[PATCH v3 7/7] x86: switch the 64bit uncached page clear to SSE/AVX v2

[Kirill A. Shutemov]

From: Andi Kleen <ak at linux.intel.com>

With multiple threads vector stores are more efficient, so use them.
This will cause the page clear to run non preemptable and add some
overhead. However on 32bit it was already non preempable (due to
kmap_atomic) and there is an preemption opportunity every 4K unit.

On a NPB (Nasa Parallel Benchmark) 128GB run on a Westmere this improves
the performance regression of enabling transparent huge pages
by ~2% (2.81% to 0.81%), near the runtime variability now.
On a system with AVX support more is expected.

Signed-off-by: Andi Kleen <ak at linux.intel.com>
[kirill.shutemov at linux.intel.com: Properly save/restore arguments]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
---
 arch/x86/lib/clear_page_64.S |   79 ++++++++++++++++++++++++++++++++++--------
 1 files changed, 64 insertions(+), 15 deletions(-)

diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 9d2f3c2..b302cff 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -73,30 +73,79 @@ ENDPROC(clear_page)
 			     .Lclear_page_end-clear_page,3b-2b
 	.previous
 
+#define SSE_UNROLL 128
+
 /*
  * Zero a page avoiding the caches
  * rdi	page
  */
 ENTRY(clear_page_nocache)
 	CFI_STARTPROC
-	xorl   %eax,%eax
-	movl   $4096/64,%ecx
+	pushq_cfi %rdi
+	call   kernel_fpu_begin
+	popq_cfi  %rdi
+	sub    $16,%rsp
+	CFI_ADJUST_CFA_OFFSET 16
+	movdqu %xmm0,(%rsp)
+	xorpd  %xmm0,%xmm0
+	movl   $4096/SSE_UNROLL,%ecx
 	.p2align 4
 .Lloop_nocache:
 	decl	%ecx
-#define PUT(x) movnti %rax,x*8(%rdi)
-	movnti %rax,(%rdi)
-	PUT(1)
-	PUT(2)
-	PUT(3)
-	PUT(4)
-	PUT(5)
-	PUT(6)
-	PUT(7)
-#undef PUT
-	leaq	64(%rdi),%rdi
+	.set x,0
+	.rept SSE_UNROLL/16
+	movntdq %xmm0,x(%rdi)
+	.set x,x+16
+	.endr
+	leaq	SSE_UNROLL(%rdi),%rdi
 	jnz	.Lloop_nocache
-	nop
-	ret
+	movdqu (%rsp),%xmm0
+	addq   $16,%rsp
+	CFI_ADJUST_CFA_OFFSET -16
+	jmp   kernel_fpu_end
 	CFI_ENDPROC
 ENDPROC(clear_page_nocache)
+
+#ifdef CONFIG_AS_AVX
+
+	.section .altinstr_replacement,"ax"
+1:	.byte 0xeb					/* jmp <disp8> */
+	.byte (clear_page_nocache_avx - clear_page_nocache) - (2f - 1b)
+	/* offset */
+2:
+	.previous
+	.section .altinstructions,"a"
+	altinstruction_entry clear_page_nocache,1b,X86_FEATURE_AVX,\
+	                     16, 2b-1b
+	.previous
+
+#define AVX_UNROLL 256 /* TUNE ME */
+
+ENTRY(clear_page_nocache_avx)
+	CFI_STARTPROC
+	pushq_cfi %rdi
+	call   kernel_fpu_begin
+	popq_cfi  %rdi
+	sub    $32,%rsp
+	CFI_ADJUST_CFA_OFFSET 32
+	vmovdqu %ymm0,(%rsp)
+	vxorpd  %ymm0,%ymm0,%ymm0
+	movl   $4096/AVX_UNROLL,%ecx
+	.p2align 4
+.Lloop_avx:
+	decl	%ecx
+	.set x,0
+	.rept AVX_UNROLL/32
+	vmovntdq %ymm0,x(%rdi)
+	.set x,x+32
+	.endr
+	leaq	AVX_UNROLL(%rdi),%rdi
+	jnz	.Lloop_avx
+	vmovdqu (%rsp),%ymm0
+	addq   $32,%rsp
+	CFI_ADJUST_CFA_OFFSET -32
+	jmp   kernel_fpu_end
+	CFI_ENDPROC
+ENDPROC(clear_page_nocache_avx)
+
+#endif
-- 
1.7.7.6