Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 269833bd authored by Ma Ling's avatar Ma Ling Committed by Ingo Molnar
Browse files

x86/asm: Clean up copy_page_*() comments and code 



Modern CPUs use fast-string instruction to accelerate copy
performance, by combining data into 128 bit chunks.

Modify comments and coding style to match it.

Signed-off-by: default avatarMa Ling <ling.ma@intel.com>
Cc: iant@google.com
Link: http://lkml.kernel.org/r/1350503565-19167-1-git-send-email-ling.ma@intel.com


[ Cleaned up the clean up. ]
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 0e9e3e30

arch/x86/lib/copy_page_64.S

+59 −61
Original line number Diff line number Diff line
@@ -5,18 +5,18 @@ 
#include <asm/alternative-asm.h>



	ALIGN

copy_page_c:

copy_page_rep:

	CFI_STARTPROC

	movl	$4096/8, %ecx

	rep	movsq

	ret

	CFI_ENDPROC

ENDPROC(copy_page_c)

ENDPROC(copy_page_rep)



/* Don't use streaming store because it's better when the target

   ends up in cache. */

	    

/* Could vary the prefetch distance based on SMP/UP */

/*

 *  Don't use streaming copy unless the CPU indicates X86_FEATURE_REP_GOOD.

 *  Could vary the prefetch distance based on SMP/UP.

*/



ENTRY(copy_page)

	CFI_STARTPROC
@@ -31,26 +31,25 @@ ENTRY(copy_page) 
	.p2align 4

.Loop64:

	dec	%rcx



	movq        (%rsi), %rax

	movq      8 (%rsi), %rbx

	movq     16 (%rsi), %rdx

	movq     24 (%rsi), %r8

	movq     32 (%rsi), %r9

	movq     40 (%rsi), %r10

	movq     48 (%rsi), %r11

	movq     56 (%rsi), %r12

	movq	0x8*0(%rsi), %rax

	movq	0x8*1(%rsi), %rbx

	movq	0x8*2(%rsi), %rdx

	movq	0x8*3(%rsi), %r8

	movq	0x8*4(%rsi), %r9

	movq	0x8*5(%rsi), %r10

	movq	0x8*6(%rsi), %r11

	movq	0x8*7(%rsi), %r12



	prefetcht0 5*64(%rsi)



	movq     %rax,    (%rdi)

	movq     %rbx,  8 (%rdi)

	movq     %rdx, 16 (%rdi)

	movq     %r8,  24 (%rdi)

	movq     %r9,  32 (%rdi)

	movq     %r10, 40 (%rdi)

	movq     %r11, 48 (%rdi)

	movq     %r12, 56 (%rdi)

	movq	%rax, 0x8*0(%rdi)

	movq	%rbx, 0x8*1(%rdi)

	movq	%rdx, 0x8*2(%rdi)

	movq	%r8,  0x8*3(%rdi)

	movq	%r9,  0x8*4(%rdi)

	movq	%r10, 0x8*5(%rdi)

	movq	%r11, 0x8*6(%rdi)

	movq	%r12, 0x8*7(%rdi)



	leaq	64 (%rsi), %rsi

	leaq	64 (%rdi), %rdi
@@ -62,27 +61,26 @@ ENTRY(copy_page) 
.Loop2:

	decl	%ecx



	movq        (%rsi), %rax

	movq      8 (%rsi), %rbx

	movq     16 (%rsi), %rdx

	movq     24 (%rsi), %r8

	movq     32 (%rsi), %r9

	movq     40 (%rsi), %r10

	movq     48 (%rsi), %r11

	movq     56 (%rsi), %r12



	movq     %rax,    (%rdi)

	movq     %rbx,  8 (%rdi)

	movq     %rdx, 16 (%rdi)

	movq     %r8,  24 (%rdi)

	movq     %r9,  32 (%rdi)

	movq     %r10, 40 (%rdi)

	movq     %r11, 48 (%rdi)

	movq     %r12, 56 (%rdi)

	movq	0x8*0(%rsi), %rax

	movq	0x8*1(%rsi), %rbx

	movq	0x8*2(%rsi), %rdx

	movq	0x8*3(%rsi), %r8

	movq	0x8*4(%rsi), %r9

	movq	0x8*5(%rsi), %r10

	movq	0x8*6(%rsi), %r11

	movq	0x8*7(%rsi), %r12



	movq	%rax, 0x8*0(%rdi)

	movq	%rbx, 0x8*1(%rdi)

	movq	%rdx, 0x8*2(%rdi)

	movq	%r8,  0x8*3(%rdi)

	movq	%r9,  0x8*4(%rdi)

	movq	%r10, 0x8*5(%rdi)

	movq	%r11, 0x8*6(%rdi)

	movq	%r12, 0x8*7(%rdi)



	leaq	64(%rdi), %rdi

	leaq	64(%rsi), %rsi



	jnz	.Loop2



	movq	(%rsp), %rbx
@@ -103,7 +101,7 @@ ENDPROC(copy_page) 


	.section .altinstr_replacement,"ax"

1:	.byte 0xeb					/* jmp <disp8> */

	.byte (copy_page_c - copy_page) - (2f - 1b)	/* offset */

	.byte (copy_page_rep - copy_page) - (2f - 1b)	/* offset */

2:

	.previous

	.section .altinstructions,"a"