This avoids potential "bleeding" when size == 0 as cache line would be
dirtied (and possibly fetched from other cores) and due to the same
reaons more optimal too.
Signed-off-by: Vineet Gupta <[email protected]>
---
arch/arc/lib/memset-archs.S | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index d2e09fece5bc..d0a5cec4cdca 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -36,12 +36,13 @@
#endif
ENTRY_CFI(memset)
- PREFETCHW_INSTR r0, 0 ; Prefetch the first write location
mov.f 0, r2
;;; if size is zero
jz.d [blink]
mov r3, r0 ; don't clobber ret val
+ PREFETCHW_INSTR r0, 0 ; Prefetch the first write location
+
;;; if length < 8
brls.d.nt r2, 8, .Lsmallchunk
mov.f lp_count,r2
--
2.34.1