Commit e680a41f authored by Ingo Molnar's avatar Ingo Molnar
Browse files

Merge tag 'perf-core-for-mingo-5.5-20191128' of... 

Merge tag 'perf-core-for-mingo-5.5-20191128' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

 into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf script:

  Adrian Hunter:

  - Fix brstackinsn for AUXTRACE.

  - Fix invalid LBR/binary mismatch error.

perf diff:

  Arnaldo Carvalho de Melo:

  - Use llabs() with 64-bit values, fixing the build in some 32-bit
    architectures.

perf pmu:

  Andi Kleen:

  - Use file system cache to optimize sysfs access.

x86:

  Adrian Hunter:

  - Add some more Intel instructions to the opcode map and to the perf
    test entry:

      gf2p8affineinvqb, gf2p8affineqb, gf2p8mulb, v4fmaddps,
      v4fmaddss, v4fnmaddps, v4fnmaddss, vaesdec, vaesdeclast, vaesenc,
      vaesenclast, vcvtne2ps2bf16, vcvtneps2bf16, vdpbf16ps,
      vgf2p8affineinvqb, vgf2p8affineqb, vgf2p8mulb, vp2intersectd,
      vp2intersectq, vp4dpwssd, vp4dpwssds, vpclmulqdq, vpcompressb,
      vpcompressw, vpdpbusd, vpdpbusds, vpdpwssd, vpdpwssds, vpexpandb,
      vpexpandw, vpopcntb, vpopcntd, vpopcntq, vpopcntw, vpshldd, vpshldq,
      vpshldvd, vpshldvq, vpshldvw, vpshldw, vpshrdd, vpshrdq, vpshrdvd,
      vpshrdvq, vpshrdvw, vpshrdw, vpshufbitqmb.

perf affinity:

  Andi Kleen:

  - Add infrastructure to save/restore affinity

perf maps:

  Arnaldo Carvalho de Melo:

  - Merge 'struct maps' with 'struct map_groups', as there is a
    1x1 relationship, simplifying code overal.

perf build:

  Jiri Olsa:

  - Allow to link with libbpf dynamicaly.

Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parents 405b4537 5172672d

arch/x86/lib/x86-opcode-map.txt

+32 −12
Original line number Diff line number Diff line
@@ -695,16 +695,28 @@ AVXcode: 2 
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)

4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)

4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)

# Skip 0x50-0x57

50: vpdpbusd Vx,Hx,Wx (66),(ev)

51: vpdpbusds Vx,Hx,Wx (66),(ev)

52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)

53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)

54: vpopcntb/w Vx,Wx (66),(ev)

55: vpopcntd/q Vx,Wx (66),(ev)

58: vpbroadcastd Vx,Wx (66),(v)

59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)

5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)

5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)

# Skip 0x5c-0x63

# Skip 0x5c-0x61

62: vpexpandb/w Vx,Wx (66),(ev)

63: vpcompressb/w Wx,Vx (66),(ev)

64: vpblendmd/q Vx,Hx,Wx (66),(ev)

65: vblendmps/d Vx,Hx,Wx (66),(ev)

66: vpblendmb/w Vx,Hx,Wx (66),(ev)

# Skip 0x67-0x74

68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)

# Skip 0x69-0x6f

70: vpshldvw Vx,Hx,Wx (66),(ev)

71: vpshldvd/q Vx,Hx,Wx (66),(ev)

72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)

73: vpshrdvd/q Vx,Hx,Wx (66),(ev)

75: vpermi2b/w Vx,Hx,Wx (66),(ev)

76: vpermi2d/q Vx,Hx,Wx (66),(ev)

77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
@@ -727,6 +739,7 @@ AVXcode: 2 
8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)

8d: vpermb/w Vx,Hx,Wx (66),(ev)

8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)

8f: vpshufbitqmb Kx,Hx,Wx (66),(ev)

# 0x0f 0x38 0x90-0xbf (FMA)

90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)

91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
@@ -738,8 +751,8 @@ AVXcode: 2 
97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)

98: vfmadd132ps/d Vx,Hx,Wx (66),(v)

99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)

9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)

9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)

9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev)

9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev)

9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)

9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)

9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
@@ -752,8 +765,8 @@ a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) 
a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)

a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)

a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)

aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)

ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)

aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev)

ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev)

ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)

ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)

ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
@@ -780,11 +793,12 @@ ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) 
cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)

cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)

cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)

cf: vgf2p8mulb Vx,Wx (66)

db: VAESIMC Vdq,Wdq (66),(v1)

dc: VAESENC Vdq,Hdq,Wdq (66),(v1)

dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)

de: VAESDEC Vdq,Hdq,Wdq (66),(v1)

df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)

dc: vaesenc Vx,Hx,Wx (66)

dd: vaesenclast Vx,Hx,Wx (66)

de: vaesdec Vx,Hx,Wx (66)

df: vaesdeclast Vx,Hx,Wx (66)

f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)

f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)

f2: ANDN Gy,By,Ey (v)
@@ -848,7 +862,7 @@ AVXcode: 3 
41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)

42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)

43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)

44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)

44: vpclmulqdq Vx,Hx,Wx,Ib (66)

46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)

4a: vblendvps Vx,Hx,Wx,Lx (66),(v)

4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
@@ -865,7 +879,13 @@ AVXcode: 3 
63: vpcmpistri Vdq,Wdq,Ib (66),(v1)

66: vfpclassps/d Vk,Wx,Ib (66),(ev)

67: vfpclassss/d Vk,Wx,Ib (66),(ev)

70: vpshldw Vx,Hx,Wx,Ib (66),(ev)

71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev)

72: vpshrdw Vx,Hx,Wx,Ib (66),(ev)

73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev)

cc: sha1rnds4 Vdq,Wdq,Ib

ce: vgf2p8affineqb Vx,Wx,Ib (66)

cf: vgf2p8affineinvqb Vx,Wx,Ib (66)

df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)

f0: RORX Gy,Ey,Ib (F2),(v)

EndTable

tools/arch/x86/lib/x86-opcode-map.txt

+32 −12
Original line number Diff line number Diff line
@@ -695,16 +695,28 @@ AVXcode: 2 
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)

4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)

4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)

# Skip 0x50-0x57

50: vpdpbusd Vx,Hx,Wx (66),(ev)

51: vpdpbusds Vx,Hx,Wx (66),(ev)

52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)

53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)

54: vpopcntb/w Vx,Wx (66),(ev)

55: vpopcntd/q Vx,Wx (66),(ev)

58: vpbroadcastd Vx,Wx (66),(v)

59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)

5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)

5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)

# Skip 0x5c-0x63

# Skip 0x5c-0x61

62: vpexpandb/w Vx,Wx (66),(ev)

63: vpcompressb/w Wx,Vx (66),(ev)

64: vpblendmd/q Vx,Hx,Wx (66),(ev)

65: vblendmps/d Vx,Hx,Wx (66),(ev)

66: vpblendmb/w Vx,Hx,Wx (66),(ev)

# Skip 0x67-0x74

68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)

# Skip 0x69-0x6f

70: vpshldvw Vx,Hx,Wx (66),(ev)

71: vpshldvd/q Vx,Hx,Wx (66),(ev)

72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)

73: vpshrdvd/q Vx,Hx,Wx (66),(ev)

75: vpermi2b/w Vx,Hx,Wx (66),(ev)

76: vpermi2d/q Vx,Hx,Wx (66),(ev)

77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
@@ -727,6 +739,7 @@ AVXcode: 2 
8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)

8d: vpermb/w Vx,Hx,Wx (66),(ev)

8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)

8f: vpshufbitqmb Kx,Hx,Wx (66),(ev)

# 0x0f 0x38 0x90-0xbf (FMA)

90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)

91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
@@ -738,8 +751,8 @@ AVXcode: 2 
97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)

98: vfmadd132ps/d Vx,Hx,Wx (66),(v)

99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)

9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)

9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)

9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev)

9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev)

9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)

9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)

9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
@@ -752,8 +765,8 @@ a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) 
a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)

a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)

a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)

aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)

ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)

aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev)

ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev)

ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)

ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)

ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
@@ -780,11 +793,12 @@ ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) 
cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)

cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)

cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)

cf: vgf2p8mulb Vx,Wx (66)

db: VAESIMC Vdq,Wdq (66),(v1)

dc: VAESENC Vdq,Hdq,Wdq (66),(v1)

dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)

de: VAESDEC Vdq,Hdq,Wdq (66),(v1)

df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)

dc: vaesenc Vx,Hx,Wx (66)

dd: vaesenclast Vx,Hx,Wx (66)

de: vaesdec Vx,Hx,Wx (66)

df: vaesdeclast Vx,Hx,Wx (66)

f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)

f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)

f2: ANDN Gy,By,Ey (v)
@@ -848,7 +862,7 @@ AVXcode: 3 
41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)

42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)

43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)

44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)

44: vpclmulqdq Vx,Hx,Wx,Ib (66)

46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)

4a: vblendvps Vx,Hx,Wx,Lx (66),(v)

4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
@@ -865,7 +879,13 @@ AVXcode: 3 
63: vpcmpistri Vdq,Wdq,Ib (66),(v1)

66: vfpclassps/d Vk,Wx,Ib (66),(ev)

67: vfpclassss/d Vk,Wx,Ib (66),(ev)

70: vpshldw Vx,Hx,Wx,Ib (66),(ev)

71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev)

72: vpshrdw Vx,Hx,Wx,Ib (66),(ev)

73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev)

cc: sha1rnds4 Vdq,Wdq,Ib

ce: vgf2p8affineqb Vx,Wx,Ib (66)

cf: vgf2p8affineinvqb Vx,Wx,Ib (66)

df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)

f0: RORX Gy,Ey,Ib (F2),(v)

EndTable

tools/build/Makefile.feature

+2 −1
Original line number Diff line number Diff line
@@ -96,7 +96,8 @@ FEATURE_TESTS_EXTRA := \ 
         cxx                            \

         llvm                           \

         llvm-version                   \

         clang

         clang                          \

         libbpf



FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)

tools/build/feature/Makefile

+4 −0
Original line number Diff line number Diff line
@@ -53,6 +53,7 @@ FILES= \ 
         test-zlib.bin                          \

         test-lzma.bin                          \

         test-bpf.bin                           \

         test-libbpf.bin                        \

         test-get_cpuid.bin                     \

         test-sdt.bin                           \

         test-cxx.bin                           \
@@ -270,6 +271,9 @@ $(OUTPUT)test-get_cpuid.bin: 
$(OUTPUT)test-bpf.bin:

	$(BUILD)



$(OUTPUT)test-libbpf.bin:

	$(BUILD) -lbpf



$(OUTPUT)test-sdt.bin:

	$(BUILD)

tools/build/feature/test-libbpf.c

0 → 100644
+7 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

#include <bpf/libbpf.h>



int main(void)

{

	return bpf_object__open("test") ? 0 : -1;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE