x86/cpufeatures: Add support for fast short REP; MOVSB

>From the Intel Optimization Reference Manual:

3.7.6.1 Fast Short REP MOVSB
Beginning with processors based on Ice Lake Client microarchitecture,
REP MOVSB performance of short operations is enhanced. The enhancement
applies to string lengths between 1 and 128 bytes long.  Support for
fast-short REP MOVSB is enumerated by the CPUID feature flag: CPUID
[EAX=7H, ECX=0H).EDX.FAST_SHORT_REP_MOVSB[bit 4] = 1. There is no change
in the REP STOS performance.

Add an X86_FEATURE_FSRM flag for this.

memmove() avoids REP MOVSB for short (< 32 byte) copies. Check FSRM and
use REP MOVSB for short copies on systems that support it.

 [ bp: Massage and add comment. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20191216214254.26492-1-tony.luck@intel.com

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index e9b62498fe75a3f3fce3692678e5ff28bbb28880..98c60fa31cedab4417daf1b183e0c478378b4295 100644 (file)
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -357,6 +357,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW      (18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS      (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM               (18*32+ 4) /* Fast Short Rep Mov */
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR           (18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT    (18*32+13) /* "" TSX_FORCE_ABORT */

diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 337830d7a59c75adfb1fc81be3ee1c51e092b18e..7ff00ea64e4fe558f11a8f4c8961551edf35d84b 100644 (file)
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -29,10 +29,7 @@
 SYM_FUNC_START_ALIAS(memmove)
 SYM_FUNC_START(__memmove)
 
-       /* Handle more 32 bytes in loop */
        mov %rdi, %rax
-       cmp $0x20, %rdx
-       jb      1f
 
        /* Decide forward/backward copy mode */
        cmp %rdi, %rsi
@@ -42,7 +39,9 @@ SYM_FUNC_START(__memmove)
        cmp %rdi, %r8
        jg 2f
 
+       /* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
+       ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
        ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS
 
        /*
@@ -114,6 +113,8 @@ SYM_FUNC_START(__memmove)
         */
        .p2align 4
 2:
+       cmp $0x20, %rdx
+       jb 1f
        cmp $680, %rdx
        jb 6f
        cmp %dil, %sil