[PATCH 1/5] x86_64: use REP MOVSB in copy_page()

[Alexey Dobriyan]

On my Broadwell-era Xeon copying page with REP MOVSB is ~7.8% faster
than with REP MOVSQ. Choose REP MOVSB copy_page() at runtime
with alternatives.

Signed-off-by: Alexey Dobriyan <adobriyan@xxxxxxxxx>
---

 arch/x86/lib/copy_page_64.S |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -13,13 +13,21 @@
  */
 	ALIGN
 ENTRY(copy_page)
-	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
+	ALTERNATIVE_2 "jmp copy_page_regs",	\
+		"", X86_FEATURE_REP_GOOD,	\
+		"jmp copy_page_rep_movsb", X86_FEATURE_ERMS
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
 ENDPROC(copy_page)
 EXPORT_SYMBOL(copy_page)
 
+ENTRY(copy_page_rep_movsb)
+	mov	$4096, %ecx
+	rep movsb
+	ret
+ENDPROC(copy_page_rep_movsb)
+
 ENTRY(copy_page_regs)
 	subq	$2*8,	%rsp
 	movq	%rbx,	(%rsp)