arm64: lib: improve copy_page to deal with 128 bytes at a time

We want to avoid lots of different copy_page implementations, settling
for something that is "good enough" everywhere and hopefully easy to
understand and maintain whilst we're at it.

This patch reworks our copy_page implementation based on discussions
with Cavium on the list and benchmarking on Cortex-A processors so that:

  - The loop is unrolled to copy 128 bytes per iteration

  - The reads are offset so that we read from the next 128-byte block
    in the same iteration that we store the previous block

  - Explicit prefetch instructions are removed for now, since they hurt
    performance on CPUs with hardware prefetching

  - The loop exit condition is calculated at the start of the loop

Signed-off-by: Will Deacon <will.deacon@arm.com>
Tested-by: Andrew Pinski <apinski@cavium.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/lib/copy_page.S

@@ -27,20 +27,50 @@
  *	x1 - src
  */
 ENTRY(copy_page)
-	/* Assume cache line size is 64 bytes. */
-	prfm	pldl1strm, [x1, #64]
-1:	ldp	x2, x3, [x1]
+	ldp	x2, x3, [x1]
 	ldp	x4, x5, [x1, #16]
 	ldp	x6, x7, [x1, #32]
 	ldp	x8, x9, [x1, #48]
-	add	x1, x1, #64
-	prfm	pldl1strm, [x1, #64]
+	ldp	x10, x11, [x1, #64]
+	ldp	x12, x13, [x1, #80]
+	ldp	x14, x15, [x1, #96]
+	ldp	x16, x17, [x1, #112]
+
+	mov	x18, #(PAGE_SIZE - 128)
+	add	x1, x1, #128
+1:
+	subs	x18, x18, #128
+
+	stnp	x2, x3, [x0]
+	ldp	x2, x3, [x1]
+	stnp	x4, x5, [x0, #16]
+	ldp	x4, x5, [x1, #16]
+	stnp	x6, x7, [x0, #32]
+	ldp	x6, x7, [x1, #32]
+	stnp	x8, x9, [x0, #48]
+	ldp	x8, x9, [x1, #48]
+	stnp	x10, x11, [x0, #64]
+	ldp	x10, x11, [x1, #64]
+	stnp	x12, x13, [x0, #80]
+	ldp	x12, x13, [x1, #80]
+	stnp	x14, x15, [x0, #96]
+	ldp	x14, x15, [x1, #96]
+	stnp	x16, x17, [x0, #112]
+	ldp	x16, x17, [x1, #112]
+
+	add	x0, x0, #128
+	add	x1, x1, #128
+
+	b.gt	1b
+
 	stnp	x2, x3, [x0]
 	stnp	x4, x5, [x0, #16]
 	stnp	x6, x7, [x0, #32]
 	stnp	x8, x9, [x0, #48]
-	add	x0, x0, #64
-	tst	x1, #(PAGE_SIZE - 1)
-	b.ne	1b
+	stnp	x10, x11, [x0, #64]
+	stnp	x12, x13, [x0, #80]
+	stnp	x14, x15, [x0, #96]
+	stnp	x16, x17, [x0, #112]
+
 	ret
 ENDPROC(copy_page)