mm, pagealloc: micro-optimisation: save two branches on hot page allocation path
This patch makes ALLOC_KSWAPD equal to __GFP_KSWAPD_RECLAIM (cast to int).
Thanks to that code like:
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
alloc_flags |= ALLOC_KSWAPD;
can be changed to:
alloc_flags |= (__force int) (gfp_mask &__GFP_KSWAPD_RECLAIM);
Thanks to this one branch less is generated in the assembly.
In case of ALLOC_KSWAPD flag two branches are saved, first one in code
that always executes in the beginning of page allocation and the second
one in loop in page allocator slowpath.
Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: http://lkml.kernel.org/r/20200304162118.14784-1-mateusznosek0@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fb0b3ff..2dedf5a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3536,10 +3536,13 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
static inline unsigned int
alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
{
- unsigned int alloc_flags = 0;
+ unsigned int alloc_flags;
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
- alloc_flags |= ALLOC_KSWAPD;
+ /*
+ * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+ * to save a branch.
+ */
+ alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
#ifdef CONFIG_ZONE_DMA32
if (!zone)
@@ -4175,8 +4178,13 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
{
unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+ /*
+ * __GFP_HIGH is assumed to be the same as ALLOC_HIGH
+ * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+ * to save two branches.
+ */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
+ BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
/*
* The caller may dip into page reserves a bit more if the caller
@@ -4184,7 +4192,8 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
* set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
*/
- alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
+ alloc_flags |= (__force int)
+ (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
if (gfp_mask & __GFP_ATOMIC) {
/*
@@ -4201,9 +4210,6 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
- alloc_flags |= ALLOC_KSWAPD;
-
#ifdef CONFIG_CMA
if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
