diff options
author | Dan Williams <dan.j.williams@intel.com> | 2018-05-03 17:06:11 -0700 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2018-05-15 08:32:41 +0200 |
commit | da7bc9c57eb0e91e048d05f7dbe5014a8b81ccfa (patch) | |
tree | a9f7f781dc1e2b803ffed73e16f8860ff1d086f9 | |
parent | 67b8d5c7081221efa252e111cd52532ec6d4266f (diff) | |
download | op-kernel-dev-da7bc9c57eb0e91e048d05f7dbe5014a8b81ccfa.zip op-kernel-dev-da7bc9c57eb0e91e048d05f7dbe5014a8b81ccfa.tar.gz |
x86/asm/memcpy_mcsafe: Remove loop unrolling
In preparation for teaching memcpy_mcsafe() to return 'bytes remaining'
rather than pass / fail, simplify the implementation to remove loop
unrolling. The unrolling complicates the fault handling for negligible
benefit given modern CPUs perform loop stream detection.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: hch@lst.de
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-nvdimm@lists.01.org
Link: http://lkml.kernel.org/r/152539237092.31796.9115692316555638048.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r-- | arch/x86/include/asm/string_64.h | 4 | ||||
-rw-r--r-- | arch/x86/lib/memcpy_64.S | 59 |
2 files changed, 12 insertions, 51 deletions
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 533f74c..4752f89 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -116,7 +116,7 @@ int strcmp(const char *cs, const char *ct); #endif #define __HAVE_ARCH_MEMCPY_MCSAFE 1 -__must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt); +__must_check int __memcpy_mcsafe(void *dst, const void *src, size_t cnt); DECLARE_STATIC_KEY_FALSE(mcsafe_key); /** @@ -138,7 +138,7 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt) { #ifdef CONFIG_X86_MCE if (static_branch_unlikely(&mcsafe_key)) - return memcpy_mcsafe_unrolled(dst, src, cnt); + return __memcpy_mcsafe(dst, src, cnt); else #endif memcpy(dst, src, cnt); diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 9a53a06..54c9718 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -184,11 +184,11 @@ ENDPROC(memcpy_orig) #ifndef CONFIG_UML /* - * memcpy_mcsafe_unrolled - memory copy with machine check exception handling + * __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_unrolled) +ENTRY(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -213,49 +213,18 @@ ENTRY(memcpy_mcsafe_unrolled) 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: +.L_copy_words: movq (%rsi), %r8 - mov %r8, (%rdi) - leaq 8(%rsi), %rsi - leaq 8(%rdi), %rdi + movq %r8, (%rdi) + addq $8, %rsi + addq $8, %rdi decl %ecx - jnz .L_copy_trailing_words + jnz .L_copy_words /* Any trailing bytes? */ .L_no_whole_words: @@ -276,8 +245,8 @@ ENTRY(memcpy_mcsafe_unrolled) .L_done_memcpy_trap: xorq %rax, %rax ret -ENDPROC(memcpy_mcsafe_unrolled) -EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) +ENDPROC(__memcpy_mcsafe) +EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" /* Return -EFAULT for any failure */ @@ -288,14 +257,6 @@ EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) .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_w2, .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_words, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) #endif |