From: Paolo Abeni <pabeni@xxxxxxxxxx> commit 236222d39347e0e486010f10c1493e83dbbdfba8 upstream. According to the Intel datasheet, the REP MOVSB instruction exposes a pretty heavy setup cost (50 ticks), which hurts short string copy operations. This change tries to avoid this cost by calling the explicit loop available in the unrolled code for strings shorter than 64 bytes. The 64 bytes cutoff value is arbitrary from the code logic point of view - it has been selected based on measurements, as the largest value that still ensures a measurable gain. Micro benchmarks of the __copy_from_user() function with lengths in the [0-63] range show this performance gain (shorter the string, larger the gain): - in the [55%-4%] range on Intel Xeon(R) CPU E5-2690 v4 - in the [72%-9%] range on Intel Core i7-4810MQ Other tested CPUs - namely Intel Atom S1260 and AMD Opteron 8216 - show no difference, because they do not expose the ERMS feature bit. Signed-off-by: Paolo Abeni <pabeni@xxxxxxxxxx> Acked-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Alan Cox <gnomes@xxxxxxxxxxxxxxxxxxx> Cc: Andy Lutomirski <luto@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Brian Gerst <brgerst@xxxxxxxxx> Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx> Cc: H. Peter Anvin <hpa@xxxxxxxxx> Cc: Hannes Frederic Sowa <hannes@xxxxxxxxxxxxxxxxxxx> Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx> Cc: Kees Cook <keescook@xxxxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Link: http://lkml.kernel.org/r/4533a1d101fd460f80e21329a34928fad521c1d4.1498744345.git.pabeni@xxxxxxxxxx [ Clarified the changelog. ] Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> --- arch/x86/lib/copy_user_64.S | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index c5959576c315..020f75cc8cf6 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -37,7 +37,7 @@ ENTRY(copy_user_generic_unrolled) movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_copy_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -58,7 +58,8 @@ ENTRY(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -17: movl %edx,%ecx +.L_copy_short_string: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx jz 20f @@ -174,6 +175,8 @@ EXPORT_SYMBOL(copy_user_generic_string) */ ENTRY(copy_user_enhanced_fast_string) ASM_STAC + cmpl $64,%edx + jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */ movl %edx,%ecx 1: rep movsb -- 2.13.1