amd64: switch pagecopy from non-temporal stores to rep movsq

The copied data is accessed in part soon after and it results with additional
cache misses during a -j 1 buildkernel WITHOUT_CTF=yes KERNFAST=1, as measured
with pmc stat.

before:
       256165411  cache-references	#	0.003 refs/inst
        15105408  cache-misses		#	5.897%
           20.70  real			#	99.67% cpu
           13.24  user			#	63.94% cpu
            7.40  sys			#	35.73% cpu

after:
       256764469  cache-references	#	0.003 refs/inst
        11913551  cache-misses		#	4.640%
           20.70  real			#	99.67% cpu
           13.19  user			#	63.73% cpu
            7.44  sys			#	35.95% cpu

Note the real time did not change, but traffic to RAM was reduced (multiple
measurements performed with switching the implementation at runtime).
Since nobody else is using non-temporal for this and there is no apparent
benefit at least these days, don't use them either.

Side note is that pagecopy arguments should probably get reversed to not
have to flip them around in the primitive.

Discussed with:		jeff

1 files changed, 6 insertions, 20 deletions

diff --git a/sys/amd64/amd64/support.S b/sys/amd64/amd64/support.S
index d3e1c5319811..3bdaac548cc6 100644
--- a/sys/amd64/amd64/support.S
+++ b/sys/amd64/amd64/support.S
@@ -281,26 +281,12 @@ END(memset)
  */
 ENTRY(pagecopy)
 	PUSH_FRAME_POINTER
-	movq	$-PAGE_SIZE,%rax
-	movq	%rax,%rdx
-	subq	%rax,%rdi
-	subq	%rax,%rsi
-1:
-	prefetchnta (%rdi,%rax)
-	addq	$64,%rax
-	jne	1b
-2:
-	movq	(%rdi,%rdx),%rax
-	movnti	%rax,(%rsi,%rdx)
-	movq	8(%rdi,%rdx),%rax
-	movnti	%rax,8(%rsi,%rdx)
-	movq	16(%rdi,%rdx),%rax
-	movnti	%rax,16(%rsi,%rdx)
-	movq	24(%rdi,%rdx),%rax
-	movnti	%rax,24(%rsi,%rdx)
-	addq	$32,%rdx
-	jne	2b
-	sfence
+	movq	$PAGE_SIZE/8,%rcx
+	movq	%rdi,%r9
+	movq	%rsi,%rdi
+	movq	%r9,%rsi
+	rep
+	movsq
 	POP_FRAME_POINTER
 	ret
 END(pagecopy)