diff mbox series

x86/lib: Optimise copy loop for long buffers in csum-partial_64.c

Message ID 04c41a96f4eb4fe782d10ae2691ad93e@AcuMS.aculab.com (mailing list archive)
State Not Applicable
Delegated to: Netdev Maintainers
Headers show
Series x86/lib: Optimise copy loop for long buffers in csum-partial_64.c | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch

Commit Message

David Laight Jan. 6, 2022, 4:19 p.m. UTC
gcc converts the loop into one that only increments the pointer
but makes a mess of calculating the limit and gcc 9.1+ completely
refuses to use the final value of 'buff' from the last iteration.

Explicitly code a pointer comparison and don't bother changing len.

Signed-off-by: David Laight <david.laight@aculab.com>
---

The asm("" : "+r" (buff)); forces gcc to use the loop-updated
value of 'buff' and removes at least 6 instructions.

The gcc folk really ought to look at why gcc 9.1 onwards is so
much worse that gcc 8.
See https://godbolt.org/z/T39PcnvfE


 arch/x86/lib/csum-partial_64.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index edd3e579c2a7..342de5f24fcb 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -27,21 +27,24 @@  __wsum csum_partial(const void *buff, int len, __wsum sum)
 	u64 temp64 = (__force u64)sum;
 	unsigned result;
 
-	while (unlikely(len >= 64)) {
-		asm("addq 0*8(%[src]),%[res]\n\t"
-		    "adcq 1*8(%[src]),%[res]\n\t"
-		    "adcq 2*8(%[src]),%[res]\n\t"
-		    "adcq 3*8(%[src]),%[res]\n\t"
-		    "adcq 4*8(%[src]),%[res]\n\t"
-		    "adcq 5*8(%[src]),%[res]\n\t"
-		    "adcq 6*8(%[src]),%[res]\n\t"
-		    "adcq 7*8(%[src]),%[res]\n\t"
-		    "adcq $0,%[res]"
-		    : [res] "+r" (temp64)
-		    : [src] "r" (buff)
-		    : "memory");
-		buff += 64;
-		len -= 64;
+	if (unlikely(len >= 64)) {
+		const void *lim = buff + (len & ~63u);
+		do {
+			asm("addq 0*8(%[src]),%[res]\n\t"
+			    "adcq 1*8(%[src]),%[res]\n\t"
+			    "adcq 2*8(%[src]),%[res]\n\t"
+			    "adcq 3*8(%[src]),%[res]\n\t"
+			    "adcq 4*8(%[src]),%[res]\n\t"
+			    "adcq 5*8(%[src]),%[res]\n\t"
+			    "adcq 6*8(%[src]),%[res]\n\t"
+			    "adcq 7*8(%[src]),%[res]\n\t"
+			    "adcq $0,%[res]"
+			    : [res] "+r" (temp64)
+			    : [src] "r" (buff)
+			    : "memory");
+			asm("" : "+r" (buff));
+			buff += 64;
+		} while (buff < lim);
 	}
 
 	if (len & 32) {