Skip to contentSkip to conversation

mm, slaub: Add __GFP_ATOMIC to the GFP reclaim mask

PATCH Applied Mel Gorman 3 participants 3 messages Jun 10, 2016 – Jun 14, 2016

Subsystems (2)
Memory management MM core
lore
Share & tools
lore

Mel Gorman

author
#0 lore raw

PATCH 1/1 mm, slaub: Add __GFP_ATOMIC to the GFP reclaim mask

Commit d0164adc89f6 ("mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd") modified __GFP_WAIT to explicitly identify the difference between atomic callers and those that were unwilling to sleep. Later the definition was removed entirely.

The GFP_RECLAIM_MASK is the set of flags that affect watermark checking and reclaim behaviour but __GFP_ATOMIC was never added. Without it, atomic users of the slab allocator strip the __GFP_ATOMIC flag and cannot access the page allocator atomic reserves. This patch addresses the problem.

The user-visible impact depends on the workload but potentially atomic allocations unnecessarily fail without this path.

Cc <[email protected]> # 4.4+
Reported-by Marcin Wojtas <[email protected]>
Signed-off-by Mel Gorman <[email protected]>
---
 mm/internal.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
mm/internal.h +2 -1
index a37e5b6f9d25..2524ec880e24 100644
@@ -24,7 +24,8 @@
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
+			__GFP_ATOMIC)
 
 /* The GFP flags allowed during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Acked-by on v1 1/1
#1 lore raw
Quoted 10 lines · Mel Gorman

Commit d0164adc89f6 ("mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd") modified __GFP_WAIT to explicitly identify the difference between atomic callers and those that were unwilling to sleep. Later the definition was removed entirely.

The GFP_RECLAIM_MASK is the set of flags that affect watermark checking and reclaim behaviour but __GFP_ATOMIC was never added. Without it, atomic users of the slab allocator strip the __GFP_ATOMIC flag and cannot access the page allocator atomic reserves. This patch addresses the problem.

Quoted 6 lines

The user-visible impact depends on the workload but potentially atomic allocations unnecessarily fail without this path.

Cc <[email protected]> # 4.4+
Reported-by Marcin Wojtas <[email protected]>
Signed-off-by Mel Gorman <[email protected]>
Acked-by Vlastimil Babka <[email protected]>
Quoted 10 lines
---
 mm/internal.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
mm/internal.h +0 -0
index a37e5b6f9d25..2524ec880e24 100644

mm/internal.h line 31

Quoted 9 lines
mm/internal.h +2 -1
@@ -24,7 +24,8 @@
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
+			__GFP_ATOMIC)
 
 /* The GFP flags allowed during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Acked-by on v1 1/1
#2 lore raw
In reply to Mel Gorman
Quoted 10 lines · Mel Gorman

Commit d0164adc89f6 ("mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd") modified __GFP_WAIT to explicitly identify the difference between atomic callers and those that were unwilling to sleep. Later the definition was removed entirely.

The GFP_RECLAIM_MASK is the set of flags that affect watermark checking and reclaim behaviour but __GFP_ATOMIC was never added. Without it, atomic users of the slab allocator strip the __GFP_ATOMIC flag and cannot access the page allocator atomic reserves. This patch addresses the problem.

Quoted 6 lines

The user-visible impact depends on the workload but potentially atomic allocations unnecessarily fail without this path.

Cc <[email protected]> # 4.4+
Reported-by Marcin Wojtas <[email protected]>
Signed-off-by Mel Gorman <[email protected]>
Acked-by Michal Hocko <[email protected]>
Quoted 24 lines
---
 mm/internal.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
mm/internal.h +2 -2
index a37e5b6f9d25..2524ec880e24 100644
@@ -24,7 +24,8 @@
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
+			__GFP_ATOMIC)
 
 /* The GFP flags allowed during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
 
--

To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Signature · 8 lines
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>