linux-kernel - [RFC PATCH] mm: Micro-optimisation: Save two branches on hot

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:   Wed,  4 Mar 2020 15:22:30 +0100
From:   mateusznosek0@...il.com
To:     linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc:     Mateusz Nosek <mateusznosek0@...il.com>, akpm@...ux-foundation.org
Subject: [RFC PATCH] mm: Micro-optimisation: Save two branches on hot - page allocation path

From: Mateusz Nosek <mateusznosek0@...il.com>

This patch makes ALLOC_KSWAPD
equal to __GFP_KSWAPD_RACLAIM (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 beggining of page allocation
and the second one in loop in page allocator slowpath.

Signed-off-by: Mateusz Nosek <mateusznosek0@...il.com>
---
 mm/internal.h   |  2 +-
 mm/page_alloc.c | 23 +++++++++++++++--------
 2 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 86372d164476..7fb724977743 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -535,7 +535,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #else
 #define ALLOC_NOFRAGMENT	  0x0
 #endif
-#define ALLOC_KSWAPD		0x200 /* allow waking of kswapd */
+#define ALLOC_KSWAPD		0x800 /* allow waking of kswapd */
 
 enum ttu_flags;
 struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 79e950d76ffc..73afd883eab5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3609,10 +3609,14 @@ 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.
+	 */
+	BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
+	alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
 
 #ifdef CONFIG_ZONE_DMA32
 	if (!zone)
@@ -4248,8 +4252,13 @@ 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
@@ -4257,7 +4266,8 @@ 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) {
 		/*
@@ -4274,9 +4284,6 @@ 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;
-- 
2.17.1