[PATCH v2] arch/x86: Improve 'rep movs{b|q}' usage in memmove_64.S

[Noah Goldstein]

Add check for "short distance movsb" for forwards FSRM usage and
entirely remove backwards 'rep movsq'. Both of these usages hit "slow
modes" that are an order of magnitude slower than usual.

'rep movsb' has some noticeable VERY slow modes that the current
implementation is either 1) not checking for or 2) intentionally
using.

All times are in cycles and measuring the throughput of copying 1024
bytes.

1. For FSRM, when 'dst - src' is in (1, 63] or (4GB, 4GB + 63] it is
   an order of magnitude slower than normal and much slower than a 4x
   'movq' loop.

    FSRM forward (dst - src == 32)   -> 1113.156
    FSRM forward (dst - src == 64)   -> 120.669

    ERMS forward (dst - src == 32)   -> 209.326
    ERMS forward (dst - src == 64)   -> 118.22

2. For both FSRM and ERMS backwards 'rep movsb' is always slow. Both
   of the times below are with dst % 256 == src % 256 which mirrors
   the usage of the previous implementation.

    FSRM backward                    -> 1196.039
    ERMS backward                    -> 1191.873

As a reference this is how a 4x 'movq' performances:

    4x Forward (dst - src == 32)     -> 128.273
    4x Backward                      -> 130.183

Signed-off-by: Noah Goldstein <goldstein.w.n@xxxxxxxxx>
---
Mistake in V1. Had forgotten to remove the logic jumping to backwards
'rep movsq'.
 arch/x86/lib/memmove_64.S | 34 +++++++++++-----------------------
 1 file changed, 11 insertions(+), 23 deletions(-)

diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 64801010d312..90eb2487fde2 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -39,7 +39,16 @@ SYM_FUNC_START(__memmove)
 
 	/* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
-	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
+	/*
+	 * Don't use FSRM 'rep movsb' if 'dst - src' in (0, 63] or (4GB, 4GB +
+	 * 63]. It hits a slow case which is an order of magnitude slower.
+	 */
+	ALTERNATIVE "cmp $0x20, %rdx;"
+				"jb 1f;"
+				"mov %edi, %ecx;"
+				"sub %esi, %ecx;"
+				"cmp $63, %ecx;"
+				"jb 3f;", "", X86_FEATURE_FSRM
 	ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS
 
 	/*
@@ -89,23 +98,6 @@ SYM_FUNC_START(__memmove)
 	jmp 13f
 .Lmemmove_end_forward:
 
-	/*
-	 * Handle data backward by movsq.
-	 */
-	.p2align 4
-7:
-	movq %rdx, %rcx
-	movq (%rsi), %r11
-	movq %rdi, %r10
-	leaq -8(%rsi, %rdx), %rsi
-	leaq -8(%rdi, %rdx), %rdi
-	shrq $3, %rcx
-	std
-	rep movsq
-	cld
-	movq %r11, (%r10)
-	jmp 13f
-
 	/*
 	 * Start to prepare for backward copy.
 	 */
@@ -113,11 +105,7 @@ SYM_FUNC_START(__memmove)
 2:
 	cmp $0x20, %rdx
 	jb 1f
-	cmp $680, %rdx
-	jb 6f
-	cmp %dil, %sil
-	je 7b
-6:
+
 	/*
 	 * Calculate copy position to tail.
 	 */
-- 
2.25.1