mm/dmapool.c: micro-optimisation remove unnecessary branch

Previously there was a check if 'size' is aligned to 'align' and if not then it was aligned. This check was expensive as both branch and division are expensive instructions in most architectures. 'ALIGN' function on already aligned value will not change it, and as it is cheaper than branch + division it can be executed all the time and branch can be removed. Signed-off-by: Mateusz Nosek <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Reviewed-by: Andrew Morton <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Linus Torvalds <[email protected]>
ambv · Apr 7, 2020 · 1386f7a · 1386f7a
1 parent 1d90b64
commit 1386f7a
Showing 1 changed file with 1 addition and 3 deletions.
diff --git a/mm/dmapool.c b/mm/dmapool.c
@@ -144,9 +144,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
 	else if (size < 4)
 		size = 4;
 
-	if ((size % align) != 0)
-		size = ALIGN(size, align);
-
+	size = ALIGN(size, align);
 	allocation = max_t(size_t, size, PAGE_SIZE);
 
 	if (!boundary)