[PATCH 3/3] x86: branchless copy_page()

[Alexey Dobriyan]

Apply alternatives at the call site instead of function body.
Save branch per copied page.

Rename individual function, show immediately in profiles
which method is being used.

RBX and R12 are saved and restored by unrolled-mov implementation,
don't clobber them explicitly.

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

 arch/x86/include/asm/page_64.h   |   15 ++++++++++++++-
 arch/x86/kernel/x8664_ksyms_64.c |    4 +++-
 arch/x86/lib/copy_page_64.S      |   14 ++++----------
 3 files changed, 21 insertions(+), 12 deletions(-)

--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -49,8 +49,21 @@ static __always_inline void clear_page(void *page)
 		: "rax", "rcx", "memory"
 	);
 }
-void copy_page(void *to, void *from);
 
+void copy_page_mov(void *to, void *from);
+void copy_page_rep_movsq(void *to, void *from);
+void copy_page_rep_movsb(void *to, void *from);
+static __always_inline void copy_page(void *to, void *from)
+{
+	alternative_call_2(
+		copy_page_mov,
+		copy_page_rep_movsq, X86_FEATURE_REP_GOOD,
+		copy_page_rep_movsb, X86_FEATURE_ERMS,
+		ASM_OUTPUT2("=D" (to), "=S" (from)),
+		"0" (to), "1" (from)
+		: "rax", "rcx", "rdx", "r8", "r9", "r10", "r11", "memory"
+	);
+}
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -40,7 +40,9 @@ EXPORT_SYMBOL(_copy_to_user);
 
 EXPORT_SYMBOL_GPL(memcpy_mcsafe);
 
-EXPORT_SYMBOL(copy_page);
+EXPORT_SYMBOL(copy_page_mov);
+EXPORT_SYMBOL(copy_page_rep_movsq);
+EXPORT_SYMBOL(copy_page_rep_movsb);
 EXPORT_SYMBOL(clear_page_mov);
 EXPORT_SYMBOL(clear_page_rep_stosq);
 EXPORT_SYMBOL(clear_page_rep_stosb);
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,8 +1,6 @@
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
 
 /*
  * Some CPUs run faster using the string copy instructions (sane microcode).
@@ -11,15 +9,11 @@
  * prefetch distance based on SMP/UP.
  */
 	ALIGN
-ENTRY(copy_page)
-	ALTERNATIVE_2 "jmp copy_page_regs",	\
-		"", X86_FEATURE_REP_GOOD,	\
-		"jmp copy_page_rep_movsb", X86_FEATURE_ERMS
-
+ENTRY(copy_page_rep_movsq)
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
-ENDPROC(copy_page)
+ENDPROC(copy_page_rep_movsq)
 
 ENTRY(copy_page_rep_movsb)
 	mov	$4096, %ecx
@@ -27,7 +21,7 @@ ENTRY(copy_page_rep_movsb)
 	ret
 ENDPROC(copy_page_rep_movsb)
 
-ENTRY(copy_page_regs)
+ENTRY(copy_page_mov)
 	subq	$2*8,	%rsp
 	movq	%rbx,	(%rsp)
 	movq	%r12,	1*8(%rsp)
@@ -92,4 +86,4 @@ ENTRY(copy_page_regs)
 	movq	1*8(%rsp), %r12
 	addq	$2*8, %rsp
 	ret
-ENDPROC(copy_page_regs)
+ENDPROC(copy_page_mov)