From da7bc9c57eb0e91e048d05f7dbe5014a8b81ccfa Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 3 May 2018 17:06:11 -0700 Subject: 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 Signed-off-by: Dan Williams Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck 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 --- arch/x86/lib/memcpy_64.S | 59 ++++++++---------------------------------------- 1 file changed, 10 insertions(+), 49 deletions(-) (limited to 'arch/x86/lib') diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 9a53a06e5a3e..54c971892db5 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 -- cgit v1.2.3