef2a92c15..c0dd73176d42 100644 --- a/tools/perf/ui/browsers/res_sample.c +++ b/tools/perf/ui/browsers/res_sample.c @@ -36,9 +36,6 @@ int res_sample_browse(struct res_sample *res_samples, int num_res, struct res_sample *r; char extra_format[256]; - /* For now since ui__popup_menu doesn't like lists that don't fit */ - num_res = max(min(SLtt_Screen_Rows - 4, num_res), 0); - names = calloc(num_res, sizeof(char *)); if (!names) return -1; From e3b74de50a5f8bbfacbd772874c8b5d9220ebcdb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 11 Mar 2019 07:45:00 -0700 Subject: [PATCH 049/256] perf tools report: Add custom scripts to script menu Add a way to define custom scripts through ~/.perfconfig, which are then added to the scripts menu. The scripts get the same arguments as 'perf script', in particular -i, --cpu, --tid. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190311144502.15423-10-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 8 ++++++++ tools/perf/ui/browsers/scripts.c | 20 ++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 2d0fb7613134..95054a8176a2 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -590,6 +590,14 @@ samples.*:: 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/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 96e5cd3b0eee..27cf3ab88d13 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -6,6 +6,7 @@ #include "../../util/symbol.h" #include "../browser.h" #include "../libslang.h" +#include "config.h" #define SCRIPT_NAMELEN 128 #define SCRIPT_MAX_NO 64 @@ -53,6 +54,24 @@ static int add_script_option(const char *name, const char *opt, 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. @@ -87,6 +106,7 @@ static int list_scripts(char *script_name, bool *custom, &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; From dfcbc2f2994b8a3af3605a26dc29c07ad7378bf4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Mar 2019 17:07:52 -0300 Subject: [PATCH 050/256] tools lib bpf: Fix the build by adding a missing stdarg.h include The libbpf_print_fn_t typedef uses va_list without including the header where that type is defined, stdarg.h, breaking in places where we're unlucky for that type not to be already defined by some previously included header. Noticed while building on fedora 24 cross building tools/perf to the ARC architecture using the uClibc C library: 28 fedora:24-x-ARC-uClibc : FAIL arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 CC /tmp/build/perf/tests/llvm.o In file included from tests/llvm.c:3:0: /git/linux/tools/lib/bpf/libbpf.h:57:20: error: unknown type name 'va_list' const char *, va_list ap); ^~~~~~~ /git/linux/tools/lib/bpf/libbpf.h:59:34: error: unknown type name 'libbpf_print_fn_t' LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn); ^~~~~~~~~~~~~~~~~ mv: cannot stat '/tmp/build/perf/tests/.llvm.o.tmp': No such file or directory Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jakub Kicinski Cc: Jiri Olsa Cc: Namhyung Kim Cc: Quentin Monnet Cc: Stanislav Fomichev Cc: Yonghong Song Fixes: a8a1f7d09cfc ("libbpf: fix libbpf_print") Link: https://lkml.kernel.org/n/tip-5270n2quu2gqz22o7itfdx00@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index b4652aa1a58a..aa1521a51687 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 #include #include #include From cdb8faa00e3fcdd0ad10add743516d616dc7d38e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Petr=20=C5=A0tetiar?= Date: Mon, 11 Mar 2019 22:08:22 +0100 Subject: [PATCH 051/256] mips: bcm47xx: Enable USB power on Netgear WNDR3400v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Eric has reported on OpenWrt's bug tracking system[1], that he's not able to use USB devices on his WNDR3400v2 device after the boot, until he turns on GPIO #21 manually through sysfs. 1. https://bugs.openwrt.org/index.php?do=details&task_id=2170 Cc: Rafał Miłecki Cc: Hauke Mehrtens Reported-by: Eric Bohlman Tested-by: Eric Bohlman Signed-off-by: Petr Štetiar Signed-off-by: Paul Burton --- arch/mips/bcm47xx/workarounds.c | 1 + 1 file changed, 1 insertion(+) 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; From 9a18b5a412baf23137c8fddb4ea7f0c14087f31c Mon Sep 17 00:00:00 2001 From: "Enrico Weigelt, metux IT consult" Date: Mon, 11 Mar 2019 14:57:59 +0100 Subject: [PATCH 052/256] arch: arc: Kconfig: pedantic formatting Formatting of Kconfig files doesn't look so pretty, so let the Great White Handkerchief come around and clean it up. Signed-off-by: Enrico Weigelt, metux IT consult Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 12 ++++++------ arch/arc/plat-eznps/Kconfig | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 95fb11a85566..68401536e718 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 @@ -423,7 +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/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 - Thread + Core + 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" - depends on EZNPS_MTM_EXT - default n - help + bool "ARC-EZchip Memory error as an exception" + depends on EZNPS_MTM_EXT + default n + 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 From f6cab793d4a70808e4946baa8f5df4ea9adacc82 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 14 Mar 2019 17:40:16 +0000 Subject: [PATCH 053/256] MIPS: Remove custom MIPS32 __kernel_fsid_t type For MIPS32 kernels we have a custom definition of __kernel_fsid_t. This differs from the asm-generic version used by all other architectures & MIPS64 in one way - it declares the val field as an array of long, rather than an array of int. Since int & long have identical size & alignment when targeting MIPS32 anyway, this makes little sense. Beyond the pointlessness this causes problems for code which prints entries from the val array, for example the fanotify_encode_fid() function [1]. If such code uses a format specified suited to an int then it encounters compiler warnings when building for MIPS32, such as: In file included from include/linux/kernel.h:14:0, from include/linux/list.h:9, from include/linux/preempt.h:11, from include/linux/spinlock.h:51, from include/linux/fdtable.h:11, from fs/notify/fanotify/fanotify.c:3: fs/notify/fanotify/fanotify.c: In function 'fanotify_encode_fid': include/linux/kern_levels.h:5:18: warning: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'long int' [-Wformat=] Remove the custom __kernel_fsid_t definition & make use of the asm-generic version which will have an identical layout in memory anyway, in order to remove the inconsistency with other architectures. One possible regression this could cause if is any code is attempting to print entries from the val array with a long-sized format specifier, in which case it would begin seeing compiler warnings when built against kernel headers including this change. Since such code is exceedingly rare, and would have to be MIPS32-specific to expect a long, this seems to be a problem that it's extremely unlikely anyone will encounter. [1] https://lore.kernel.org/linux-mips/CAOQ4uxiEkczB7PNCXegFC-eYb9zAGaio_o=OgHAJHFd7eavBxA@mail.gmail.com/T/#mb43103277c79ef06b884359209e817db1c136140 Signed-off-by: Paul Burton Cc: Amir Goldstein Cc: Arnd Bergmann Cc: Jan Kara Cc: linux-arch@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- arch/mips/include/uapi/asm/posix_types.h | 7 ------- 1 file changed, 7 deletions(-) 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 #endif /* _ASM_POSIX_TYPES_H */ From fa30dde38aa8628c73a6dded7cb0bba38c27b576 Mon Sep 17 00:00:00 2001 From: Jiufei Xue Date: Thu, 14 Mar 2019 23:19:22 -0400 Subject: [PATCH 054/256] ext4: fix NULL pointer dereference while journal is aborted We see the following NULL pointer dereference while running xfstests generic/475: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 PGD 8000000c84bad067 P4D 8000000c84bad067 PUD c84e62067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 7 PID: 9886 Comm: fsstress Kdump: loaded Not tainted 5.0.0-rc8 #10 RIP: 0010:ext4_do_update_inode+0x4ec/0x760 ... Call Trace: ? jbd2_journal_get_write_access+0x42/0x50 ? __ext4_journal_get_write_access+0x2c/0x70 ? ext4_truncate+0x186/0x3f0 ext4_mark_iloc_dirty+0x61/0x80 ext4_mark_inode_dirty+0x62/0x1b0 ext4_truncate+0x186/0x3f0 ? unmap_mapping_pages+0x56/0x100 ext4_setattr+0x817/0x8b0 notify_change+0x1df/0x430 do_truncate+0x5e/0x90 ? generic_permission+0x12b/0x1a0 This is triggered because the NULL pointer handle->h_transaction was dereferenced in function ext4_update_inode_fsync_trans(). I found that the h_transaction was set to NULL in jbd2__journal_restart but failed to attached to a new transaction while the journal is aborted. Fix this by checking the handle before updating the inode. Fixes: b436b9bef84d ("ext4: Wait for proper transaction commit on fsync") Signed-off-by: Jiufei Xue Signed-off-by: Theodore Ts'o Reviewed-by: Joseph Qi Cc: stable@kernel.org --- fs/ext4/ext4_jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 15b6dd733780..df908ef79cce 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; From 372a03e01853f860560eade508794dd274e9b390 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 14 Mar 2019 23:20:25 -0400 Subject: [PATCH 055/256] ext4: fix data corruption caused by unaligned direct AIO Ext4 needs to serialize unaligned direct AIO because the zeroing of partial blocks of two competing unaligned AIOs can result in data corruption. However it decides not to serialize if the potentially unaligned aio is past i_size with the rationale that no pending writes are possible past i_size. Unfortunately if the i_size is not block aligned and the second unaligned write lands past i_size, but still into the same block, it has the potential of corrupting the previous unaligned write to the same block. This is (very simplified) reproducer from Frank // 41472 = (10 * 4096) + 512 // 37376 = 41472 - 4096 ftruncate(fd, 41472); io_prep_pwrite(iocbs[0], fd, buf[0], 4096, 37376); io_prep_pwrite(iocbs[1], fd, buf[1], 4096, 41472); io_submit(io_ctx, 1, &iocbs[1]); io_submit(io_ctx, 1, &iocbs[2]); io_getevents(io_ctx, 2, 2, events, NULL); Without this patch the 512B range from 40960 up to the start of the second unaligned write (41472) is going to be zeroed overwriting the data written by the first write. This is a data corruption. 00000000 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 00009200 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 * 0000a000 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 0000a200 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 With this patch the data corruption is avoided because we will recognize the unaligned_aio and wait for the unwritten extent conversion. 00000000 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 00009200 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 * 0000a200 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 * 0000b200 Reported-by: Frank Sorenson Signed-off-by: Lukas Czerner Signed-off-by: Theodore Ts'o Fixes: e9e3bcecf44c ("ext4: serialize unaligned asynchronous DIO") Cc: stable@vger.kernel.org --- fs/ext4/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) From 1dc1097ff60e4105216da7cd0aa99032b039a994 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 14 Mar 2019 23:46:05 -0400 Subject: [PATCH 056/256] ext4: avoid panic during forced reboot When admin calls "reboot -f" - i.e., does a hard system reboot by directly calling reboot(2) - ext4 filesystem mounted with errors=panic can panic the system. This happens because the underlying device gets disabled without unmounting the filesystem and thus some syscall running in parallel to reboot(2) can result in the filesystem getting IO errors. This is somewhat surprising to the users so try improve the behavior by switching to errors=remount-ro behavior when the system is running reboot(2). Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6e4cac646345..1a5729d8f9ec 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; - } - if (test_opt(sb, ERRORS_PANIC)) { + } else if (test_opt(sb, ERRORS_PANIC)) { if (EXT4_SB(sb)->s_journal && !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) return; From 7cf77140777364d77b2b6e392e7e081a205a08c5 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 14 Mar 2019 23:51:13 -0400 Subject: [PATCH 057/256] ext4: remove useless ext4_pin_inode() This function is never used from the beginning (and is commented out); let's remove it. Signed-off-by: Jason Yan Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 30 ------------------------------ 1 file changed, 30 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f84cf62fd290..e5014a6f76e2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -6082,36 +6082,6 @@ 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; From e65ef56db4945fb18a0d522e056c02ddf939e644 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Mar 2019 10:16:44 -0600 Subject: [PATCH 058/256] io_uring: use regular request ref counts Get rid of the special casing of "normal" requests not having any references to the io_kiocb. We initialize the ref count to 2, one for the submission side, and one or the completion side. Signed-off-by: Jens Axboe --- fs/io_uring.c | 54 +++++++++++++++++++++++++++++++++------------------ 1 file changed, 35 insertions(+), 19 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 5d99376d2369..9071fca118a4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -411,7 +411,8 @@ 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 +430,14 @@ 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)) { - io_ring_drop_ctx_refs(req->ctx, 1); - 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); } /* @@ -453,7 +458,8 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_cqring_fill_event(ctx, req->user_data, req->error, 0); - reqs[to_free++] = req; + if (refcount_dec_and_test(&req->refs)) + reqs[to_free++] = req; (*nr_events)++; /* @@ -616,7 +622,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) 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) @@ -1083,7 +1089,7 @@ static int io_nop(struct io_kiocb *req, u64 user_data) io_fput(req); } io_cqring_add_event(ctx, user_data, err, 0); - io_free_req(req); + io_put_req(req); return 0; } @@ -1146,7 +1152,7 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, io_fput(req); io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); - io_free_req(req); + io_put_req(req); return 0; } @@ -1204,7 +1210,7 @@ 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; } @@ -1212,7 +1218,7 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask) { io_cqring_add_event(req->ctx, req->user_data, mangle_poll(mask), 0); io_fput(req); - io_free_req(req); + io_put_req(req); } static void io_poll_complete_work(struct work_struct *work) @@ -1346,9 +1352,6 @@ 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 */ @@ -1380,13 +1383,12 @@ out: * 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); + io_put_req(req); return ipt.error; } if (mask) io_poll_complete(req, mask); - io_free_req(req); return 0; } @@ -1524,10 +1526,13 @@ 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 */ @@ -1649,11 +1654,22 @@ 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; } } + + /* 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; } From d64264d6218e6892edd832dc3a5a5857c2856c53 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 15 Mar 2019 00:15:32 -0400 Subject: [PATCH 059/256] ext4: add missing brelse() in add_new_gdb_meta_bg() Currently in add_new_gdb_meta_bg() there is a missing brelse of gdb_bh in case ext4_journal_get_write_access() fails. Additionally kvfree() is missing in the same error path. Fix it by moving the ext4_journal_get_write_access() before the ext4 sb update as Ted suggested and release n_group_desc and gdb_bh in case it fails. Fixes: 61a9c11e5e7a ("ext4: add missing brelse() add_new_gdb_meta_bg()'s error path") Signed-off-by: Lukas Czerner Signed-off-by: Theodore Ts'o --- fs/ext4/resize.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 3d9b18505c0c..90061c3d048b 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; } From 6c7328400e0488f7d49e19e02290ba343b6811b2 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 15 Mar 2019 00:22:28 -0400 Subject: [PATCH 060/256] ext4: report real fs size after failed resize Currently when the file system resize using ext4_resize_fs() fails it will report into log that "resized filesystem to ". However this may not be true in the case of failure. Use the current block count as returned by ext4_blocks_count() to report the block count. Additionally, report a warning that "error occurred during file system resize" Signed-off-by: Lukas Czerner Signed-off-by: Theodore Ts'o --- fs/ext4/resize.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 90061c3d048b..e7ae26e36c9c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -2080,6 +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; } From e0c5c576d5074b5bb7b1b4b59848c25ceb521331 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Mar 2019 10:18:47 -0600 Subject: [PATCH 061/256] io_uring: make io_read/write return an integer The callers all convert to an integer, and we only return 0/-ERROR anyway. Signed-off-by: Jens Axboe --- fs/io_uring.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 9071fca118a4..caf39663466f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -893,7 +893,7 @@ 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; } @@ -951,15 +951,15 @@ 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, - bool force_nonblock, struct io_submit_state *state) +static int io_read(struct io_kiocb *req, const struct sqe_submit *s, + 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) @@ -1004,15 +1004,15 @@ out_fput: return ret; } -static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) +static int io_write(struct io_kiocb *req, const struct sqe_submit *s, + 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) @@ -1396,8 +1396,7 @@ 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 opcode; + int ret, opcode; if (unlikely(s->index >= ctx->sq_entries)) return -EINVAL; @@ -1623,7 +1622,7 @@ 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)) From d530a402a114efcf6d2b88d7f628856dade5b90b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 13 Mar 2019 12:15:01 -0600 Subject: [PATCH 062/256] io_uring: add prepped flag We currently use the fact that if ->ki_filp is already set, then we've done the prep. In preparation for moving the file assignment earlier, use a separate flag to tell whether the request has been prepped for IO or not. Signed-off-by: Jens Axboe --- fs/io_uring.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index caf39663466f..d259e8a6cb2e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -214,6 +214,7 @@ 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; @@ -741,7 +742,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, int fd, ret; /* For -EAGAIN retry, everything is already prepped */ - if (kiocb->ki_filp) + if (req->flags & REQ_F_PREPPED) return 0; flags = READ_ONCE(sqe->flags); @@ -799,6 +800,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, } kiocb->ki_complete = io_complete_rw; } + req->flags |= REQ_F_PREPPED; return 0; out_fput: if (!(flags & IOSQE_FIXED_FILE)) { @@ -1099,8 +1101,8 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) unsigned flags; int fd; - /* Prep already done */ - if (req->rw.ki_filp) + /* Prep already done (EAGAIN retry) */ + if (req->flags & REQ_F_PREPPED) return 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) @@ -1122,6 +1124,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EBADF; } + req->flags |= REQ_F_PREPPED; return 0; } @@ -1632,8 +1635,6 @@ 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_submit_sqe(ctx, req, s, true, state); if (ret == -EAGAIN) { struct io_uring_sqe *sqe_copy; From 09bb839434bd845c01da3d159b0c126fe7fa90da Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 13 Mar 2019 12:39:28 -0600 Subject: [PATCH 063/256] io_uring: fix fget/fput handling This isn't a straight port of commit 84c4e1f89fef for aio.c, since io_uring doesn't use files in exactly the same way. But it's pretty close. See the commit message for that commit. This essentially fixes a use-after-free with the poll command handling, but it takes cue from Linus's approach to just simplifying the file handling. We move the setup of the file into a higher level location, so the individual commands don't have to deal with it. And then we release the reference when we free the associated io_kiocb. Fixes: 221c5eb23382 ("io_uring: add support for IORING_OP_POLL") Signed-off-by: Jens Axboe --- fs/io_uring.c | 230 +++++++++++++++++++++----------------------------- 1 file changed, 97 insertions(+), 133 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index d259e8a6cb2e..c08fa62e1978 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -189,6 +189,10 @@ struct sqe_submit { bool needs_fixed_file; }; +/* + * First field must be the file pointer in all the + * iocb unions! See also 'struct kiocb' in + */ struct io_poll_iocb { struct file *file; struct wait_queue_head *head; @@ -198,8 +202,15 @@ struct io_poll_iocb { 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; }; @@ -431,6 +442,8 @@ 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 (req->file && !(req->flags & REQ_F_FIXED_FILE)) + fput(req->file); io_ring_drop_ctx_refs(req->ctx, 1); kmem_cache_free(req_cachep, req); } @@ -448,45 +461,34 @@ 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); - - if (refcount_dec_and_test(&req->refs)) - reqs[to_free++] = req; (*nr_events)++; - /* - * Batched puts of the same file, to avoid dirtying the - * file usage count multiple times, if avoidable. - */ - if (!(req->flags & REQ_F_FIXED_FILE)) { - if (!file) { - file = req->rw.ki_filp; - file_count = 1; - } else if (file == req->rw.ki_filp) { - file_count++; + if (refcount_dec_and_test(&req->refs)) { + /* If we're not using fixed files, we have to pair the + * completion part with the file put. Use regular + * completions for those, only batch free for fixed + * file. + */ + if (req->flags & REQ_F_FIXED_FILE) { + reqs[to_free++] = req; + if (to_free == ARRAY_SIZE(reqs)) + io_free_req_many(ctx, reqs, &to_free); } else { - fput_many(file, file_count); - file = req->rw.ki_filp; - file_count = 1; + io_free_req(req); } } - - if (to_free == ARRAY_SIZE(reqs)) - io_free_req_many(ctx, reqs, &to_free); } - io_commit_cqring(ctx); - if (file) - fput_many(file, file_count); + io_commit_cqring(ctx); io_free_req_many(ctx, reqs, &to_free); } @@ -609,19 +611,12 @@ 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_put_req(req); } @@ -738,31 +733,18 @@ 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; - int fd, ret; + unsigned ioprio; + int ret; + if (!req->file) + return -EBADF; /* For -EAGAIN retry, everything is already prepped */ if (req->flags & REQ_F_PREPPED) return 0; - flags = READ_ONCE(sqe->flags); - fd = READ_ONCE(sqe->fd); + if (force_nonblock && !io_file_supports_async(req->file)) + 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)); @@ -771,7 +753,7 @@ 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 @@ -779,39 +761,26 @@ 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) { - ret = -EINVAL; - goto out_fput; - } + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; 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) @@ -968,16 +937,14 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, return ret; file = kiocb->ki_filp; - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) - goto out_fput; - ret = -EINVAL; + return -EBADF; 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); @@ -999,10 +966,6 @@ static int 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; } @@ -1020,17 +983,15 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, if (ret) return ret; - ret = -EBADF; file = kiocb->ki_filp; if (unlikely(!(file->f_mode & FMODE_WRITE))) - goto out_fput; - ret = -EINVAL; + return -EBADF; 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); @@ -1062,10 +1023,6 @@ static int 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; } @@ -1080,16 +1037,6 @@ 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_put_req(req); return 0; @@ -1098,9 +1045,9 @@ static int io_nop(struct io_kiocb *req, u64 user_data) 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; + if (!req->file) + return -EBADF; /* Prep already done (EAGAIN retry) */ if (req->flags & REQ_F_PREPPED) return 0; @@ -1110,20 +1057,6 @@ 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); - 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; - } - req->flags |= REQ_F_PREPPED; return 0; } @@ -1153,7 +1086,6 @@ 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_put_req(req); return 0; @@ -1220,7 +1152,6 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) static void io_poll_complete(struct io_kiocb *req, __poll_t mask) { io_cqring_add_event(req->ctx, req->user_data, mangle_poll(mask), 0); - io_fput(req); io_put_req(req); } @@ -1314,34 +1245,20 @@ 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; __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->canceled = false; @@ -1380,8 +1297,6 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) out: if (unlikely(ipt.error)) { - if (!(flags & IOSQE_FIXED_FILE)) - 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. @@ -1621,6 +1536,50 @@ 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) { @@ -1635,6 +1594,10 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, if (unlikely(!req)) return -EAGAIN; + 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) { struct io_uring_sqe *sqe_copy; @@ -1664,6 +1627,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, } } +out: /* drop submission reference */ io_put_req(req); From 8c838788775a593527803786d376393b7c28f589 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Mar 2019 15:48:16 -0600 Subject: [PATCH 064/256] io_uring: fix poll races This is a straight port of Al's fix for the aio poll implementation, since the io_uring version is heavily based on that. The below description is almost straight from that patch, just modified to fit the io_uring situation. io_poll() has to cope with several unpleasant problems: * requests that might stay around indefinitely need to be made visible for io_cancel(2); that must not be done to a request already completed, though. * in cases when ->poll() has placed us on a waitqueue, wakeup might have happened (and request completed) before ->poll() returns. * worse, in some early wakeup cases request might end up re-added into the queue later - we can't treat "woken up and currently not in the queue" as "it's not going to stick around indefinitely" * ... moreover, ->poll() might have decided not to put it on any queues to start with, and that needs to be distinguished from the previous case * ->poll() might have tried to put us on more than one queue. Only the first will succeed for io poll, so we might end up missing wakeups. OTOH, we might very well notice that only after the wakeup hits and request gets completed (all before ->poll() gets around to the second poll_wait()). In that case it's too late to decide that we have an error. req->woken was an attempt to deal with that. Unfortunately, it was broken. What we need to keep track of is not that wakeup has happened - the thing might come back after that. It's that async reference is already gone and won't come back, so we can't (and needn't) put the request on the list of cancellables. The easiest case is "request hadn't been put on any waitqueues"; we can tell by seeing NULL apt.head, and in that case there won't be anything async. We should either complete the request ourselves (if vfs_poll() reports anything of interest) or return an error. In all other cases we get exclusion with wakeups by grabbing the queue lock. If request is currently on queue and we have something interesting from vfs_poll(), we can steal it and complete the request ourselves. If it's on queue and vfs_poll() has not reported anything interesting, we either put it on the cancellable list, or, if we know that it hadn't been put on all queues ->poll() wanted it on, we steal it and return an error. If it's _not_ on queue, it's either been already dealt with (in which case we do nothing), or there's io_poll_complete_work() about to be executed. In that case we either put it on the cancellable list, or, if we know it hadn't been put on all queues ->poll() wanted it on, simulate what cancel would've done. Fixes: 221c5eb23382 ("io_uring: add support for IORING_OP_POLL") Signed-off-by: Jens Axboe --- fs/io_uring.c | 119 +++++++++++++++++++++++++------------------------- 1 file changed, 60 insertions(+), 59 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c08fa62e1978..12bb238aed6b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -197,7 +197,7 @@ 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; }; @@ -367,20 +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)) - wake_up(&ctx->wait); - if (waitqueue_active(&ctx->sqo_wait)) - wake_up(&ctx->sqo_wait); + io_cqring_ev_posted(ctx); } static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) @@ -1149,10 +1154,12 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) 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); - io_put_req(req); + req->poll.done = true; + io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask), 0); + io_commit_cqring(ctx); } static void io_poll_complete_work(struct work_struct *work) @@ -1180,9 +1187,11 @@ 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, @@ -1193,29 +1202,25 @@ 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); - - poll->woken = true; + unsigned long flags; /* for instances that support it check for an event match first: */ - if (mask) { - unsigned long flags; - - if (!(mask & poll->events)) - return 0; - - /* try to complete the iocb inline if we can: */ - if (spin_trylock_irqsave(&ctx->completion_lock, flags)) { - list_del(&req->list); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - - list_del_init(&poll->wait.entry); - io_poll_complete(req, mask); - return 1; - } - } + if (mask && !(mask & poll->events)) + return 0; list_del_init(&poll->wait.entry); - queue_work(ctx->sqo_wq, &req->work); + + if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) { + list_del(&req->list); + io_poll_complete(ctx, req, mask); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + + io_cqring_ev_posted(ctx); + io_put_req(req); + } else { + queue_work(ctx->sqo_wq, &req->work); + } + return 1; } @@ -1245,6 +1250,7 @@ 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; + bool cancel = false; __poll_t mask; u16 events; @@ -1260,7 +1266,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; poll->head = NULL; - poll->woken = false; + poll->done = false; poll->canceled = false; ipt.pt._qproc = io_poll_queue_proc; @@ -1273,41 +1279,36 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) init_waitqueue_func_entry(&poll->wait, io_poll_wake); 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 (poll->woken) { - /* wake_up context handles the rest */ - mask = 0; - ipt.error = 0; - } else if (mask || ipt.error) { - /* 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); + if (likely(poll->head)) { + spin_lock(&poll->head->lock); + if (unlikely(list_empty(&poll->wait.entry))) { + 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; + io_poll_complete(ctx, req, mask); } - spin_unlock(&poll->head->lock); spin_unlock_irq(&ctx->completion_lock); -out: - if (unlikely(ipt.error)) { - /* - * Drop one of our refs to this req, __io_submit_sqe() will - * drop the other one since we're returning an error. - */ + if (mask) { + io_cqring_ev_posted(ctx); io_put_req(req); - return ipt.error; } - - if (mask) - io_poll_complete(req, mask); - return 0; + return ipt.error; } static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, From 6ade657d6125ec3ec07f95fa51e28138aef6208f Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Thu, 14 Mar 2019 22:58:29 -0500 Subject: [PATCH 065/256] ALSA: echoaudio: add a check for ioremap_nocache In case ioremap_nocache fails, the fix releases chip and returns an error code upstream to avoid NULL pointer dereference. Signed-off-by: Kangjie Lu Signed-off-by: Takashi Iwai --- sound/pci/echoaudio/echoaudio.c | 5 +++++ 1 file changed, 5 insertions(+) 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)) { From dcd0feac9bab901d5739de51b3f69840851f8919 Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Thu, 14 Mar 2019 23:04:14 -0500 Subject: [PATCH 066/256] ALSA: sb8: add a check for request_region In case request_region fails, the fix returns an error code to avoid NULL pointer dereference. Signed-off-by: Kangjie Lu Signed-off-by: Takashi Iwai --- sound/isa/sb/sb8.c | 4 ++++ 1 file changed, 4 insertions(+) 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], From 2d012c65a9ca26a0ef87ea0a42f1653dd37155f5 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 17 Mar 2019 15:49:29 +0900 Subject: [PATCH 067/256] ALSA: firewire-motu: use 'version' field of unit directory to identify model Current ALSA firewire-motu driver uses the value of 'model' field of unit directory in configuration ROM for modalias for MOTU FireWire models. However, as long as I checked, Pre8 and 828mk3(Hybrid) have the same value for the field (=0x100800). unit | version | model --------------- | --------- | ---------- 828mkII | 0x000003 | 0x101800 Traveler | 0x000009 | 0x107800 Pre8 | 0x00000f | 0x100800 <- 828mk3(FW) | 0x000015 | 0x106800 AudioExpress | 0x000033 | 0x104800 828mk3(Hybrid) | 0x000035 | 0x100800 <- When updating firmware for MOTU 8pre FireWire from v1.0.0 to v1.0.3, I got change of the value from 0x100800 to 0x103800. On the other hand, the value of 'version' field is fixed to 0x00000f. As a quick glance, the higher 12 bits of the value of 'version' field represent firmware version, while the lower 12 bits is unknown. By induction, the value of 'version' field represents actual model. This commit changes modalias to match the value of 'version' field, instead of 'model' field. For degug, long name of added sound card includes hexadecimal value of 'model' field. Fixes: 6c5e1ac0e144 ("ALSA: firewire-motu: add support for Motu Traveler") Signed-off-by: Takashi Sakamoto Cc: # v4.19+ Signed-off-by: Takashi Iwai --- sound/firewire/motu/motu.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) 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(0x107800, &snd_motu_spec_traveler), - SND_MOTU_DEV_ENTRY(0x106800, &motu_828mk3), /* FireWire only. */ - SND_MOTU_DEV_ENTRY(0x100800, &motu_828mk3), /* Hybrid. */ - SND_MOTU_DEV_ENTRY(0x104800, &motu_audio_express), + SND_MOTU_DEV_ENTRY(0x000003, &motu_828mk2), + SND_MOTU_DEV_ENTRY(0x000009, &snd_motu_spec_traveler), + SND_MOTU_DEV_ENTRY(0x000015, &motu_828mk3), /* FireWire only. */ + SND_MOTU_DEV_ENTRY(0x000035, &motu_828mk3), /* Hybrid. */ + SND_MOTU_DEV_ENTRY(0x000033, &motu_audio_express), { } }; MODULE_DEVICE_TABLE(ieee1394, motu_id_table); From 41c8d0adf3c4df1867d98cee4a2c4531352a33ad Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 12 Mar 2019 16:44:28 +0200 Subject: [PATCH 068/256] auxdisplay: hd44780: Fix memory leak on ->remove() We have to free on ->remove() the allocated resources on ->probe(). Fixes: d47d88361fee ("auxdisplay: Add HD44780 Character LCD support") Reviewed-by: Geert Uytterhoeven Signed-off-by: Andy Shevchenko Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/hd44780.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c index 9ad93ea42fdc..3cde351fb5c9 100644 --- a/drivers/auxdisplay/hd44780.c +++ b/drivers/auxdisplay/hd44780.c @@ -280,6 +280,8 @@ static int hd44780_remove(struct platform_device *pdev) struct charlcd *lcd = platform_get_drvdata(pdev); charlcd_unregister(lcd); + + kfree(lcd); return 0; } From b658a2113ba4d4b99e2a57926379b0c0b0c648ab Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 12 Mar 2019 16:44:29 +0200 Subject: [PATCH 069/256] auxdisplay: charlcd: Move to_priv() to charlcd namespace In order to be more particular in names, rename to_priv() macro to charlcd_to_priv(). No functional change intended. Reviewed-by: Geert Uytterhoeven Signed-off-by: Andy Shevchenko Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/charlcd.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 60e0b772673f..407acd22efa8 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; @@ -766,7 +766,7 @@ static void charlcd_puts(struct charlcd *lcd, const char *s) /* 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) { @@ -866,7 +866,7 @@ 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-"); From 8e44fc85060ec997e9c6f3c49a04274db6621d26 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 12 Mar 2019 16:44:30 +0200 Subject: [PATCH 070/256] auxdisplay: charlcd: Introduce charlcd_free() helper The charlcd_free() is a counterpart to charlcd_alloc() and should be called symmetrically on tear down. Reviewed-by: Geert Uytterhoeven Signed-off-by: Andy Shevchenko Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/charlcd.c | 6 ++++++ include/misc/charlcd.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 407acd22efa8..a351a9400054 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -818,6 +818,12 @@ 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) { 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); From 9b11d63966fc70b5496013bb211fa9025cd1ad61 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 12 Mar 2019 16:44:31 +0200 Subject: [PATCH 071/256] auxdisplay: panel: Convert to use charlcd_free() Convert to use charlcd_free() instead of kfree() for sake of type check. Reviewed-by: Geert Uytterhoeven Signed-off-by: Andy Shevchenko Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/panel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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; } From cb79eb95c56fe6afe2baf1df01f22b1bed3f6060 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 12 Mar 2019 16:44:32 +0200 Subject: [PATCH 072/256] auxdisplay: hd44780: Convert to use charlcd_free() Convert to use charlcd_free() instead of kfree() for sake of type check. Reviewed-by: Geert Uytterhoeven Signed-off-by: Andy Shevchenko Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/hd44780.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c index 3cde351fb5c9..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; } @@ -281,7 +281,7 @@ static int hd44780_remove(struct platform_device *pdev) charlcd_unregister(lcd); - kfree(lcd); + charlcd_free(lcd); return 0; } From 24c764abfd0d4b6e8e33c3818b668edbb4936d6f Mon Sep 17 00:00:00 2001 From: Mans Rullgard Date: Fri, 1 Mar 2019 18:48:14 +0000 Subject: [PATCH 073/256] auxdisplay: deconfuse configuration The auxdisplay Kconfig is confusing. It creates two separate menus even though the settings are closely related. Moreover, the options for setting the boot message depend on CONFIG_PARPORT even though they are used by drivers that do not. Clear up the confusion by moving the "Parallel port LCD/Keypad" menu under auxdisplay where it logically belongs. Change the boot message options to depend only on CONFIG_CHARLCD, making them accessible also when only the HD44780 is selected. Since the "Parallel port LCD/Keypad" driver now has a new dependency on CONFIG_AUXDISPLAY, rename its Kconfig symbol and keep the old one such that make oldconfig will not disable the driver. Signed-off-by: Mans Rullgard Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/Kconfig | 17 ++++++++++++----- drivers/auxdisplay/Makefile | 2 +- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index 57410f9c5d44..7d3fe27d6868 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 PANEL +menuconfig PARPORT_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 +445,13 @@ 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 +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 From c9171722459fdeab0f27790ae04c0c5a4ae5a9b2 Mon Sep 17 00:00:00 2001 From: Mans Rullgard Date: Fri, 1 Mar 2019 18:48:15 +0000 Subject: [PATCH 074/256] auxdisplay: charlcd: simplify init message display If CONFIG_PANEL_CHANGE_MESSAGE is set, CONFIG_PANEL_BOOT_MESSAGE will also be defined, so the double ifdef is pointless. Simplify the code further by using an intermediate macro rather duplicating most of the line. Signed-off-by: Mans Rullgard Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/charlcd.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index a351a9400054..5212675564d7 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -763,6 +763,12 @@ 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 + /* initialize the LCD driver */ static int charlcd_init(struct charlcd *lcd) { @@ -784,13 +790,8 @@ static int charlcd_init(struct charlcd *lcd) return ret; /* display a short message */ -#ifdef CONFIG_PANEL_CHANGE_MESSAGE -#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 + charlcd_puts(lcd, "\x1b[Lc\x1b[Lb\x1b[L*" LCD_INIT_TEXT); + /* clear the display on the next device opening */ priv->must_clear = true; charlcd_home(lcd); From cc5d04d840d62d7c75e268c51da7cd0be2ee03c0 Mon Sep 17 00:00:00 2001 From: Mans Rullgard Date: Fri, 1 Mar 2019 18:48:16 +0000 Subject: [PATCH 075/256] auxdisplay: charlcd: make backlight initial state configurable The charlcd driver currently flashes the backlight once on init. This may not be desirable. Thus, add options for turning the backlight off or on as well. Signed-off-by: Mans Rullgard Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/Kconfig | 21 +++++++++++++++++++++ drivers/auxdisplay/charlcd.c | 10 +++++++++- 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index 7d3fe27d6868..c52c738e554a 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -445,6 +445,27 @@ 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. +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 diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 5212675564d7..92745efefb54 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -769,6 +769,14 @@ static void charlcd_puts(struct charlcd *lcd, const char *s) #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) { @@ -790,7 +798,7 @@ static int charlcd_init(struct charlcd *lcd) return ret; /* display a short message */ - charlcd_puts(lcd, "\x1b[Lc\x1b[Lb\x1b[L*" LCD_INIT_TEXT); + charlcd_puts(lcd, "\x1b[Lc\x1b[Lb" LCD_INIT_BL LCD_INIT_TEXT); /* clear the display on the next device opening */ priv->must_clear = true; From 8f3b487685b2acf71b42bb30d68fd9271bec8695 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 15 Mar 2019 11:37:20 +1000 Subject: [PATCH 076/256] drm/udl: use drm_gem_object_put_unlocked. When Daniel removed struct_mutex he didn't fix this call to the unlocked variant which is required since we no longer use struct mutex. This fixes a bunch of: WARNING: CPU: 4 PID: 1370 at drivers/gpu/drm/drm_gem.c:931 drm_gem_object_put+0x2b/0x30 [drm] Modules linked in: udl xt_CHECKSUM ipt_MASQUERADE tun bridge stp llc nf_conntrack_netbios_ns nf_conntrack_broadcast xt_CT ip6t> CPU: 4 PID: 1370 Comm: Xorg Not tainted 5.0.0+ #2 backtraces when you plug in a udl device. Fixes: ae358dacd217 (drm/udl: Get rid of dev->struct_mutex usage) Reviewed-by: Daniel Vetter Cc: Sean Paul Signed-off-by: Dave Airlie --- drivers/gpu/drm/udl/udl_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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; From 587443e7773e150ae29e643ee8f41a1eed226565 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 6 Mar 2019 19:17:56 +0200 Subject: [PATCH 077/256] IB/mlx4: Fix race condition between catas error reset and aliasguid flows Code review revealed a race condition which could allow the catas error flow to interrupt the alias guid query post mechanism at random points. Thiis is fixed by doing cancel_delayed_work_sync() instead of cancel_delayed_work() during the alias guid mechanism destroy flow. Fixes: a0c64a17aba8 ("mlx4: Add alias_guid mechanism") Signed-off-by: Jack Morgenstein Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx4/alias_GUID.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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, From f84b66b9cce78e8f9d38204fdaa75f07c75f4911 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 6 Mar 2019 19:20:50 +0200 Subject: [PATCH 078/256] net/mlx5: Fix DCT creation bad flow In case the DCT creation command has succeeded a DRAIN must be issued before calling DESTROY. In addition, the original code used the wrong parameter for the DESTROY command, 'in' instead of 'din', which caused another creation try instead of destroying. Cc: # 4.15 Fixes: 57cda166bbe0 ("net/mlx5: Add DCT command interface") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 66 +++++++++++--------- 1 file changed, 36 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 370ca94b6775..c7c2920c05c4 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) { @@ -227,13 +230,42 @@ 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 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; @@ -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_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)); + _mlx5_core_destroy_dct(dev, dct, false); 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}; - 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; + return _mlx5_core_destroy_dct(dev, dct, true); } EXPORT_SYMBOL_GPL(mlx5_core_destroy_dct); From c5ae1954c47d3fd8815bd5a592aba18702c93f33 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 6 Mar 2019 19:21:42 +0200 Subject: [PATCH 079/256] IB/mlx5: Use mlx5 core to create/destroy a DEVX DCT To prevent a hardware memory leak when a DEVX DCT object is destroyed without calling DRAIN DCT before, (e.g. under cleanup flow), need to manage its creation and destruction via mlx5 core. In that case the DRAIN DCT command will be called and only once that it will be completed the DESTROY DCT command will be called. Otherwise, the DESTROY DCT may fail and a hardware leak may occur. As of that change the DRAIN DCT command should not be exposed any more from DEVX, it's managed internally by the driver to work as expected by the device specification. Fixes: 7efce3691d33 ("IB/mlx5: Add obj create and destroy functionality") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/devx.c | 34 +++++++++++++++----- drivers/infiniband/hw/mlx5/qp.c | 4 ++- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 6 ++-- include/linux/mlx5/qp.h | 3 +- 4 files changed, 34 insertions(+), 13 deletions(-) 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, - cmd_in_len, - cmd_out, cmd_out_len); + if (opcode == MLX5_CMD_OP_CREATE_DCT) { + obj->flags |= DEVX_OBJ_FLAGS_DCT; + 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/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/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index c7c2920c05c4..b8ba74de9555 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -263,16 +263,16 @@ destroy: 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}; 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; 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, From cd27287562d69629c5f007c6f64c27b6ff15f3e5 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 11 Mar 2019 14:35:58 +0200 Subject: [PATCH 080/256] IB/mlx5: Fix mapping of link-mode to IB width and speed Add mapping of link mode: CAUI4 100Gbps CR4/KR4 with 4 lines and 25Gbps. Fix mapping of link mode: GAUI2 50Gbps CR2/KR2 to be 2 lines with 25Gbps. Fixes: 08e8676f1607 ("IB/mlx5: Add support for 50Gbps per lane link modes") Signed-off-by: Aya Levin Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/main.c | 7 +++++++ 1 file changed, 7 insertions(+) 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; From ec4fe4bcc584b55e24e8d1768f5510a62c0fd619 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 14 Mar 2019 18:37:29 +0800 Subject: [PATCH 081/256] i40iw: Avoid panic when handling the inetdev event There is a panic reported that on a system with x722 ethernet, when doing the operations like: # ip link add br0 type bridge # ip link set eno1 master br0 # systemctl restart systemd-networkd The system will panic "BUG: unable to handle kernel null pointer dereference at 0000000000000034", with call chain: i40iw_inetaddr_event notifier_call_chain blocking_notifier_call_chain notifier_call_chain __inet_del_ifa inet_rtm_deladdr rtnetlink_rcv_msg netlink_rcv_skb rtnetlink_rcv netlink_unicast netlink_sendmsg sock_sendmsg __sys_sendto It is caused by "local_ipaddr = ntohl(in->ifa_list->ifa_address)", while the in->ifa_list is NULL. So add a check for the "in->ifa_list == NULL" case, and skip the ARP operation accordingly. Signed-off-by: Feng Tang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/i40iw/i40iw_utils.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) 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, From b5b4453e7912f056da1ca7572574cada32ecb60c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 14 Mar 2019 00:14:38 +1100 Subject: [PATCH 082/256] powerpc/vdso64: Fix CLOCK_MONOTONIC inconsistencies across Y2038 Jakub Drnec reported: Setting the realtime clock can sometimes make the monotonic clock go back by over a hundred years. Decreasing the realtime clock across the y2k38 threshold is one reliable way to reproduce. Allegedly this can also happen just by running ntpd, I have not managed to reproduce that other than booting with rtc at >2038 and then running ntp. When this happens, anything with timers (e.g. openjdk) breaks rather badly. And included a test case (slightly edited for brevity): #define _POSIX_C_SOURCE 199309L #include #include #include #include long get_time(void) { struct timespec tp; clock_gettime(CLOCK_MONOTONIC, &tp); return tp.tv_sec + tp.tv_nsec / 1000000000; } int main(void) { long last = get_time(); while(1) { long now = get_time(); if (now < last) { printf("clock went backwards by %ld seconds!\n", last - now); } last = now; sleep(1); } return 0; } Which when run concurrently with: # date -s 2040-1-1 # date -s 2037-1-1 Will detect the clock going backward. The root cause is that wtom_clock_sec in struct vdso_data is only a 32-bit signed value, even though we set its value to be equal to tk->wall_to_monotonic.tv_sec which is 64-bits. Because the monotonic clock starts at zero when the system boots the wall_to_montonic.tv_sec offset is negative for current and future dates. Currently on a freshly booted system the offset will be in the vicinity of negative 1.5 billion seconds. However if the wall clock is set past the Y2038 boundary, the offset from wall to monotonic becomes less than negative 2^31, and no longer fits in 32-bits. When that value is assigned to wtom_clock_sec it is truncated and becomes positive, causing the VDSO assembly code to calculate CLOCK_MONOTONIC incorrectly. That causes CLOCK_MONOTONIC to jump ahead by ~4 billion seconds which it is not meant to do. Worse, if the time is then set back before the Y2038 boundary CLOCK_MONOTONIC will jump backward. We can fix it simply by storing the full 64-bit offset in the vdso_data, and using that in the VDSO assembly code. We also shuffle some of the fields in vdso_data to avoid creating a hole. The original commit that added the CLOCK_MONOTONIC support to the VDSO did actually use a 64-bit value for wtom_clock_sec, see commit a7f290dad32e ("[PATCH] powerpc: Merge vdso's and add vdso support to 32 bits kernel") (Nov 2005). However just 3 days later it was converted to 32-bits in commit 0c37ec2aa88b ("[PATCH] powerpc: vdso fixes (take #2)"), and the bug has existed since then AFAICS. Fixes: 0c37ec2aa88b ("[PATCH] powerpc: vdso fixes (take #2)") Cc: stable@vger.kernel.org # v2.6.15+ Link: http://lkml.kernel.org/r/HaC.ZfES.62bwlnvAvMP.1STMMj@seznam.cz Reported-by: Jakub Drnec Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/vdso_datapage.h | 8 ++++---- arch/powerpc/kernel/vdso64/gettimeofday.S | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) 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 */ - __s32 wtom_clock_nsec; - struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */ + __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ + 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/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 */ From e60a582bcde01158a64ff948fb799f21f5d31a11 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 7 Mar 2019 11:09:19 +0100 Subject: [PATCH 083/256] mmc: pxamci: fix enum type confusion clang points out several instances of mismatched types in this drivers, all coming from a single declaration: drivers/mmc/host/pxamci.c:193:15: error: implicit conversion from enumeration type 'enum dma_transfer_direction' to different enumeration type 'enum dma_data_direction' [-Werror,-Wenum-conversion] direction = DMA_DEV_TO_MEM; ~ ^~~~~~~~~~~~~~ drivers/mmc/host/pxamci.c:212:62: error: implicit conversion from enumeration type 'enum dma_data_direction' to different enumeration type 'enum dma_transfer_direction' [-Werror,-Wenum-conversion] tx = dmaengine_prep_slave_sg(chan, data->sg, host->dma_len, direction, The behavior is correct, so this must be a simply typo from dma_data_direction and dma_transfer_direction being similarly named types with a similar purpose. Fixes: 6464b7140951 ("mmc: pxamci: switch over to dmaengine use") Signed-off-by: Arnd Bergmann Reviewed-by: Nathan Chancellor Acked-by: Robert Jarzmik Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/pxamci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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; From 9ce58dd7d9da3ca0d7cb8c9568f1c6f4746da65a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 7 Mar 2019 11:10:11 +0100 Subject: [PATCH 084/256] mmc: davinci: remove extraneous __init annotation Building with clang finds a mistaken __init tag: WARNING: vmlinux.o(.text+0x5e4250): Section mismatch in reference from the function davinci_mmcsd_probe() to the function .init.text:init_mmcsd_host() The function davinci_mmcsd_probe() references the function __init init_mmcsd_host(). This is often because davinci_mmcsd_probe lacks a __init annotation or the annotation of init_mmcsd_host is wrong. Signed-off-by: Arnd Bergmann Acked-by: Wolfram Sang Reviewed-by: Nathan Chancellor Signed-off-by: Ulf Hansson --- drivers/mmc/host/davinci_mmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From 4e50ce03976fbc8ae995a000c4b10c737467beaa Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 13 Mar 2019 10:03:17 +0100 Subject: [PATCH 085/256] iommu/amd: fix sg->dma_address for sg->offset bigger than PAGE_SIZE Take into account that sg->offset can be bigger than PAGE_SIZE when setting segment sg->dma_address. Otherwise sg->dma_address will point at diffrent page, what makes DMA not possible with erros like this: xhci_hcd 0000:38:00.3: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x00000000fdaa70c0 flags=0x0020] xhci_hcd 0000:38:00.3: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x00000000fdaa7040 flags=0x0020] xhci_hcd 0000:38:00.3: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x00000000fdaa7080 flags=0x0020] xhci_hcd 0000:38:00.3: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x00000000fdaa7100 flags=0x0020] xhci_hcd 0000:38:00.3: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x00000000fdaa7000 flags=0x0020] Additinally with wrong sg->dma_address unmap_sg will free wrong pages, what what can cause crashes like this: Feb 28 19:27:45 kernel: BUG: Bad page state in process cinnamon pfn:39e8b1 Feb 28 19:27:45 kernel: Disabling lock debugging due to kernel taint Feb 28 19:27:45 kernel: flags: 0x2ffff0000000000() Feb 28 19:27:45 kernel: raw: 02ffff0000000000 0000000000000000 ffffffff00000301 0000000000000000 Feb 28 19:27:45 kernel: raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 Feb 28 19:27:45 kernel: page dumped because: nonzero _refcount Feb 28 19:27:45 kernel: Modules linked in: ccm fuse arc4 nct6775 hwmon_vid amdgpu nls_iso8859_1 nls_cp437 edac_mce_amd vfat fat kvm_amd ccp rng_core kvm mt76x0u mt76x0_common mt76x02_usb irqbypass mt76_usb mt76x02_lib mt76 crct10dif_pclmul crc32_pclmul chash mac80211 amd_iommu_v2 ghash_clmulni_intel gpu_sched i2c_algo_bit ttm wmi_bmof snd_hda_codec_realtek snd_hda_codec_generic drm_kms_helper snd_hda_codec_hdmi snd_hda_intel drm snd_hda_codec aesni_intel snd_hda_core snd_hwdep aes_x86_64 crypto_simd snd_pcm cfg80211 cryptd mousedev snd_timer glue_helper pcspkr r8169 input_leds realtek agpgart libphy rfkill snd syscopyarea sysfillrect sysimgblt fb_sys_fops soundcore sp5100_tco k10temp i2c_piix4 wmi evdev gpio_amdpt pinctrl_amd mac_hid pcc_cpufreq acpi_cpufreq sg ip_tables x_tables ext4(E) crc32c_generic(E) crc16(E) mbcache(E) jbd2(E) fscrypto(E) sd_mod(E) hid_generic(E) usbhid(E) hid(E) dm_mod(E) serio_raw(E) atkbd(E) libps2(E) crc32c_intel(E) ahci(E) libahci(E) libata(E) xhci_pci(E) xhci_hcd(E) Feb 28 19:27:45 kernel: scsi_mod(E) i8042(E) serio(E) bcache(E) crc64(E) Feb 28 19:27:45 kernel: CPU: 2 PID: 896 Comm: cinnamon Tainted: G B W E 4.20.12-arch1-1-custom #1 Feb 28 19:27:45 kernel: Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./B450M Pro4, BIOS P1.20 06/26/2018 Feb 28 19:27:45 kernel: Call Trace: Feb 28 19:27:45 kernel: dump_stack+0x5c/0x80 Feb 28 19:27:45 kernel: bad_page.cold.29+0x7f/0xb2 Feb 28 19:27:45 kernel: __free_pages_ok+0x2c0/0x2d0 Feb 28 19:27:45 kernel: skb_release_data+0x96/0x180 Feb 28 19:27:45 kernel: __kfree_skb+0xe/0x20 Feb 28 19:27:45 kernel: tcp_recvmsg+0x894/0xc60 Feb 28 19:27:45 kernel: ? reuse_swap_page+0x120/0x340 Feb 28 19:27:45 kernel: ? ptep_set_access_flags+0x23/0x30 Feb 28 19:27:45 kernel: inet_recvmsg+0x5b/0x100 Feb 28 19:27:45 kernel: __sys_recvfrom+0xc3/0x180 Feb 28 19:27:45 kernel: ? handle_mm_fault+0x10a/0x250 Feb 28 19:27:45 kernel: ? syscall_trace_enter+0x1d3/0x2d0 Feb 28 19:27:45 kernel: ? __audit_syscall_exit+0x22a/0x290 Feb 28 19:27:45 kernel: __x64_sys_recvfrom+0x24/0x30 Feb 28 19:27:45 kernel: do_syscall_64+0x5b/0x170 Feb 28 19:27:45 kernel: entry_SYSCALL_64_after_hwframe+0x44/0xa9 Cc: stable@vger.kernel.org Reported-and-tested-by: Jan Viktorin Reviewed-by: Alexander Duyck Signed-off-by: Stanislaw Gruszka Fixes: 80187fd39dcb ('iommu/amd: Optimize map_sg and unmap_sg') Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) 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; } From 721f1e6c1fd137e7e2053d8e103b666faaa2d50c Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Mon, 18 Mar 2019 13:45:43 +0100 Subject: [PATCH 086/256] ALSA: hda - add Lenovo IdeaCentre B550 to the power_save_blacklist Another machine which does not like the power saving (noise): https://bugzilla.redhat.com/show_bug.cgi?id=1689623 Also, reorder the Lenovo C50 entry to keep the table sorted. Reported-by: hs.guimaraes@outlook.com Signed-off-by: Jaroslav Kysela Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e5c49003e75f..4f502c92061f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -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 */ From b4748e7ab731e436cf5db4786358ada5dd2db6dd Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sun, 17 Mar 2019 23:21:24 +0000 Subject: [PATCH 087/256] ALSA: opl3: fix mismatch between snd_opl3_drum_switch definition and declaration The function snd_opl3_drum_switch declaration in the header file has the order of the two arguments on_off and vel swapped when compared to the definition arguments of vel and on_off. Fix this by swapping them around to match the definition. This error predates the git history, so no idea when this error was introduced. Signed-off-by: Colin Ian King Signed-off-by: Takashi Iwai --- sound/drivers/opl3/opl3_voice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) From 4622a2d43101ea2e3d54a2af090f25a5886c648b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 11 Mar 2019 08:30:27 +0000 Subject: [PATCH 088/256] powerpc/6xx: fix setup and use of SPRN_SPRG_PGDIR for hash32 Not only the 603 but all 6xx need SPRN_SPRG_PGDIR to be initialised at startup. This patch move it from __setup_cpu_603() to start_here() and __secondary_start(), close to the initialisation of SPRN_THREAD. Previously, virt addr of PGDIR was retrieved from thread struct. Now that it is the phys addr which is stored in SPRN_SPRG_PGDIR, hash_page() shall not convert it to phys anymore. This patch removes the conversion. Fixes: 93c4a162b014 ("powerpc/6xx: Store PGDIR physical address in a SPRG") Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/cpu_setup_6xx.S | 3 --- arch/powerpc/kernel/head_32.S | 6 ++++++ arch/powerpc/mm/hash_low_32.S | 8 ++++---- 3 files changed, 10 insertions(+), 7 deletions(-) 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/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 */ - addi r5,r5,swapper_pg_dir@l /* kernel page table */ + lis r5, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ + 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 */ From 6ce59025f1182125e75c8d121daf44056b65dd1f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Mar 2019 08:08:43 -0600 Subject: [PATCH 089/256] paride/pf: cleanup queues when detection fails The driver allocates queues for all the units it potentially supports. But if we fail to detect any drives, then we fail loading the module without cleaning up those queues. This is now evident with the switch to blk-mq, though the bug has been there forever as far as I can tell. Also fix cleanup through regular module exit. Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Jens Axboe --- drivers/block/paride/pf.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) 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) - continue; - del_gendisk(pf->disk); + if (pf->present) + 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); } } From 81b74ac68c28fddb3589ad5d4d5e587baf4bb781 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Mar 2019 08:10:32 -0600 Subject: [PATCH 090/256] paride/pcd: cleanup queues when detection fails The driver allocates queues for all the units it potentially supports. But if we fail to detect any drives, then we fail loading the module without cleaning up those queues. This is now evident with the switch to blk-mq, though the bug has been there forever as far as I can tell. Also fix cleanup through regular module exit. Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Jens Axboe --- drivers/block/paride/pcd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) 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; } From aa36e3616532f82a920b5ebf4e059fbafae63d88 Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Sat, 19 Jan 2019 17:15:23 +0100 Subject: [PATCH 091/256] thermal/intel_powerclamp: fix __percpu declaration of worker_data This variable is declared as: static struct powerclamp_worker_data * __percpu worker_data; In other words, a percpu pointer to struct ... But this variable not used like so but as a pointer to a percpu struct powerclamp_worker_data. So fix the declaration as: static struct powerclamp_worker_data __percpu *worker_data; This also quiets Sparse's warnings from __verify_pcpu_ptr(), like: 494:49: warning: incorrect type in initializer (different address spaces) 494:49: expected void const [noderef] *__vpp_verify 494:49: got struct powerclamp_worker_data * Signed-off-by: Luc Van Oostenryck Reviewed-by: Petr Mladek Signed-off-by: Zhang Rui --- drivers/thermal/intel/intel_powerclamp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index 7571f7c2e7c9..b12ecd436e23 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 From 3b5236cc5d086dd3ddd01113ee9255421aab9fab Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 22 Jan 2019 16:47:41 +0100 Subject: [PATCH 092/256] thermal: samsung: Fix incorrect check after code merge Merge commit 19785cf93b6c ("Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal") broke the code introduced by commit ffe6e16f14fa ("thermal: exynos: Reduce severity of too early temperature read"). Restore the original code from the mentioned commit to finally fix the warning message during boot: thermal thermal_zone0: failed to read out thermal zone (-22) Reported-by: Marian Mihailescu Signed-off-by: Marek Szyprowski Fixes: 19785cf93b6c ("Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal") Reviewed-by: Krzysztof Kozlowski Signed-off-by: Zhang Rui --- drivers/thermal/samsung/exynos_tmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) /* From 35122495a8c6683e863acf7b05a7036b2be64c7a Mon Sep 17 00:00:00 2001 From: Phil Elwell Date: Tue, 29 Jan 2019 09:55:57 +0000 Subject: [PATCH 093/256] thermal: bcm2835: Fix crash in bcm2835_thermal_debugfs "cat /sys/kernel/debug/bcm2835_thermal/regset" causes a NULL pointer dereference in bcm2835_thermal_debugfs. The driver makes use of the implementation details of the thermal framework to retrieve a pointer to its private data from a struct thermal_zone_device, and gets it wrong - leading to the crash. Instead, store its private data as the drvdata and retrieve the thermal_zone_device pointer from it. Fixes: bcb7dd9ef206 ("thermal: bcm2835: add thermal driver for bcm2835 SoC") Signed-off-by: Phil Elwell Signed-off-by: Zhang Rui --- drivers/thermal/broadcom/bcm2835_thermal.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) 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 = tz->devdata; + struct bcm2835_thermal_data *data = platform_get_drvdata(pdev); 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 = tz->devdata; + struct bcm2835_thermal_data *data = platform_get_drvdata(pdev); + struct thermal_zone_device *tz = data->tz; debugfs_remove_recursive(data->debugfsdir); thermal_zone_of_sensor_unregister(&pdev->dev, tz); From e0fda7377d30685feaef4d93d9fdfde91c5d7d9a Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Mon, 18 Feb 2019 14:22:30 +0800 Subject: [PATCH 094/256] thermal: cpu_cooling: Remove unused cur_freq variable The 'cur_freq' local variable became unused after commit 84fe2cab4859 ("cpu_cooling: Drop static-power related stuff"), let's remove it. Cc: Amit Daniel Kachhap Cc: Viresh Kumar Cc: Javi Merino Cc: Zhang Rui Cc: Eduardo Valentin Cc: Daniel Lezcano Signed-off-by: Shaokun Zhang Acked-by: Viresh Kumar Signed-off-by: Zhang Rui --- drivers/thermal/cpu_cooling.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) 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; From 16fc8eca1975358111dbd7ce65e4ce42d1a848fb Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 10 Oct 2018 01:30:06 -0700 Subject: [PATCH 095/256] thermal/int340x_thermal: Add additional UUIDs Add more supported DPTF policies than the driver currently exposes. Signed-off-by: Matthew Garrett Cc: Nisha Aram Signed-off-by: Zhang Rui --- .../intel/int340x_thermal/int3400_thermal.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 61ca7ce3624e..e0f39cacbc18 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 { From 396ee4d0cd52c13b3f6421b8d324d65da5e7e409 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 10 Oct 2018 01:30:07 -0700 Subject: [PATCH 096/256] thermal/int340x_thermal: fix mode setting int3400 only pushes the UUID into the firmware when the mode is flipped to "enable". The current code only exposes the mode flag if the firmware supports the PASSIVE_1 UUID, which not all machines do. Remove the restriction. Signed-off-by: Matthew Garrett Signed-off-by: Zhang Rui --- drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index e0f39cacbc18..5f3ed24e26ec 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -313,10 +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.set_mode = int3400_thermal_set_mode; - } + int3400_thermal_ops.get_mode = int3400_thermal_get_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); From 684b73245cd4d2608f4f2214f6bff02ba6ceca5f Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Fri, 15 Mar 2019 11:05:10 +0800 Subject: [PATCH 097/256] blk-mq: use blk_mq_sched_mark_restart_hctx to set RESTART Let blk_mq_mark_tag_wait() use the blk_mq_sched_mark_restart_hctx() to set BLK_MQ_S_SCHED_RESTART. Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index a9c181603cbd..ea01c23b58a3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1093,8 +1093,7 @@ 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)) - set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + blk_mq_sched_mark_restart_hctx(hctx); /* * It's possible that a tag was freed in the window between the From f7c8a4120eedf24c36090b7542b179ff7a649219 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Mon, 18 Mar 2019 20:23:17 +0800 Subject: [PATCH 098/256] loop: access lo_backing_file only when the loop device is Lo_bound Commit 758a58d0bc67 ("loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()") separates "lo->lo_backing_file = NULL" and "lo->lo_state = Lo_unbound" into different critical regions protected by loop_ctl_mutex. However, there is below race that the NULL lo->lo_backing_file would be accessed when the backend of a loop is another loop device, e.g., loop0's backend is a file, while loop1's backend is loop0. loop0's backend is file loop1's backend is loop0 __loop_clr_fd() mutex_lock(&loop_ctl_mutex); lo->lo_backing_file = NULL; --> set to NULL mutex_unlock(&loop_ctl_mutex); loop_set_fd() mutex_lock_killable(&loop_ctl_mutex); loop_validate_file() f = l->lo_backing_file; --> NULL access if loop0 is not Lo_unbound mutex_lock(&loop_ctl_mutex); lo->lo_state = Lo_unbound; mutex_unlock(&loop_ctl_mutex); lo->lo_backing_file should be accessed only when the loop device is Lo_bound. In fact, the problem has been introduced already in commit 7ccd0791d985 ("loop: Push loop_ctl_mutex down into loop_clr_fd()") after which loop_validate_file() could see devices in Lo_rundown state with which it did not count. It was harmless at that point but still. Fixes: 7ccd0791d985 ("loop: Push loop_ctl_mutex down into loop_clr_fd()") Reported-by: syzbot+9bdc1adc1c55e7fe765b@syzkaller.appspotmail.com Signed-off-by: Dongli Zhang Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- drivers/block/loop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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; From fb4d83f293e072ad96848959d20664e2a9f2235b Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Wed, 9 Jan 2019 13:57:24 +0800 Subject: [PATCH 099/256] thermal: mtk: Allocate enough space for mtk_thermal. The mtk_thermal struct contains a 'struct mtk_thermal_bank banks[];', but the allocation only allocates sizeof(struct mtk_thermal) bytes, which cause out of bound access with the ->banks[] member. Change it to a fixed size array instead. Signed-off-by: Pi-Hsun Shih Reviewed-by: Daniel Lezcano Signed-off-by: Zhang Rui --- drivers/thermal/mtk_thermal.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) 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 */ From e925b5be5751f6a7286bbd9a4cbbc4ac90cc5fa6 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Mon, 18 Mar 2019 22:26:33 +0800 Subject: [PATCH 100/256] thermal/intel_powerclamp: fix truncated kthread name kthread name only allows 15 characters (TASK_COMMON_LEN is 16). Thus rename the kthreads created by intel_powerclamp driver from "kidle_inject/ + decimal cpuid" to "kidle_inj/ + decimal cpuid" to avoid truncated kthead name for cpu 100 and later. Signed-off-by: Zhang Rui --- drivers/thermal/intel/intel_powerclamp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index 7571f7c2e7c9..9434f4eb421a 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -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; From d3ca4651d05c0ff7259d087d8c949bcf3e14fb46 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 11 Mar 2019 15:04:18 +0100 Subject: [PATCH 101/256] udf: Fix crash on IO error during truncate When truncate(2) hits IO error when reading indirect extent block the code just bugs with: kernel BUG at linux-4.15.0/fs/udf/truncate.c:249! ... Fix the problem by bailing out cleanly in case of IO error. CC: stable@vger.kernel.org Reported-by: jean-luc malet Signed-off-by: Jan Kara --- fs/udf/truncate.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index b647f0bd150c..94220ba85628 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -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; if (elen) indirect_ext_len = (elen + sb->s_blocksize - 1) >> From 2b42be5eb24564227b15e66f54f088e5a26549c7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 11 Mar 2019 15:27:02 +0100 Subject: [PATCH 102/256] udf: Propagate errors from udf_truncate_extents() Make udf_truncate_extents() properly propagate errors to its callers and let udf_setsize() handle the error properly as well. This lets userspace know in case there's some error when truncating blocks. Signed-off-by: Jan Kara --- fs/udf/inode.c | 4 +++- fs/udf/truncate.c | 7 ++++--- fs/udf/udfdecl.h | 2 +- 3 files changed, 8 insertions(+), 5 deletions(-) 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 94220ba85628..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); @@ -262,7 +262,7 @@ void udf_truncate_extents(struct inode *inode) udf_get_lb_pblock(sb, &eloc, 0)); /* Error reading indirect block? */ if (!epos.bh) - return; + return -EIO; if (elen) indirect_ext_len = (elen + sb->s_blocksize - 1) >> @@ -286,4 +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 *, From 6a1afffb08ce5f9fb9ccc20f7ab24846c0142984 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Sun, 17 Mar 2019 14:46:53 +0100 Subject: [PATCH 103/256] selinux: fix NULL dereference in policydb_destroy() The conversion to kvmalloc() forgot to account for the possibility that p->type_attr_map_array might be null in policydb_destroy(). Fix this by destroying its contents only if it is not NULL. Also make sure ebitmap_init() is called on all entries before policydb_destroy() can be called. Right now this is a no-op, because both kvcalloc() and ebitmap_init() just zero out the whole struct, but let's rather not rely on a specific implementation. Reported-by: syzbot+a57b2aff60832666fc28@syzkaller.appspotmail.com Fixes: acdf52d97f82 ("selinux: convert to kvmalloc") Signed-off-by: Ondrej Mosnacek Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- security/selinux/ss/policydb.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) 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++) - ebitmap_destroy(&p->type_attr_map_array[i]); - kvfree(p->type_attr_map_array); + if (p->type_attr_map_array) { + for (i = 0; i < p->p_types.nprim; i++) + 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) From fd6fab2cb78d3b6023c26ec53e0aa6f0b477d2f7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 14 Mar 2019 16:30:06 -0600 Subject: [PATCH 104/256] io_uring: retry bulk slab allocs as single allocs I've seen cases where bulk alloc fails, since the bulk alloc API is all-or-nothing - either we get the number we ask for, or it returns 0 as number of entries. If we fail a batch bulk alloc, retry a "normal" kmem_cache_alloc() and just use that instead of failing with -EAGAIN. While in there, ensure we use GFP_KERNEL. That was an oversight in the original code, when we switched away from GFP_ATOMIC. Signed-off-by: Jens Axboe --- fs/io_uring.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 12bb238aed6b..4c6a5e60ddbe 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -399,13 +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) { @@ -413,10 +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, - state->reqs); - if (unlikely(ret <= 0)) - goto out; + ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs); + + /* + * 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]; From bf33a7699e992b12d4c7d39dc3f0b61f6b26c5c2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 14 Mar 2019 15:22:18 -0600 Subject: [PATCH 105/256] io_uring: mark me as the maintainer And io_uring as maintained in general. Signed-off-by: Jens Axboe --- MAINTAINERS | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 17b59b66474b..a90137af48c2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8091,6 +8091,16 @@ F: include/linux/iommu.h F: include/linux/of_iommu.h F: include/linux/iova.h +IO_URING +M: Jens Axboe +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 S: Maintained From 875f1d0769cdcfe1596ff0ca609b453359e42ec9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 27 Feb 2019 13:05:25 -0700 Subject: [PATCH 106/256] iov_iter: add ITER_BVEC_FLAG_NO_REF flag For ITER_BVEC, if we're holding on to kernel pages, the caller doesn't need to grab a reference to the bvec pages, and drop that same reference on IO completion. This is essentially safe for any ITER_BVEC, but some use cases end up reusing pages and uncondtionally dropping a page reference on completion. And example of that is sendfile(2), that ends up being a splice_in + splice_out on the pipe pages. Add a flag that tells us it's fine to not grab a page reference to the bvec pages, since that caller knows not to drop a reference when it's done with the pages. Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 +++ include/linux/uio.h | 24 +++++++++++++++++++----- 2 files changed, 22 insertions(+), 5 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 4c6a5e60ddbe..c592a0933b0d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -855,6 +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; } diff --git a/include/linux/uio.h b/include/linux/uio.h index ecf584f6b82d..4e926641fa80 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -23,14 +23,23 @@ struct kvec { }; enum iter_type { - ITER_IOVEC = 0, - ITER_KVEC = 2, - ITER_BVEC = 4, - ITER_PIPE = 8, - ITER_DISCARD = 16, + /* set if ITER_BVEC doesn't hold a bv_page ref */ + ITER_BVEC_FLAG_NO_REF = 2, + + /* iter types */ + 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. * From 399254aaf4892113c806816f7e64cf40c804d46d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 27 Feb 2019 13:13:23 -0700 Subject: [PATCH 107/256] block: add BIO_NO_PAGE_REF flag If bio_iov_iter_get_pages() is called on an iov_iter that is flagged with NO_REF, then we don't need to add a page reference for the pages that we add. Add BIO_NO_PAGE_REF to track this in the bio, so IO completion knows not to drop a reference to these pages. Signed-off-by: Jens Axboe --- block/bio.c | 43 ++++++++++++++++++++++----------------- fs/block_dev.c | 12 ++++++----- fs/iomap.c | 12 ++++++----- include/linux/blk_types.h | 1 + 4 files changed, 39 insertions(+), 29 deletions(-) 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; - int i; + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { + 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 - * page. This isn't strictly needed for the common case, but some call paths - * end up releasing pages from eg a pipe and we can't easily control these. - * See comment in __bio_iov_bvec_add_pages(). + * pages. If we're adding kernel pages, and the caller told us it's safe to + * do so, we just have to add the pages to the bio directly. We don't grab an + * extra reference to those pages (the user should already have that), and we + * 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/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; - int i; - struct bvec_iter_all iter_all; + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + int i; - bio_for_each_segment_all(bvec, bio, i, iter_all) - put_page(bvec->bv_page); + bio_for_each_segment_all(bvec, bio, i, iter_all) + put_page(bvec->bv_page); + } bio_put(bio); } } 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; - int i; - struct bvec_iter_all iter_all; + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + int i; - bio_for_each_segment_all(bvec, bio, i, iter_all) - put_page(bvec->bv_page); + bio_for_each_segment_all(bvec, bio, i, iter_all) + put_page(bvec->bv_page); + } bio_put(bio); } } 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 */ From 6f8f89ce1e18de1e391c9c1c14e7738881d1c00c Mon Sep 17 00:00:00 2001 From: Nick Crews Date: Mon, 11 Mar 2019 09:58:38 -0600 Subject: [PATCH 108/256] platform/chrome: Fix locking pattern in wilco_ec_mailbox() Before, ec->data_buffer could be written to from multiple contexts at the same time. Since the ec is shared data, it needs to be inside the mutex as well. Fixes: 7b3d4f44abf0 ("platform/chrome: Add new driver for Wilco EC") Signed-off-by: Nick Crews Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- drivers/platform/chrome/wilco_ec/mailbox.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From 16d80c54ad42c573a897ae7bcf5a9816be54e6fe Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 15 Mar 2019 14:50:04 +0100 Subject: [PATCH 109/256] rbd: set io_min, io_opt and discard_granularity to alloc_size Now that we have alloc_size that controls our discard behavior, it doesn't make sense to have these set to object (set) size. alloc_size defaults to 64k, but because discard_granularity is likely 4M, only ranges that are equal to or bigger than 4M can be considered during fstrim. A smaller io_min is also more likely to be met, resulting in fewer deferred writes on bluestore OSDs. Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- drivers/block/rbd.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4ba967d65cf9..3b2c9289dccb 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; } @@ -4203,12 +4203,12 @@ 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_opt(q, objset_bytes); + blk_queue_io_min(q, rbd_dev->opts->alloc_size); + 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); } From 165aa2bfb42904b1bec4bf2fa257c8c603c14a06 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 28 Jan 2019 15:24:42 +0100 Subject: [PATCH 110/256] scsi: iscsi: flush running unbind operations when removing a session In some cases, the iscsi_remove_session() function is called while an unbind_work operation is still running. This may cause a situation where sysfs objects are removed in an incorrect order, triggering a kernel warning. [ 605.249442] ------------[ cut here ]------------ [ 605.259180] sysfs group 'power' not found for kobject 'target2:0:0' [ 605.321371] WARNING: CPU: 1 PID: 26794 at fs/sysfs/group.c:235 sysfs_remove_group+0x76/0x80 [ 605.341266] Modules linked in: dm_service_time target_core_user target_core_pscsi target_core_file target_core_iblock iscsi_target_mod target_core_mod nls_utf8 isofs ppdev bochs_drm nfit ttm libnvdimm drm_kms_helper syscopyarea sysfillrect sysimgblt joydev pcspkr fb_sys_fops drm i2c_piix4 sg parport_pc parport xfs libcrc32c dm_multipath sr_mod sd_mod cdrom ata_generic 8021q garp mrp ata_piix stp crct10dif_pclmul crc32_pclmul llc libata crc32c_intel virtio_net net_failover ghash_clmulni_intel serio_raw failover sunrpc dm_mirror dm_region_hash dm_log dm_mod be2iscsi bnx2i cnic uio cxgb4i cxgb4 libcxgbi libcxgb qla4xxx iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi [ 605.627479] CPU: 1 PID: 26794 Comm: kworker/u32:2 Not tainted 4.18.0-60.el8.x86_64 #1 [ 605.721401] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20180724_192412-buildhw-07.phx2.fedoraproject.org-1.fc29 04/01/2014 [ 605.823651] Workqueue: scsi_wq_2 __iscsi_unbind_session [scsi_transport_iscsi] [ 605.830940] RIP: 0010:sysfs_remove_group+0x76/0x80 [ 605.922907] Code: 48 89 df 5b 5d 41 5c e9 38 c4 ff ff 48 89 df e8 e0 bf ff ff eb cb 49 8b 14 24 48 8b 75 00 48 c7 c7 38 73 cb a7 e8 24 77 d7 ff <0f> 0b 5b 5d 41 5c c3 0f 1f 00 0f 1f 44 00 00 41 56 41 55 41 54 55 [ 606.122304] RSP: 0018:ffffbadcc8d1bda8 EFLAGS: 00010286 [ 606.218492] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 606.326381] RDX: ffff98bdfe85eb40 RSI: ffff98bdfe856818 RDI: ffff98bdfe856818 [ 606.514498] RBP: ffffffffa7ab73e0 R08: 0000000000000268 R09: 0000000000000007 [ 606.529469] R10: 0000000000000000 R11: ffffffffa860d9ad R12: ffff98bdf978e838 [ 606.630535] R13: ffff98bdc2cd4010 R14: ffff98bdc2cd3ff0 R15: ffff98bdc2cd4000 [ 606.824707] FS: 0000000000000000(0000) GS:ffff98bdfe840000(0000) knlGS:0000000000000000 [ 607.018333] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 607.117844] CR2: 00007f84b78ac024 CR3: 000000002c00a003 CR4: 00000000003606e0 [ 607.117844] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 607.420926] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 607.524236] Call Trace: [ 607.530591] device_del+0x56/0x350 [ 607.624393] ? ata_tlink_match+0x30/0x30 [libata] [ 607.727805] ? attribute_container_device_trigger+0xb4/0xf0 [ 607.829911] scsi_target_reap_ref_release+0x39/0x50 [ 607.928572] scsi_remove_target+0x1a2/0x1d0 [ 608.017350] __iscsi_unbind_session+0xb3/0x160 [scsi_transport_iscsi] [ 608.117435] process_one_work+0x1a7/0x360 [ 608.132917] worker_thread+0x30/0x390 [ 608.222900] ? pwq_unbound_release_workfn+0xd0/0xd0 [ 608.323989] kthread+0x112/0x130 [ 608.418318] ? kthread_bind+0x30/0x30 [ 608.513821] ret_from_fork+0x35/0x40 [ 608.613909] ---[ end trace 0b98c310c8a6138c ]--- Signed-off-by: Maurizio Lombardi Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 2 ++ 1 file changed, 2 insertions(+) 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 */ From 6e0473633af059a559ce7b4cbaa51e389c94085e Mon Sep 17 00:00:00 2001 From: Thomas Preston Date: Wed, 6 Mar 2019 20:06:18 +0000 Subject: [PATCH 111/256] drm/i915/bios: assume eDP is present on port A when there is no VBT We rely on VBT DDI port info for eDP detection on GEN9 platforms and above. This breaks GEN9 platforms which don't have VBT because port A eDP now defaults to false. Fix this by defaulting to true when VBT is missing. Fixes: a98d9c1d7e9b ("drm/i915/ddi: Rely on VBT DDI port info for eDP detection") Signed-off-by: Thomas Preston Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20190306200618.17405-1-thomas.preston@codethink.co.uk (cherry picked from commit 2131bc0ced6088648e47f126566c3da58b07e4ef) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_bios.c | 1 + 1 file changed, 1 insertion(+) 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); } } From 65f26e978d7c55c3c3d04296058d95cf7b6e3f14 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 15 Mar 2019 16:39:33 +0000 Subject: [PATCH 112/256] drm/i915: Fix off-by-one in reporting hanging process ffs() is 1-indexed, but we want to use it as an index into an array, so use __ffs() instead. Fixes: eb8d0f5af4ec ("drm/i915: Remove GPU reset dependence on struct_mutex") Signed-off-by: Chris Wilson Cc: Mika Kuoppala Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20190315163933.19352-1-chris@chris-wilson.co.uk (cherry picked from commit 9073e5b26743b8b675cc44a9c0c8f8c3d584e1c0) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_gpu_error.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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]", From 000c4f90e3f0194eef218ff2c6a8fd8ca1de4313 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 14 Mar 2019 07:58:29 +0000 Subject: [PATCH 113/256] drm/i915: Sanity check mmap length against object size We assumed that vm_mmap() would reject an attempt to mmap past the end of the filp (our object), but we were wrong. Applications that tried to use the mmap beyond the end of the object would be greeted by a SIGBUS. After this patch, those applications will be told about the error on creating the mmap, rather than at a random moment on later access. Reported-by: Antonio Argenziano Testcase: igt/gem_mmap/bad-size Signed-off-by: Chris Wilson Cc: Antonio Argenziano Cc: Joonas Lahtinen Cc: Tvrtko Ursulin Cc: stable@vger.kernel.org Reviewed-by: Tvrtko Ursulin Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20190314075829.16838-1-chris@chris-wilson.co.uk (cherry picked from commit 794a11cb67201ad1bb61af510bb8460280feb3f3) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_gem.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) 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); - return -ENXIO; + addr = -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); - return -EINTR; + addr = -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; } From 744c67ffeb06f2d2493f4049ba0bd19698ce0adf Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Tue, 19 Mar 2019 09:28:43 +0800 Subject: [PATCH 114/256] ALSA: hda - Don't trigger jackpoll_work in azx_resume The commit 3baffc4a84d7 (ALSA: hda/intel: Refactoring PM code) changed the behaviour of azx_resume(), it triggers the jackpoll_work after applying this commit. This change introduced a new issue, all codecs are runtime active after S3, and will not call runtime_suspend() automatically. The root cause is the jackpoll_work calls snd_hda_power_up/down_pm, and it calls up_pm before snd_hdac_enter_pm is called, while calls the down_pm in the middle of enter_pm and leave_pm is called. This makes the dev->power.usage_count unbalanced after S3. To fix it, let azx_resume() don't trigger jackpoll_work as before it did. Fixes: 3baffc4a84d7 ("ALSA: hda/intel: Refactoring PM code") Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4f502c92061f..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) & From b5a236c175b0d984552a5f7c9d35141024c2b261 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Tue, 19 Mar 2019 09:28:44 +0800 Subject: [PATCH 115/256] ALSA: hda - Enforces runtime_resume after S3 and S4 for each codec Recently we found the audio jack detection stop working after suspend on many machines with Realtek codec. Sometimes the audio selection dialogue didn't show up after users plugged headhphone/headset into the headset jack, sometimes after uses plugged headphone/headset, then click the sound icon on the upper-right corner of gnome-desktop, it also showed the speaker rather than the headphone. The root cause is that before suspend, the codec already call the runtime_suspend since this codec is not used by any apps, then in resume, it will not call runtime_resume for this codec. But for some realtek codec (so far, alc236, alc255 and alc891) with the specific BIOS, if it doesn't run runtime_resume after suspend, all codec functions including jack detection stop working anymore. This problem existed for a long time, but it was not exposed, that is because when problem happens, if users play sound or open sound-setting to check audio device, this will trigger calling to runtime_resume (via snd_hda_power_up), then the codec starts working again before users notice this problem. Since we don't know how many codec and BIOS combinations have this problem, to fix it, let the driver call runtime_resume for all codecs in pm_resume, maybe for some codecs, this is not needed, but it is harmless. After a codec is runtime resumed, if it is not used by any apps, it will be runtime suspended soon and furthermore we don't run suspend frequently, this change will not add much power consumption. Fixes: cc72da7d4d06 ("ALSA: hda - Use standard runtime PM for codec power-save control") Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_codec.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) 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 */ From b2d22b6bb33aac10c415e4ba13c8eade201c6f09 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Mar 2019 12:42:37 +0100 Subject: [PATCH 116/256] fanotify: Allow copying of file handle to userspace When file handle is embedded inside fanotify_event and usercopy checks are enabled, we get a warning like: Bad or missing usercopy whitelist? Kernel memory exposure attempt detected from SLAB object 'fanotify_event' (offset 40, size 8)! WARNING: CPU: 1 PID: 7649 at mm/usercopy.c:78 usercopy_warn+0xeb/0x110 mm/usercopy.c:78 Annotate handling in fanotify_event properly to mark copying it to userspace is fine. Reported-by: syzbot+2c49971e251e36216d1f@syzkaller.appspotmail.com Fixes: a8b13aa20afb ("fanotify: enable FAN_REPORT_FID init flag") Signed-off-by: Kees Cook Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) 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 */ From a23314e9d88d89d49e69db08f60b7caa470f04e1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Mar 2019 09:32:02 +0100 Subject: [PATCH 117/256] sched/cpufreq: Fix 32-bit math overflow Vincent Wang reported that get_next_freq() has a mult overflow bug on 32-bit platforms in the IOWAIT boost case, since in that case {util,max} are in freq units instead of capacity units. Solve this by moving the IOWAIT boost to capacity units. And since this means @max is constant; simplify the code. Reported-by: Vincent Wang Tested-by: Vincent Wang Signed-off-by: Peter Zijlstra (Intel) Acked-by: Rafael J. Wysocki Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Chunyan Zhang Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J. Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190305083202.GU32494@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/cpufreq_schedutil.c | 59 ++++++++++++++------------------ 1 file changed, 25 insertions(+), 34 deletions(-) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 033ec7c45f13..1ccf77f6d346 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->sg_policy->policy->min : 0; + sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->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; - if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max) - sg_cpu->iowait_boost = sg_cpu->iowait_boost_max; + sg_cpu->iowait_boost = + min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE); 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, - unsigned long *util, unsigned long *max) +static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, + 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; - /* - * 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 { + if (!sg_cpu->iowait_boost_pending) { /* - * Otherwise: reduce the boost value and disable it when we - * reach the minimum. + * No boost pending; reduce the boost value. */ 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 - * utilization is smaller then the current IO boost level. + * @util is already in capacity scale; convert iowait_boost + * into the same scale so we can compare. */ - boost_util = sg_cpu->iowait_boost; - boost_max = sg_cpu->iowait_boost_max; - if (*util * boost_max < *max * boost_util) { - *util = boost_util; - *max = boost_max; - } + boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT; + return max(boost, util); } #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) { From 4c47acd824aaaa8fc6dc519fb4e08d1522105b7a Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 6 Mar 2019 20:11:42 +0300 Subject: [PATCH 118/256] sched/core: Fix buffer overflow in cgroup2 property cpu.max Add limit into sscanf format string for on-stack buffer. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Johannes Weiner Cc: Li Zefan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Fixes: 0d5936344f30 ("sched: Implement interface for cgroup unified hierarchy") Link: https://lkml.kernel.org/r/155189230232.2620.13120481613524200065.stgit@buzz Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6b2c055564b5..b7a4afdc33cb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6943,7 +6943,7 @@ 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; From e25a7a944f1936b5134b7ee06bc432fc701e4aa3 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 11 Feb 2019 17:59:44 +0000 Subject: [PATCH 119/256] sched/fair: Comment some nohz_balancer_kick() kick conditions We now have a comment explaining the first sched_domain based NOHZ kick, so might as well comment them all. While at it, unwrap a line that fits under 80 characters. Co-authored-by: Peter Zijlstra Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dietmar.Eggemann@arm.com Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: morten.rasmussen@arm.com Cc: vincent.guittot@linaro.org Link: https://lkml.kernel.org/r/20190211175946.4961-2-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8213ff6e365d..e6f7d39d4d45 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9612,8 +9612,12 @@ static void nohz_balancer_kick(struct rq *rq) 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; } @@ -9621,6 +9625,11 @@ 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; From a0fe2cf086aef213d1b4bca1b1291a3dee8357c9 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 11 Feb 2019 17:59:45 +0000 Subject: [PATCH 120/256] sched/fair: Tune down misfit NOHZ kicks In this commit: 3b1baa6496e6 ("sched/fair: Add 'group_misfit_task' load-balance type") we set rq->misfit_task_load whenever the current running task has a utilization greater than 80% of rq->cpu_capacity. A non-zero value in this field enables misfit load balancing. However, if the task being looked at is already running on a CPU of highest capacity, there's nothing more we can do for it. We can currently spot this in update_sd_pick_busiest(), which prevents us from selecting a sched_group of group_type == group_misfit_task as the busiest group, but we don't do any of that in nohz_balancer_kick(). This means that we could repeatedly kick NOHZ CPUs when there's no improvements in terms of load balance to be done. Introduce a check_misfit_status() helper that returns true iff there is a CPU in the system that could give more CPU capacity to a rq's misfit task - IOW, there exists a CPU of higher capacity_orig or the rq's CPU is severely pressured by rt/IRQ. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dietmar.Eggemann@arm.com Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: morten.rasmussen@arm.com Cc: vincent.guittot@linaro.org Link: https://lkml.kernel.org/r/20190211175946.4961-3-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e6f7d39d4d45..f0d2f8a352bf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8058,6 +8058,18 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) (rq->cpu_capacity_orig * 100)); } +/* + * 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. @@ -9585,7 +9597,7 @@ 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; } @@ -9623,6 +9635,18 @@ 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; + } + } + sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); if (sd) { /* From b9a7b8831600afc51c9ba52c05f12db2266f01c7 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 11 Feb 2019 17:59:46 +0000 Subject: [PATCH 121/256] sched/fair: Skip LLC NOHZ logic for asymmetric systems The LLC NOHZ condition will become true as soon as >=2 CPUs in a single LLC domain are busy. On big.LITTLE systems, this translates to two or more CPUs of a "cluster" (big or LITTLE) being busy. Issuing a NOHZ kick in these conditions isn't desired for asymmetric systems, as if the busy CPUs can provide enough compute capacity to the running tasks, then we can leave the NOHZ CPUs in peace. Skip the LLC NOHZ condition for asymmetric systems, and rely on nr_running & capacity checks to trigger NOHZ kicks when the system actually needs them. Suggested-by: Morten Rasmussen Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dietmar.Eggemann@arm.com Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: vincent.guittot@linaro.org Link: https://lkml.kernel.org/r/20190211175946.4961-4-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 69 +++++++++++++++++++++++++-------------------- 1 file changed, 39 insertions(+), 30 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f0d2f8a352bf..51003e1c794d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9603,24 +9603,6 @@ static void nohz_balancer_kick(struct rq *rq) } 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) { @@ -9635,18 +9617,6 @@ 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; - } - } - sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); if (sd) { /* @@ -9661,6 +9631,45 @@ 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: From a3151724437f54076cc10bc02b1c4f0003ae36cd Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 18 Mar 2019 22:24:03 +0100 Subject: [PATCH 122/256] x86/mm: Don't leak kernel addresses Since commit: ad67b74d2469d9b8 ("printk: hash addresses printed with %p") at boot "____ptrval____" is printed instead of actual addresses: found SMP MP-table at [mem 0x000f5cc0-0x000f5ccf] mapped at [(____ptrval____)] Instead of changing the print to "%px", and leaking a kernel addresses, just remove the print completely, like in: 071929dbdd865f77 ("arm64: Stop printing the virtual memory layout"). Signed-off-by: Matteo Croce Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/kernel/mpparse.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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", - base, base + sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n", + base, base + sizeof(*mpf) - 1); memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) From a872fc8bf0304fd56347e94468f07d7e82c679ea Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 13 Feb 2019 00:43:22 +0900 Subject: [PATCH 123/256] arm64: kprobes: Move extable address check into arch_prepare_kprobe() Move extable address check into arch_prepare_kprobe() from arch_within_kprobe_blacklist(). The blacklist is exposed via debugfs as a list of symbols. The extable entries are smaller, so must be filtered out by arch_prepare_kprobe(). Acked-by: Will Deacon Reviewed-by: James Morse Signed-off-by: Masami Hiramatsu Signed-off-by: Catalin Marinas --- arch/arm64/kernel/probes/kprobes.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 7fb6f3aa5ceb..16bc3b2e9351 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -102,6 +102,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (in_exception_text(probe_addr)) return -EINVAL; + + if (search_exception_tables(probe_addr)) + return -EINVAL; + if (probe_addr >= (unsigned long) __start_rodata && probe_addr <= (unsigned long) __end_rodata) return -EINVAL; @@ -485,8 +489,7 @@ bool arch_within_kprobe_blacklist(unsigned long addr) (addr >= (unsigned long)__idmap_text_start && addr < (unsigned long)__idmap_text_end) || (addr >= (unsigned long)__hyp_text_start && - addr < (unsigned long)__hyp_text_end) || - !!search_exception_tables(addr)) + addr < (unsigned long)__hyp_text_end)) return true; if (!is_kernel_in_hyp_mode()) { From b5586163de1ce90317cd4037f69b14105be9f656 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 13 Feb 2019 00:43:51 +0900 Subject: [PATCH 124/256] arm64: kprobes: Remove unneeded RODATA check Remove unneeded RODATA check from arch_prepare_kprobe(). Since check_kprobe_address_safe() already ensured that the probe address is in kernel text, we don't need to check whether the address in RODATA or not. That must be always false. Acked-by: Will Deacon Signed-off-by: Masami Hiramatsu Signed-off-by: Catalin Marinas --- arch/arm64/kernel/probes/kprobes.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 16bc3b2e9351..b168873147f5 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; @@ -106,10 +104,6 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) 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 */ switch (arm_kprobe_decode_insn(p->addr, &p->ainsn)) { case INSN_REJECTED: /* insn not supported */ From 6e08af0f10dcde01f0bdcc64cf91fea9d25e77cc Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 13 Feb 2019 00:44:19 +0900 Subject: [PATCH 125/256] arm64: kprobes: Move exception_text check in blacklist Move exception/irqentry text address check in blacklist, since those are symbol based rejection. If we prohibit probing on the symbols in exception_text, those should be blacklisted. Acked-by: Will Deacon Signed-off-by: Masami Hiramatsu Signed-off-by: Catalin Marinas --- arch/arm64/kernel/probes/kprobes.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index b168873147f5..d6697930d075 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -98,9 +98,6 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) /* copy instruction */ p->opcode = le32_to_cpu(*p->addr); - if (in_exception_text(probe_addr)) - return -EINVAL; - if (search_exception_tables(probe_addr)) return -EINVAL; @@ -483,7 +480,8 @@ bool arch_within_kprobe_blacklist(unsigned long addr) (addr >= (unsigned long)__idmap_text_start && addr < (unsigned long)__idmap_text_end) || (addr >= (unsigned long)__hyp_text_start && - addr < (unsigned long)__hyp_text_end)) + addr < (unsigned long)__hyp_text_end) || + in_exception_text(addr)) return true; if (!is_kernel_in_hyp_mode()) { From 6a019a92aa580cd5abdaae578a2a297c9af80174 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 13 Feb 2019 00:44:48 +0900 Subject: [PATCH 126/256] arm64: kprobes: Use arch_populate_kprobe_blacklist() Use arch_populate_kprobe_blacklist() instead of arch_within_kprobe_blacklist() so that we can see the full blacklisted symbols under the debugfs. Acked-by: Will Deacon Signed-off-by: Masami Hiramatsu [catalin.marinas@arm.com: Add arch_populate_kprobe_blacklist() comment] Signed-off-by: Catalin Marinas --- arch/arm64/kernel/probes/kprobes.c | 47 ++++++++++++++++++------------ 1 file changed, 29 insertions(+), 18 deletions(-) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d6697930d075..7a679caf4585 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -471,26 +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 && - addr < (unsigned long)__kprobes_text_end) || - (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end) || - (addr >= (unsigned long)__idmap_text_start && - addr < (unsigned long)__idmap_text_end) || - (addr >= (unsigned long)__hyp_text_start && - addr < (unsigned long)__hyp_text_end) || - in_exception_text(addr)) - return true; + int ret; - if (!is_kernel_in_hyp_mode()) { - if ((addr >= (unsigned long)__hyp_idmap_text_start && - addr < (unsigned long)__hyp_idmap_text_end)) - return true; - } - - return false; + ret = kprobe_add_area_blacklist((unsigned long)__entry_text_start, + (unsigned long)__entry_text_end); + if (ret) + return ret; + ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, + (unsigned long)__irqentry_text_end); + if (ret) + return ret; + ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start, + (unsigned long)__exception_text_end); + if (ret) + return ret; + ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start, + (unsigned long)__idmap_text_end); + if (ret) + 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) From 3dbcea54b3ff706c58f8e8d4470f5e5d3d24a6a0 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 15 Mar 2019 12:22:36 +0000 Subject: [PATCH 127/256] arm64: apply workaround on A64FX v1r0 Fujitsu erratum 010001 applies to A64FX v0r0 and v1r0, and we try to handle either by masking MIDR with MIDR_FUJITSU_ERRATUM_010001_MASK before comparing it to MIDR_FUJITSU_ERRATUM_010001. Unfortunately, MIDR_FUJITSU_ERRATUM_010001 is constructed incorrectly using MIDR_VARIANT(), which is intended to extract the variant field from MIDR_EL1, rather than generate the field in-place. This results in MIDR_FUJITSU_ERRATUM_010001 being all-ones, and we only match A64FX v0r0. This patch uses MIDR_CPU_VAR_REV() to generate an in-place mask for the variant field, ensuring the we match both v0r0 and v1r0. Fixes: 3e32131abc311a5c ("arm64: Add workaround for Fujitsu A64FX erratum 010001") Reported-by: "Okamoto, Takayuki" Signed-off-by: Mark Rutland [catalin.marinas@arm.com: fixed the patch author] Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cputype.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 2afb1338b48a..f3b659587a36 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -129,7 +129,7 @@ /* 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__ From c82fd1e6bd55ecc001e610e5484e292a7d8a39fc Mon Sep 17 00:00:00 2001 From: William Cohen Date: Fri, 1 Mar 2019 15:00:41 -0500 Subject: [PATCH 128/256] arm64/stacktrace: Export save_stack_trace_regs() The ARM64 implements the save_stack_trace_regs function, but it is unusable for any diagnostic tooling compiled as a kernel module due the missing EXPORT_SYMBOL_GPL for the function. Export save_stack_trace_regs() to align with other architectures such as s390, openrisc, and powerpc. This is similar to the ARM64 export of save_stack_trace_tsk() added in git commit e27c7fa015d6. Signed-off-by: William Cohen Signed-off-by: Catalin Marinas --- arch/arm64/kernel/stacktrace.c | 1 + 1 file changed, 1 insertion(+) 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) From efd00c722ca855745fcc35a7e6675b5a782a3fc8 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Tue, 5 Mar 2019 21:40:57 +0800 Subject: [PATCH 129/256] arm64: Add MIDR encoding for HiSilicon Taishan CPUs Adding the MIDR encodings for HiSilicon Taishan v110 CPUs, which is used in Kunpeng ARM64 server SoCs. TSV110 is the abbreviation of Taishan v110. Signed-off-by: Hanjun Guo Reviewed-by: John Garry Reviewed-by: Zhangshaokun Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cputype.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index f3b659587a36..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) @@ -126,6 +129,7 @@ #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 From 0ecc471a2cb7d4d386089445a727f47b59dc9b6e Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Tue, 5 Mar 2019 21:40:58 +0800 Subject: [PATCH 130/256] arm64: kpti: Whitelist HiSilicon Taishan v110 CPUs HiSilicon Taishan v110 CPUs didn't implement CSV3 field of the ID_AA64PFR0_EL1 and are not susceptible to Meltdown, so whitelist the MIDR in kpti_safe_list[] table. Signed-off-by: Hanjun Guo Reviewed-by: John Garry Reviewed-by: Zhangshaokun Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 1 + 1 file changed, 1 insertion(+) 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"; From 6f40b2a5dac4b448fe1e8d94dc4238cd95cd5e34 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:49:53 -0700 Subject: [PATCH 131/256] perf list: Filter metrics too When a filter is specified on the command line, filter the metrics too. Before: % perf list foo List of pre-defined events (to be used in -e): Metric Groups: DSB: DSB_Coverage [Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)] ... more metrics ... After: % perf list foo List of pre-defined events (to be used in -e): Metric Groups: Signed-off-by: Andi Kleen Acked-by: Jiri Olsa LPU-Reference: 20190314225002.30108-1-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-1y8oi2s8c4jhjtykgs5zvda1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-list.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); } } From 03724b2e9c45d931eff0f304f2d3363ade65ca89 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:49:55 -0700 Subject: [PATCH 132/256] perf record: Allow to limit number of reported perf.data files When doing long term recording and waiting for some event to snapshot on, we often only care about the last minute or so. The --switch-output command line option supports rotating the perf.data file when the size exceeds a threshold. But the disk would still be filled with unnecessary old files. Add a new option to only keep a number of rotated files, so that the disk space usage can be limited. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa LPU-Reference: 20190314225002.30108-3-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-y5u2lik0ragt4vlktz6qc9ks@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 ++++ tools/perf/builtin-record.c | 30 +++++++++++++++++++++++- tools/perf/util/data.c | 11 ++++----- tools/perf/util/data.h | 2 +- 4 files changed, 39 insertions(+), 8 deletions(-) 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/builtin-record.c b/tools/perf/builtin-record.c index a468d882e74f..02d7c40b2d10 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 { @@ -892,6 +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"; @@ -912,7 +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; @@ -922,6 +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); @@ -1973,6 +1992,8 @@ static struct option __record_options[] = { &record.switch_output.set, "signal,size,time", "Switch output when receive SIGUSR2 or cross size,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 @@ -2059,6 +2080,13 @@ 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/util/data.c b/tools/perf/util/data.c index c6b67efea11a..6a64f713710d 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -361,9 +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)) @@ -371,15 +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)) - pr_warning("Failed to rename %s to %s\n", data->path, new_filepath); + if (rename(data->path, *new_filepath)) + pr_warning("Failed to rename %s to %s\n", data->path, *new_filepath); if (!at_exit) { close(data->file.fd); @@ -396,7 +396,6 @@ int perf_data__switch(struct perf_data *data, } ret = data->file.fd; out: - free(new_filepath); return ret; } diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 6aef8746469f..259868a39019 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -70,7 +70,7 @@ 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); From 9496c015ed39ddfce971d63a1442e6d258504a7d Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Tue, 19 Mar 2019 23:05:18 +0800 Subject: [PATCH 133/256] blk-mq: remove unused 'nr_expired' from blk_mq_hw_ctx There is no usage of 'nr_expired'. The 'nr_expired' was introduced by commit 1d9bd5161ba3 ("blk-mq: replace timeout synchronization with a RCU and generation based scheme"). Its usage was removed since commit 12f5b9314545 ("blk-mq: Remove generation seqeunce"). Signed-off-by: Dongli Zhang Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b0c814bcc7e3..35359697318b 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; From 0e3edd94448001a33ed7f8af2179cd4a280348a2 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 19 Mar 2019 23:20:42 +0800 Subject: [PATCH 134/256] drivers: base: swnode: Make two functions static Fix sparse warning: drivers/base/swnode.c:475:22: warning: symbol 'software_node_get_parent' was not declared. Should it be static? drivers/base/swnode.c:484:22: warning: symbol 'software_node_get_next_child' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Rafael J. Wysocki --- drivers/base/swnode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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) { From 2a95496634a017c19641f26f00907af75b962f01 Mon Sep 17 00:00:00 2001 From: David Arcari Date: Tue, 12 Feb 2019 09:34:39 -0500 Subject: [PATCH 135/256] tools/power turbostat: return the exit status of a command turbostat failed to return a non-zero exit status even though the supplied command (turbostat ) failed. Currently when turbostat forks a command it returns zero instead of the actual exit status of the command. Modify the code to return the exit status. Signed-off-by: David Arcari Acked-by: Len Brown Signed-off-by: Rafael J. Wysocki --- tools/power/x86/turbostat/turbostat.c | 3 +++ 1 file changed, 3 insertions(+) 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() From 57aeef7f7a6848024b92c32bf23e8c85a8ac896d Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 19 Mar 2019 09:32:36 -0700 Subject: [PATCH 136/256] platform/chrome: cros_ec_debugfs: cancel/schedule logging work only if supported The following traceback was reported on ASUS C201, which does not support console logging. ------------[ cut here ]------------ WARNING: CPU: 2 PID: 361 at kernel/workqueue.c:3030 __flush_work+0x38/0x154 Modules linked in: snd_soc_hdmi_codec cros_ec_debugfs cros_ec_sysfs uvcvideo dw_hdmi_cec dw_hdmi_i2s_audio videobuf2_vmalloc cfg80211 gpio_charger rk_crypto rfkill videobuf2_memops videobuf2_v4l2 des_generic videobuf2_common ofpart m25p80 spi_nor tpm_i2c_infineon sbs_battery mtd tpm joydev cros_ec_dev coreboot_table evdev mousedev ip_tables x_tables [last unloaded: brcmutil] CPU: 2 PID: 361 Comm: systemd-sleep Not tainted 5.1.0-rc1-1-ARCH+ #1 Hardware name: Rockchip (Device Tree) [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x7c/0x9c) [] (dump_stack) from [] (__warn+0xd0/0xec) [] (__warn) from [] (warn_slowpath_null+0x38/0x44) [] (warn_slowpath_null) from [] (__flush_work+0x38/0x154) [] (__flush_work) from [] (__cancel_work_timer+0x114/0x1a4) [] (__cancel_work_timer) from [] (cros_ec_debugfs_suspend+0x14/0x1c [cros_ec_debugfs]) [] (cros_ec_debugfs_suspend [cros_ec_debugfs]) from [] (dpm_run_callback+0x64/0xcc) [] (dpm_run_callback) from [] (__device_suspend+0x174/0x3a8) [] (__device_suspend) from [] (dpm_suspend+0x174/0x1e0) [] (dpm_suspend) from [] (suspend_devices_and_enter+0x6c/0x50c) [] (suspend_devices_and_enter) from [] (pm_suspend+0x20c/0x274) [] (pm_suspend) from [] (state_store+0x54/0x88) [] (state_store) from [] (kernfs_fop_write+0x114/0x180) [] (kernfs_fop_write) from [] (__vfs_write+0x1c/0x154) [] (__vfs_write) from [] (vfs_write+0xb8/0x198) [] (vfs_write) from [] (ksys_write+0x3c/0x74) [] (ksys_write) from [] (ret_fast_syscall+0x0/0x4c) Exception stack(0xe9365fa8 to 0xe9365ff0) 5fa0: 00000004 beef8b28 00000004 beef8b28 00000004 00000000 5fc0: 00000004 beef8b28 02319170 00000004 beef8b28 00000004 b6f3d900 beef8b74 5fe0: 0000006c beef8a98 b6c0adac b6c66534 ---[ end trace f4ee5df14e8ea0ec ]--- If console logging is not supported, the work structure is never initialized, resulting in the traceback. Calling cancel/schedule functions conditionally fixes the problem. While at it, also fix error handling in the probe function. Reported-by: Urja Rannikko Cc: Urja Rannikko Fixes: 6fce0a2cf5a05 ("mfd / platform: cros_ec: Move debugfs attributes to its own driver") Signed-off-by: Guenter Roeck Signed-off-by: Benson Leung --- drivers/platform/chrome/cros_ec_debugfs.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) 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; } From db983f6eef57a9d78af79bc32389b7e60eb3c47d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 18 Mar 2019 09:29:26 -0700 Subject: [PATCH 137/256] scsi: core: Also call destroy_rcu_head() for passthrough requests cmd->rcu is initialized by scsi_initialize_rq(). For passthrough requests, blk_get_request() calls scsi_initialize_rq(). For filesystem requests, scsi_init_command() calls scsi_initialize_rq(). Make sure that destroy_rcu_head() is called for passthrough requests. Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Ewan D. Milne Cc: Johannes Thumshirn Reported-by: Ewan D. Milne Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 20189675677a..f0db2dd0be75 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -585,9 +585,16 @@ 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. From 17605afaae825b0291f80c62a7f6565879edaa8a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Mar 2019 16:27:58 -0700 Subject: [PATCH 138/256] scsi: core: Avoid that a kernel warning appears during system resume Since scsi_device_quiesce() skips SCSI devices that have another state than RUNNING, OFFLINE or TRANSPORT_OFFLINE, scsi_device_resume() should not complain about SCSI devices that have been skipped. Hence this patch. This patch avoids that the following warning appears during resume: WARNING: CPU: 3 PID: 1039 at blk_clear_pm_only+0x2a/0x30 CPU: 3 PID: 1039 Comm: kworker/u8:49 Not tainted 5.0.0+ #1 Hardware name: LENOVO 4180F42/4180F42, BIOS 83ET75WW (1.45 ) 05/10/2013 Workqueue: events_unbound async_run_entry_fn RIP: 0010:blk_clear_pm_only+0x2a/0x30 Call Trace: ? scsi_device_resume+0x28/0x50 ? scsi_dev_type_resume+0x2b/0x80 ? async_run_entry_fn+0x2c/0xd0 ? process_one_work+0x1f0/0x3f0 ? worker_thread+0x28/0x3c0 ? process_one_work+0x3f0/0x3f0 ? kthread+0x10c/0x130 ? __kthread_create_on_node+0x150/0x150 ? ret_from_fork+0x1f/0x30 Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Ming Lei Cc: Johannes Thumshirn Cc: Oleksandr Natalenko Cc: Martin Steigerwald Cc: Reported-by: Jisheng Zhang Tested-by: Jisheng Zhang Fixes: 3a0a529971ec ("block, scsi: Make SCSI quiesce and resume work reliably") # v4.15 Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index f0db2dd0be75..601b9f1de267 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2548,8 +2548,10 @@ void scsi_device_resume(struct scsi_device *sdev) * device deleted during suspend) */ mutex_lock(&sdev->state_mutex); - sdev->quiesced_by = NULL; - blk_clear_pm_only(sdev->request_queue); + if (sdev->quiesced_by) { + 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); From 4705f10e82c63924bd84a9b31d15839ec9ba3d06 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 15 Mar 2019 15:04:18 -0700 Subject: [PATCH 139/256] scsi: qla2xxx: Fix FC-AL connection target discovery Commit 7f147f9bfd44 ("scsi: qla2xxx: Fix N2N target discovery with Local loop") fixed N2N target discovery for local loop. However, same code is used for FC-AL discovery as well. Added check to make sure we are bypassing area and domain check only in N2N topology for target discovery. Fixes: 7f147f9bfd44 ("scsi: qla2xxx: Fix N2N target discovery with Local loop") Cc: stable@vger.kernel.org # 5.0+ Signed-off-by: Quinn Tran Signed-off-by: Himanshu Madhani Reviewed-by: Ewan D. Milne Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 7 +++++++ 1 file changed, 7 insertions(+) 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; From ac444b4f0ace05d7c4c99f6b1e5b0cae0852f025 Mon Sep 17 00:00:00 2001 From: Himanshu Madhani Date: Fri, 15 Mar 2019 15:04:19 -0700 Subject: [PATCH 140/256] scsi: qla2xxx: Fix NULL pointer crash due to stale CPUID This patch fixes crash due to NULL pointer derefrence because CPU pointer is not set and used by driver. Instead, driver is passes CPU as tag via ha->isp_ops->{lun_reset|target_reset} [ 30.160780] qla2xxx [0000:a0:00.1]-8038:9: Cable is unplugged... [ 69.984045] qla2xxx [0000:a0:00.0]-8009:8: DEVICE RESET ISSUED nexus=8:0:0 cmd=00000000b0d62f46. [ 69.992849] BUG: unable to handle kernel NULL pointer dereference at 0000000000000040 [ 70.000680] PGD 0 P4D 0 [ 70.003232] Oops: 0000 [#1] SMP PTI [ 70.006727] CPU: 2 PID: 6714 Comm: sg_reset Kdump: loaded Not tainted 4.18.0-67.el8.x86_64 #1 [ 70.015258] Hardware name: NEC Express5800/T110j [N8100-2758Y]/MX32-PH0-NJ, BIOS F11 02/13/2019 [ 70.024016] RIP: 0010:blk_mq_rq_cpu+0x9/0x10 [ 70.028315] Code: 01 58 01 00 00 48 83 c0 28 48 3d 80 02 00 00 75 ab c3 0f 1f 44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 47 08 <8b> 40 40 c3 0f 1f 00 0f 1f 44 00 00 48 83 ec 10 48 c7 c6 20 6e 7c [ 70.047087] RSP: 0018:ffff99a481487d58 EFLAGS: 00010246 [ 70.052322] RAX: 0000000000000000 RBX: ffffffffc041b08b RCX: 0000000000000000 [ 70.059466] RDX: 0000000000000000 RSI: ffff8d10b6b16898 RDI: ffff8d10b341e400 [ 70.066615] RBP: ffffffffc03a6bd0 R08: 0000000000000415 R09: 0000000000aaaaaa [ 70.073765] R10: 0000000000000001 R11: 0000000000000001 R12: ffff8d10b341e528 [ 70.080914] R13: ffff8d10aadefc00 R14: ffff8d0f64efa998 R15: ffff8d0f64efa000 [ 70.088083] FS: 00007f90a201e540(0000) GS:ffff8d10b6b00000(0000) knlGS:0000000000000000 [ 70.096188] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 70.101959] CR2: 0000000000000040 CR3: 0000000268886005 CR4: 00000000003606e0 [ 70.109127] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 70.116277] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 70.123425] Call Trace: [ 70.125896] __qla2xxx_eh_generic_reset+0xb1/0x220 [qla2xxx] [ 70.131572] scsi_ioctl_reset+0x1f5/0x2a0 [ 70.135600] scsi_ioctl+0x18e/0x397 [ 70.139099] ? sd_ioctl+0x7c/0x100 [sd_mod] [ 70.143287] blkdev_ioctl+0x32b/0x9f0 [ 70.146954] ? __check_object_size+0xa3/0x181 [ 70.151323] block_ioctl+0x39/0x40 [ 70.154735] do_vfs_ioctl+0xa4/0x630 [ 70.158322] ? syscall_trace_enter+0x1d3/0x2c0 [ 70.162769] ksys_ioctl+0x60/0x90 [ 70.166104] __x64_sys_ioctl+0x16/0x20 [ 70.169859] do_syscall_64+0x5b/0x1b0 [ 70.173532] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 70.178587] RIP: 0033:0x7f90a1b3445b [ 70.182183] Code: 0f 1e fa 48 8b 05 2d aa 2c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d fd a9 2c 00 f7 d8 64 89 01 48 [ 70.200956] RSP: 002b:00007fffdca88b68 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 70.208535] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f90a1b3445b [ 70.215684] RDX: 00007fffdca88b84 RSI: 0000000000002284 RDI: 0000000000000003 [ 70.222833] RBP: 00007fffdca88ca8 R08: 00007fffdca88b84 R09: 0000000000000000 [ 70.229981] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffdca88b84 [ 70.237131] R13: 0000000000000000 R14: 000055ab09b0bd28 R15: 0000000000000000 [ 70.244284] Modules linked in: nft_chain_route_ipv4 xt_CHECKSUM nft_chain_nat_ipv4 ipt_MASQUERADE nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack libcrc32c ipt_REJECT nf_reject_ipv4 nft_counter nft_compat tun bridge stp llc nf_tables nfnetli nk devlink sunrpc vfat fat intel_rapl intel_pmc_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm wmi_bmof iTCO_wdt iTCO_ vendor_support irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ipmi_ssif intel_cstate intel_uncore intel_rapl_perf ipmi_si jo ydev pcspkr ipmi_devintf sg wmi ipmi_msghandler video acpi_power_meter acpi_pad mei_me i2c_i801 mei ip_tables ext4 mbcache jbd2 sr_mod cd rom sd_mod qla2xxx ast i2c_algo_bit drm_kms_helper nvme_fc syscopyarea sysfillrect uas sysimgblt fb_sys_fops nvme_fabrics ttm [ 70.314805] usb_storage nvme_core crc32c_intel scsi_transport_fc ahci drm libahci tg3 libata megaraid_sas pinctrl_cannonlake pinctrl_ intel [ 70.327335] CR2: 0000000000000040 Fixes: 9cf2bab630765 ("block: kill request ->cpu member") Signed-off-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_os.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From 39bbd3310ec304a7b695240c6791893a88ec9729 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 13 Mar 2019 09:36:52 +0100 Subject: [PATCH 141/256] drm/amdgpu: revert "cleanup setting bulk_movable" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 8466cc61da89d33441e0d7a98de1ba98697cd465. It can trigger a reference counter bug in TTM. Need to investigate further, but for now revert the offending change. Signed-off-by: Christian König Reviewed-by: Michel Dänzer Tested-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 ++ 1 file changed, 2 insertions(+) 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; From 72464382fc2d3673eb51f21a57f2c0a320c1552f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 18 Mar 2019 11:09:54 +0100 Subject: [PATCH 142/256] drm/amdgpu: fix invalid use of change_bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We only need to clear the bit in a 32bit integer. This fixes a crah on ARM64 and PPC64LE caused by "drm/amdgpu: update the vm invalidation engine layout V2" Signed-off-by: Christian König Acked-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From c38dab7df7ee4fdecd51e390d4d33d5ef5cff49d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:49:56 -0700 Subject: [PATCH 143/256] perf record: Clarify help for --switch-output The help description for --switch-output looks like there are multiple comma separated fields. But it's actually a choice of different options. Make it clear and less confusing. Before: % perf record -h ... --switch-output[=] Switch output when receive SIGUSR2 or cross size,time threshold After: % perf record -h ... --switch-output[=] Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold Signed-off-by: Andi Kleen Acked-by: Jiri Olsa LPU-Reference: 20190314225002.30108-4-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-9yecyuha04nyg8toyd1b2pgi@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 02d7c40b2d10..e7144a1c1c82 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1989,8 +1989,8 @@ 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", - "Switch output when receive SIGUSR2 or cross size,time threshold", + &record.switch_output.set, "signal or size[BKMG] or time[smhd]", + "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"), From 702fb9b415e7c99bd671fc0d1da26574c125471a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:49:57 -0700 Subject: [PATCH 144/256] perf report: Show all sort keys in help output Show all the supported sort keys in the command line help output, so that it's not needed to refer to the manpage. Before: % perf report -h ... -s, --sort sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ... Please refer the man page for the complete list. After: % perf report -h ... -s, --sort sort by key(s): overhead overhead_sys overhead_us overhead_guest_sys overhead_guest_us overhead_children sample period pid comm dso symbol parent cpu ... Signed-off-by: Andi Kleen Acked-by: Jiri Olsa LPU-Reference: 20190314225002.30108-5-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-9r3uz2ch4izoi1uln3f889co@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 5 ++-- tools/perf/util/sort.c | 52 +++++++++++++++++++++++++++++++++++++ tools/perf/util/sort.h | 2 ++ 3 files changed, 56 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1921aaa9cece..4054eb1f98ac 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1083,10 +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, ..." - " Please refer the man page for the complete list."), + sort_help("sort by key(s):")), 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, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index bdd30cab51cb..5d2518e89fc4 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -13,6 +13,7 @@ #include "evsel.h" #include "evlist.h" #include "strlist.h" +#include "strbuf.h" #include #include "mem-events.h" #include "annotate.h" @@ -3107,3 +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 bb9442ab7a0c..ce376a73f964 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -296,6 +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); From a4e7e6efabc57e85e0737c2eaa391525c0ae36f3 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:49:59 -0700 Subject: [PATCH 145/256] perf report: Indicate JITed code better in report Print [TID] tid %d instead of the crypted /tmp/perf-%d.map default. % cat >loop.java public class loop { public static void main(String[] args) { for (;;); } } ^D % javac loop.java % perf record java loop ^C Before: % perf report --stdio ... 56.09% java perf-34724.map [.] 0x00007fd5bd021896 19.12% java perf-34724.map [.] 0x00007fd5bd021887 9.79% java perf-34724.map [.] 0x00007fd5bd021783 8.97% java perf-34724.map [.] 0x00007fd5bd02175b After: % perf report --stdio ... 56.09% java [JIT] tid 34724 [.] 0x00007fd5bd021896 19.12% java [JIT] tid 34724 [.] 0x00007fd5bd021887 9.79% java [JIT] tid 34724 [.] 0x00007fd5bd021783 8.97% java [JIT] tid 34724 [.] 0x00007fd5bd02175b Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo LPU-Reference: 20190314225002.30108-7-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-r17l6py9g0sezb7mi1f286gt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 42 ++++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 18 deletions(-) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index ba58ba603b69..ab8a455d2283 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1141,28 +1141,34 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) static void dso__set_basename(struct dso *dso) { - /* - * basename() may modify path buffer, so we must pass - * a copy. - */ - char *base, *lname = strdup(dso->long_name); + char *base, *lname; + int tid; - if (!lname) - return; + if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) { + if (asprintf(&base, "[JIT] tid %d", tid) < 0) + return; + } else { + /* + * basename() may modify path buffer, so we must pass + * a copy. + */ + lname = strdup(dso->long_name); + if (!lname) + return; - /* - * basename() may return a pointer to internal - * storage which is reused in subsequent calls - * so copy the result. - */ - base = strdup(basename(lname)); + /* + * basename() may return a pointer to internal + * storage which is reused in subsequent calls + * so copy the result. + */ + base = strdup(basename(lname)); - free(lname); + free(lname); - if (!base) - 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) From 90b10f47c0ee2a70bd036d9da5e810f522b54a8f Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:50:00 -0700 Subject: [PATCH 146/256] perf script: Support relative time When comparing time stamps in 'perf script' traces it can be annoying to work with the full perf time stamps. Add a --reltime option that displays time stamps relative to the trace start to make it easier to read the traces. Note: not currently supported for --time. Report an error in this case. Before: % perf script swapper 0 [000] 245402.891216: 1 cycles:ppp: ffffffffa0068814 native_write_msr+0x4 ([kernel.kallsyms]) swapper 0 [000] 245402.891223: 1 cycles:ppp: ffffffffa0068814 native_write_msr+0x4 ([kernel.kallsyms]) swapper 0 [000] 245402.891227: 5 cycles:ppp: ffffffffa0068814 native_write_msr+0x4 ([kernel.kallsyms]) swapper 0 [000] 245402.891231: 41 cycles:ppp: ffffffffa0068816 native_write_msr+0x6 ([kernel.kallsyms]) swapper 0 [000] 245402.891235: 355 cycles:ppp: ffffffffa000dd51 intel_bts_enable_local+0x21 ([kernel.kallsyms]) swapper 0 [000] 245402.891239: 3084 cycles:ppp: ffffffffa0a0150a end_repeat_nmi+0x48 ([kernel.kallsyms]) After: % perf script --reltime swapper 0 [000] 0.000000: 1 cycles:ppp: ffffffffa0068814 native_write_msr+0x4 ([kernel.kallsyms]) swapper 0 [000] 0.000006: 1 cycles:ppp: ffffffffa0068814 native_write_msr+0x4 ([kernel.kallsyms]) swapper 0 [000] 0.000010: 5 cycles:ppp: ffffffffa0068814 native_write_msr+0x4 ([kernel.kallsyms]) swapper 0 [000] 0.000014: 41 cycles:ppp: ffffffffa0068816 native_write_msr+0x6 ([kernel.kallsyms]) swapper 0 [000] 0.000018: 355 cycles:ppp: ffffffffa000dd51 intel_bts_enable_local+0x21 ([kernel.kallsyms]) swapper 0 [000] 0.000022: 3084 cycles:ppp: ffffffffa0a0150a end_repeat_nmi+0x48 ([kernel.kallsyms]) Committer notes: Do not use 'time' as the name of a variable, as this breaks the build on older glibcs: cc1: warnings being treated as errors builtin-script.c: In function 'perf_sample__fprintf_start': builtin-script.c:691: warning: declaration of 'time' shadows a global declaration /usr/include/time.h:187: warning: shadowed declaration is here Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa LPU-Reference: 20190314225002.30108-8-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-bpahyi6pr9r399mvihu65fvc@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 3 +++ tools/perf/builtin-script.c | 18 ++++++++++++++++-- 2 files changed, 19 insertions(+), 2 deletions(-) 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/builtin-script.c b/tools/perf/builtin-script.c index 2f93d60c5a17..61cfd8f70989 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -53,6 +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; @@ -686,7 +688,13 @@ 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; @@ -694,7 +702,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, 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); } } @@ -3413,6 +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, @@ -3487,6 +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; From 75998bb263bf48c1c85d78cd2d2f3a97d3747cab Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:50:01 -0700 Subject: [PATCH 147/256] perf stat: Fix --no-scale The -c option to enable multiplex scaling has been useless for quite some time because scaling is default. It's only useful as --no-scale to disable scaling. But the non scaling code path has bitrotted and doesn't print anything because perf output code relies on value run/ena information. Also even when we don't want to scale a value it's still useful to show its multiplex percentage. This patch: - Fixes help and documentation to show --no-scale instead of -c - Removes -c, only keeps the long option because -c doesn't support negatives. - Enables running/enabled even with --no-scale - And fixes some other problems in the no-scale output. Before: $ perf stat --no-scale -e cycles true Performance counter stats for 'true': cycles 0.000984154 seconds time elapsed After: $ ./perf stat --no-scale -e cycles true Performance counter stats for 'true': 706,070 cycles 0.001219821 seconds time elapsed Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo LPU-Reference: 20190314225002.30108-9-andi@firstfloor.org Link: https://lkml.kernel.org/n/tip-xggjvwcdaj2aqy8ib3i4b1g6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 5 ++--- tools/perf/builtin-stat.c | 3 ++- tools/perf/util/evsel.c | 3 +-- tools/perf/util/stat.c | 12 ++++-------- 4 files changed, 9 insertions(+), 14 deletions(-) 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:: ---scale:: - scale/normalize counter values +--no-scale:: + Don't scale/normalize counter values -d:: --detailed:: 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/util/evsel.c b/tools/perf/util/evsel.c index 3bbf73e979c0..53ec40cacd4b 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1344,8 +1344,7 @@ void perf_counts_values__scale(struct perf_counts_values *count, scaled = 1; count->val = (u64)((double) count->val * count->ena / count->run + 0.5); } - } else - count->ena = count->run = 0; + } if (pscaled) *pscaled = scaled; 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->run += count->run; - } + aggr->ena += count->ena; + 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 | - PERF_FORMAT_TOTAL_TIME_RUNNING; - } + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; /* * The event is part of non trivial group, let's enable From 42a5864cf0a9a7e4eb541b5f390749a69c288c80 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Mar 2019 15:50:02 -0700 Subject: [PATCH 148/256] perf stat: Improve scaling The multiplexing scaling in perf stat mysteriously adds 0.5 to the value. This dates back to the original perf tool. Other scaling code doesn't use that strange convention. Remove the extra 0.5. Before: $ perf stat -e 'cycles,cycles,cycles,cycles,cycles,cycles' grep -rq foo Performance counter stats for 'grep -rq foo': 6,403,580 cycles (81.62%) 6,404,341 cycles (81.64%) 6,402,983 cycles (81.62%) 6,399,941 cycles (81.63%) 6,399,451 cycles (81.62%) 6,436,105 cycles (91.87%) 0.005843799 seconds time elapsed 0.002905000 seconds user 0.002902000 seconds sys After: $ perf stat -e 'cycles,cycles,cycles,cycles,cycles,cycles' grep -rq foo Performance counter stats for 'grep -rq foo': 6,422,704 cycles (81.68%) 6,401,842 cycles (81.68%) 6,398,432 cycles (81.68%) 6,397,098 cycles (81.68%) 6,396,074 cycles (81.67%) 6,434,980 cycles (91.62%) 0.005884437 seconds time elapsed 0.003580000 seconds user 0.002356000 seconds sys Signed-off-by: Andi Kleen Acked-by: Jiri Olsa LPU-Reference: 20190314225002.30108-10-andi@firstfloor.org Tested-by: Arnaldo Carvalho de Melo Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 53ec40cacd4b..16f02b83b23f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1342,7 +1342,7 @@ 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); } } From c3b4d5c4afb0856e62a60db04c71205712b0d24f Mon Sep 17 00:00:00 2001 From: Mamatha Inamdar Date: Thu, 7 Feb 2019 15:09:28 +0530 Subject: [PATCH 149/256] perf vendor events: Remove P8 HW events which are not supported This patch is to remove following hardware events from JSON file which are not supported on POWER8. pm_co_disp_fail pm_co_tm_sc_footprint pm_iside_disp pm_iside_disp_fail pm_iside_disp_fail_other pm_iside_mru_touch pm_l2_castout_mod pm_l2_castout_shr pm_l2_dc_inv pm_l2_disp_all_l2miss pm_l2_grp_guess_correct pm_l2_grp_guess_wrong pm_l2_ic_inv pm_l2_inst pm_l2_inst_miss pm_l2_ld pm_l2_ld_disp pm_l2_ld_hit pm_l2_ld_miss pm_l2_loc_guess_correct pm_l2_loc_guess_wrong pm_l2_rcld_disp pm_l2_rcld_disp_fail_addr pm_l2_rcld_disp_fail_other pm_l2_rcst_disp pm_l2_rcst_disp_fail_addr pm_l2_rcst_disp_fail_other pm_l2_rc_st_done pm_l2_rty_ld pm_l2_sn_m_rd_done pm_l2_sn_m_wr_done pm_l2_sn_sx_i_done pm_l2_st_disp pm_l2_st_hit pm_l2_sys_guess_correct pm_l2_sys_guess_wrong pm_l2_sys_pump pm_l3_ci_hit pm_l3_ci_miss pm_l3_cinj pm_l3_co pm_l3_co_lco pm_l3_grp_guess_correct pm_l3_grp_guess_wrong_high pm_l3_grp_guess_wrong_low pm_l3_hit pm_l3_l2_co_hit pm_l3_l2_co_miss pm_l3_lat_ci_hit pm_l3_lat_ci_miss pm_l3_ld_hit pm_l3_ld_miss pm_l3_loc_guess_correct pm_l3_loc_guess_wrong pm_l3_miss pm_l3_p0_co_l31 pm_l3_p0_co_mem pm_l3_p0_co_rty pm_l3_p0_grp_pump pm_l3_p0_lco_data pm_l3_p0_lco_no_data pm_l3_p0_lco_rty pm_l3_p0_node_pump pm_l3_p0_pf_rty pm_l3_p0_sn_hit pm_l3_p0_sn_inv pm_l3_p0_sn_miss pm_l3_p0_sys_pump pm_l3_p1_co_l31 pm_l3_p1_co_mem pm_l3_p1_co_rty pm_l3_p1_grp_pump pm_l3_p1_lco_data pm_l3_p1_lco_no_data pm_l3_p1_lco_rty pm_l3_p1_node_pump pm_l3_p1_pf_rty pm_l3_p1_sn_hit pm_l3_p1_sn_inv pm_l3_p1_sn_miss pm_l3_p1_sys_pump pm_l3_pf_hit_l3 pm_l3_sys_guess_correct pm_l3_sys_guess_wrong pm_l3_trans_pf pm_l3_wi0_busy pm_l3_wi_usage pm_non_tm_rst_sc pm_rd_clearing_sc pm_rd_forming_sc pm_rd_hit_pf pm_snp_tm_hit_m pm_snp_tm_hit_t pm_st_caused_fail pm_tm_cam_overflow pm_tm_cap_overflow pm_tm_fav_caused_fail pm_tm_ld_caused_fail pm_tm_ld_conf pm_tm_rst_sc pm_tm_sc_co pm_tm_st_caused_fail pm_tm_st_conf Signed-off-by: Mamatha Inamdar Acked-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sukadev Bhattiprolu Fixes: 2a81fa3bb5ed ("perf vendor events: Add power8 PMU events") Link: http://lkml.kernel.org/r/154953186583.11022.14819560028300370163.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/powerpc/power8/other.json | 594 ------------------ 1 file changed, 594 deletions(-) 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 @@ -347,18 +347,6 @@ "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave RC livetime(mach0 used as sample point)", "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", @@ -1577,36 +1565,12 @@ "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a instruction side request", "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", @@ -1733,222 +1697,36 @@ "BriefDescription": "Instruction Demand sectors wriittent into IL1", "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", @@ -1961,36 +1739,12 @@ "BriefDescription": "TM marked store abort", "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", @@ -2009,120 +1763,18 @@ "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 ( lossy)", "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", @@ -2147,120 +1799,6 @@ "BriefDescription": "L3 LCO received retry port 0", "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", @@ -2273,12 +1811,6 @@ "BriefDescription": "lifetime, sample of PF machine 0 valid", "PublicDescription": "" }, - {, - "EventCode": "0x428084", - "EventName": "PM_L3_PF_HIT_L3", - "BriefDescription": "l3 pf hit in l3", - "PublicDescription": "" - }, {, "EventCode": "0x18080", "EventName": "PM_L3_PF_MISS_L3", @@ -2369,42 +1901,12 @@ "BriefDescription": "Data stream touchto L3", "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", @@ -3311,12 +2813,6 @@ "BriefDescription": "Dispatch time non favored tbegin", "PublicDescription": "" }, - {, - "EventCode": "0x328084", - "EventName": "PM_NON_TM_RST_SC", - "BriefDescription": "non tm snp rst tm sc", - "PublicDescription": "" - }, {, "EventCode": "0x2001a", "EventName": "PM_NTCG_ALL_FIN", @@ -3419,24 +2915,6 @@ "BriefDescription": "Continuous 16 cycle(2to1) window where this signals rotates thru sampling each L2 RC machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running", "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", @@ -3503,18 +2981,6 @@ "BriefDescription": "TLBIE snoop", "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", @@ -3533,12 +2999,6 @@ "BriefDescription": "STCX executed reported at sent to nest", "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", @@ -3623,18 +3083,6 @@ "BriefDescription": "Tm any tbegin", "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", @@ -3689,48 +3137,6 @@ "BriefDescription": "Transactional conflict from LSU, whatever gets reported to texas", "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", From af7a14a750b8eb3cdb26ec15344616ca170b06f2 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:41 +0800 Subject: [PATCH 150/256] perf tools: Add doc about how to build perf with Asan and UBSan AddressSanitizer (or ASan) and UndefinedBehaviorSanitizer (or UBSan) are very useful tools to detect program bugs: - AddressSanitizer (or ASan) is a GCC feature that detects memory corruption bugs such as buffer overflows and memory leaks. - UndefinedBehaviorSanitizer (or UBSan) is a fast undefined behavior detector supported by GCC. UBSan detects undefined behaviors of programs at runtime. This patch adds a document about how to use them on perf. Later patches will fix some of the issues disclosed by them. Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Link: http://lkml.kernel.org/r/20190316080556.3075-2-changbin.du@gmail.com [ Make some changes based on comments made by Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/Build.txt | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) 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.'. + +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. From 39df730b09774bd860e39ea208a48d15078236cb Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:42 +0800 Subject: [PATCH 151/256] perf list: Don't forget to drop the reference to the allocated thread_map Detected via gcc's ASan: Direct leak of 2048 byte(s) in 64 object(s) allocated from: 6 #0 0x7f606512e370 in __interceptor_realloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee370) 7 #1 0x556b0f1d7ddd in thread_map__realloc util/thread_map.c:43 8 #2 0x556b0f1d84c7 in thread_map__new_by_tid util/thread_map.c:85 9 #3 0x556b0f0e045e in is_event_supported util/parse-events.c:2250 10 #4 0x556b0f0e1aa1 in print_hwcache_events util/parse-events.c:2382 11 #5 0x556b0f0e3231 in print_events util/parse-events.c:2514 12 #6 0x556b0ee0a66e in cmd_list /home/changbin/work/linux/tools/perf/builtin-list.c:58 13 #7 0x556b0f01e0ae in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 14 #8 0x556b0f01e859 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 15 #9 0x556b0f01edc8 in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 16 #10 0x556b0f01f71f in main /home/changbin/work/linux/tools/perf/perf.c:520 17 #11 0x7f6062ccf09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 89896051f8da ("perf tools: Do not put a variable sized type not at the end of a struct") Link: http://lkml.kernel.org/r/20190316080556.3075-3-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4dcc01b2532c..2e9035c4c252 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; } From 11c1ea6f1a9bc97bf857fd12f72eacb6c69794e2 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:43 +0800 Subject: [PATCH 152/256] perf tools: Fix errors under optimization level '-Og' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Optimization level '-Og' offers a reasonable level of optimization while maintaining fast compilation and a good debugging experience. This patch tries to make it work. $ make DEBUG=1 EXTRA_CFLAGS='-Og' bench/epoll-ctl.c: In function ‘do_threads’: bench/epoll-ctl.c:274:9: error: ‘ret’ may be used uninitialized in this function [-Werror=maybe-uninitialized] return ret; ^~~ ... Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Link: http://lkml.kernel.org/r/20190316080556.3075-4-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.c | 2 +- tools/perf/bench/epoll-ctl.c | 2 +- tools/perf/bench/epoll-wait.c | 2 +- tools/perf/tests/backward-ring-buffer.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index f5eb60379c8d..4884557aa17f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -622,7 +622,7 @@ 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) 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/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); From 9b40dff7ba3caaf0d1919f98e136fa3400bd34aa Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:44 +0800 Subject: [PATCH 153/256] perf config: Fix an error in the config template documentation The option 'sort-order' should be 'sort_order'. Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 893c5c798be9 ("perf config: Show default report configuration in example and docs") Link: http://lkml.kernel.org/r/20190316080556.3075-5-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 95054a8176a2..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 From 54569ba4b06d5baedae4614bde33a25a191473ba Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:45 +0800 Subject: [PATCH 154/256] perf config: Fix a memory leak in collect_config() Detected with gcc's ASan: Direct leak of 66 byte(s) in 5 object(s) allocated from: #0 0x7ff3b1f32070 in __interceptor_strdup (/usr/lib/x86_64-linux-gnu/libasan.so.5+0x3b070) #1 0x560c8761034d in collect_config util/config.c:597 #2 0x560c8760d9cb in get_value util/config.c:169 #3 0x560c8760dfd7 in perf_parse_file util/config.c:285 #4 0x560c8760e0d2 in perf_config_from_file util/config.c:476 #5 0x560c876108fd in perf_config_set__init util/config.c:661 #6 0x560c87610c72 in perf_config_set__new util/config.c:709 #7 0x560c87610d2f in perf_config__init util/config.c:718 #8 0x560c87610e5d in perf_config util/config.c:730 #9 0x560c875ddea0 in main /home/changbin/work/linux/tools/perf/perf.c:442 #10 0x7ff3afb8609a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Cc: Taeung Song Fixes: 20105ca1240c ("perf config: Introduce perf_config_set class") Link: http://lkml.kernel.org/r/20190316080556.3075-6-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/config.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) 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, From 8bde8516893da5a5fdf06121f74d11b52ab92df5 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:46 +0800 Subject: [PATCH 155/256] perf build-id: Fix memory leak in print_sdt_events() Detected with gcc's ASan: Direct leak of 4356 byte(s) in 120 object(s) allocated from: #0 0x7ff1a2b5a070 in __interceptor_strdup (/usr/lib/x86_64-linux-gnu/libasan.so.5+0x3b070) #1 0x55719aef4814 in build_id_cache__origname util/build-id.c:215 #2 0x55719af649b6 in print_sdt_events util/parse-events.c:2339 #3 0x55719af66272 in print_events util/parse-events.c:2542 #4 0x55719ad1ecaa in cmd_list /home/changbin/work/linux/tools/perf/builtin-list.c:58 #5 0x55719aec745d in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #6 0x55719aec7d1a in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #7 0x55719aec8184 in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #8 0x55719aeca41a in main /home/changbin/work/linux/tools/perf/perf.c:520 #9 0x7ff1a07ae09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 40218daea1db ("perf list: Show SDT and pre-cached events") Link: http://lkml.kernel.org/r/20190316080556.3075-7-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 1 + tools/perf/util/parse-events.c | 1 + 2 files changed, 2 insertions(+) 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/parse-events.c b/tools/perf/util/parse-events.c index 2e9035c4c252..5ef4939408f2 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2342,6 +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) { From 0dba9e4be95b59e77060645ca8e37ca3231061f5 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:47 +0800 Subject: [PATCH 156/256] perf top: Delete the evlist before perf_session, fixing heap-use-after-free issue The evlist should be destroyed before the perf session. Detected with gcc's ASan: ================================================================= ==27350==ERROR: AddressSanitizer: heap-use-after-free on address 0x62b000002e38 at pc 0x5611da276999 bp 0x7ffce8f1d1a0 sp 0x7ffce8f1d190 WRITE of size 8 at 0x62b000002e38 thread T0 #0 0x5611da276998 in __list_del /home/work/linux/tools/include/linux/list.h:89 #1 0x5611da276d4a in __list_del_entry /home/work/linux/tools/include/linux/list.h:102 #2 0x5611da276e77 in list_del_init /home/work/linux/tools/include/linux/list.h:145 #3 0x5611da2781cd in thread__put util/thread.c:130 #4 0x5611da2cc0a8 in __thread__zput util/thread.h:68 #5 0x5611da2d2dcb in hist_entry__delete util/hist.c:1148 #6 0x5611da2cdf91 in hists__delete_entry util/hist.c:337 #7 0x5611da2ce19e in hists__delete_entries util/hist.c:365 #8 0x5611da2db2ab in hists__delete_all_entries util/hist.c:2639 #9 0x5611da2db325 in hists_evsel__exit util/hist.c:2651 #10 0x5611da1c5352 in perf_evsel__exit util/evsel.c:1304 #11 0x5611da1c5390 in perf_evsel__delete util/evsel.c:1309 #12 0x5611da1b35f0 in perf_evlist__purge util/evlist.c:124 #13 0x5611da1b38e2 in perf_evlist__delete util/evlist.c:148 #14 0x5611da069781 in cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1645 #15 0x5611da17d038 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #16 0x5611da17d577 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #17 0x5611da17d97b in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #18 0x5611da17e0e9 in main /home/changbin/work/linux/tools/perf/perf.c:520 #19 0x7fdcc970f09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) #20 0x5611d9ff35c9 in _start (/home/work/linux/tools/perf/perf+0x3e95c9) 0x62b000002e38 is located 11320 bytes inside of 27448-byte region [0x62b000000200,0x62b000006d38) freed by thread T0 here: #0 0x7fdccb04ab70 in free (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xedb70) #1 0x5611da260df4 in perf_session__delete util/session.c:201 #2 0x5611da063de5 in __cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1300 #3 0x5611da06973c in cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1642 #4 0x5611da17d038 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #5 0x5611da17d577 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #6 0x5611da17d97b in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #7 0x5611da17e0e9 in main /home/changbin/work/linux/tools/perf/perf.c:520 #8 0x7fdcc970f09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) previously allocated by thread T0 here: #0 0x7fdccb04b138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5611da26010c in zalloc util/util.h:23 #2 0x5611da260824 in perf_session__new util/session.c:118 #3 0x5611da0633a6 in __cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1192 #4 0x5611da06973c in cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1642 #5 0x5611da17d038 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #6 0x5611da17d577 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #7 0x5611da17d97b in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #8 0x5611da17e0e9 in main /home/changbin/work/linux/tools/perf/perf.c:520 #9 0x7fdcc970f09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) SUMMARY: AddressSanitizer: heap-use-after-free /home/work/linux/tools/include/linux/list.h:89 in __list_del Shadow bytes around the buggy address: 0x0c567fff8570: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff8580: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff8590: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff85a0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff85b0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd =>0x0c567fff85c0: fd fd fd fd fd fd fd[fd]fd fd fd fd fd fd fd fd 0x0c567fff85d0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff85e0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff85f0: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff8600: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd 0x0c567fff8610: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb ==27350==ABORTING Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Link: http://lkml.kernel.org/r/20190316080556.3075-8-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 42 ++++++++++++++++++---------------------- 1 file changed, 19 insertions(+), 23 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 231a90daa958..614f278235fa 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1189,23 +1189,19 @@ 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(); @@ -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) - goto out_err_cpu_topo; + if (ret < 0) { + 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 @@ -1639,10 +1628,17 @@ 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; + } + status = __cmd_top(&top); out_delete_evlist: perf_evlist__delete(top.evlist); + perf_session__delete(top.session); return status; } From 70c819e4bf1c5f492768b399d898d458ccdad2b6 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:48 +0800 Subject: [PATCH 157/256] perf top: Fix error handling in cmd_top() We should go to the cleanup path, to avoid leaks, detected using gcc's ASan. Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Link: http://lkml.kernel.org/r/20190316080556.3075-9-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 614f278235fa..2508a7a552fa 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1617,8 +1617,9 @@ 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) - return -1; + status = symbol__init(NULL); + if (status < 0) + goto out_delete_evlist; sort__setup_elide(stdout); From cb6186aeffda4d27e56066c79e9579e7831541d3 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:49 +0800 Subject: [PATCH 158/256] perf hist: Add missing map__put() in error case We need to map__put() before returning from failure of sample__resolve_callchain(). Detected with gcc's ASan. Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Krister Johansen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 9c68ae98c6f7 ("perf callchain: Reference count maps") Link: http://lkml.kernel.org/r/20190316080556.3075-10-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 1f230285d78a..7ace7a10054d 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1111,8 +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) From b49265e04410b97b31a5ee66ef6782c1b2d6cd2c Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:50 +0800 Subject: [PATCH 159/256] perf map: Remove map from 'names' tree in __maps__remove() There are two trees for each map inserted by maps__insert(), so remove it from the 'names' tree in __maps__remove(). Detected with gcc's ASan. Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Eric Saint-Etienne Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 1e6285699b30 ("perf symbols: Fix slowness due to -ffunction-section") Link: http://lkml.kernel.org/r/20190316080556.3075-11-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index fbeb0c6efaa6..64bea5eb8bf6 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -917,6 +917,9 @@ 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) From da3a53a7390a89391bd63bead0c2e9af4c5ef3d6 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:51 +0800 Subject: [PATCH 160/256] perf maps: Purge all maps from the 'names' tree Add function __maps__purge_names() to purge all maps from the names tree. We need to cleanup the names tree in maps__exit(). Detected with gcc's ASan. Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Eric Saint-Etienne Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 1e6285699b30 ("perf symbols: Fix slowness due to -ffunction-section") Link: http://lkml.kernel.org/r/20190316080556.3075-12-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 64bea5eb8bf6..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); } From 1e5b0cf8672e622257df024074e6e09bfbcb7750 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:52 +0800 Subject: [PATCH 161/256] perf top: Fix global-buffer-overflow issue The array str[] should have six elements. ================================================================= ==4322==ERROR: AddressSanitizer: global-buffer-overflow on address 0x56463844e300 at pc 0x564637e7ad0d bp 0x7f30c8c89d10 sp 0x7f30c8c89d00 READ of size 8 at 0x56463844e300 thread T9 #0 0x564637e7ad0c in __ordered_events__flush util/ordered-events.c:316 #1 0x564637e7b0e4 in ordered_events__flush util/ordered-events.c:338 #2 0x564637c6a57d in process_thread /home/changbin/work/linux/tools/perf/builtin-top.c:1073 #3 0x7f30d173a163 in start_thread (/lib/x86_64-linux-gnu/libpthread.so.0+0x8163) #4 0x7f30cfffbdee in __clone (/lib/x86_64-linux-gnu/libc.so.6+0x11adee) 0x56463844e300 is located 32 bytes to the left of global variable 'flags' defined in 'util/trace-event-parse.c:229:26' (0x56463844e320) of size 192 0x56463844e300 is located 0 bytes to the right of global variable 'str' defined in 'util/ordered-events.c:268:28' (0x56463844e2e0) of size 32 SUMMARY: AddressSanitizer: global-buffer-overflow util/ordered-events.c:316 in __ordered_events__flush Shadow bytes around the buggy address: 0x0ac947081c10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081c20: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081c30: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081c40: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081c50: 00 00 00 00 00 00 00 00 f9 f9 f9 f9 00 00 00 00 =>0x0ac947081c60:[f9]f9 f9 f9 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081c70: 00 00 00 00 00 00 00 00 00 00 00 00 f9 f9 f9 f9 0x0ac947081c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081c90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081ca0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0x0ac947081cb0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb Thread T9 created by T0 here: #0 0x7f30d179de5f in __interceptor_pthread_create (/usr/lib/x86_64-linux-gnu/libasan.so.5+0x4ae5f) #1 0x564637c6b954 in __cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1253 #2 0x564637c7173c in cmd_top /home/changbin/work/linux/tools/perf/builtin-top.c:1642 #3 0x564637d85038 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #4 0x564637d85577 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #5 0x564637d8597b in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #6 0x564637d860e9 in main /home/changbin/work/linux/tools/perf/perf.c:520 #7 0x7f30cff0509a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Cc: Jiri Olsa Fixes: 16c66bc167cc ("perf top: Add processing thread") Fixes: 68ca5d07de20 ("perf ordered_events: Add ordered_events__flush_time interface") Link: http://lkml.kernel.org/r/20190316080556.3075-13-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 2 ++ 1 file changed, 2 insertions(+) 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; From 42dfa451d825a2ad15793c476f73e7bbc0f9d312 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 18 Mar 2019 16:41:28 -0300 Subject: [PATCH 162/256] perf evsel: Free evsel->counts in perf_evsel__exit() Using gcc's ASan, Changbin reports: ================================================================= ==7494==ERROR: LeakSanitizer: detected memory leaks Direct leak of 48 byte(s) in 1 object(s) allocated from: #0 0x7f0333a89138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5625e5330a5e in zalloc util/util.h:23 #2 0x5625e5330a9b in perf_counts__new util/counts.c:10 #3 0x5625e5330ca0 in perf_evsel__alloc_counts util/counts.c:47 #4 0x5625e520d8e5 in __perf_evsel__read_on_cpu util/evsel.c:1505 #5 0x5625e517a985 in perf_evsel__read_on_cpu /home/work/linux/tools/perf/util/evsel.h:347 #6 0x5625e517ad1a in test__openat_syscall_event tests/openat-syscall.c:47 #7 0x5625e51528e6 in run_test tests/builtin-test.c:358 #8 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #9 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #10 0x5625e515572f in cmd_test tests/builtin-test.c:722 #11 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #12 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #13 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #14 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #15 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Indirect leak of 72 byte(s) in 1 object(s) allocated from: #0 0x7f0333a89138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5625e532560d in zalloc util/util.h:23 #2 0x5625e532566b in xyarray__new util/xyarray.c:10 #3 0x5625e5330aba in perf_counts__new util/counts.c:15 #4 0x5625e5330ca0 in perf_evsel__alloc_counts util/counts.c:47 #5 0x5625e520d8e5 in __perf_evsel__read_on_cpu util/evsel.c:1505 #6 0x5625e517a985 in perf_evsel__read_on_cpu /home/work/linux/tools/perf/util/evsel.h:347 #7 0x5625e517ad1a in test__openat_syscall_event tests/openat-syscall.c:47 #8 0x5625e51528e6 in run_test tests/builtin-test.c:358 #9 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #10 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #11 0x5625e515572f in cmd_test tests/builtin-test.c:722 #12 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #13 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #14 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #15 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #16 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) His patch took care of evsel->prev_raw_counts, but the above backtraces are about evsel->counts, so fix that instead. Reported-by: Changbin Du Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Link: https://lkml.kernel.org/n/tip-hd1x13g59f0nuhe4anxhsmfp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 16f02b83b23f..1a2023da5d9c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -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); From 93faa52e8371f0291ee1ff4994edae2b336b6233 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:54 +0800 Subject: [PATCH 163/256] perf tests: Fix a memory leak of cpu_map object in the openat_syscall_event_on_all_cpus test ================================================================= ==7497==ERROR: LeakSanitizer: detected memory leaks Direct leak of 40 byte(s) in 1 object(s) allocated from: #0 0x7f0333a88f30 in __interceptor_malloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xedf30) #1 0x5625e5326213 in cpu_map__trim_new util/cpumap.c:45 #2 0x5625e5326703 in cpu_map__read util/cpumap.c:103 #3 0x5625e53267ef in cpu_map__read_all_cpu_map util/cpumap.c:120 #4 0x5625e5326915 in cpu_map__new util/cpumap.c:135 #5 0x5625e517b355 in test__openat_syscall_event_on_all_cpus tests/openat-syscall-all-cpus.c:36 #6 0x5625e51528e6 in run_test tests/builtin-test.c:358 #7 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #8 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #9 0x5625e515572f in cmd_test tests/builtin-test.c:722 #10 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #11 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #12 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #13 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #14 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: f30a79b012e5 ("perf tools: Add reference counting for cpu_map object") Link: http://lkml.kernel.org/r/20190316080556.3075-15-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/openat-syscall-all-cpus.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) 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; From f97a8991d3b998e518f56794d879f645964de649 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:55 +0800 Subject: [PATCH 164/256] perf tests: Fix memory leak by expr__find_other() in test__expr() ================================================================= ==7506==ERROR: LeakSanitizer: detected memory leaks Direct leak of 13 byte(s) in 3 object(s) allocated from: #0 0x7f03339d6070 in __interceptor_strdup (/usr/lib/x86_64-linux-gnu/libasan.so.5+0x3b070) #1 0x5625e53aaef0 in expr__find_other util/expr.y:221 #2 0x5625e51bcd3f in test__expr tests/expr.c:52 #3 0x5625e51528e6 in run_test tests/builtin-test.c:358 #4 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #5 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #6 0x5625e515572f in cmd_test tests/builtin-test.c:722 #7 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #8 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #9 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #10 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #11 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Signed-off-by: Changbin Du Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 075167363f8b ("perf tools: Add a simple expression parser for JSON") Link: http://lkml.kernel.org/r/20190316080556.3075-16-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) 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; From d982b33133284fa7efa0e52ae06b88f9be3ea764 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Sat, 16 Mar 2019 16:05:56 +0800 Subject: [PATCH 165/256] perf tests: Fix a memory leak in test__perf_evsel__tp_sched_test() ================================================================= ==20875==ERROR: LeakSanitizer: detected memory leaks Direct leak of 1160 byte(s) in 1 object(s) allocated from: #0 0x7f1b6fc84138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x55bd50005599 in zalloc util/util.h:23 #2 0x55bd500068f5 in perf_evsel__newtp_idx util/evsel.c:327 #3 0x55bd4ff810fc in perf_evsel__newtp /home/work/linux/tools/perf/util/evsel.h:216 #4 0x55bd4ff81608 in test__perf_evsel__tp_sched_test tests/evsel-tp-sched.c:69 #5 0x55bd4ff528e6 in run_test tests/builtin-test.c:358 #6 0x55bd4ff52baf in test_and_print tests/builtin-test.c:388 #7 0x55bd4ff543fe in __cmd_test tests/builtin-test.c:583 #8 0x55bd4ff5572f in cmd_test tests/builtin-test.c:722 #9 0x55bd4ffc4087 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #10 0x55bd4ffc45c6 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #11 0x55bd4ffc49ca in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #12 0x55bd4ffc5138 in main /home/changbin/work/linux/tools/perf/perf.c:520 #13 0x7f1b6e34809a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Indirect leak of 19 byte(s) in 1 object(s) allocated from: #0 0x7f1b6fc83f30 in __interceptor_malloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xedf30) #1 0x7f1b6e3ac30f in vasprintf (/lib/x86_64-linux-gnu/libc.so.6+0x8830f) Signed-off-by: Changbin Du Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Fixes: 6a6cd11d4e57 ("perf test: Add test for the sched tracepoint format fields") Link: http://lkml.kernel.org/r/20190316080556.3075-17-changbin.du@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/evsel-tp-sched.c | 1 + 1 file changed, 1 insertion(+) 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; } From 71184c6ab7e60fd59d8dbc8fed62a1c753dc4934 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:37 -0700 Subject: [PATCH 166/256] perf record: Replace option --bpf-event with --no-bpf-event Currently, monitoring of BPF programs through bpf_event is off by default for 'perf record'. To turn it on, the user need to use option "--bpf-event". As BPF gets wider adoption in different subsystems, this option becomes inconvenient. This patch makes bpf_event on by default, and adds option "--no-bpf-event" to turn it off. Since option --bpf-event is not released yet, it is safe to remove it. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: kernel-team@fb.com Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-2-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- tools/perf/perf.h | 2 +- tools/perf/util/bpf-event.c | 2 +- tools/perf/util/evsel.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e7144a1c1c82..f29874192d3e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1891,7 +1891,7 @@ 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'", 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/util/bpf-event.c b/tools/perf/util/bpf-event.c index 028c8ec1f62a..ea012b735a37 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -187,7 +187,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, } /* Synthesize PERF_RECORD_BPF_EVENT */ - if (opts->bpf_event) { + if (!opts->no_bpf_event) { *bpf_event = (struct bpf_event){ .header = { .type = PERF_RECORD_BPF_EVENT, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1a2023da5d9c..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) From 34be16466d4dc06f3d604dafbcdb3327b72e78da Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:38 -0700 Subject: [PATCH 167/256] tools lib bpf: Introduce bpf_program__get_prog_info_linear() Currently, bpf_prog_info includes 9 arrays. The user has the option to fetch any combination of these arrays. However, this requires a lot of handling. This work becomes more tricky when we need to store bpf_prog_info to a file, because these arrays are allocated independently. This patch introduces 'struct bpf_prog_info_linear', which stores arrays of bpf_prog_info in continuous memory. Helper functions are introduced to unify the work to get different sets of bpf_prog_info. Specifically, bpf_program__get_prog_info_linear() allows the user to select which arrays to fetch, and handles details for the user. Please see the comments right before 'enum bpf_prog_info_array' for more details and examples. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Acked-by: Daniel Borkmann Link: https://lkml.kernel.org/r/ce92c091-e80d-a0c1-4aa0-987706c42b20@iogearbox.net Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: kernel-team@fb.com Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-3-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.c | 251 +++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.h | 63 ++++++++++ tools/lib/bpf/libbpf.map | 3 + 3 files changed, 317 insertions(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 4884557aa17f..8fb6e89b4b2c 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; @@ -2997,3 +3002,249 @@ 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 aa1521a51687..c70785cc8ef5 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -378,6 +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, ); + * 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; From cae73f2339231d61022769f09c94e4500e8ad47a Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:39 -0700 Subject: [PATCH 168/256] bpftool: use bpf_program__get_prog_info_linear() in prog.c:do_dump() This patches uses bpf_program__get_prog_info_linear() to simplify the logic in prog.c do_dump(). Committer testing: Before: # bpftool prog dump xlated id 208 > /tmp/dump.xlated.before # bpftool prog dump jited id 208 > /tmp/dump.jited.before # bpftool map dump id 107 > /tmp/map.dump.before After: # ~acme/git/perf/tools/bpf/bpftool/bpftool map dump id 107 > /tmp/map.dump.after # ~acme/git/perf/tools/bpf/bpftool/bpftool prog dump xlated id 208 > /tmp/dump.xlated.after # ~acme/git/perf/tools/bpf/bpftool/bpftool prog dump jited id 208 > /tmp/dump.jited.after # diff -u /tmp/dump.xlated.before /tmp/dump.xlated.after # diff -u /tmp/dump.jited.before /tmp/dump.jited.after # diff -u /tmp/map.dump.before /tmp/map.dump.after # ~acme/git/perf/tools/bpf/bpftool/bpftool prog dump xlated id 208 0: (bf) r6 = r1 1: (85) call bpf_get_current_pid_tgid#80800 2: (63) *(u32 *)(r10 -328) = r0 3: (bf) r2 = r10 4: (07) r2 += -328 5: (18) r1 = map[id:107] 7: (85) call __htab_map_lookup_elem#85680 8: (15) if r0 == 0x0 goto pc+1 9: (07) r0 += 56 10: (b7) r7 = 0 11: (55) if r0 != 0x0 goto pc+52 12: (bf) r1 = r10 13: (07) r1 += -328 14: (b7) r2 = 64 15: (bf) r3 = r6 16: (85) call bpf_probe_read#-46848 17: (bf) r2 = r10 18: (07) r2 += -320 19: (18) r1 = map[id:106] 21: (07) r1 += 208 22: (61) r0 = *(u32 *)(r2 +0) 23: (35) if r0 >= 0x200 goto pc+3 24: (67) r0 <<= 3 25: (0f) r0 += r1 26: (05) goto pc+1 27: (b7) r0 = 0 28: (15) if r0 == 0x0 goto pc+35 29: (71) r1 = *(u8 *)(r0 +0) 30: (15) if r1 == 0x0 goto pc+33 31: (b7) r5 = 64 32: (79) r1 = *(u64 *)(r10 -320) 33: (15) if r1 == 0x2 goto pc+2 34: (15) if r1 == 0x101 goto pc+3 35: (55) if r1 != 0x15 goto pc+19 36: (79) r3 = *(u64 *)(r6 +16) 37: (05) goto pc+1 38: (79) r3 = *(u64 *)(r6 +24) 39: (15) if r3 == 0x0 goto pc+15 40: (b7) r1 = 0 41: (63) *(u32 *)(r10 -260) = r1 42: (bf) r1 = r10 43: (07) r1 += -256 44: (b7) r2 = 256 45: (85) call bpf_probe_read_str#-46704 46: (b7) r5 = 328 47: (63) *(u32 *)(r10 -264) = r0 48: (bf) r1 = r0 49: (67) r1 <<= 32 50: (77) r1 >>= 32 51: (25) if r1 > 0xff goto pc+3 52: (07) r0 += 72 53: (57) r0 &= 255 54: (bf) r5 = r0 55: (bf) r4 = r10 56: (07) r4 += -328 57: (bf) r1 = r6 58: (18) r2 = map[id:105] 60: (18) r3 = 0xffffffff 62: (85) call bpf_perf_event_output_tp#-45104 63: (bf) r7 = r0 64: (bf) r0 = r7 65: (95) exit # Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Acked-by: Daniel Borkmann Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: kernel-team@fb.com Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-4-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/bpf/bpftool/prog.c | 272 +++++++++------------------------------ 1 file changed, 62 insertions(+), 210 deletions(-) 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; - void *func_info = NULL, *linfo = NULL, *jited_linfo = NULL; - unsigned int nr_finfo, nr_linfo = 0, nr_jited_linfo = 0; + struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; - unsigned long *func_ksyms = NULL; - struct bpf_prog_info info = {}; - unsigned int *func_lens = NULL; + enum {DUMP_JITED, DUMP_XLATED} mode; const char *disasm_opt = NULL; - unsigned int nr_func_ksyms; - unsigned int nr_func_lens; + struct bpf_prog_info *info; 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; - __u64 *member_ptr; + __u32 member_len; + __u64 arrays; ssize_t n; - int err; int fd; if (is_prefix(*argv, "jited")) { if (disasm_init()) return -1; - - member_len = &info.jited_prog_len; - member_ptr = &info.jited_prog_insns; + mode = DUMP_JITED; } else if (is_prefix(*argv, "xlated")) { - member_len = &info.xlated_prog_len; - member_ptr = &info.xlated_prog_insns; + mode = DUMP_XLATED; } 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 (err) { - p_err("can't get prog info: %s", strerror(errno)); - return -1; - } + if (mode == DUMP_JITED) + arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; + else + arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; - if (!*member_len) { - p_info("no instructions returned"); - close(fd); - return 0; - } + 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_size = *member_len; - - buf = malloc(buf_size); - if (!buf) { - p_err("mem alloc failed"); - close(fd); - return -1; - } - - nr_func_ksyms = info.nr_jited_ksyms; - if (nr_func_ksyms) { - func_ksyms = malloc(nr_func_ksyms * sizeof(__u64)); - if (!func_ksyms) { - 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; - } - } - - nr_finfo = info.nr_func_info; - finfo_rec_size = info.func_info_rec_size; - if (nr_finfo && finfo_rec_size) { - func_info = malloc(nr_finfo * finfo_rec_size); - if (!func_info) { - p_err("mem alloc failed"); - close(fd); - goto err_free; - } - } - - linfo_rec_size = info.line_info_rec_size; - 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); + info_linear = bpf_program__get_prog_info_linear(fd, arrays); close(fd); - if (err) { + if (IS_ERR_OR_NULL(info_linear)) { p_err("can't get prog info: %s", strerror(errno)); - goto err_free; + return -1; } - if (*member_len > buf_size) { - p_err("too many instructions returned"); - goto err_free; + info = &info_linear->info; + if (mode == DUMP_JITED) { + if (info->jited_prog_len == 0) { + p_info("no instructions returned"); + goto err_free; + } + buf = (unsigned char *)(info->jited_prog_insns); + member_len = info->jited_prog_len; + } else { /* DUMP_XLATED */ + if (info->xlated_prog_len == 0) { + p_err("error retrieving insn dump: kernel.kptr_restrict set?"); + goto err_free; + } + buf = (unsigned char *)info->xlated_prog_insns; + member_len = info->xlated_prog_len; } - 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)) { + if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) { p_err("failed to get btf"); goto err_free; } - if (nr_linfo) { - prog_linfo = bpf_prog_linfo__new(&info); + func_info = (void *)info->func_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) { - name = ifindex_to_bfd_params(info.ifindex, - info.netns_dev, - info.netns_ino, + if (info->ifindex) { + name = ifindex_to_bfd_params(info->ifindex, + info->netns_dev, + 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; - for (i = 0; i < info.nr_jited_func_lens; i++) { + lens = (__u32 *) info->jited_func_lens; + 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.jited_ksyms = (__u64 *) info.jited_ksyms; + dd.nr_jited_ksyms = info->nr_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(func_ksyms); - free(func_lens); - free(func_info); - free(linfo); - free(jited_linfo); - bpf_prog_linfo__free(prog_linfo); + free(info_linear); return 0; err_free: - free(buf); - free(func_ksyms); - free(func_lens); - free(func_info); - free(linfo); - free(jited_linfo); - bpf_prog_linfo__free(prog_linfo); + free(info_linear); return -1; } From a742258af131e570a68ad8cf16cd2cc4692675a0 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:40 -0700 Subject: [PATCH 169/256] perf bpf: Synthesize bpf events with bpf_program__get_prog_info_linear() With bpf_program__get_prog_info_linear, we can simplify the logic that synthesizes bpf events. This patch doesn't change the behavior of the code. Commiter notes: Needed this (for all four variables), suggested by Song, to overcome build failure on debian experimental cross building to MIPS 32-bit: - u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(info->prog_tags); + u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags); util/bpf-event.c: In function 'perf_event__synthesize_one_bpf_prog': util/bpf-event.c:143:35: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(info->prog_tags); ^ util/bpf-event.c:144:22: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] __u32 *prog_lens = (__u32 *)(info->jited_func_lens); ^ util/bpf-event.c:145:23: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] __u64 *prog_addrs = (__u64 *)(info->jited_ksyms); ^ util/bpf-event.c:146:22: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] void *func_infos = (void *)(info->func_info); ^ cc1: all warnings being treated as errors Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: kernel-team@fb.com Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-5-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 118 ++++++++++++------------------------ 1 file changed, 40 insertions(+), 78 deletions(-) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index ea012b735a37..e0cbe7f87170 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -3,7 +3,9 @@ #include #include #include +#include #include +#include #include "bpf-event.h" #include "debug.h" #include "symbol.h" @@ -49,99 +51,62 @@ 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; - u8 (*prog_tags)[BPF_TAG_SIZE] = NULL; - struct bpf_prog_info info = { .type = 0, }; - u32 info_len = sizeof(info); - void *func_infos = NULL; - u64 *prog_addrs = NULL; + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info *info; struct btf *btf = NULL; - u32 *prog_lens = NULL; bool has_btf = false; - char errbuf[512]; + u32 sub_prog_cnt, i; int err = 0; + u64 arrays; - /* Call bpf_obj_get_info_by_fd() to get sizes of arrays */ - err = bpf_obj_get_info_by_fd(fd, &info, &info_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_PROG_TAGS; - if (err) { - pr_debug("%s: failed to get BPF program info: %s, aborting\n", - __func__, str_error_r(errno, errbuf, sizeof(errbuf))); + info_linear = bpf_program__get_prog_info_linear(fd, arrays); + if (IS_ERR_OR_NULL(info_linear)) { + 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; - if (sub_prog_cnt != info.nr_prog_tags || - sub_prog_cnt != info.nr_jited_func_lens) + sub_prog_cnt = info->nr_jited_ksyms; + if (sub_prog_cnt != info->nr_prog_tags || + 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; - func_infos = calloc(sub_prog_cnt, func_info_rec_size); - if (!func_infos) { - pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__); - return -1; + 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); + err = -1; + btf = NULL; + goto out; } has_btf = true; } - /* - * 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++) { + u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags); + __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); + __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); + void *func_infos = (void *)(uintptr_t)(info->func_info); const struct bpf_func_info *finfo; const char *short_name = NULL; const struct btf_type *t; @@ -163,13 +128,13 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, KSYM_NAME_LEN - name_len, prog_tags[i], BPF_TAG_SIZE); if (has_btf) { - finfo = func_infos + i * info.func_info_rec_size; + 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; + if (info->name[0]) + short_name = info->name; } else short_name = "F"; if (short_name) @@ -195,9 +160,9 @@ 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; err = perf_tool__process_synth_event(tool, event, @@ -205,10 +170,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool, } out: - free(prog_tags); - free(prog_lens); - free(prog_addrs); - free(func_infos); + free(info_linear); free(btf); return err ? -1 : 0; } From e5416950454fa79b7bdc86dac45661b97d887c97 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:41 -0700 Subject: [PATCH 170/256] perf bpf: Make synthesize_bpf_events() receive perf_session pointer instead of perf_tool This patch changes the arguments of perf_event__synthesize_bpf_events() to include perf_session* instead of perf_tool*. perf_session will be used in the next patch. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-6-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/util/bpf-event.c | 8 +++++--- tools/perf/util/bpf-event.h | 4 ++-- 4 files changed, 9 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f29874192d3e..e79faccd7842 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1114,7 +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"); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 2508a7a552fa..77e6190211d2 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1208,7 +1208,7 @@ static int __cmd_top(struct perf_top *top) 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) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index e0cbe7f87170..5237e8f11997 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -10,6 +10,7 @@ #include "debug.h" #include "symbol.h" #include "machine.h" +#include "session.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -42,7 +43,7 @@ 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, @@ -52,6 +53,7 @@ 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; struct bpf_prog_info_linear *info_linear; + struct perf_tool *tool = session->tool; struct bpf_prog_info *info; struct btf *btf = NULL; bool has_btf = false; @@ -175,7 +177,7 @@ out: 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) @@ -209,7 +211,7 @@ 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); diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 7890067e1a37..6698683612a7 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -15,7 +15,7 @@ struct record_opts; 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); @@ -27,7 +27,7 @@ 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) From e4378f0cb90be0368c48baad69a99203c58e3196 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:42 -0700 Subject: [PATCH 171/256] perf bpf: Save bpf_prog_info in a rbtree in perf_env bpf_prog_info contains information necessary to annotate bpf programs. This patch saves bpf_prog_info for bpf programs loaded in the system. Some big picture of the next few patches: To fully annotate BPF programs with source code mapping, 4 different informations are needed: 1) PERF_RECORD_KSYMBOL 2) PERF_RECORD_BPF_EVENT 3) bpf_prog_info 4) btf Before this set, 1) and 2) in the list are already saved to perf.data file. For BPF programs that are already loaded before perf run, 1) and 2) are synthesized by perf_event__synthesize_bpf_events(). For short living BPF programs, 1) and 2) are generated by kernel. This set handles 3) and 4) from the list. Again, it is necessary to handle existing BPF program and short living program separately. This patch handles 3) for exising BPF programs while synthesizing 1) and 2) in perf_event__synthesize_bpf_events(). These data are stored in perf_env. The next patch saves these data from perf_env to perf.data as headers. Similarly, the two patches after the next saves 4) of existing BPF programs to perf_env and perf.data. Another patch later will handle 3) and 4) for short living BPF programs by monitoring 1) and 2) in a dedicate thread. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-7-songliubraving@fb.com [ set env->bpf_progs.infos_cnt to zero in perf_env__purge_bpf() as noted by jolsa ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf.c | 1 + tools/perf/util/bpf-event.c | 30 ++++++++++++- tools/perf/util/bpf-event.h | 7 ++- tools/perf/util/env.c | 88 +++++++++++++++++++++++++++++++++++++ tools/perf/util/env.h | 19 ++++++++ tools/perf/util/session.c | 1 + 6 files changed, 144 insertions(+), 2 deletions(-) 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/util/bpf-event.c b/tools/perf/util/bpf-event.c index 5237e8f11997..37ee4e2a728a 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -10,6 +10,7 @@ #include "debug.h" #include "symbol.h" #include "machine.h" +#include "env.h" #include "session.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -54,17 +55,28 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, struct bpf_event *bpf_event = &event->bpf_event; struct bpf_prog_info_linear *info_linear; struct perf_tool *tool = session->tool; + struct bpf_prog_info_node *info_node; struct bpf_prog_info *info; struct btf *btf = NULL; bool has_btf = false; + struct perf_env *env; u32 sub_prog_cnt, i; 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; + 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)) { @@ -153,8 +165,8 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, machine, process); } - /* Synthesize PERF_RECORD_BPF_EVENT */ if (!opts->no_bpf_event) { + /* Synthesize PERF_RECORD_BPF_EVENT */ *bpf_event = (struct bpf_event){ .header = { .type = PERF_RECORD_BPF_EVENT, @@ -167,6 +179,22 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, 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); } diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 6698683612a7..fad932f7404f 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -3,14 +3,19 @@ #define __PERF_BPF_EVENT_H #include +#include #include "event.h" struct machine; union perf_event; struct perf_sample; -struct perf_tool; struct record_opts; +struct bpf_prog_info_node { + struct bpf_prog_info_linear *info_linear; + struct rb_node rb_node; +}; + #ifdef HAVE_LIBBPF_SUPPORT int machine__process_bpf_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 4c23779e271a..98cd36f0e317 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -3,15 +3,97 @@ #include "env.h" #include "sane_ctype.h" #include "util.h" +#include "bpf-event.h" #include #include +#include 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; +} + +/* 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; + + 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 +120,12 @@ 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; + 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..24b11c564ba4 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -3,7 +3,9 @@ #define __PERF_ENV_H #include +#include #include "cpumap.h" +#include "rwsem.h" struct cpu_topology_map { int socket_id; @@ -64,8 +66,20 @@ 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; + } bpf_progs; }; +struct bpf_prog_info_node; + extern struct perf_env perf_env; void perf_env__exit(struct perf_env *env); @@ -80,4 +94,9 @@ 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); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0ec34227bd60..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; From 606f972b1361f477cbd4e6e8ac00742fde4b39db Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:43 -0700 Subject: [PATCH 172/256] perf bpf: Save bpf_prog_info information as headers to perf.data This patch enables perf-record to save bpf_prog_info information as headers to perf.data. A new header type HEADER_BPF_PROG_INFO is introduced for this data. Committer testing: As root, being on the kernel sources top level directory, run: # perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c -e *msg Just to compile and load a BPF program that attaches to the raw_syscalls:sys_{enter,exit} tracepoints to trace the syscalls ending in "msg" (recvmsg, sendmsg, recvmmsg, sendmmsg, etc). Then do a systemwide perf record session for a few seconds: # perf record -a sleep 2s Then look at: # perf report --header-only | grep -i bpf # bpf_prog_info of id 13 # bpf_prog_info of id 14 # bpf_prog_info of id 15 # bpf_prog_info of id 16 # bpf_prog_info of id 17 # bpf_prog_info of id 18 # bpf_prog_info of id 21 # bpf_prog_info of id 22 # bpf_prog_info of id 208 # bpf_prog_info of id 209 # We need to show more info about these programs, like bpftool does for the ones running on the system, i.e. 'perf record/perf report' become a way of saving the BPF state in a machine to then analyse on another, together with all the other information that is already saved in the perf.data header: # perf report --header-only # ======== # captured on : Tue Mar 12 11:42:13 2019 # header version : 1 # data offset : 296 # data size : 16294184 # feat offset : 16294480 # hostname : quaco # os release : 5.0.0+ # perf version : 5.0.gd783c8 # arch : x86_64 # nrcpus online : 8 # nrcpus avail : 8 # cpudesc : Intel(R) Core(TM) i7-8650U CPU @ 1.90GHz # cpuid : GenuineIntel,6,142,10 # total memory : 24555720 kB # cmdline : /home/acme/bin/perf (deleted) record -a # event : name = cycles:ppp, , id = { 3190123, 3190124, 3190125, 3190126, 3190127, 3190128, 3190129, 3190130 }, size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|CPU|PERIOD, read_format = ID, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1 # CPU_TOPOLOGY info available, use -I to display # NUMA_TOPOLOGY info available, use -I to display # pmu mappings: intel_pt = 8, software = 1, power = 11, uprobe = 7, uncore_imc = 12, cpu = 4, cstate_core = 18, uncore_cbox_2 = 15, breakpoint = 5, uncore_cbox_0 = 13, tracepoint = 2, cstate_pkg = 19, uncore_arb = 17, kprobe = 6, i915 = 10, msr = 9, uncore_cbox_3 = 16, uncore_cbox_1 = 14 # CACHE info available, use -I to display # time of first sample : 116392.441701 # time of last sample : 116400.932584 # sample duration : 8490.883 ms # MEM_TOPOLOGY info available, use -I to display # bpf_prog_info of id 13 # bpf_prog_info of id 14 # bpf_prog_info of id 15 # bpf_prog_info of id 16 # bpf_prog_info of id 17 # bpf_prog_info of id 18 # bpf_prog_info of id 21 # bpf_prog_info of id 22 # bpf_prog_info of id 208 # bpf_prog_info of id 209 # missing features: TRACING_DATA BRANCH_STACK GROUP_DESC AUXTRACE STAT CLOCKID DIR_FORMAT # ======== # Committer notes: We can't use the libbpf unconditionally, as the build may have been with NO_LIBBPF, when we end up with linking errors, so provide dummy {process,write}_bpf_prog_info() wrapped by HAVE_LIBBPF_SUPPORT for that case. Printing are not affected by this, so can continue as is. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-8-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 153 ++++++++++++++++++++++++++++++++++++++- tools/perf/util/header.h | 1 + 2 files changed, 153 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b0683bf4d9f3..e6a81af516f6 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -18,6 +18,7 @@ #include #include #include +#include #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" @@ -876,6 +878,56 @@ static int write_dir_format(struct feat_fd *ff, 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 cpu_cache_level__sort(const void *a, const void *b) { struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a; @@ -1367,6 +1419,29 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp) 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); + fprintf(fp, "# bpf_prog_info of id %u\n", + node->info_linear->info.id); + } + + up_read(&env->bpf_progs.lock); +} + static void free_event_desc(struct perf_evsel *events) { struct perf_evsel *evsel; @@ -2414,6 +2489,81 @@ static int process_dir_format(struct feat_fd *ff, 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 + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2474,7 +2624,8 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(SAMPLE_TIME, sample_time, false), FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), FEAT_OPR(CLOCKID, clockid, false), - FEAT_OPN(DIR_FORMAT, dir_format, false) + FEAT_OPN(DIR_FORMAT, dir_format, false), + FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false) }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 6a231340238d..1dc85f0f895d 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -40,6 +40,7 @@ enum { HEADER_MEM_TOPOLOGY, HEADER_CLOCKID, HEADER_DIR_FORMAT, + HEADER_BPF_PROG_INFO, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; From 3792cb2ff43b1b193136a03ce1336462a827d792 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:44 -0700 Subject: [PATCH 173/256] perf bpf: Save BTF in a rbtree in perf_env BTF contains information necessary to annotate BPF programs. This patch saves BTF for BPF programs loaded in the system. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-9-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 23 +++++++++++++ tools/perf/util/bpf-event.h | 7 ++++ tools/perf/util/env.c | 67 +++++++++++++++++++++++++++++++++++++ tools/perf/util/env.h | 5 +++ 4 files changed, 102 insertions(+) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 37ee4e2a728a..a4fc52b4ffae 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -34,6 +34,28 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused, 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; +} + /* * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf * program. One PERF_RECORD_BPF_EVENT is generated for the program. And @@ -113,6 +135,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, goto out; } has_btf = true; + perf_env__fetch_btf(env, info->btf_id, btf); } /* Synthesize PERF_RECORD_KSYMBOL */ diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index fad932f7404f..b9ec394dc7c7 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -16,6 +16,13 @@ struct bpf_prog_info_node { 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); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 98cd36f0e317..c6351b557bb0 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -64,6 +64,58 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, 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) { @@ -86,6 +138,20 @@ static void perf_env__purge_bpf(struct perf_env *env) 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); } @@ -123,6 +189,7 @@ void perf_env__exit(struct perf_env *env) 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); } diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 24b11c564ba4..4f8e2b485c01 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -75,10 +75,13 @@ struct perf_env { 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; @@ -99,4 +102,6 @@ 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 */ From a70a1123174ab592c5fa8ecf09f9fad9b335b872 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:45 -0700 Subject: [PATCH 174/256] perf bpf: Save BTF information as headers to perf.data This patch enables 'perf record' to save BTF information as headers to perf.data. A new header type HEADER_BPF_BTF is introduced for this data. Committer testing: As root, being on the kernel sources top level directory, run: # perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c -e *msg Just to compile and load a BPF program that attaches to the raw_syscalls:sys_{enter,exit} tracepoints to trace the syscalls ending in "msg" (recvmsg, sendmsg, recvmmsg, sendmmsg, etc). Make sure you have a recent enough clang, say version 9, to get the BTF ELF sections needed for this testing: # clang --version | head -1 clang version 9.0.0 (https://git.llvm.org/git/clang.git/ 7906282d3afec5dfdc2b27943fd6c0309086c507) (https://git.llvm.org/git/llvm.git/ a1b5de1ff8ae8bc79dc8e86e1f82565229bd0500) # readelf -SW tools/perf/examples/bpf/augmented_raw_syscalls.o | grep BTF [22] .BTF PROGBITS 0000000000000000 000ede 000b0e 00 0 0 1 [23] .BTF.ext PROGBITS 0000000000000000 0019ec 0002a0 00 0 0 1 [24] .rel.BTF.ext REL 0000000000000000 002fa8 000270 10 30 23 8 Then do a systemwide perf record session for a few seconds: # perf record -a sleep 2s Then look at: # perf report --header-only | grep b[pt]f # event : name = cycles:ppp, , id = { 1116204, 1116205, 1116206, 1116207, 1116208, 1116209, 1116210, 1116211 }, size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, read_format = ID, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, ksymbol = 1, bpf_event = 1 # bpf_prog_info of id 13 # bpf_prog_info of id 14 # bpf_prog_info of id 15 # bpf_prog_info of id 16 # bpf_prog_info of id 17 # bpf_prog_info of id 18 # bpf_prog_info of id 21 # bpf_prog_info of id 22 # bpf_prog_info of id 51 # bpf_prog_info of id 52 # btf info of id 8 # We need to show more info about these BPF and BTF entries , but that can be done later. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-10-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 101 ++++++++++++++++++++++++++++++++++++++- tools/perf/util/header.h | 1 + 2 files changed, 101 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index e6a81af516f6..01dda2f65d36 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -928,6 +928,39 @@ static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, } #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; @@ -1442,6 +1475,28 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *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; @@ -2564,6 +2619,49 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _ } #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); @@ -2625,7 +2723,8 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), FEAT_OPR(CLOCKID, clockid, false), FEAT_OPN(DIR_FORMAT, dir_format, false), - FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, 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 1dc85f0f895d..386da49e1bfa 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -41,6 +41,7 @@ enum { HEADER_CLOCKID, HEADER_DIR_FORMAT, HEADER_BPF_PROG_INFO, + HEADER_BPF_BTF, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; From ee7a112fbcc8edb4cf2f84ce5fcc2da7818fd4b8 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:46 -0700 Subject: [PATCH 175/256] perf top: Add option --no-bpf-event This patch adds option --no-bpf-event to 'perf top', which is the same as the option of 'perf record'. The following patches will use this option. Committer testing: # perf top -vv 2> /tmp/perf_event_attr.out # cat /tmp/perf_event_attr.out ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|CPU|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 bpf_event 1 ------------------------------------------------------------ # After this patch: # perf top --no-bpf-event -vv 2> /tmp/perf_event_attr.out # cat /tmp/perf_event_attr.out ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|CPU|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ # Signed-off-by: Song Liu Tested-by: Arnaldo Carvalho de Melo Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-11-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 77e6190211d2..c2ea22c4ea67 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1469,6 +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", From 31be9478ed7f43d6351e0d5a2257ca76609c83d3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:47 -0700 Subject: [PATCH 176/256] perf feature detection: Add -lopcodes to feature-libbfd Both libbfd and libopcodes are distributed with binutil-dev/devel. When libbfd is present, it is OK to assume that libopcodes also present. This has been a safe assumption for bpftool. This patch adds -lopcodes to perf/Makefile.config. libopcodes will be used in the next commit for BPF annotation. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-12-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0f11d5891301..df4ad45599ca 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -713,7 +713,7 @@ 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 @@ -724,10 +724,10 @@ else $(call feature_check,libbfd-liberty-z) ifeq ($(feature-libbfd-liberty), 1) - EXTLIBS += -lbfd -liberty + EXTLIBS += -lbfd -lopcodes -liberty else ifeq ($(feature-libbfd-liberty-z), 1) - EXTLIBS += -lbfd -liberty -lz + EXTLIBS += -lbfd -lopcodes -liberty -lz endif endif endif From 9b86d04d53b98399017fea44e9047165ffe12d42 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:48 -0700 Subject: [PATCH 177/256] perf symbols: Introduce DSO_BINARY_TYPE__BPF_PROG_INFO Introduce a new dso type DSO_BINARY_TYPE__BPF_PROG_INFO for BPF programs. In symbol__disassemble(), DSO_BINARY_TYPE__BPF_PROG_INFO dso will call into a new function symbol__disassemble_bpf() in an upcoming patch, where annotation line information is filled based bpf_prog_info and btf saved in given perf_env. Committer notes: Removed the unnamed union with 'bpf_prog' and 'cache' in 'struct dso', to fix this bug when exiting 'perf top': # perf top perf: Segmentation fault -------- backtrace -------- perf[0x5a785a] /lib64/libc.so.6(+0x385bf)[0x7fd68443c5bf] perf(rb_first+0x2b)[0x4d6eeb] perf(dso__delete+0xb7)[0x4dffb7] perf[0x4f9e37] perf(perf_session__delete+0x64)[0x504df4] perf(cmd_top+0x1957)[0x454467] perf[0x4aad18] perf(main+0x61c)[0x42ec7c] /lib64/libc.so.6(__libc_start_main+0xf2)[0x7fd684428412] perf(_start+0x2d)[0x42eead] # # addr2line -fe ~/bin/perf 0x4dffb7 dso_cache__free /home/acme/git/perf/tools/perf/util/dso.c:713 That is trying to access the dso->data.cache, and that is not used with BPF programs, so we end up accessing what is in bpf_prog.first_member, b00m. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-13-songliubraving@fb.com [ split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 1 + tools/perf/util/dso.h | 8 ++++++++ tools/perf/util/symbol.c | 1 + 3 files changed, 10 insertions(+) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index ab8a455d2283..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; 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/symbol.c b/tools/perf/util/symbol.c index 58442ca5e3c4..5cbad55cd99d 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1455,6 +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; From 3ca3877a9732b68cf0289367a859f6c163a79bfa Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:49 -0700 Subject: [PATCH 178/256] perf bpf: Process PERF_BPF_EVENT_PROG_LOAD for annotation This patch adds processing of PERF_BPF_EVENT_PROG_LOAD, which sets proper DSO type/id/etc of memory regions mapped to BPF programs to DSO_BINARY_TYPE__BPF_PROG_INFO. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-14-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 54 +++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index a4fc52b4ffae..852e960692cb 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -12,6 +12,7 @@ #include "machine.h" #include "env.h" #include "session.h" +#include "map.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -25,12 +26,65 @@ 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 *)(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; } From 54e3aca84e571559915998aa6cc05e5ac37c043b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 18 Mar 2019 21:47:09 +0300 Subject: [PATCH 179/256] ACPI / utils: Drop reference in test for device presence When commit 8661423eea1a ("ACPI / utils: Add new acpi_dev_present helper") introduced acpi_dev_present(), it missed the fact that bus_find_device() took a reference on the device found by it and the callers of acpi_dev_present() don't drop that reference. Drop the reference on the device in acpi_dev_present(). Fixes: 8661423eea1a ("ACPI / utils: Add new acpi_dev_present helper") Signed-off-by: Andy Shevchenko Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- drivers/acpi/utils.c | 1 + 1 file changed, 1 insertion(+) 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); From 2071ac985d37efe496782c34318dbead93beb02f Mon Sep 17 00:00:00 2001 From: Jiada Wang Date: Tue, 12 Mar 2019 15:51:28 +0900 Subject: [PATCH 180/256] PM / Domains: Avoid a potential deadlock Lockdep warns that prepare_lock and genpd->mlock can cause a deadlock the deadlock scenario is like following: First thread is probing cs2000 cs2000_probe() clk_register() __clk_core_init() clk_prepare_lock() ----> acquires prepare_lock cs2000_recalc_rate() i2c_smbus_read_byte_data() rcar_i2c_master_xfer() dma_request_chan() rcar_dmac_of_xlate() rcar_dmac_alloc_chan_resources() pm_runtime_get_sync() __pm_runtime_resume() rpm_resume() rpm_callback() genpd_runtime_resume() ----> acquires genpd->mlock Second thread is attaching any device to the same PM domain genpd_add_device() genpd_lock() ----> acquires genpd->mlock cpg_mssr_attach_dev() of_clk_get_from_provider() __of_clk_get_from_provider() __clk_create_clk() clk_prepare_lock() ----> acquires prepare_lock Since currently no PM provider access genpd's critical section in .attach_dev, and .detach_dev callbacks, so there is no need to protect these two callbacks with genpd->mlock. This patch avoids a potential deadlock by moving out .attach_dev and .detach_dev from genpd->mlock, so that genpd->mlock won't be held when prepare_lock is acquired in .attach_dev and .detach_dev Signed-off-by: Jiada Wang Reviewed-by: Ulf Hansson Tested-by: Geert Uytterhoeven Reviewed-by: Geert Uytterhoeven Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) 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; From 4b9ce3a651a37c60527101db4451a315a8b9588f Mon Sep 17 00:00:00 2001 From: Deepak Rawat Date: Thu, 28 Feb 2019 10:29:54 -0800 Subject: [PATCH 181/256] drm/vmwgfx: Return 0 when gmrid::get_node runs out of ID's If it's not a system error and get_node implementation accommodate the buffer object then it should return 0 with memm::mm_node set to NULL. v2: Test for id != -ENOMEM instead of id == -ENOSPC. Cc: Fixes: 4eb085e42fde ("drm/vmwgfx: Convert to new IDA API") Signed-off-by: Deepak Rawat Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From c2d311553855395764e2e5bf401d987ba65c2056 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 18 Mar 2019 15:47:58 +0100 Subject: [PATCH 182/256] drm/vmwgfx: Don't double-free the mode stored in par->set_mode When calling vmw_fb_set_par(), the mode stored in par->set_mode gets free'd twice. The first free is in vmw_fb_kms_detach(), the second is near the end of vmw_fb_set_par() under the name of 'old_mode'. The mode-setting code only works correctly if the mode doesn't actually change. Removing 'old_mode' in favor of using par->set_mode directly fixes the problem. Cc: Fixes: a278724aa23c ("drm/vmwgfx: Implement fbdev on kms v2") Signed-off-by: Thomas Zimmermann Reviewed-by: Deepak Rawat Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) 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)) { - drm_mode_destroy(vmw_priv->dev, mode); - mode = old_mode; - old_mode = NULL; - } else if (!vmw_kms_validate_mode_vram(vmw_priv, + 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) - drm_mode_destroy(vmw_priv->dev, old_mode); + if (par->set_mode) + drm_mode_destroy(vmw_priv->dev, par->set_mode); par->set_mode = mode; mutex_unlock(&par->bo_mutex); From 8bc086899816214fbc6047c9c7e15fcab49552bf Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sun, 17 Mar 2019 01:17:56 +0000 Subject: [PATCH 183/256] powerpc/mm: Only define MAX_PHYSMEM_BITS in SPARSEMEM configurations MAX_PHYSMEM_BITS only needs to be defined if CONFIG_SPARSEMEM is enabled, and that was the case before commit 4ffe713b7587 ("powerpc/mm: Increase the max addressable memory to 2PB"). On 32-bit systems, where CONFIG_SPARSEMEM is not enabled, we now define it as 46. That is larger than the real number of physical address bits, and breaks calculations in zsmalloc: mm/zsmalloc.c:130:49: warning: right shift count is negative MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) ^~ ... mm/zsmalloc.c:253:21: error: variably modified 'size_class' at file scope struct size_class *size_class[ZS_SIZE_CLASSES]; ^~~~~~~~~~ Fixes: 4ffe713b7587 ("powerpc/mm: Increase the max addressable memory to 2PB") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Ben Hutchings Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/mmu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 From bb229bbb3bf63d23128e851a1f3b85c083178fa1 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 20 Mar 2019 09:46:58 +0100 Subject: [PATCH 184/256] libceph: wait for latest osdmap in ceph_monc_blacklist_add() Because map updates are distributed lazily, an OSD may not know about the new blacklist for quite some time after "osd blacklist add" command is completed. This makes it possible for a blacklisted but still alive client to overwrite a post-blacklist update, resulting in data corruption. Waiting for latest osdmap in ceph_monc_blacklist_add() and thus using the post-blacklist epoch for all post-blacklist requests ensures that all such requests "wait" for the blacklist to come into force on their respective OSDs. Cc: stable@vger.kernel.org Fixes: 6305a3b41515 ("libceph: support for blacklisting clients") Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- include/linux/ceph/libceph.h | 2 ++ net/ceph/ceph_common.c | 18 +++++++++++++++++- net/ceph/mon_client.c | 9 +++++++++ 3 files changed, 28 insertions(+), 1 deletion(-) 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/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; From 9d4a227f6ef189cf37eb22641f6ee788b7dc41bb Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 20 Mar 2019 10:58:05 +0100 Subject: [PATCH 185/256] rbd: drop wait_for_latest_osdmap() Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- drivers/block/rbd.c | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 3b2c9289dccb..2210c1b9491b 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -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); From e5a5af7718610c819c4d368bb62655ee43a38011 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 20 Mar 2019 10:20:56 -0700 Subject: [PATCH 186/256] arm64: remove obsolete selection of MULTI_IRQ_HANDLER The arm64 config selects MULTI_IRQ_HANDLER, which was renamed to GENERIC_IRQ_MULTI_HANDLER by commit 4c301f9b6a94 ("ARM: Convert to GENERIC_IRQ_MULTI_HANDLER"). The 'new' option is already selected, so just remove the obsolete entry. Signed-off-by: Matthias Kaehlcke Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 1 - 1 file changed, 1 deletion(-) 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 From 89dc891792c2e046b030f87600109c22209da32e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 12 Mar 2019 18:33:46 +0100 Subject: [PATCH 187/256] irqchip/gic-v3-its: Fix comparison logic in lpi_range_cmp The lpi_range_list is supposed to be sorted in ascending order of ->base_id (at least if the range merging is to work), but the current comparison function returns a positive value if rb->base_id > ra->base_id, which means that list_sort() will put A after B in that case - and vice versa, of course. Fixes: 880cb3cddd16 (irqchip/gic-v3-its: Refactor LPI allocator) Cc: stable@vger.kernel.org (v4.19+) Signed-off-by: Rasmus Villemoes Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index fb7157188294..783810716015 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1476,7 +1476,7 @@ 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) From 0e83fc61eee62979260f6aeadd23ee8b615ee1a2 Mon Sep 17 00:00:00 2001 From: Luo Jiaxing Date: Wed, 20 Mar 2019 18:21:34 +0800 Subject: [PATCH 188/256] scsi: hisi_sas: Add softreset in hisi_sas_I_T_nexus_reset() We found out that for v2 hw, a SATA disk can not be written to after the system comes up. In commit ffb1c820b8b6 ("scsi: hisi_sas: remove the check of sas_dev status in hisi_sas_I_T_nexus_reset()"), we introduced a path where we may issue an internal abort for a SATA device, but without following it with a softreset. We need to always follow an internal abort with a software reset, as per HW programming flow, so add this. Fixes: ffb1c820b8b6 ("scsi: hisi_sas: remove the check of sas_dev status in hisi_sas_I_T_nexus_reset()") Signed-off-by: Luo Jiaxing Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/hisi_sas/hisi_sas_main.c | 6 ++++++ 1 file changed, 6 insertions(+) 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)) From 8a1b1718214cfd945fef14b3031e4e7262882a86 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:48 -0700 Subject: [PATCH 189/256] perf build: Check what binutils's 'disassembler()' signature to use Commit 003ca0fd2286 ("Refactor disassembler selection") in the binutils repo, which changed the disassembler() function signature, so we must use the feature test introduced in fb982666e380 ("tools/bpftool: fix bpftool build with bintutils >= 2.9") to deal with that. Committer testing: After adding the missing function call to test-all.c, and: FEATURE_CHECK_LDFLAGS-disassembler-four-args = -bfd -lopcodes And the fallbacks for cases where we need -liberty and sometimes -lz to tools/perf/Makefile.config, we get: $ make -C tools/perf O=/tmp/build/perf install-bin make: Entering directory '/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j8' parallel build Auto-detecting system features: ... dwarf: [ on ] ... dwarf_getlocations: [ on ] ... glibc: [ on ] ... gtk2: [ on ] ... libaudit: [ on ] ... libbfd: [ on ] ... libelf: [ on ] ... libnuma: [ on ] ... numa_num_possible_cpus: [ on ] ... libperl: [ on ] ... libpython: [ on ] ... libslang: [ on ] ... libcrypto: [ on ] ... libunwind: [ on ] ... libdw-dwarf-unwind: [ on ] ... zlib: [ on ] ... lzma: [ on ] ... get_cpuid: [ on ] ... bpf: [ on ] ... libaio: [ on ] ... disassembler-four-args: [ on ] CC /tmp/build/perf/jvmti/libjvmti.o CC /tmp/build/perf/builtin-bench.o $ $ The feature detection test-all.bin gets successfully built and linked: $ ls -la /tmp/build/perf/feature/test-all.bin -rwxrwxr-x. 1 acme acme 2680352 Mar 19 11:07 /tmp/build/perf/feature/test-all.bin $ nm /tmp/build/perf/feature/test-all.bin | grep -w disassembler 0000000000061f90 T disassembler $ Time to move on to the patches that make use of this disassembler() routine in binutils's libopcodes. Signed-off-by: Song Liu Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jakub Kicinski Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-13-songliubraving@fb.com [ split from a larger patch, added missing FEATURE_CHECK_LDFLAGS-disassembler-four-args ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 6 ++++-- tools/build/feature/test-all.c | 5 +++++ tools/perf/Makefile.config | 9 +++++++++ 3 files changed, 18 insertions(+), 2 deletions(-) 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/perf/Makefile.config b/tools/perf/Makefile.config index df4ad45599ca..fe3f97e342fa 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -227,6 +227,8 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt +FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes + CFLAGS += -fno-omit-frame-pointer CFLAGS += -ggdb3 CFLAGS += -funwind-tables @@ -725,11 +727,14 @@ else ifeq ($(feature-libbfd-liberty), 1) EXTLIBS += -lbfd -lopcodes -liberty + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl else ifeq ($(feature-libbfd-liberty-z), 1) 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) From 6987561c9e86eace45f2dbb0c564964a63f4150a Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:48 -0700 Subject: [PATCH 190/256] perf annotate: Enable annotation of BPF programs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In symbol__disassemble(), DSO_BINARY_TYPE__BPF_PROG_INFO dso calls into a new function symbol__disassemble_bpf(), where annotation line information is filled based on the bpf_prog_info and btf data saved in given perf_env. symbol__disassemble_bpf() uses binutils's libopcodes to disassemble bpf programs. Committer testing: After fixing this: - u64 *addrs = (u64 *)(info_linear->info.jited_ksyms); + u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms); Detected when crossbuilding to a 32-bit arch. And making all this dependent on HAVE_LIBBFD_SUPPORT and HAVE_LIBBPF_SUPPORT: 1) Have a BPF program running, one that has BTF info, etc, I used the tools/perf/examples/bpf/augmented_raw_syscalls.c put in place by 'perf trace'. # grep -B1 augmented_raw ~/.perfconfig [trace] add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c # # perf trace -e *mmsg dnf/6245 sendmmsg(20, 0x7f5485a88030, 2, MSG_NOSIGNAL) = 2 NetworkManager/10055 sendmmsg(22, 0x7f8126ad1bb0, 2, MSG_NOSIGNAL) = 2 2) Then do a 'perf record' system wide for a while: # perf record -a ^C[ perf record: Woken up 68 times to write data ] [ perf record: Captured and wrote 19.427 MB perf.data (366891 samples) ] # 3) Check that we captured BPF and BTF info in the perf.data file: # perf report --header-only | grep 'b[pt]f' # event : name = cycles:ppp, , id = { 294789, 294790, 294791, 294792, 294793, 294794, 294795, 294796 }, size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|CPU|PERIOD, read_format = ID, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, ksymbol = 1, bpf_event = 1 # bpf_prog_info of id 13 # bpf_prog_info of id 14 # bpf_prog_info of id 15 # bpf_prog_info of id 16 # bpf_prog_info of id 17 # bpf_prog_info of id 18 # bpf_prog_info of id 21 # bpf_prog_info of id 22 # bpf_prog_info of id 41 # bpf_prog_info of id 42 # btf info of id 2 # 4) Check which programs got recorded: # perf report | grep bpf_prog | head 0.16% exe bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter 0.14% exe bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit 0.08% fuse-overlayfs bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter 0.07% fuse-overlayfs bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit 0.01% clang-4.0 bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit 0.01% clang-4.0 bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter 0.00% clang bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit 0.00% runc bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter 0.00% clang bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter 0.00% sh bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit # This was with the default --sort order for 'perf report', which is: --sort comm,dso,symbol If we just look for the symbol, for instance: # perf report --sort symbol | grep bpf_prog | head 0.26% [k] bpf_prog_819967866022f1e1_sys_enter - - 0.24% [k] bpf_prog_c1bd85c092d6e4aa_sys_exit - - # or the DSO: # perf report --sort dso | grep bpf_prog | head 0.26% bpf_prog_819967866022f1e1_sys_enter 0.24% bpf_prog_c1bd85c092d6e4aa_sys_exit # We'll see the two BPF programs that augmented_raw_syscalls.o puts in place, one attached to the raw_syscalls:sys_enter and another to the raw_syscalls:sys_exit tracepoints, as expected. Now we can finally do, from the command line, annotation for one of those two symbols, with the original BPF program source coude intermixed with the disassembled JITed code: # perf annotate --stdio2 bpf_prog_819967866022f1e1_sys_enter Samples: 950 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 553756947, [percent: local period] bpf_prog_819967866022f1e1_sys_enter() bpf_prog_819967866022f1e1_sys_enter Percent int sys_enter(struct syscall_enter_args *args) 53.41 push %rbp 0.63 mov %rsp,%rbp 0.31 sub $0x170,%rsp 1.93 sub $0x28,%rbp 7.02 mov %rbx,0x0(%rbp) 3.20 mov %r13,0x8(%rbp) 1.07 mov %r14,0x10(%rbp) 0.61 mov %r15,0x18(%rbp) 0.11 xor %eax,%eax 1.29 mov %rax,0x20(%rbp) 0.11 mov %rdi,%rbx return bpf_get_current_pid_tgid(); 2.02 → callq *ffffffffda6776d9 2.76 mov %eax,-0x148(%rbp) mov %rbp,%rsi int sys_enter(struct syscall_enter_args *args) add $0xfffffffffffffeb8,%rsi return bpf_map_lookup_elem(pids, &pid) != NULL; movabs $0xffff975ac2607800,%rdi 1.26 → callq *ffffffffda6789e9 cmp $0x0,%rax 2.43 → je 0 add $0x38,%rax 0.21 xor %r13d,%r13d if (pid_filter__has(&pids_filtered, getpid())) 0.81 cmp $0x0,%rax → jne 0 mov %rbp,%rdi probe_read(&augmented_args.args, sizeof(augmented_args.args), args); 2.22 add $0xfffffffffffffeb8,%rdi 0.11 mov $0x40,%esi 0.32 mov %rbx,%rdx 2.74 → callq *ffffffffda658409 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr); 0.22 mov %rbp,%rsi 1.69 add $0xfffffffffffffec0,%rsi syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr); movabs $0xffff975bfcd36000,%rdi add $0xd0,%rdi 0.21 mov 0x0(%rsi),%eax 0.93 cmp $0x200,%rax → jae 0 0.10 shl $0x3,%rax 0.11 add %rdi,%rax 0.11 → jmp 0 xor %eax,%eax if (syscall == NULL || !syscall->enabled) 1.07 cmp $0x0,%rax → je 0 if (syscall == NULL || !syscall->enabled) 6.57 movzbq 0x0(%rax),%rdi if (syscall == NULL || !syscall->enabled) cmp $0x0,%rdi 0.95 → je 0 mov $0x40,%r8d switch (augmented_args.args.syscall_nr) { mov -0x140(%rbp),%rdi switch (augmented_args.args.syscall_nr) { cmp $0x2,%rdi → je 0 cmp $0x101,%rdi → je 0 cmp $0x15,%rdi → jne 0 case SYS_OPEN: filename_arg = (const void *)args->args[0]; mov 0x10(%rbx),%rdx → jmp 0 case SYS_OPENAT: filename_arg = (const void *)args->args[1]; mov 0x18(%rbx),%rdx if (filename_arg != NULL) { cmp $0x0,%rdx → je 0 xor %edi,%edi augmented_args.filename.reserved = 0; mov %edi,-0x104(%rbp) augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, mov %rbp,%rdi add $0xffffffffffffff00,%rdi augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, mov $0x100,%esi → callq *ffffffffda658499 mov $0x148,%r8d augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, mov %eax,-0x108(%rbp) augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, mov %rax,%rdi shl $0x20,%rdi shr $0x20,%rdi if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { cmp $0xff,%rdi → ja 0 len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; add $0x48,%rax len &= sizeof(augmented_args.filename.value) - 1; and $0xff,%rax mov %rax,%r8 mov %rbp,%rcx return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); add $0xfffffffffffffeb8,%rcx mov %rbx,%rdi movabs $0xffff975fbd72d800,%rsi mov $0xffffffff,%edx → callq *ffffffffda658ad9 mov %rax,%r13 } mov %r13,%rax 0.72 mov 0x0(%rbp),%rbx mov 0x8(%rbp),%r13 1.16 mov 0x10(%rbp),%r14 0.10 mov 0x18(%rbp),%r15 0.42 add $0x28,%rbp 0.54 leaveq 0.54 ← retq # Please see 'man perf-config' to see how to control what should be seen, via ~/.perfconfig [annotate] section, for instance, one can suppress the source code and see just the disassembly, etc. Alternatively, use the TUI bu just using 'perf annotate', press '/bpf_prog' to see the bpf symbols, press enter and do the interactive annotation, which allows for dumping to a file after selecting the the various output tunables, for instance, the above without source code intermixed, plus showing all the instruction offsets: # perf annotate bpf_prog_819967866022f1e1_sys_enter Then press: 's' to hide the source code + 'O' twice to show all instruction offsets, then 'P' to print to the bpf_prog_819967866022f1e1_sys_enter.annotation file, which will have: # cat bpf_prog_819967866022f1e1_sys_enter.annotation bpf_prog_819967866022f1e1_sys_enter() bpf_prog_819967866022f1e1_sys_enter Event: cycles:ppp 53.41 0: push %rbp 0.63 1: mov %rsp,%rbp 0.31 4: sub $0x170,%rsp 1.93 b: sub $0x28,%rbp 7.02 f: mov %rbx,0x0(%rbp) 3.20 13: mov %r13,0x8(%rbp) 1.07 17: mov %r14,0x10(%rbp) 0.61 1b: mov %r15,0x18(%rbp) 0.11 1f: xor %eax,%eax 1.29 21: mov %rax,0x20(%rbp) 0.11 25: mov %rdi,%rbx 2.02 28: → callq *ffffffffda6776d9 2.76 2d: mov %eax,-0x148(%rbp) 33: mov %rbp,%rsi 36: add $0xfffffffffffffeb8,%rsi 3d: movabs $0xffff975ac2607800,%rdi 1.26 47: → callq *ffffffffda6789e9 4c: cmp $0x0,%rax 2.43 50: → je 0 52: add $0x38,%rax 0.21 56: xor %r13d,%r13d 0.81 59: cmp $0x0,%rax 5d: → jne 0 63: mov %rbp,%rdi 2.22 66: add $0xfffffffffffffeb8,%rdi 0.11 6d: mov $0x40,%esi 0.32 72: mov %rbx,%rdx 2.74 75: → callq *ffffffffda658409 0.22 7a: mov %rbp,%rsi 1.69 7d: add $0xfffffffffffffec0,%rsi 84: movabs $0xffff975bfcd36000,%rdi 8e: add $0xd0,%rdi 0.21 95: mov 0x0(%rsi),%eax 0.93 98: cmp $0x200,%rax 9f: → jae 0 0.10 a1: shl $0x3,%rax 0.11 a5: add %rdi,%rax 0.11 a8: → jmp 0 aa: xor %eax,%eax 1.07 ac: cmp $0x0,%rax b0: → je 0 6.57 b6: movzbq 0x0(%rax),%rdi bb: cmp $0x0,%rdi 0.95 bf: → je 0 c5: mov $0x40,%r8d cb: mov -0x140(%rbp),%rdi d2: cmp $0x2,%rdi d6: → je 0 d8: cmp $0x101,%rdi df: → je 0 e1: cmp $0x15,%rdi e5: → jne 0 e7: mov 0x10(%rbx),%rdx eb: → jmp 0 ed: mov 0x18(%rbx),%rdx f1: cmp $0x0,%rdx f5: → je 0 f7: xor %edi,%edi f9: mov %edi,-0x104(%rbp) ff: mov %rbp,%rdi 102: add $0xffffffffffffff00,%rdi 109: mov $0x100,%esi 10e: → callq *ffffffffda658499 113: mov $0x148,%r8d 119: mov %eax,-0x108(%rbp) 11f: mov %rax,%rdi 122: shl $0x20,%rdi 126: shr $0x20,%rdi 12a: cmp $0xff,%rdi 131: → ja 0 133: add $0x48,%rax 137: and $0xff,%rax 13d: mov %rax,%r8 140: mov %rbp,%rcx 143: add $0xfffffffffffffeb8,%rcx 14a: mov %rbx,%rdi 14d: movabs $0xffff975fbd72d800,%rsi 157: mov $0xffffffff,%edx 15c: → callq *ffffffffda658ad9 161: mov %rax,%r13 164: mov %r13,%rax 0.72 167: mov 0x0(%rbp),%rbx 16b: mov 0x8(%rbp),%r13 1.16 16f: mov 0x10(%rbp),%r14 0.10 173: mov 0x18(%rbp),%r15 0.42 177: add $0x28,%rbp 0.54 17b: leaveq 0.54 17c: ← retq Another cool way to test all this is to symple use 'perf top' look for those symbols, go there and press enter, annotate it live :-) Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-13-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 163 +++++++++++++++++++++++++++++++++++- tools/perf/util/annotate.h | 1 + tools/perf/util/bpf-event.c | 2 +- 3 files changed, 164 insertions(+), 2 deletions(-) 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 #include #include +#include +#include +#include +#include #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 #include #include +#include /* 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 +#include + +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, + ¬es->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, ¬es->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/bpf-event.c b/tools/perf/util/bpf-event.c index 852e960692cb..7ffe7db59828 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -46,7 +46,7 @@ static int machine__process_bpf_event_load(struct machine *machine, info_linear = info_node->info_linear; for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) { - u64 *addrs = (u64 *)(info_linear->info.jited_ksyms); + u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms); u64 addr = addrs[i]; struct map *map; From 29ece8b4354f8c5eaee798a3d8a1b356efee426f Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Mon, 18 Mar 2019 22:44:41 +0800 Subject: [PATCH 191/256] block: add BLK_MQ_POLL_CLASSIC for hybrid poll and return EINVAL for unexpected value For q->poll_nsec == -1, means doing classic poll, not hybrid poll. We introduce a new flag BLK_MQ_POLL_CLASSIC to replace -1, which may make code much easier to read. Additionally, since val is an int obtained with kstrtoint(), val can be a negative value other than -1, so return -EINVAL for that case. Thanks to Damien Le Moal for some good suggestion. Reviewed-by: Damien Le Moal Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 ++-- block/blk-sysfs.c | 12 +++++++----- include/linux/blkdev.h | 3 +++ 3 files changed, 12 insertions(+), 7 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index ea01c23b58a3..76a3f78c566a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2856,7 +2856,7 @@ 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); @@ -3391,7 +3391,7 @@ 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-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) - val = -1; + if (q->poll_nsec == BLK_MQ_POLL_CLASSIC) + 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) - q->poll_nsec = -1; - else + if (val == BLK_MQ_POLL_CLASSIC) + q->poll_nsec = BLK_MQ_POLL_CLASSIC; + else if (val >= 0) q->poll_nsec = val * 1000; + else + return -EINVAL; return count; } 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. From e6c987120e24cb913cb7bd4e675129a30fa49e0d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 20 Mar 2019 13:14:37 -0700 Subject: [PATCH 192/256] block: Unexport blk_mq_add_to_requeue_list() This function is not used outside the block layer core. Hence unexport it. Cc: Christoph Hellwig Cc: Ming Lei Signed-off-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-mq.c | 1 - block/blk-mq.h | 2 ++ include/linux/blk-mq.h | 2 -- 3 files changed, 2 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 76a3f78c566a..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) { 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/include/linux/blk-mq.h b/include/linux/blk-mq.h index 35359697318b..cb2aa7ecafff 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -299,8 +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); From 373e915cd8e84544609eced57a44fbc084f8d60f Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 20 Mar 2019 13:15:01 -0700 Subject: [PATCH 193/256] blk-iolatency: #include "blk.h" This patch avoids that the following warning is reported when building with W=1: block/blk-iolatency.c:734:5: warning: no previous prototype for 'blk_iolatency_init' [-Wmissing-prototypes] Cc: Josef Bacik Fixes: d70675121546 ("block: introduce blk-iolatency io controller") # v4.19 Signed-off-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-iolatency.c | 1 + 1 file changed, 1 insertion(+) 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 #include "blk-rq-qos.h" #include "blk-stat.h" +#include "blk.h" #define DEFAULT_SCALE_COOKIE 1000000U From 537d71b3f774c3e825540ab626bad6c0ed2b5ff7 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 20 Mar 2019 13:18:45 -0700 Subject: [PATCH 194/256] blkcg: Fix kernel-doc warnings Avoid that the following warnings are reported when building with W=1: block/blk-cgroup.c:1755: warning: Function parameter or member 'q' not described in 'blkcg_schedule_throttle' block/blk-cgroup.c:1755: warning: Function parameter or member 'use_memdelay' not described in 'blkcg_schedule_throttle' block/blk-cgroup.c:1779: warning: Function parameter or member 'blkg' not described in 'blkcg_add_delay' block/blk-cgroup.c:1779: warning: Function parameter or member 'now' not described in 'blkcg_add_delay' block/blk-cgroup.c:1779: warning: Function parameter or member 'delta' not described in 'blkcg_add_delay' Signed-off-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) 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 - * @use_memdelay - do we charge this to memory delay for PSI + * @q: the request queue IO was submitted on + * @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 - * @delta - how many nanoseconds of delay to add + * @blkg: blkg of interest + * @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. From 7205981e045e752ccf96cf6ddd703a98c59d4339 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 13:41:50 -0500 Subject: [PATCH 195/256] scsi: ibmvscsi: Protect ibmvscsi_head from concurrent modificaiton For each ibmvscsi host created during a probe or destroyed during a remove we either add or remove that host to/from the global ibmvscsi_head list. This runs the risk of concurrent modification. This patch adds a simple spinlock around the list modification calls to prevent concurrent updates as is done similarly in the ibmvfc driver and ipr driver. Fixes: 32d6e4b6e4ea ("scsi: ibmvscsi: add vscsi hosts to global list_head") Cc: # v4.10+ Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvscsi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 1135e74646e2..2b22969f3f63 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: @@ -2292,7 +2295,9 @@ 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); + spin_lock(&ibmvscsi_driver_lock); list_del(&hostdata->host_list); + spin_unlock(&ibmvscsi_driver_lock); unmap_persist_bufs(hostdata); release_event_pool(&hostdata->pool, hostdata); ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, From 7f5203c13ba8a7b7f9f6ecfe5a4d5567188d7835 Mon Sep 17 00:00:00 2001 From: Tyrel Datwyler Date: Wed, 20 Mar 2019 13:41:51 -0500 Subject: [PATCH 196/256] scsi: ibmvscsi: Fix empty event pool access during host removal The event pool used for queueing commands is destroyed fairly early in the ibmvscsi_remove() code path. Since, this happens prior to the call so scsi_remove_host() it is possible for further calls to queuecommand to be processed which manifest as a panic due to a NULL pointer dereference as seen here: PANIC: "Unable to handle kernel paging request for data at address 0x00000000" Context process backtrace: DSISR: 0000000042000000 ????Syscall Result: 0000000000000000 4 [c000000002cb3820] memcpy_power7 at c000000000064204 [Link Register] [c000000002cb3820] ibmvscsi_send_srp_event at d000000003ed14a4 5 [c000000002cb3920] ibmvscsi_send_srp_event at d000000003ed14a4 [ibmvscsi] ?(unreliable) 6 [c000000002cb39c0] ibmvscsi_queuecommand at d000000003ed2388 [ibmvscsi] 7 [c000000002cb3a70] scsi_dispatch_cmd at d00000000395c2d8 [scsi_mod] 8 [c000000002cb3af0] scsi_request_fn at d00000000395ef88 [scsi_mod] 9 [c000000002cb3be0] __blk_run_queue at c000000000429860 10 [c000000002cb3c10] blk_delay_work at c00000000042a0ec 11 [c000000002cb3c40] process_one_work at c0000000000dac30 12 [c000000002cb3cd0] worker_thread at c0000000000db110 13 [c000000002cb3d80] kthread at c0000000000e3378 14 [c000000002cb3e30] ret_from_kernel_thread at c00000000000982c The kernel buffer log is overfilled with this log: [11261.952732] ibmvscsi: found no event struct in pool! This patch reorders the operations during host teardown. Start by calling the SRP transport and Scsi_Host remove functions to flush any outstanding work and set the host offline. LLDD teardown follows including destruction of the event pool, freeing the Command Response Queue (CRQ), and unmapping any persistent buffers. The event pool destruction is protected by the scsi_host lock, and the pool is purged prior of any requests for which we never received a response. Finally, move the removal of the scsi host from our global list to the end so that the host is easily locatable for debugging purposes during teardown. Cc: # v2.6.12+ Signed-off-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi/ibmvscsi.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 2b22969f3f63..8cec5230fe31 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2295,17 +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); - spin_lock(&ibmvscsi_driver_lock); - list_del(&hostdata->host_list); - spin_unlock(&ibmvscsi_driver_lock); - unmap_persist_bufs(hostdata); + unsigned long flags; + + 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); - scsi_remove_host(hostdata->host); + unmap_persist_bufs(hostdata); + + spin_lock(&ibmvscsi_driver_lock); + list_del(&hostdata->host_list); + spin_unlock(&ibmvscsi_driver_lock); + scsi_host_put(hostdata->host); return 0; From 6a3b45ada960ac475ec2b4103d43e57943b2b8d3 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Tue, 19 Mar 2019 14:05:11 +0100 Subject: [PATCH 197/256] drm/exynos/mixer: fix MIXER shadow registry synchronisation code MIXER on Exynos5 SoCs uses different synchronisation method than Exynos4 to update internal state (shadow registers). Apparently the driver implements it incorrectly. The rule should be as follows: - do not request updating registers until previous request was finished, ie. MXR_CFG_LAYER_UPDATE_COUNT must be 0. - before setting registers synchronisation on VSYNC should be turned off, ie. MXR_STATUS_SYNC_ENABLE should be reset, - after finishing MXR_STATUS_SYNC_ENABLE should be set again. The patch hopefully implements it correctly. Below sample kernel log from page fault caused by the bug: [ 25.670038] exynos-sysmmu 14650000.sysmmu: 14450000.mixer: PAGE FAULT occurred at 0x2247b800 [ 25.677888] ------------[ cut here ]------------ [ 25.682164] kernel BUG at ../drivers/iommu/exynos-iommu.c:450! [ 25.687971] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM [ 25.693778] Modules linked in: [ 25.696816] CPU: 5 PID: 1553 Comm: fb-release_test Not tainted 5.0.0-rc7-01157-g5f86b1566bdd #136 [ 25.705646] Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [ 25.711710] PC is at exynos_sysmmu_irq+0x1c0/0x264 [ 25.716470] LR is at lock_is_held_type+0x44/0x64 v2: added missing MXR_CFG_LAYER_UPDATE bit setting in mixer_enable_sync Reported-by: Marian Mihailescu Signed-off-by: Andrzej Hajda Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_mixer.c | 110 +++++++++++++++----------- 1 file changed, 66 insertions(+), 44 deletions(-) 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 +#include #include #include #include @@ -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 */ - mixer_reg_writemask(ctx, MXR_STATUS, enable ? - MXR_STATUS_SYNC_ENABLE : 0, MXR_STATUS_SYNC_ENABLE); + u32 base, shadow; + 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_SHADOW_UPDATE_ENABLE : 0); + vp_reg_write(ctx, VP_SHADOW_UPDATE, VP_SHADOW_UPDATE_ENABLE); } 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_VP_ENABLED, &ctx->flags) && - vp_reg_read(ctx, VP_SHADOW_UPDATE)) - 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; - } + if (test_bit(MXR_BIT_INTERLACE, &ctx->flags) + && !mixer_is_synced(ctx)) + 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); } From 667a8f73753908c4d0171e52b71774f9be5d6713 Mon Sep 17 00:00:00 2001 From: Jian-Hong Pan Date: Fri, 15 Mar 2019 17:51:09 +0800 Subject: [PATCH 198/256] ALSA: hda/realtek: Enable headset MIC of Acer AIO with ALC286 Some Acer AIO desktops like Veriton Z6860G, Z4860G and Z4660G cannot record sound from headset MIC. This patch adds the ALC286_FIXUP_ACER_AIO_HEADSET_MIC quirk to fix this issue. Fixes: 9f8aefed9623 ("ALSA: hda/realtek: Fix mic issue on Acer AIO Veriton Z4660G") Fixes: b72f936f6b32 ("ALSA: hda/realtek: Fix mic issue on Acer AIO Veriton Z4860G/Z6860G") Signed-off-by: Jian-Hong Pan Reviewed-by: Kailang Yang Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) 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, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", 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_HEADSET_MIC), + 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), From 2b77158ffa92b820a0c5da9a3c6ead7aa069c71c Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sun, 17 Mar 2019 12:58:25 +0300 Subject: [PATCH 199/256] mmc: mxcmmc: "Revert mmc: mxcmmc: handle highmem pages" This reverts commit b189e7589f6d3411e85c6b7ae6eef158f08f388f. Unable to handle kernel paging request at virtual address c8358000 pgd = efa405c3 [c8358000] *pgd=00000000 Internal error: Oops: 805 [#1] PREEMPT ARM CPU: 0 PID: 711 Comm: kworker/0:2 Not tainted 4.20.0+ #30 Hardware name: Freescale i.MX27 (Device Tree Support) Workqueue: events mxcmci_datawork PC is at mxcmci_datawork+0xbc/0x2ac LR is at mxcmci_datawork+0xac/0x2ac pc : [] lr : [] psr: 60000013 sp : c6c93f08 ip : 24004180 fp : 00000008 r10: c8358000 r9 : c78b3e24 r8 : c6c92000 r7 : 00000000 r6 : c7bb8680 r5 : c7bb86d4 r4 : c78b3de0 r3 : 00002502 r2 : c090b2e0 r1 : 00000880 r0 : 00000000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 0005317f Table: a68a8000 DAC: 00000055 Process kworker/0:2 (pid: 711, stack limit = 0x389543bc) Stack: (0xc6c93f08 to 0xc6c94000) 3f00: c7bb86d4 00000000 00000000 c6cbfde0 c7bb86d4 c7ee4200 3f20: 00000000 c0907ea8 00000000 c7bb86d8 c0907ea8 c012077c c6cbfde0 c7bb86d4 3f40: c6cbfde0 c6c92000 c6cbfdf4 c09280ba c0907ea8 c090b2e0 c0907ebc c0120c18 3f60: c6cbfde0 00000000 00000000 c6cbb580 c7ba7c40 c7837edc c6cbb598 00000000 3f80: c6cbfde0 c01208f8 00000000 c01254fc c7ba7c40 c0125400 00000000 00000000 3fa0: 00000000 00000000 00000000 c01010d0 00000000 00000000 00000000 00000000 3fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 3fe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000 [] (mxcmci_datawork) from [] (process_one_work+0x1f0/0x338) [] (process_one_work) from [] (worker_thread+0x320/0x474) [] (worker_thread) from [] (kthread+0xfc/0x118) [] (kthread) from [] (ret_from_fork+0x14/0x24) Exception stack(0xc6c93fb0 to 0xc6c93ff8) 3fa0: 00000000 00000000 00000000 00000000 3fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 3fe0: 00000000 00000000 00000000 00000000 00000013 00000000 Code: e3500000 1a000059 e5153050 e5933038 (e48a3004) ---[ end trace 54ca629b75f0e737 ]--- note: kworker/0:2[711] exited with preempt_count 1 Signed-off-by: Alexander Shiyan Fixes: b189e7589f6d ("mmc: mxcmmc: handle highmem pages") Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/mxcmmc.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) 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) { - void *buf = kmap_atomic(sg_page(sg) + sg->offset); - buffer_swap32(buf, sg->length); - kunmap_atomic(buf); - } + for_each_sg(data->sg, sg, data->sg_len, i) + buffer_swap32(sg_virt(sg), sg->length); } #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, buf, sg->length); - kunmap(buf); + stat = mxcmci_pull(host, sg_virt(sg), sg->length); 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, buf, sg->length); - kunmap(buf); + stat = mxcmci_push(host, sg_virt(sg), sg->length); if (stat) return stat; host->datasize += sg->length; From 92edf8df0ff2ae86cc632eeca0e651fd8431d40d Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 21 Mar 2019 15:24:33 +1100 Subject: [PATCH 200/256] powerpc/security: Fix spectre_v2 reporting When I updated the spectre_v2 reporting to handle software count cache flush I got the logic wrong when there's no software count cache enabled at all. The result is that on systems with the software count cache flush disabled we print: Mitigation: Indirect branch cache disabled, Software count cache flush Which correctly indicates that the count cache is disabled, but incorrectly says the software count cache flush is enabled. The root of the problem is that we are trying to handle all combinations of options. But we know now that we only expect to see the software count cache flush enabled if the other options are false. So split the two cases, which simplifies the logic and fixes the bug. We were also missing a space before "(hardware accelerated)". The result is we see one of: Mitigation: Indirect branch serialisation (kernel only) Mitigation: Indirect branch cache disabled Mitigation: Software count cache flush Mitigation: Software count cache flush (hardware accelerated) Fixes: ee13cb249fab ("powerpc/64s: Add support for software count cache flush") Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Michael Ellerman Reviewed-by: Michael Neuling Reviewed-by: Diana Craciun Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/security.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-) 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) { - bool comma = false; + if (bcs || ccd) { seq_buf_printf(&s, "Mitigation: "); - if (bcs) { + if (bcs) seq_buf_printf(&s, "Indirect branch serialisation (kernel only)"); - comma = true; - } - if (ccd) { - if (comma) - seq_buf_printf(&s, ", "); - seq_buf_printf(&s, "Indirect branch cache disabled"); - comma = true; - } - - if (comma) + if (bcs && ccd) 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 { From 031d2ccc16775c9531800979069e141fbedeb2f7 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 21 Mar 2019 11:45:44 +0530 Subject: [PATCH 201/256] mmc: sdhci-omap: Set caps2 to indicate no physical write protect pin After commit 6d5cd068ee59fba ("mmc: sdhci: use WP GPIO in sdhci_check_ro()") and commit 39ee32ce486756f ("mmc: sdhci-omap: drop ->get_ro() implementation"), sdhci-omap relied on SDHCI_PRESENT_STATE to check if the card is read-only, if wp-gpios is not populated in device tree. However SDHCI_PRESENT_STATE in sdhci-omap does not have correct read-only state. sdhci-omap can be used by platforms with both micro SD slot and standard SD slot with physical write protect pin (using GPIO). Set caps2 to MMC_CAP2_NO_WRITE_PROTECT based on if wp-gpios property is populated or not. This fix is required since existing device-tree node doesn't have "disable-wp" property and to preserve old-dt compatibility. Fixes: 6d5cd068ee59fba ("mmc: sdhci: use WP GPIO in sdhci_check_ro()") Fixes: 39ee32ce486756f ("mmc: sdhci-omap: drop ->get_ro() implementation") Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-omap.c | 3 +++ 1 file changed, 3 insertions(+) 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); From 5ea47691bd99e1100707ec63364aff72324e2af4 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Wed, 20 Mar 2019 14:36:53 +0800 Subject: [PATCH 202/256] mmc: alcor: fix DMA reads Setting max_blk_count to 1 here was causing the mmc block layer to always use the MMC_READ_SINGLE_BLOCK command here, which the driver does not DMA-accelerate. Drop the max_blk_ settings here. The mmc host defaults suffice, along with the max_segs and max_seg_size settings, which I have now documented in more detail. Now each MMC command reads 4 512-byte blocks, using DMA instead of PIO. On my SD card, this increases read performance (measured with dd) from 167kb/sec to 4.6mb/sec. Link: http://lkml.kernel.org/r/CAD8Lp47L5T3jnAjBiPs1cQ+yFA3L6LJtgFvMETnBrY63-Zdi2g@mail.gmail.com Signed-off-by: Daniel Drake Reviewed-by: Oleksij Rempel Fixes: c5413ad815a6 ("mmc: add new Alcor Micro Cardreader SD/MMC driver") Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/alcor.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) 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_blk_size = mmc->max_seg_size; - mmc->max_blk_count = mmc->max_segs; - - mmc->max_req_size = mmc->max_seg_size * mmc->max_segs; + mmc->max_req_size = mmc->max_seg_size; } static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) From c9a9497ccef205ed4ed2e247011382627876d831 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 19 Mar 2019 11:12:59 +0100 Subject: [PATCH 203/256] mmc: renesas_sdhi: limit block count to 16 bit for old revisions R-Car Gen2 has two different SDHI incarnations in the same chip. The older one does not support the recently introduced 32 bit register access to the block count register. Make sure we use this feature only after the first known version. Thanks to the Renesas Testing team for this bug report! Fixes: 5603731a15ef ("mmc: tmio: fix access width of Block Count Register") Reported-by: Yoshihiro Shimoda Signed-off-by: Wolfram Sang Reviewed-by: Simon Horman Tested-by: Phong Hoang Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/renesas_sdhi_core.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) 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 */ From 551417af91b163bd697eb50b3601adae2177c28a Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 18 Mar 2019 14:51:23 +0800 Subject: [PATCH 204/256] genirq: Fix typo in comment of IRQD_MOVE_PCNTXT Signed-off-by: Peter Xu Signed-off-by: Thomas Gleixner Cc: Marc Zyngier Cc: Dou Liyang Cc: Julien Thierry Link: https://lkml.kernel.org/r/20190318065123.11862-1-peterx@redhat.com --- include/linux/irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 From 82efcab3b9f3ef59e9713237c6e3c05c3a95c1ae Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 11 Mar 2019 16:02:55 -0700 Subject: [PATCH 205/256] workqueue: Only unregister a registered lockdep key The recent change to prevent use after free and a memory leak introduced an unconditional call to wq_unregister_lockdep() in the error handling path. If the lockdep key had not been registered yet, then the lockdep core emits a warning. Only call wq_unregister_lockdep() if wq_register_lockdep() has been called first. Fixes: 009bb421b6ce ("workqueue, lockdep: Fix an alloc_workqueue() error path") Reported-by: syzbot+be0c198232f86389c3dd@syzkaller.appspotmail.com Signed-off-by: Bart Van Assche Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Tejun Heo Cc: Qian Cai Link: https://lkml.kernel.org/r/20190311230255.176081-1-bvanassche@acm.org --- kernel/workqueue.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) 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; From dc3173c7067ebbac44ed4a5c3636dc0ff27f981b Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 20 Mar 2019 22:22:20 +0800 Subject: [PATCH 206/256] irqchip/brcmstb-l2: Make two init functions static Fix sparse warnings: drivers/irqchip/irq-brcmstb-l2.c:278:12: warning: symbol 'brcmstb_l2_edge_intc_of_init' was not declared. Should it be static? drivers/irqchip/irq-brcmstb-l2.c:285:12: warning: symbol 'brcmstb_l2_lvl_intc_of_init' was not declared. Should it be static? Signed-off-by: YueHaibing Reviewed-by: Florian Fainelli Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-brcmstb-l2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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); From 096048cb120d5318b3a9a7c1e062a4b11c0e80ab Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 20 Mar 2019 21:40:27 +0800 Subject: [PATCH 207/256] irqchip/mmp: Make mmp_irq_domain_ops static Fix sparse warning: drivers/irqchip/irq-mmp.c:182:29: warning: symbol 'mmp_irq_domain_ops' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-mmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 25f32e1d7764..85d1c4d49572 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -176,7 +176,7 @@ 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, }; From 24105bf4d10485143f8e26337cda8bcb7f6e6da5 Mon Sep 17 00:00:00 2001 From: Fabrizio Castro Date: Tue, 19 Mar 2019 11:02:01 +0000 Subject: [PATCH 208/256] dt-bindings: irqchip: renesas-irqc: Document r8a774c0 support Document RZ/G2E (R8A774C0) SoC bindings. Signed-off-by: Fabrizio Castro Reviewed-by: Geert Uytterhoeven Reviewed-by: Simon Horman Reviewed-by: Rob Herring Signed-off-by: Marc Zyngier --- .../devicetree/bindings/interrupt-controller/renesas,irqc.txt | 1 + 1 file changed, 1 insertion(+) 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) From 0dda09666f50eae9c5b794dd89b1fd8a8d89d714 Mon Sep 17 00:00:00 2001 From: Fabien Dessenne Date: Thu, 7 Mar 2019 19:40:35 +0100 Subject: [PATCH 209/256] irqchip/stm32: Don't clear rising/falling config registers at init Falling and rising configuration and status registers are not banked. As they are shared with M4 co-processor, they should not be cleared at probe time, else M4 co-processor configuration will be lost. Fixes: f9fc1745501e ("irqchip/stm32: Add host and driver data structures") Signed-off-by: Loic Pallardy Signed-off-by: Fabien Dessenne Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-stm32-exti.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 6edfd4bfa169..dab37fbfab82 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -735,11 +735,6 @@ stm32_exti_chip_data *stm32_exti_chip_init(struct stm32_exti_host_data *h_data, */ 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); From 6a77623d78b307b34d4cf7886da6a907689bf388 Mon Sep 17 00:00:00 2001 From: Fabien Dessenne Date: Thu, 7 Mar 2019 19:40:36 +0100 Subject: [PATCH 210/256] irqchip/stm32: Don't set rising configuration registers at init The rising configuration status register (rtsr) is not banked. As it is shared with the co-processor, it should not be written at probe time, else the co-processor configuration will be lost. Fixes: f9fc1745501e ("irqchip/stm32: Add host and driver data structures") Signed-off-by: Fabien Dessenne Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-stm32-exti.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index dab37fbfab82..6b19bffbad78 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]; @@ -725,10 +724,6 @@ 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 From fca269f201a8d9985c0a31fb60b15d4eb57cef80 Mon Sep 17 00:00:00 2001 From: Jianguo Chen Date: Wed, 20 Mar 2019 18:54:21 +0000 Subject: [PATCH 211/256] irqchip/mbigen: Don't clear eventid when freeing an MSI mbigen_write_msg clears eventid bits of a mbigen register when free a interrupt, because msi_domain_deactivate memset struct msg to zero. Then multiple mbigen pins with zero eventid will report the same interrupt number. The eventid clear call trace: free_irq __free_irq irq_shutdown irq_domain_deactivate_irq __irq_domain_deactivate_irq __irq_domain_deactivate_irq msi_domain_deactivate platform_msi_write_msg mbigen_write_msg Signed-off-by: Jianguo Chen [maz: massaged subject] Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-mbigen.c | 3 +++ 1 file changed, 3 insertions(+) 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); From a9c640ac96e19b3966357ec9bb586edd2e1e74de Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 14 Mar 2019 15:14:57 -0700 Subject: [PATCH 212/256] x86/boot: Restrict header scope to make Clang happy The inclusion of was causing issue as the definition of __arch_hweight64 from arch/x86/include/asm/arch_hweight.h eventually gets included. The definition is problematic when compiled with -m16 (all code in arch/x86/boot/ is) as the "D" inline assembly constraint is rejected by both compilers when passed an argument of type long long (regardless of signedness, anything smaller is fine). Because GCC performs inlining before semantic analysis, and __arch_hweight64 is dead in this translation unit, GCC does not report any issues at compile time. Clang does the semantic analysis in the front end, before inlining (run in the middle) can determine the code is dead. I consider this another case of PR33587, which I think we can do more work to solve. It turns out that arch/x86/boot/string.c doesn't actually need linux/kernel.h, simply linux/limits.h and linux/compiler.h. Suggested-by: Stephen Rothwell Signed-off-by: Nick Desaulniers Signed-off-by: Thomas Gleixner Tested-by: Nathan Chancellor Reviewed-by: Nathan Chancellor Cc: bp@alien8.de Cc: niravd@google.com Cc: "H. Peter Anvin" Cc: Chao Fan Cc: Uros Bizjak Link: https://bugs.llvm.org/show_bug.cgi?id=33587 Link: https://github.com/ClangBuiltLinux/linux/issues/347 Link: https://lkml.kernel.org/r/20190314221458.83047-1-ndesaulniers@google.com --- arch/x86/boot/string.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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 -#include +#include #include +#include #include #include "ctype.h" #include "string.h" From 725e29db8cb9058976559bc3239c97ef7db40eea Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 14 Mar 2019 23:08:38 +0000 Subject: [PATCH 213/256] x86/lib: Fix indentation issue, remove extra tab The increment of buff is indented one level too deeply, clean this up by removing a tab. Signed-off-by: Colin Ian King Signed-off-by: Thomas Gleixner Cc: Borislav Petkov Cc: "H . Peter Anvin" Cc: kernel-janitors@vger.kernel.org Link: https://lkml.kernel.org/r/20190314230838.18256-1-colin.king@canonical.com --- arch/x86/lib/csum-partial_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From 2e84f116afca3719c9d0a1a78b47b48f75fd5724 Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Mon, 18 Mar 2019 21:19:56 -0500 Subject: [PATCH 214/256] x86/hpet: Prevent potential NULL pointer dereference hpet_virt_address may be NULL when ioremap_nocache fail, but the code lacks a check. Add a check to prevent NULL pointer dereference. Signed-off-by: Aditya Pakki Signed-off-by: Thomas Gleixner Cc: kjlu@umn.edu Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Kees Cook Cc: Joe Perches Cc: Nicolai Stange Cc: Roland Dreier Link: https://lkml.kernel.org/r/20190319021958.17275-1-pakki001@umn.edu --- arch/x86/kernel/hpet.c | 2 ++ 1 file changed, 2 insertions(+) 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: From 534c89c22e26b183d838294f0937ee092c82ad3a Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Thu, 14 Mar 2019 00:46:51 -0500 Subject: [PATCH 215/256] x86/hyperv: Prevent potential NULL pointer dereference The page allocation in hv_cpu_init() can fail, but the code does not have a check for that. Add a check and return -ENOMEM when the allocation fails. [ tglx: Massaged changelog ] Signed-off-by: Kangjie Lu Signed-off-by: Thomas Gleixner Reviewed-by: Mukesh Ojha Acked-by: "K. Y. Srinivasan" Cc: pakki001@umn.edu Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Sasha Levin Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: linux-hyperv@vger.kernel.org Link: https://lkml.kernel.org/r/20190314054651.1315-1-kjlu@umn.edu --- arch/x86/hyperv/hv_init.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) 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); From 9bd681251b7c1db1c6cfe29a72c5ea1b1c0ba022 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 13 Mar 2019 12:00:22 +0100 Subject: [PATCH 216/256] x86/microcode: Announce reload operation's completion By popular demand, issue a single line to dmesg after the reload operation completes to let the user know that a reload has at least been attempted. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20190313110022.8229-1-bp@alien8.de --- arch/x86/kernel/cpu/microcode/core.c | 2 ++ 1 file changed, 2 insertions(+) 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; } From 18fb053f9b827bd98cfc64f2a35df8ab19745a1d Mon Sep 17 00:00:00 2001 From: Matthew Whitehead Date: Thu, 14 Mar 2019 16:46:00 -0400 Subject: [PATCH 217/256] x86/cpu/cyrix: Use correct macros for Cyrix calls on Geode processors There are comments in processor-cyrix.h advising you to _not_ make calls using the deprecated macros in this style: setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80); This is because it expands the macro into a non-functioning calling sequence. The calling order must be: outb(CX86_CCR2, 0x22); inb(0x23); From the comments: * 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); The new macros fix this problem, so use them instead. Tested on an actual Geode processor. Signed-off-by: Matthew Whitehead Signed-off-by: Thomas Gleixner Cc: luto@kernel.org Link: https://lkml.kernel.org/r/1552596361-8967-2-git-send-email-tedheadster@gmail.com --- arch/x86/kernel/cpu/cyrix.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) 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); From 0f4d3aa761b71cd6984330baca1e18bf0590e441 Mon Sep 17 00:00:00 2001 From: Matthew Whitehead Date: Thu, 14 Mar 2019 16:46:01 -0400 Subject: [PATCH 218/256] x86/cpu/cyrix: Remove {get,set}Cx86_old macros used for Cyrix processors The getCx86_old() and setCx86_old() macros have been replaced with correctly working getCx86() and setCx86(), so remove these unused macros. Signed-off-by: Matthew Whitehead Signed-off-by: Thomas Gleixner Cc: luto@kernel.org Link: https://lkml.kernel.org/r/1552596361-8967-3-git-send-email-tedheadster@gmail.com --- arch/x86/include/asm/processor-cyrix.h | 21 --------------------- 1 file changed, 21 deletions(-) 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) - From 657ee5531903339b06697581532ed32d4762526e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:50 -0700 Subject: [PATCH 219/256] perf evlist: Introduce side band thread This patch introduces side band thread that captures extended information for events like PERF_RECORD_BPF_EVENT. This new thread uses its own evlist that uses ring buffer with very low watermark for lower latency. To use side band thread, we need to: 1. add side band event(s) by calling perf_evlist__add_sb_event(); 2. calls perf_evlist__start_sb_thread(); 3. at the end of perf run, perf_evlist__stop_sb_thread(). In the next patch, we use this thread to handle PERF_RECORD_BPF_EVENT. Committer notes: Add fix by Jiri Olsa for when te sb_tread can't get started and then at the end the stop_sb_thread() segfaults when joining the (non-existing) thread. That can happen when running 'perf top' or 'perf record' as a normal user, for instance. Further checks need to be done on top of this to more graciously handle these possible failure scenarios. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-15-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 9 +++ tools/perf/builtin-top.c | 9 +++ tools/perf/util/evlist.c | 119 ++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 12 ++++ tools/perf/util/evsel.h | 6 ++ 5 files changed, 155 insertions(+) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e79faccd7842..6f645fd72fed 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1137,6 +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); @@ -1237,6 +1238,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } + 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; @@ -1487,6 +1493,9 @@ out_child: out_delete_session: perf_session__delete(session); + + if (!opts->no_bpf_event) + perf_evlist__stop_sb_thread(sb_evlist); return status; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c2ea22c4ea67..3ce8a8db6c1d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1501,6 +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 []", NULL @@ -1636,8 +1637,16 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } + 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); 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 #include @@ -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.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 { From d56354dc49091e33d9ffca732ac913ed2df70537 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 11 Mar 2019 22:30:51 -0700 Subject: [PATCH 220/256] perf tools: Save bpf_prog_info and BTF of new BPF programs To fully annotate BPF programs with source code mapping, 4 different information are needed: 1) PERF_RECORD_KSYMBOL 2) PERF_RECORD_BPF_EVENT 3) bpf_prog_info 4) btf This patch handles 3) and 4) for BPF programs loaded after 'perf record|top'. For timely process of these information, a dedicated event is added to the side band evlist. When PERF_RECORD_BPF_EVENT is received via the side band event, the polling thread gathers 3) and 4) vis sys_bpf and store them in perf_env. This information is saved to perf.data at the end of 'perf record'. Committer testing: The 'wakeup_watermark' member in 'struct perf_event_attr' is inside a unnamed union, so can't be used in a struct designated initialization with older gccs, get it out of that, isolating as 'attr.wakeup_watermark = 1;' to work with all gcc versions. We also need to add '--no-bpf-event' to the 'perf record' perf_event_attr tests in 'perf test', as the way that that test goes is to intercept the events being setup and looking if they match the fields described in the control files, since now it finds first the side band event used to catch the PERF_RECORD_BPF_EVENT, they all fail. With these issues fixed: Same scenario as for testing BPF programs loaded before 'perf record' or 'perf top' starts, only start the BPF programs after 'perf record|top', so that its information get collected by the sideband threads, the rest works as for the programs loaded before start monitoring. Add missing 'inline' to the bpf_event__add_sb_event() when HAVE_LIBBPF_SUPPORT is not defined, fixing the build in systems without binutils devel files installed. Signed-off-by: Song Liu Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190312053051.2690567-16-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 3 + tools/perf/builtin-top.c | 3 + tools/perf/tests/attr/test-record-C0 | 2 +- tools/perf/tests/attr/test-record-basic | 2 +- tools/perf/tests/attr/test-record-branch-any | 2 +- .../tests/attr/test-record-branch-filter-any | 2 +- .../attr/test-record-branch-filter-any_call | 2 +- .../attr/test-record-branch-filter-any_ret | 2 +- .../tests/attr/test-record-branch-filter-hv | 2 +- .../attr/test-record-branch-filter-ind_call | 2 +- .../tests/attr/test-record-branch-filter-k | 2 +- .../tests/attr/test-record-branch-filter-u | 2 +- tools/perf/tests/attr/test-record-count | 2 +- tools/perf/tests/attr/test-record-data | 2 +- tools/perf/tests/attr/test-record-freq | 2 +- .../perf/tests/attr/test-record-graph-default | 2 +- tools/perf/tests/attr/test-record-graph-dwarf | 2 +- tools/perf/tests/attr/test-record-graph-fp | 2 +- tools/perf/tests/attr/test-record-group | 2 +- .../tests/attr/test-record-group-sampling | 2 +- tools/perf/tests/attr/test-record-group1 | 2 +- .../perf/tests/attr/test-record-no-buffering | 2 +- tools/perf/tests/attr/test-record-no-inherit | 2 +- tools/perf/tests/attr/test-record-no-samples | 2 +- tools/perf/tests/attr/test-record-period | 2 +- tools/perf/tests/attr/test-record-raw | 2 +- tools/perf/util/bpf-event.c | 100 ++++++++++++++++++ tools/perf/util/bpf-event.h | 15 +++ 28 files changed, 145 insertions(+), 24 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 6f645fd72fed..4e2d953d4bc5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1238,6 +1238,9 @@ 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; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 3ce8a8db6c1d..1999d6533d12 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1637,6 +1637,9 @@ int cmd_top(int argc, const char **argv) 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; 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/util/bpf-event.c b/tools/perf/util/bpf-event.c index 7ffe7db59828..2a8c245ca942 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -13,6 +13,7 @@ #include "env.h" #include "session.h" #include "map.h" +#include "evlist.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -330,3 +331,102 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, 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); +} diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index b9ec394dc7c7..8cb1189149ec 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -4,12 +4,17 @@ #include #include +#include +#include #include "event.h" struct machine; union perf_event; +struct perf_env; struct perf_sample; struct record_opts; +struct evlist; +struct target; struct bpf_prog_info_node { struct bpf_prog_info_linear *info_linear; @@ -31,6 +36,9 @@ 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); + #else static inline int machine__process_bpf_event(struct machine *machine __maybe_unused, union perf_event *event __maybe_unused, @@ -46,5 +54,12 @@ static inline int perf_event__synthesize_bpf_events(struct perf_session *session { return 0; } + +static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_unused, + struct perf_env *env __maybe_unused) +{ + return 0; +} + #endif // HAVE_LIBBPF_SUPPORT #endif From fc462ac75b36daaa61e9bda7fba66ed1b3a500b4 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 19 Mar 2019 09:54:53 -0700 Subject: [PATCH 221/256] perf bpf: Extract logic to create program names from perf_event__synthesize_one_bpf_prog() Extract logic to create program names to synthesize_bpf_prog_name(), so that it can be reused in header.c:print_bpf_prog_info(). This commit doesn't change the behavior. Signed-off-by: Song Liu Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190319165454.1298742-2-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 62 +++++++++++++++++++++---------------- 1 file changed, 35 insertions(+), 27 deletions(-) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 2a8c245ca942..d5b041649f26 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -111,6 +111,38 @@ static int perf_env__fetch_btf(struct perf_env *env, 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 @@ -135,7 +167,6 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, struct bpf_prog_info_node *info_node; struct bpf_prog_info *info; struct btf *btf = NULL; - bool has_btf = false; struct perf_env *env; u32 sub_prog_cnt, i; int err = 0; @@ -189,19 +220,13 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, btf = NULL; goto out; } - has_btf = true; perf_env__fetch_btf(env, info->btf_id, btf); } /* Synthesize PERF_RECORD_KSYMBOL */ for (i = 0; i < sub_prog_cnt; i++) { - u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags); - __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); + __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); - void *func_infos = (void *)(uintptr_t)(info->func_info); - const struct bpf_func_info *finfo; - const char *short_name = NULL; - const struct btf_type *t; int name_len; *ksymbol_event = (struct ksymbol_event){ @@ -214,26 +239,9 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, .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)); From f8dfeae009effc0b6dac2741cf8d7cbb91edb982 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 19 Mar 2019 09:54:54 -0700 Subject: [PATCH 222/256] perf bpf: Show more BPF program info in print_bpf_prog_info() This patch enables showing bpf program name, address, and size in the header. Before the patch: perf report --header-only ... # bpf_prog_info of id 9 # bpf_prog_info of id 10 # bpf_prog_info of id 13 After the patch: # bpf_prog_info 9: bpf_prog_7be49e3934a125ba addr 0xffffffffa0024947 size 229 # bpf_prog_info 10: bpf_prog_2a142ef67aaad174 addr 0xffffffffa007c94d size 229 # bpf_prog_info 13: bpf_prog_47368425825d7384_task__task_newt addr 0xffffffffa0251137 size 369 Committer notes: Fix the fallback definition when HAVE_LIBBPF_SUPPORT is not defined, i.e. add the missing 'static inline' and add the __maybe_unused to the args. Also add stdio.h since we now use FILE * in bpf-event.h. Signed-off-by: Song Liu Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190319165454.1298742-3-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 40 +++++++++++++++++++++++++++++++++++++ tools/perf/util/bpf-event.h | 11 +++++++++- tools/perf/util/header.c | 5 +++-- 3 files changed, 53 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index d5b041649f26..2a4a0da35632 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -438,3 +438,43 @@ int bpf_event__add_sb_event(struct perf_evlist **evlist, 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 8cb1189149ec..04c33b3bfe28 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -7,6 +7,7 @@ #include #include #include "event.h" +#include struct machine; union perf_event; @@ -38,7 +39,9 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, 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, @@ -61,5 +64,11 @@ static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_un 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/header.c b/tools/perf/util/header.c index 01dda2f65d36..b9e693825873 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1468,8 +1468,9 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); - fprintf(fp, "# bpf_prog_info of id %u\n", - node->info_linear->info.id); + + bpf_event__print_bpf_prog_info(&node->info_linear->info, + env, fp); } up_read(&env->bpf_progs.lock); From f27b744baaa646a7c0a01443cc0d8b4787cac2f7 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 21 Mar 2019 23:14:48 +0800 Subject: [PATCH 223/256] irqchip/irq-mvebu-sei: Make mvebu_sei_ap806_caps static Fix sparse warning: drivers/irqchip/irq-mvebu-sei.c:481:23: warning: symbol 'mvebu_sei_ap806_caps' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Cc: Cc: Cc: Link: https://lkml.kernel.org/r/20190321151448.15600-1-yuehaibing@huawei.com --- drivers/irqchip/irq-mvebu-sei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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, From 2219c9ee922d9a0548b44fb82342166d9d9fdbc9 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 21 Feb 2019 03:38:51 +0000 Subject: [PATCH 224/256] drm/nouveau/dmem: remove set but not used variable 'drm' Fixes gcc '-Wunused-but-set-variable' warning: drivers/gpu/drm/nouveau/nouveau_dmem.c: In function 'nouveau_dmem_free': drivers/gpu/drm/nouveau/nouveau_dmem.c:103:22: warning: variable 'drm' set but not used [-Wunused-but-set-variable] struct nouveau_drm *drm; ^ Signed-off-by: YueHaibing Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 8be7a83ced9b..58b4cb389d87 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: From 18ec3c129bcad0a481ee7faf8ce5ad92d6537722 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 22 Feb 2019 09:34:04 +0300 Subject: [PATCH 225/256] drm/nouveau/dmem: Fix a NULL vs IS_ERR() check The hmm_devmem_add() function doesn't return NULL, it returns error pointers. Fixes: 5be73b690875 ("drm/nouveau/dmem: device memory helpers for SVM") Signed-off-by: Dan Carpenter Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 58b4cb389d87..b1df42f73ec2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -621,7 +621,7 @@ 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; From 909e9c9c428376e2a43d178ed4b0a2d5ba9cb7d3 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 28 Feb 2019 20:24:59 +0800 Subject: [PATCH 226/256] drm/nouveau/debugfs: Fix check of pm_runtime_get_sync failure pm_runtime_get_sync returns negative on failure. Fixes: eaeb9010bb4b ("drm/nouveau/debugfs: Wake up GPU before doing any reclocking") Signed-off-by: YueHaibing Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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); From 83857418073fda5e0d562e6639b45ae06c957131 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Thu, 21 Mar 2019 15:42:18 -0400 Subject: [PATCH 227/256] drm/nouveau/dmem: empty chunk do not have a buffer object associated with them. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Empty chunk do not have a bo associated with them so no need to pin/unpin on suspend/resume. This fix suspend/resume on 5.1rc1 when NOUVEAU_SVM is enabled. Signed-off-by: Jérôme Glisse Reviewed-by: Tobias Klausmann Tested-by: Tobias Klausmann Cc: Ben Skeggs Cc: dri-devel@lists.freedesktop.org Cc: nouveau@lists.freedesktop.org Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index b1df42f73ec2..61fc27d30ff2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -454,11 +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); } @@ -477,9 +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); } From 80ef4464d5e27408685e609d389663aad46644b9 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 20 Mar 2019 18:57:23 +0000 Subject: [PATCH 228/256] iommu/iova: Fix tracking of recently failed iova address If a 32 bit allocation request is too big to possibly succeed, it early exits with a failure and then should never update max32_alloc_ size. This patch fixes current code, now the size is only updated if the slow path failed while walking the tree. Without the fix the allocation may enter the slow path again even if there was a failure before of a request with the same or a smaller size. Cc: # 4.20+ Fixes: bee60e94a1e2 ("iommu/iova: Optimise attempts to allocate iova from 32bit address range") Reviewed-by: Robin Murphy Signed-off-by: Robert Richter Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) 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; } From 5bb71fc790a88d063507dc5d445ab8b14e845591 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 20 Mar 2019 09:58:33 +0800 Subject: [PATCH 229/256] iommu/vt-d: Check capability before disabling protected memory The spec states in 10.4.16 that the Protected Memory Enable Register should be treated as read-only for implementations not supporting protected memory regions (PLMR and PHMR fields reported as Clear in the Capability register). Cc: Jacob Pan Cc: mark gross Suggested-by: Ashok Raj Fixes: f8bab73515ca5 ("intel-iommu: PMEN support") Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 87274b54febd..f002d47d2f27 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; From 84c11e4df5aa4955acaa441f0cf1cb2e50daf64b Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 20 Mar 2019 09:58:34 +0800 Subject: [PATCH 230/256] iommu/vt-d: Save the right domain ID used by hardware The driver sets a default domain id (FLPT_DEFAULT_DID) in the first level only pasid entry, but saves a different domain id in @sdev->did. The value saved in @sdev->did will be used to invalidate the translation caches. Hence, the driver might result in invalidating the caches with a wrong domain id. Cc: Ashok Raj Cc: Jacob Pan Fixes: 1c4f88b7f1f92 ("iommu/vt-d: Shared virtual address in scalable mode") Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index f002d47d2f27..28cb713d728c 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5335,7 +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)) { From 5a07168d8d89b00fe1760120714378175b3ef992 Mon Sep 17 00:00:00 2001 From: Chen Jie Date: Fri, 15 Mar 2019 03:44:38 +0000 Subject: [PATCH 231/256] futex: Ensure that futex address is aligned in handle_futex_death() The futex code requires that the user space addresses of futexes are 32bit aligned. sys_futex() checks this in futex_get_keys() but the robust list code has no alignment check in place. As a consequence the kernel crashes on architectures with strict alignment requirements in handle_futex_death() when trying to cmpxchg() on an unaligned futex address which was retrieved from the robust list. [ tglx: Rewrote changelog, proper sizeof() based alignement check and add comment ] Fixes: 0771dfefc9e5 ("[PATCH] lightweight robust futexes: core") Signed-off-by: Chen Jie Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1552621478-119787-1-git-send-email-chenjie6@huawei.com --- kernel/futex.c | 4 ++++ 1 file changed, 4 insertions(+) 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; From 4fe64a62e04cfb2dc1daab0d8f05d212aa014161 Mon Sep 17 00:00:00 2001 From: Valdis Kletnieks Date: Tue, 12 Mar 2019 03:47:53 -0400 Subject: [PATCH 232/256] x86/mm/pti: Make local symbols static With 'make C=2 W=1', sparse and gcc both complain: CHECK arch/x86/mm/pti.c arch/x86/mm/pti.c:84:3: warning: symbol 'pti_mode' was not declared. Should it be static? arch/x86/mm/pti.c:605:6: warning: symbol 'pti_set_kernel_image_nonglobal' was not declared. Should it be static? CC arch/x86/mm/pti.o arch/x86/mm/pti.c:605:6: warning: no previous prototype for 'pti_set_kernel_image_nonglobal' [-Wmissing-prototypes] 605 | void pti_set_kernel_image_nonglobal(void) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ pti_set_kernel_image_nonglobal() is only used locally. 'pti_mode' exists in drivers/hwtracing/intel_th/pti.c as well, but it's a completely unrelated local (static) symbol. Make both static. Signed-off-by: Valdis Kletnieks Signed-off-by: Thomas Gleixner Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/27680.1552376873@turing-police --- arch/x86/mm/pti.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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 From bb2e320565f997273fe04035bb6c17f643da6f8a Mon Sep 17 00:00:00 2001 From: Valdis Kletnieks Date: Tue, 12 Mar 2019 04:17:56 -0400 Subject: [PATCH 233/256] genirq/devres: Remove excess parameter from kernel doc Building with 'make W=1' complains: CC kernel/irq/devres.o kernel/irq/devres.c:104: warning: Excess function parameter 'thread_fn' description in 'devm_request_any_context_irq' Remove it. Signed-off-by: Valdis Kletnieks Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/31207.1552378676@turing-police --- kernel/irq/devres.c | 2 -- 1 file changed, 2 deletions(-) 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 From e8750053d64a3317cbc15f8341f0f11ca751bfeb Mon Sep 17 00:00:00 2001 From: Valdis Kletnieks Date: Tue, 12 Mar 2019 04:38:35 -0400 Subject: [PATCH 234/256] time/jiffies: Make refined_jiffies static sparse complains: CHECK kernel/time/jiffies.c kernel/time/jiffies.c:92:20: warning: symbol 'refined_jiffies' was not declared. Should it be static? Its only used in file scope. Make it static. Signed-off-by: Valdis Kletnieks Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/32342.1552379915@turing-police --- kernel/time/jiffies.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) { From e898e69d6b9475bf123f99b3c5d1a67bb7cb2361 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 7 Mar 2019 14:27:56 -0700 Subject: [PATCH 235/256] x86/hw_breakpoints: Make default case in hw_breakpoint_arch_parse() return an error When building with -Wsometimes-uninitialized, Clang warns: arch/x86/kernel/hw_breakpoint.c:355:2: warning: variable 'align' is used uninitialized whenever switch default is taken [-Wsometimes-uninitialized] The default cannot be reached because arch_build_bp_info() initializes hw->len to one of the specified cases. Nevertheless the warning is valid and returning -EINVAL makes sure that this cannot be broken by future modifications. Suggested-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Signed-off-by: Thomas Gleixner Reviewed-by: Nick Desaulniers Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: clang-built-linux@googlegroups.com Link: https://github.com/ClangBuiltLinux/linux/issues/392 Link: https://lkml.kernel.org/r/20190307212756.4648-1-natechancellor@gmail.com --- arch/x86/kernel/hw_breakpoint.c | 1 + 1 file changed, 1 insertion(+) 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; } /* From 1e4471e74c75acb3f89959ffa02a241227937ae2 Mon Sep 17 00:00:00 2001 From: Shenghui Wang Date: Sat, 16 Mar 2019 16:24:37 +0800 Subject: [PATCH 236/256] sbitmap: trivial - update comment for sbitmap_deferred_clear_bit "sbitmap_batch_clear" should be "sbitmap_deferred_clear" Acked-by: Omar Sandoval Signed-off-by: Shenghui Wang Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) From d18a7408d7be0f34a120d99051ed5187d9727728 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 22 Mar 2019 22:37:08 +0800 Subject: [PATCH 237/256] clocksource/drivers/clps711x: Make clps711x_clksrc_init() static Fix sparse warning: drivers/clocksource/clps711x-timer.c:96:13: warning: symbol 'clps711x_clksrc_init' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Link: https://lkml.kernel.org/r/20190322143708.12716-1-yuehaibing@huawei.com --- drivers/clocksource/clps711x-timer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c index a8dd80576c95..cdc251524f5e 100644 --- a/drivers/clocksource/clps711x-timer.c +++ b/drivers/clocksource/clps711x-timer.c @@ -93,8 +93,9 @@ 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) +static 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); From bddee90af621914f08a03d546419fc293e9140d8 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 22 Mar 2019 22:39:40 +0800 Subject: [PATCH 238/256] clocksource/drivers/tcb_clksrc: Make tc_clksrc_suspend/resume() static Fix sparse warnings: drivers/clocksource/tcb_clksrc.c:74:6: warning: symbol 'tc_clksrc_suspend' was not declared. Should it be static? drivers/clocksource/tcb_clksrc.c:89:6: warning: symbol 'tc_clksrc_resume' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Link: https://lkml.kernel.org/r/20190322143940.12396-1-yuehaibing@huawei.com --- drivers/clocksource/tcb_clksrc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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; From 008258d995a637c77c10a5d087d134eed49a6572 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 22 Mar 2019 22:43:02 +0800 Subject: [PATCH 239/256] clocksource/drivers/timer-ti-dm: Make omap_dm_timer_set_load_start() static Fix sparse warning: drivers/clocksource/timer-ti-dm.c:589:5: warning: symbol 'omap_dm_timer_set_load_start' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Thomas Gleixner Cc: Link: https://lkml.kernel.org/r/20190322144302.6704-1-yuehaibing@huawei.com --- drivers/clocksource/timer-ti-dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) 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, - unsigned int load) +static int omap_dm_timer_set_load_start(struct omap_dm_timer *timer, + int autoreload, unsigned int load) { u32 l; From 9039de4034775f4420bf01fa879f8c04b3cd6bba Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 22 Mar 2019 22:43:59 +0800 Subject: [PATCH 240/256] clocksource/drivers/mips-gic-timer: Make gic_compare_irqaction static Fix sparse warning: drivers/clocksource/mips-gic-timer.c:70:18: warning: symbol 'gic_compare_irqaction' was not declared. Should it be static? Signed-off-by: YueHaibing Signed-off-by: Thomas Gleixner Cc: Link: https://lkml.kernel.org/r/20190322144359.19516-1-yuehaibing@huawei.com --- drivers/clocksource/mips-gic-timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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, From d53e292f0f505783d0219f58f8f8f294f45f4ee6 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 15 Mar 2019 07:54:59 +0000 Subject: [PATCH 241/256] CIFS: Fix an issue with re-sending wdata when transport returning -EAGAIN When sending a wdata, transport may return -EAGAIN. In this case we should re-obtain credits because the session may have been reconnected. Change in v2: adjust_credits before re-sending Signed-off-by: Long Li Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky --- fs/cifs/file.c | 81 +++++++++++++++++++++++++++++--------------------- 1 file changed, 47 insertions(+), 34 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2a6d20c0ce02..2aa3e62af764 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, - &credits); - - if (rc) - goto out; - - if (wsize < wdata->bytes) { - add_credits_and_wake_if(server, &credits, 0); - msleep(1000); - } - } while (wsize < wdata->bytes); - - wdata->credits = credits; - rc = -EAGAIN; - while (rc == -EAGAIN) { - rc = 0; - if (wdata->cfile->invalidHandle) + if (wdata->cfile->invalidHandle) { rc = cifs_reopen_file(wdata->cfile, false); - if (!rc) - rc = server->ops->async_writev(wdata, + if (rc == -EAGAIN) + continue; + else if (rc) + break; + } + + + /* + * 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, &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; + + rc = adjust_credits(server, &wdata->credits, wdata->bytes); + + if (!rc) { + if (wdata->cfile->invalidHandle) + rc = -EAGAIN; + else + rc = server->ops->async_writev(wdata, cifs_uncached_writedata_release); - } + } - if (!rc) { - list_add_tail(&wdata->list, wdata_list); - return 0; - } + /* If the write was successfully sent, we are done */ + if (!rc) { + list_add_tail(&wdata->list, wdata_list); + return 0; + } - add_credits_and_wake_if(server, &wdata->credits, 0); -out: + /* Roll back credits and retry if needed */ + add_credits_and_wake_if(server, &wdata->credits, 0); + } 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; } } From 0b0dfd59216755cfa5a47eab2811efaa4589db68 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 15 Mar 2019 07:55:00 +0000 Subject: [PATCH 242/256] CIFS: Fix an issue with re-sending rdata when transport returning -EAGAIN When sending a rdata, transport may return -EAGAIN. In this case we should re-obtain credits because the session may have been reconnected. Change in v2: adjust_credits before re-sending Signed-off-by: Long Li Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky --- fs/cifs/file.c | 71 +++++++++++++++++++++++++++++--------------------- 1 file changed, 41 insertions(+), 30 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2aa3e62af764..89006e044973 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3361,44 +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) - goto out; + if (rc) + goto fail; - if (rsize < rdata->bytes) { - add_credits_and_wake_if(server, &credits, 0); - msleep(1000); + if (rsize < rdata->bytes) { + add_credits_and_wake_if(server, &credits, 0); + msleep(1000); + } + } while (rsize < rdata->bytes); + rdata->credits = credits; + + rc = adjust_credits(server, &rdata->credits, rdata->bytes); + if (!rc) { + if (rdata->cfile->invalidHandle) + rc = -EAGAIN; + else + rc = server->ops->async_readv(rdata); } - } while (rsize < rdata->bytes); - rdata->credits = credits; - rc = -EAGAIN; - while (rc == -EAGAIN) { - rc = 0; - if (rdata->cfile->invalidHandle) - rc = cifs_reopen_file(rdata->cfile, true); - if (!rc) - rc = server->ops->async_readv(rdata); - } + /* If the read was successfully sent, we are done */ + if (!rc) { + /* Add to aio pending list */ + list_add_tail(&rdata->list, rdata_list); + return 0; + } - if (!rc) { - /* Add to aio pending list */ - list_add_tail(&rdata->list, rdata_list); - return 0; - } - - add_credits_and_wake_if(server, &rdata->credits, 0); -out: - kref_put(&rdata->refcount, - cifs_uncached_readdata_release); + /* Roll back credits and retry if needed */ + add_credits_and_wake_if(server, &rdata->credits, 0); + } while (rc == -EAGAIN); +fail: + kref_put(&rdata->refcount, cifs_uncached_readdata_release); return rc; } From b073a08016a10f01dfb0d0b6c7fa89da0d544963 Mon Sep 17 00:00:00 2001 From: Xiaoli Feng Date: Sat, 16 Mar 2019 12:11:54 +0800 Subject: [PATCH 243/256] cifs: fix that return -EINVAL when do dedupe operation dedupe_file_range operations is combiled into remap_file_range. But it's always skipped for dedupe operations in function cifs_remap_file_range. Example to test: Before this patch: # dd if=/dev/zero of=cifs/file bs=1M count=1 # xfs_io -c "dedupe cifs/file 4k 64k 4k" cifs/file XFS_IOC_FILE_EXTENT_SAME: Invalid argument After this patch: # dd if=/dev/zero of=cifs/file bs=1M count=1 # xfs_io -c "dedupe cifs/file 4k 64k 4k" cifs/file XFS_IOC_FILE_EXTENT_SAME: Operation not supported Influence for xfstests: generic/091 generic/112 generic/127 generic/263 These tests report this error "do_copy_range:: Invalid argument" instead of "FIDEDUPERANGE: Invalid argument". Because there are still two bugs cause these test failed. https://bugzilla.kernel.org/show_bug.cgi?id=202935 https://bugzilla.kernel.org/show_bug.cgi?id=202785 Signed-off-by: Xiaoli Feng Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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"); From 85f9987b236cf46e06ffdb5c225cf1f3c0acb789 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sun, 17 Mar 2019 15:58:38 -0500 Subject: [PATCH 244/256] fix incorrect error code mapping for OBJECTID_NOT_FOUND It was mapped to EIO which can be confusing when user space queries for an object GUID for an object for which the server file system doesn't support (or hasn't saved one). As Amir Goldstein suggested this is similar to ENOATTR (equivalently ENODATA in Linux errno definitions) so changing NT STATUS code mapping for OBJECTID_NOT_FOUND to ENODATA. Signed-off-by: Steve French CC: Amir Goldstein --- fs/cifs/smb2maperror.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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"}, From e71ab2aa06f731a944993120b0eef1556c63b81c Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Thu, 21 Mar 2019 14:59:02 +1000 Subject: [PATCH 245/256] cifs: allow guest mounts to work for smb3.11 Fix Guest/Anonymous sessions so that they work with SMB 3.11. The commit noted below tightened the conditions and forced signing for the SMB2-TreeConnect commands as per MS-SMB2. However, this should only apply to normal user sessions and not for Guest/Anonumous sessions. Fixes: 6188f28bf608 ("Tree connect for SMB3.1.1 must be signed for non-encrypted shares") Signed-off-by: Ronnie Sahlberg CC: Stable Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index c399e09b76e6..8e4a1da95418 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1628,9 +1628,13 @@ 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 + */ 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))) req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED; memset(&rqst, 0, sizeof(struct smb_rqst)); From 68ddb496800acdb46172b4981dc3753ea9b39c25 Mon Sep 17 00:00:00 2001 From: "Paulo Alcantara (SUSE)" Date: Thu, 21 Mar 2019 19:31:22 -0300 Subject: [PATCH 246/256] cifs: Fix slab-out-of-bounds when tracing SMB tcon This patch fixes the following KASAN report: [ 779.044746] BUG: KASAN: slab-out-of-bounds in string+0xab/0x180 [ 779.044750] Read of size 1 at addr ffff88814f327968 by task trace-cmd/2812 [ 779.044756] CPU: 1 PID: 2812 Comm: trace-cmd Not tainted 5.1.0-rc1+ #62 [ 779.044760] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-0-ga698c89-prebuilt.qemu.org 04/01/2014 [ 779.044761] Call Trace: [ 779.044769] dump_stack+0x5b/0x90 [ 779.044775] ? string+0xab/0x180 [ 779.044781] print_address_description+0x6c/0x23c [ 779.044787] ? string+0xab/0x180 [ 779.044792] ? string+0xab/0x180 [ 779.044797] kasan_report.cold.3+0x1a/0x32 [ 779.044803] ? string+0xab/0x180 [ 779.044809] string+0xab/0x180 [ 779.044816] ? widen_string+0x160/0x160 [ 779.044822] ? vsnprintf+0x5bf/0x7f0 [ 779.044829] vsnprintf+0x4e7/0x7f0 [ 779.044836] ? pointer+0x4a0/0x4a0 [ 779.044841] ? seq_buf_vprintf+0x79/0xc0 [ 779.044848] seq_buf_vprintf+0x62/0xc0 [ 779.044855] trace_seq_printf+0x113/0x210 [ 779.044861] ? trace_seq_puts+0x110/0x110 [ 779.044867] ? trace_raw_output_prep+0xd8/0x110 [ 779.044876] trace_raw_output_smb3_tcon_class+0x9f/0xc0 [ 779.044882] print_trace_line+0x377/0x890 [ 779.044888] ? tracing_buffers_read+0x300/0x300 [ 779.044893] ? ring_buffer_read+0x58/0x70 [ 779.044899] s_show+0x6e/0x140 [ 779.044906] seq_read+0x505/0x6a0 [ 779.044913] vfs_read+0xaf/0x1b0 [ 779.044919] ksys_read+0xa1/0x130 [ 779.044925] ? kernel_write+0xa0/0xa0 [ 779.044931] ? __do_page_fault+0x3d5/0x620 [ 779.044938] do_syscall_64+0x63/0x150 [ 779.044944] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 779.044949] RIP: 0033:0x7f62c2c2db31 [ 779.044955] Code: fe ff ff 48 8d 3d 17 9e 09 00 48 83 ec 08 e8 96 02 02 00 66 0f 1f 44 00 00 8b 05 fa fc 2c 00 48 63 ff 85 c0 75 13 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 57 f3 c3 0f 1f 44 00 00 55 53 48 89 d5 48 89 [ 779.044958] RSP: 002b:00007ffd6e116678 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 779.044964] RAX: ffffffffffffffda RBX: 0000560a38be9260 RCX: 00007f62c2c2db31 [ 779.044966] RDX: 0000000000002000 RSI: 00007ffd6e116710 RDI: 0000000000000003 [ 779.044966] RDX: 0000000000002000 RSI: 00007ffd6e116710 RDI: 0000000000000003 [ 779.044969] RBP: 00007f62c2ef5420 R08: 0000000000000000 R09: 0000000000000003 [ 779.044972] R10: ffffffffffffffa8 R11: 0000000000000246 R12: 00007ffd6e116710 [ 779.044975] R13: 0000000000002000 R14: 0000000000000d68 R15: 0000000000002000 [ 779.044981] Allocated by task 1257: [ 779.044987] __kasan_kmalloc.constprop.5+0xc1/0xd0 [ 779.044992] kmem_cache_alloc+0xad/0x1a0 [ 779.044997] getname_flags+0x6c/0x2a0 [ 779.045003] user_path_at_empty+0x1d/0x40 [ 779.045008] do_faccessat+0x12a/0x330 [ 779.045012] do_syscall_64+0x63/0x150 [ 779.045017] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 779.045019] Freed by task 1257: [ 779.045023] __kasan_slab_free+0x12e/0x180 [ 779.045029] kmem_cache_free+0x85/0x1b0 [ 779.045034] filename_lookup.part.70+0x176/0x250 [ 779.045039] do_faccessat+0x12a/0x330 [ 779.045043] do_syscall_64+0x63/0x150 [ 779.045048] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 779.045052] The buggy address belongs to the object at ffff88814f326600 which belongs to the cache names_cache of size 4096 [ 779.045057] The buggy address is located 872 bytes to the right of 4096-byte region [ffff88814f326600, ffff88814f327600) [ 779.045058] The buggy address belongs to the page: [ 779.045062] page:ffffea00053cc800 count:1 mapcount:0 mapping:ffff88815b191b40 index:0x0 compound_mapcount: 0 [ 779.045067] flags: 0x200000000010200(slab|head) [ 779.045075] raw: 0200000000010200 dead000000000100 dead000000000200 ffff88815b191b40 [ 779.045081] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 [ 779.045083] page dumped because: kasan: bad access detected [ 779.045085] Memory state around the buggy address: [ 779.045089] ffff88814f327800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 779.045093] ffff88814f327880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 779.045097] >ffff88814f327900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 779.045099] ^ [ 779.045103] ffff88814f327980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 779.045107] ffff88814f327a00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 779.045109] ================================================================== [ 779.045110] Disabling lock debugging due to kernel taint Correctly assign tree name str for smb3_tcon event. Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/trace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) 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) \ From 8c11a607d1d9cd6e7f01fd6b03923597fb0ef95a Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 22 Mar 2019 22:31:17 -0500 Subject: [PATCH 247/256] SMB3: Fix SMB3.1.1 guest mounts to Samba Workaround problem with Samba responses to SMB3.1.1 null user (guest) mounts. The server doesn't set the expected flag in the session setup response so we have to do a similar check to what is done in smb3_validate_negotiate where we also check if the user is a null user (but not sec=krb5 since username might not be passed in on mount for Kerberos case). Note that the commit below tightened the conditions and forced signing for the SMB2-TreeConnect commands as per MS-SMB2. However, this should only apply to normal user sessions and not for cases where there is no user (even if server forgets to set the flag in the response) since we don't have anything useful to sign with. This is especially important now that the more secure SMB3.1.1 protocol is in the default dialect list. An earlier patch ("cifs: allow guest mounts to work for smb3.11") fixed the guest mounts to Windows. Fixes: 6188f28bf608 ("Tree connect for SMB3.1.1 must be signed for non-encrypted shares") Reviewed-by: Ronnie Sahlberg Reviewed-by: Paulo Alcantara CC: Stable Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 8e4a1da95418..21ac19ff19cb 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1631,10 +1631,13 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, /* * 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) && - !(ses->session_flags & (SMB2_SESSION_FLAG_IS_GUEST|SMB2_SESSION_FLAG_IS_NULL))) + !(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)); From cf7d624f8dcc9b833a8489208b6ef6dcc5dd308b Mon Sep 17 00:00:00 2001 From: Steve French Date: Wed, 20 Mar 2019 16:42:50 -0500 Subject: [PATCH 248/256] cifs: update internal module version number To 2.19 Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 */ From ffc8599aa9763f39f6736a79da4d1575e7006f9a Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Fri, 8 Mar 2019 11:05:08 +0800 Subject: [PATCH 249/256] x86/gart: Exclude GART aperture from kcore On machines where the GART aperture is mapped over physical RAM, /proc/kcore contains the GART aperture range. Accessing the GART range via /proc/kcore results in a kernel crash. vmcore used to have the same issue, until it was fixed with commit 2a3e83c6f96c ("x86/gart: Exclude GART aperture from vmcore")', leveraging existing hook infrastructure in vmcore to let /proc/vmcore return zeroes when attempting to read the aperture region, and so it won't read from the actual memory. Apply the same workaround for kcore. First implement the same hook infrastructure for kcore, then reuse the hook functions introduced in the previous vmcore fix. Just with some minor adjustment, rename some functions for more general usage, and simplify the hook infrastructure a bit as there is no module usage yet. Suggested-by: Baoquan He Signed-off-by: Kairui Song Signed-off-by: Thomas Gleixner Reviewed-by: Jiri Bohac Acked-by: Baoquan He Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Omar Sandoval Cc: Dave Young Link: https://lkml.kernel.org/r/20190308030508.13548-1-kasong@redhat.com --- arch/x86/kernel/aperture_64.c | 20 +++++++++++++------- fs/proc/kcore.c | 27 +++++++++++++++++++++++++++ include/linux/kcore.h | 2 ++ 3 files changed, 42 insertions(+), 7 deletions(-) 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 +#include #include #include #include @@ -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/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/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) From 32d0be018f6f5ee2d5d19c4795304613560814cf Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 22 Mar 2019 14:54:11 -0700 Subject: [PATCH 250/256] clocksource/drivers/riscv: Fix clocksource mask For all riscv architectures (RV32, RV64 and RV128), the clocksource is a 64 bit incrementing counter. Fix the clock source mask accordingly. Tested on both 64bit and 32 bit virt machine in QEMU. Fixes: 62b019436814 ("clocksource: new RISC-V SBI timer driver") Signed-off-by: Atish Patra Signed-off-by: Thomas Gleixner Reviewed-by: Anup Patel Cc: Albert Ou Cc: Daniel Lezcano Cc: linux-riscv@lists.infradead.org Cc: Palmer Dabbelt Cc: Anup Patel Cc: Damien Le Moal Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190322215411.19362-1-atish.patra@wdc.com --- drivers/clocksource/timer-riscv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) 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, - BITS_PER_LONG, riscv_timebase); + sched_clock_register(riscv_sched_clock, 64, riscv_timebase); error = cpuhp_setup_state(CPUHP_AP_RISCV_TIMER_STARTING, "clockevents/riscv/timer:starting", From 93417a3fda2060f2a34e3341904024c5b6980d1f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 Feb 2019 15:37:14 -0600 Subject: [PATCH 251/256] genirq: Mark expected switch case fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. With -Wimplicit-fallthrough added to CFLAGS: kernel/irq/manage.c: In function ‘irq_do_set_affinity’: kernel/irq/manage.c:198:3: warning: this statement may fall through [-Wimplicit-fallthrough=] cpumask_copy(desc->irq_common_data.affinity, mask); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ kernel/irq/manage.c:199:2: note: here case IRQ_SET_MASK_OK_NOCOPY: ^~~~ Annotate it. Signed-off-by: Gustavo A. R. Silva Signed-off-by: Thomas Gleixner Cc: Kees Cook Link: https://lkml.kernel.org/r/20190228213714.GA9246@embeddedor --- kernel/irq/manage.c | 1 + 1 file changed, 1 insertion(+) 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); From 674a2b27234d1b7afcb0a9162e81b2e53aeef217 Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Sat, 23 Mar 2019 11:43:05 -0400 Subject: [PATCH 252/256] ext4: brelse all indirect buffer in ext4_ind_remove_space() All indirect buffers get by ext4_find_shared() should be released no mater the branch should be freed or not. But now, we forget to release the lower depth indirect buffers when removing space from the same higher depth indirect block. It will lead to buffer leak and futher more, it may lead to quota information corruption when using old quota, consider the following case. - Create and mount an empty ext4 filesystem without extent and quota features, - quotacheck and enable the user & group quota, - Create some files and write some data to them, and then punch hole to some files of them, it may trigger the buffer leak problem mentioned above. - Disable quota and run quotacheck again, it will create two new aquota files and write the checked quota information to them, which probably may reuse the freed indirect block(the buffer and page cache was not freed) as data block. - Enable quota again, it will invoke vfs_load_quota_inode()->invalidate_bdev() to try to clean unused buffers and pagecache. Unfortunately, because of the buffer of quota data block is still referenced, quota code cannot read the up to date quota info from the device and lead to quota information corruption. This problem can be reproduced by xfstests generic/231 on ext3 file system or ext4 file system without extent and quota features. This patch fix this problem by releasing the missing indirect buffers, in ext4_ind_remove_space(). Reported-by: Hulk Robot Signed-off-by: zhangyi (F) Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara Cc: stable@kernel.org --- fs/ext4/indirect.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index c2225f0d31b5..02c39524bda2 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1390,10 +1390,14 @@ end_range: partial->p + 1, partial2->p, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); + while (partial > chain) { + BUFFER_TRACE(partial->bh, "call brelse"); + brelse(partial->bh); + } + while (partial2 > chain2) { + BUFFER_TRACE(partial2->bh, "call brelse"); + brelse(partial2->bh); + } return 0; } From 5e86bdda41534e17621d5a071b294943cae4376e Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Sat, 23 Mar 2019 11:56:01 -0400 Subject: [PATCH 253/256] ext4: cleanup bh release code in ext4_ind_remove_space() Currently, we are releasing the indirect buffer where we are done with it in ext4_ind_remove_space(), so we can see the brelse() and BUFFER_TRACE() everywhere. It seems fragile and hard to read, and we may probably forget to release the buffer some day. This patch cleans up the code by putting of the code which releases the buffers to the end of the function. Signed-off-by: zhangyi (F) Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/ext4/indirect.c | 47 ++++++++++++++++++++++------------------------ 1 file changed, 22 insertions(+), 25 deletions(-) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 02c39524bda2..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); - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); /* Free top, but only if partial2 isn't its subtree. */ if (nr) { @@ -1390,15 +1387,7 @@ end_range: partial->p + 1, partial2->p, (chain+n-1) - partial); - while (partial > chain) { - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - } - while (partial2 > chain2) { - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); - } - return 0; + goto cleanup; } /* @@ -1413,8 +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) { @@ -1422,11 +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: @@ -1434,7 +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); @@ -1443,7 +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); @@ -1452,7 +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); @@ -1462,5 +1459,5 @@ do_indirects: case EXT4_TIND_BLOCK: ; } - return 0; + goto cleanup; } From 18915b5873f07e5030e6fb108a050fa7c71c59fb Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 23 Mar 2019 12:10:29 -0400 Subject: [PATCH 254/256] ext4: prohibit fstrim in norecovery mode The ext4 fstrim implementation uses the block bitmaps to find free space that can be discarded. If we haven't replayed the journal, the bitmaps will be stale and we absolutely *cannot* use stale metadata to zap the underlying storage. Signed-off-by: Darrick J. Wong Signed-off-by: Theodore Ts'o --- fs/ext4/ioctl.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index eb8ca8d80885..73435444b159 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; From 2a6a8e2d9004b5303fcb494588ba3a3b87a256c3 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Thu, 20 Dec 2018 14:16:26 +0300 Subject: [PATCH 255/256] clocksource/drivers/clps711x: Remove board support Since board support for the CLPS711X platform was removed, remove the board support from the clps711x-timer driver. Signed-off-by: Alexander Shiyan Signed-off-by: Thomas Gleixner Acked-by: Arnd Bergmann Cc: Daniel Lezcano Link: https://lkml.kernel.org/r/20181220111626.17140-1-shc_work@mail.ru --- drivers/clocksource/clps711x-timer.c | 45 ++++++++-------------------- 1 file changed, 13 insertions(+), 32 deletions(-) diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c index cdc251524f5e..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; - - if (!base) - return -ENOMEM; - if (IS_ERR(clock)) - return PTR_ERR(clock); - - rate = clk_get_rate(clock); + unsigned long 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; @@ -93,32 +77,29 @@ static int __init _clps711x_clkevt_init(struct clk *clock, void __iomem *base, "clps711x-timer", clkevt); } -static 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 From 8c2ffd9174779014c3fe1f96d9dc3641d9175f00 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 24 Mar 2019 14:02:26 -0700 Subject: [PATCH 256/256] Linux 5.1-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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*