[PATCH 2/5] x86_64: inline copy_page() at call site

[Alexey Dobriyan]

Avoid unconditional branch at every copy_page() call by using
alternatives and calling optimal variant directly.

Rename individual versions to immediately show which one is used in
profiles, etc.

RBX and R12 aren't clobbered because generic version restores them
and both REP versions don't touch them.

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

 arch/x86/include/asm/page_64.h |   16 ++++++++++++++--
 arch/x86/lib/copy_page_64.S    |   17 +++++++----------
 2 files changed, 21 insertions(+), 12 deletions(-)

--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -49,8 +49,20 @@ static inline void clear_page(void *page)
 			   : "memory", "rax", "rcx");
 }
 
-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", "cc", "memory"
+	);
+}
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
--- 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>
 #include <asm/export.h>
 
 /*
@@ -12,23 +10,21 @@
  * 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)
-EXPORT_SYMBOL(copy_page)
+ENDPROC(copy_page_rep_movsq)
+EXPORT_SYMBOL(copy_page_rep_movsq)
 
 ENTRY(copy_page_rep_movsb)
 	mov	$4096, %ecx
 	rep movsb
 	ret
 ENDPROC(copy_page_rep_movsb)
+EXPORT_SYMBOL(copy_page_rep_movsb)
 
-ENTRY(copy_page_regs)
+ENTRY(copy_page_mov)
 	subq	$2*8,	%rsp
 	movq	%rbx,	(%rsp)
 	movq	%r12,	1*8(%rsp)
@@ -93,4 +89,5 @@ ENTRY(copy_page_regs)
 	movq	1*8(%rsp), %r12
 	addq	$2*8, %rsp
 	ret
-ENDPROC(copy_page_regs)
+ENDPROC(copy_page_mov)
+EXPORT_SYMBOL(copy_page_mov)