perf bench: Copy kernel files needed to build mem{cpy,set} x86_64 benchmarks

We can't access kernel files directly from tools/, so copy the required
bits, and make sure that we detect when the original files, in the
kernel, gets modified.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-z7e76274ch5j4nugv048qacb@git.kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent c4b6014e
No related merge requests found
This diff is collapsed.
#ifndef _ASM_X86_DISABLED_FEATURES_H
#define _ASM_X86_DISABLED_FEATURES_H
/* These features, although they might be available in a CPU
* will not be used because the compile options to support
* them are not present.
*
* This code allows them to be checked and disabled at
* compile time without an explicit #ifdef. Use
* cpu_feature_enabled().
*/
#ifdef CONFIG_X86_INTEL_MPX
# define DISABLE_MPX 0
#else
# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31))
#endif
#ifdef CONFIG_X86_64
# define DISABLE_VME (1<<(X86_FEATURE_VME & 31))
# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31))
# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31))
# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31))
#else
# define DISABLE_VME 0
# define DISABLE_K6_MTRR 0
# define DISABLE_CYRIX_ARR 0
# define DISABLE_CENTAUR_MCR 0
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
# define DISABLE_PKU 0
# define DISABLE_OSPKE 0
#else
# define DISABLE_PKU (1<<(X86_FEATURE_PKU & 31))
# define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31))
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
/*
* Make sure to add features to the correct mask
*/
#define DISABLED_MASK0 (DISABLE_VME)
#define DISABLED_MASK1 0
#define DISABLED_MASK2 0
#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
#define DISABLED_MASK4 0
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
#define DISABLED_MASK7 0
#define DISABLED_MASK8 0
#define DISABLED_MASK9 (DISABLE_MPX)
#define DISABLED_MASK10 0
#define DISABLED_MASK11 0
#define DISABLED_MASK12 0
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
#ifndef _ASM_X86_REQUIRED_FEATURES_H
#define _ASM_X86_REQUIRED_FEATURES_H
/* Define minimum CPUID feature set for kernel These bits are checked
really early to actually display a visible error message before the
kernel dies. Make sure to assign features to the proper mask!
Some requirements that are not in CPUID yet are also in the
CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
The real information is in arch/x86/Kconfig.cpu, this just converts
the CONFIGs into a bitmask */
#ifndef CONFIG_MATH_EMULATION
# define NEED_FPU (1<<(X86_FEATURE_FPU & 31))
#else
# define NEED_FPU 0
#endif
#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
# define NEED_PAE (1<<(X86_FEATURE_PAE & 31))
#else
# define NEED_PAE 0
#endif
#ifdef CONFIG_X86_CMPXCHG64
# define NEED_CX8 (1<<(X86_FEATURE_CX8 & 31))
#else
# define NEED_CX8 0
#endif
#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
# define NEED_CMOV (1<<(X86_FEATURE_CMOV & 31))
#else
# define NEED_CMOV 0
#endif
#ifdef CONFIG_X86_USE_3DNOW
# define NEED_3DNOW (1<<(X86_FEATURE_3DNOW & 31))
#else
# define NEED_3DNOW 0
#endif
#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
# define NEED_NOPL (1<<(X86_FEATURE_NOPL & 31))
#else
# define NEED_NOPL 0
#endif
#ifdef CONFIG_MATOM
# define NEED_MOVBE (1<<(X86_FEATURE_MOVBE & 31))
#else
# define NEED_MOVBE 0
#endif
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT
/* Paravirtualized systems may not have PSE or PGE available */
#define NEED_PSE 0
#define NEED_PGE 0
#else
#define NEED_PSE (1<<(X86_FEATURE_PSE) & 31)
#define NEED_PGE (1<<(X86_FEATURE_PGE) & 31)
#endif
#define NEED_MSR (1<<(X86_FEATURE_MSR & 31))
#define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31))
#define NEED_XMM (1<<(X86_FEATURE_XMM & 31))
#define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31))
#define NEED_LM (1<<(X86_FEATURE_LM & 31))
#else
#define NEED_PSE 0
#define NEED_MSR 0
#define NEED_PGE 0
#define NEED_FXSR 0
#define NEED_XMM 0
#define NEED_XMM2 0
#define NEED_LM 0
#endif
#define REQUIRED_MASK0 (NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
NEED_XMM|NEED_XMM2)
#define SSE_MASK (NEED_XMM|NEED_XMM2)
#define REQUIRED_MASK1 (NEED_LM|NEED_3DNOW)
#define REQUIRED_MASK2 0
#define REQUIRED_MASK3 (NEED_NOPL)
#define REQUIRED_MASK4 (NEED_MOVBE)
#define REQUIRED_MASK5 0
#define REQUIRED_MASK6 0
#define REQUIRED_MASK7 0
#define REQUIRED_MASK8 0
#define REQUIRED_MASK9 0
#define REQUIRED_MASK10 0
#define REQUIRED_MASK11 0
#define REQUIRED_MASK12 0
#define REQUIRED_MASK13 0
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
#define REQUIRED_MASK16 0
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
/* Copyright 2002 Andi Kleen */
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
/*
* We build a jump to memcpy_orig by default which gets NOPped out on
* the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
* have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
* to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
*/
.weak memcpy
/*
* memcpy - Copy a memory block.
*
* Input:
* rdi destination
* rsi source
* rdx count
*
* Output:
* rax original destination
*/
ENTRY(__memcpy)
ENTRY(memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
movq %rdi, %rax
movq %rdx, %rcx
shrq $3, %rcx
andl $7, %edx
rep movsq
movl %edx, %ecx
rep movsb
ret
ENDPROC(memcpy)
ENDPROC(__memcpy)
/*
* memcpy_erms() - enhanced fast string memcpy. This is faster and
* simpler than memcpy. Use memcpy_erms when possible.
*/
ENTRY(memcpy_erms)
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
ret
ENDPROC(memcpy_erms)
ENTRY(memcpy_orig)
movq %rdi, %rax
cmpq $0x20, %rdx
jb .Lhandle_tail
/*
* We check whether memory false dependence could occur,
* then jump to corresponding copy mode.
*/
cmp %dil, %sil
jl .Lcopy_backward
subq $0x20, %rdx
.Lcopy_forward_loop:
subq $0x20, %rdx
/*
* Move in blocks of 4x8 bytes:
*/
movq 0*8(%rsi), %r8
movq 1*8(%rsi), %r9
movq 2*8(%rsi), %r10
movq 3*8(%rsi), %r11
leaq 4*8(%rsi), %rsi
movq %r8, 0*8(%rdi)
movq %r9, 1*8(%rdi)
movq %r10, 2*8(%rdi)
movq %r11, 3*8(%rdi)
leaq 4*8(%rdi), %rdi
jae .Lcopy_forward_loop
addl $0x20, %edx
jmp .Lhandle_tail
.Lcopy_backward:
/*
* Calculate copy position to tail.
*/
addq %rdx, %rsi
addq %rdx, %rdi
subq $0x20, %rdx
/*
* At most 3 ALU operations in one cycle,
* so append NOPS in the same 16 bytes trunk.
*/
.p2align 4
.Lcopy_backward_loop:
subq $0x20, %rdx
movq -1*8(%rsi), %r8
movq -2*8(%rsi), %r9
movq -3*8(%rsi), %r10
movq -4*8(%rsi), %r11
leaq -4*8(%rsi), %rsi
movq %r8, -1*8(%rdi)
movq %r9, -2*8(%rdi)
movq %r10, -3*8(%rdi)
movq %r11, -4*8(%rdi)
leaq -4*8(%rdi), %rdi
jae .Lcopy_backward_loop
/*
* Calculate copy position to head.
*/
addl $0x20, %edx
subq %rdx, %rsi
subq %rdx, %rdi
.Lhandle_tail:
cmpl $16, %edx
jb .Lless_16bytes
/*
* Move data from 16 bytes to 31 bytes.
*/
movq 0*8(%rsi), %r8
movq 1*8(%rsi), %r9
movq -2*8(%rsi, %rdx), %r10
movq -1*8(%rsi, %rdx), %r11
movq %r8, 0*8(%rdi)
movq %r9, 1*8(%rdi)
movq %r10, -2*8(%rdi, %rdx)
movq %r11, -1*8(%rdi, %rdx)
retq
.p2align 4
.Lless_16bytes:
cmpl $8, %edx
jb .Lless_8bytes
/*
* Move data from 8 bytes to 15 bytes.
*/
movq 0*8(%rsi), %r8
movq -1*8(%rsi, %rdx), %r9
movq %r8, 0*8(%rdi)
movq %r9, -1*8(%rdi, %rdx)
retq
.p2align 4
.Lless_8bytes:
cmpl $4, %edx
jb .Lless_3bytes
/*
* Move data from 4 bytes to 7 bytes.
*/
movl (%rsi), %ecx
movl -4(%rsi, %rdx), %r8d
movl %ecx, (%rdi)
movl %r8d, -4(%rdi, %rdx)
retq
.p2align 4
.Lless_3bytes:
subl $1, %edx
jb .Lend
/*
* Move data from 1 bytes to 3 bytes.
*/
movzbl (%rsi), %ecx
jz .Lstore_1byte
movzbq 1(%rsi), %r8
movzbq (%rsi, %rdx), %r9
movb %r8b, 1(%rdi)
movb %r9b, (%rdi, %rdx)
.Lstore_1byte:
movb %cl, (%rdi)
.Lend:
retq
ENDPROC(memcpy_orig)
#ifndef CONFIG_UML
/*
* memcpy_mcsafe - memory copy with machine check exception handling
* Note that we only catch machine checks when reading the source addresses.
* Writes to target are posted and don't generate machine checks.
*/
ENTRY(memcpy_mcsafe)
cmpl $8, %edx
/* Less than 8 bytes? Go to byte copy loop */
jb .L_no_whole_words
/* Check for bad alignment of source */
testl $7, %esi
/* Already aligned */
jz .L_8byte_aligned
/* Copy one byte at a time until source is 8-byte aligned */
movl %esi, %ecx
andl $7, %ecx
subl $8, %ecx
negl %ecx
subl %ecx, %edx
.L_copy_leading_bytes:
movb (%rsi), %al
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz .L_copy_leading_bytes
.L_8byte_aligned:
/* Figure out how many whole cache lines (64-bytes) to copy */
movl %edx, %ecx
andl $63, %edx
shrl $6, %ecx
jz .L_no_whole_cache_lines
/* Loop copying whole cache lines */
.L_cache_w0: movq (%rsi), %r8
.L_cache_w1: movq 1*8(%rsi), %r9
.L_cache_w2: movq 2*8(%rsi), %r10
.L_cache_w3: movq 3*8(%rsi), %r11
movq %r8, (%rdi)
movq %r9, 1*8(%rdi)
movq %r10, 2*8(%rdi)
movq %r11, 3*8(%rdi)
.L_cache_w4: movq 4*8(%rsi), %r8
.L_cache_w5: movq 5*8(%rsi), %r9
.L_cache_w6: movq 6*8(%rsi), %r10
.L_cache_w7: movq 7*8(%rsi), %r11
movq %r8, 4*8(%rdi)
movq %r9, 5*8(%rdi)
movq %r10, 6*8(%rdi)
movq %r11, 7*8(%rdi)
leaq 64(%rsi), %rsi
leaq 64(%rdi), %rdi
decl %ecx
jnz .L_cache_w0
/* Are there any trailing 8-byte words? */
.L_no_whole_cache_lines:
movl %edx, %ecx
andl $7, %edx
shrl $3, %ecx
jz .L_no_whole_words
/* Copy trailing words */
.L_copy_trailing_words:
movq (%rsi), %r8
mov %r8, (%rdi)
leaq 8(%rsi), %rsi
leaq 8(%rdi), %rdi
decl %ecx
jnz .L_copy_trailing_words
/* Any trailing bytes? */
.L_no_whole_words:
andl %edx, %edx
jz .L_done_memcpy_trap
/* Copy trailing bytes */
movl %edx, %ecx
.L_copy_trailing_bytes:
movb (%rsi), %al
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz .L_copy_trailing_bytes
/* Copy successful. Return zero */
.L_done_memcpy_trap:
xorq %rax, %rax
ret
ENDPROC(memcpy_mcsafe)
.section .fixup, "ax"
/* Return -EFAULT for any failure */
.L_memcpy_mcsafe_fail:
mov $-EFAULT, %rax
ret
.previous
_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
#endif
/* Copyright 2002 Andi Kleen, SuSE Labs */
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
.weak memset
/*
* ISO C memset - set a memory block to a byte value. This function uses fast
* string to get better performance than the original function. The code is
* simpler and shorter than the original function as well.
*
* rdi destination
* rsi value (char)
* rdx count (bytes)
*
* rax original destination
*/
ENTRY(memset)
ENTRY(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
* to use it when possible. If not available, use fast string instructions.
*
* Otherwise, use original memset function.
*/
ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memset_erms", X86_FEATURE_ERMS
movq %rdi,%r9
movq %rdx,%rcx
andl $7,%edx
shrq $3,%rcx
/* expand byte value */
movzbl %sil,%esi
movabs $0x0101010101010101,%rax
imulq %rsi,%rax
rep stosq
movl %edx,%ecx
rep stosb
movq %r9,%rax
ret
ENDPROC(memset)
ENDPROC(__memset)
/*
* ISO C memset - set a memory block to a byte value. This function uses
* enhanced rep stosb to override the fast string function.
* The code is simpler and shorter than the fast string function as well.
*
* rdi destination
* rsi value (char)
* rdx count (bytes)
*
* rax original destination
*/
ENTRY(memset_erms)
movq %rdi,%r9
movb %sil,%al
movq %rdx,%rcx
rep stosb
movq %r9,%rax
ret
ENDPROC(memset_erms)
ENTRY(memset_orig)
movq %rdi,%r10
/* expand byte value */
movzbl %sil,%ecx
movabs $0x0101010101010101,%rax
imulq %rcx,%rax
/* align dst */
movl %edi,%r9d
andl $7,%r9d
jnz .Lbad_alignment
.Lafter_bad_alignment:
movq %rdx,%rcx
shrq $6,%rcx
jz .Lhandle_tail
.p2align 4
.Lloop_64:
decq %rcx
movq %rax,(%rdi)
movq %rax,8(%rdi)
movq %rax,16(%rdi)
movq %rax,24(%rdi)
movq %rax,32(%rdi)
movq %rax,40(%rdi)
movq %rax,48(%rdi)
movq %rax,56(%rdi)
leaq 64(%rdi),%rdi
jnz .Lloop_64
/* Handle tail in loops. The loops should be faster than hard
to predict jump tables. */
.p2align 4
.Lhandle_tail:
movl %edx,%ecx
andl $63&(~7),%ecx
jz .Lhandle_7
shrl $3,%ecx
.p2align 4
.Lloop_8:
decl %ecx
movq %rax,(%rdi)
leaq 8(%rdi),%rdi
jnz .Lloop_8
.Lhandle_7:
andl $7,%edx
jz .Lende
.p2align 4
.Lloop_1:
decl %edx
movb %al,(%rdi)
leaq 1(%rdi),%rdi
jnz .Lloop_1
.Lende:
movq %r10,%rax
ret
.Lbad_alignment:
cmpq $7,%rdx
jbe .Lhandle_7
movq %rax,(%rdi) /* unaligned store */
movq $8,%r8
subq %r9,%r8
addq %r8,%rdi
subq %r8,%rdx
jmp .Lafter_bad_alignment
.Lfinal:
ENDPROC(memset_orig)
#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
#define _PERF_ASM_ALTERNATIVE_ASM_H
#ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
#define _TOOLS_ASM_ALTERNATIVE_ASM_H
/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
......
......@@ -12,6 +12,11 @@ tools/arch/sparc/include/asm/barrier_32.h
tools/arch/sparc/include/asm/barrier_64.h
tools/arch/tile/include/asm/barrier.h
tools/arch/x86/include/asm/barrier.h
tools/arch/x86/include/asm/cpufeatures.h
tools/arch/x86/include/asm/disabled-features.h
tools/arch/x86/include/asm/required-features.h
tools/arch/x86/lib/memcpy_64.S
tools/arch/x86/lib/memset_64.S
tools/arch/xtensa/include/asm/barrier.h
tools/scripts
tools/build
......@@ -31,6 +36,7 @@ tools/lib/find_bit.c
tools/lib/bitmap.c
tools/lib/str_error_r.c
tools/lib/vsprintf.c
tools/include/asm/alternative-asm.h
tools/include/asm/atomic.h
tools/include/asm/barrier.h
tools/include/asm/bug.h
......@@ -74,9 +80,6 @@ include/linux/swab.h
arch/*/include/asm/unistd*.h
arch/*/include/uapi/asm/unistd*.h
arch/*/include/uapi/asm/perf_regs.h
arch/*/lib/memcpy*.S
arch/*/lib/memset*.S
arch/*/include/asm/*features.h
include/linux/poison.h
include/linux/hw_breakpoint.h
include/uapi/linux/bpf.h
......
......@@ -348,6 +348,21 @@ $(PERF_IN): prepare FORCE
@(test -f ../../include/uapi/linux/perf_event.h && ( \
(diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
|| echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
@(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
(diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
|| echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
@(test -f ../../arch/x86/include/asm/required-features.h && ( \
(diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
|| echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
@(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
(diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
|| echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
@(test -f ../../arch/x86/lib/memcpy_64.S && ( \
(diff -B ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
|| echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
@(test -f ../../arch/x86/lib/memset_64.S && ( \
(diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
|| echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
$(Q)$(MAKE) $(build)=perf
$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
......
......@@ -6,7 +6,7 @@
#define globl p2align 4; .globl
#define _ASM_EXTABLE_FAULT(x, y)
#include "../../../arch/x86/lib/memcpy_64.S"
#include "../../arch/x86/lib/memcpy_64.S"
/*
* We need to provide note.GNU-stack section, saying that we want
* NOT executable stack. Otherwise the final linking will assume that
......
#define memset MEMSET /* don't hide glibc's memset() */
#define altinstr_replacement text
#define globl p2align 4; .globl
#include "../../../arch/x86/lib/memset_64.S"
#include "../../arch/x86/lib/memset_64.S"
/*
* We need to provide note.GNU-stack section, saying that we want
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment