arm64: atomics: prefetch the destination word for write prior to stxr

The cost of changing a cacheline from shared to exclusive state can be
significant, especially when this is triggered by an exclusive store,
since it may result in having to retry the transaction.

This patch makes use of prfm to prefetch cachelines for write prior to
ldxr/stxr loops when using the ll/sc atomic routines.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
index bc18457..43ac736 100644
--- a/arch/arm64/lib/bitops.S
+++ b/arch/arm64/lib/bitops.S
@@ -31,6 +31,7 @@
 	eor	w0, w0, w3		// Clear low bits
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
+alt_lse "	prfm	pstl1strm, [x1]",	"nop"
 	lsl	x3, x2, x3		// Create mask
 
 alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
@@ -48,6 +49,7 @@
 	eor	w0, w0, w3		// Clear low bits
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
+alt_lse "	prfm	pstl1strm, [x1]",	"nop"
 	lsl	x4, x2, x3		// Create mask
 
 alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"