2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __LINUX_GFP_H
|
|
|
|
|
#define __LINUX_GFP_H
|
|
|
|
|
|
2014-01-24 07:52:54 +08:00
|
|
|
#include <linux/mmdebug.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/mmzone.h>
|
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
|
#include <linux/linkage.h>
|
2009-03-13 21:13:37 +08:00
|
|
|
#include <linux/topology.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
struct vm_area_struct;
|
|
|
|
|
|
2010-10-27 05:22:04 +08:00
|
|
|
/* Plain integer GFP bitmasks. Do not use this directly. */
|
|
|
|
|
#define ___GFP_DMA 0x01u
|
|
|
|
|
#define ___GFP_HIGHMEM 0x02u
|
|
|
|
|
#define ___GFP_DMA32 0x04u
|
|
|
|
|
#define ___GFP_MOVABLE 0x08u
|
2015-11-07 08:28:18 +08:00
|
|
|
#define ___GFP_RECLAIMABLE 0x10u
|
2010-10-27 05:22:04 +08:00
|
|
|
#define ___GFP_HIGH 0x20u
|
|
|
|
|
#define ___GFP_IO 0x40u
|
|
|
|
|
#define ___GFP_FS 0x80u
|
|
|
|
|
#define ___GFP_COLD 0x100u
|
|
|
|
|
#define ___GFP_NOWARN 0x200u
|
|
|
|
|
#define ___GFP_REPEAT 0x400u
|
|
|
|
|
#define ___GFP_NOFAIL 0x800u
|
|
|
|
|
#define ___GFP_NORETRY 0x1000u
|
2012-08-01 07:44:03 +08:00
|
|
|
#define ___GFP_MEMALLOC 0x2000u
|
2010-10-27 05:22:04 +08:00
|
|
|
#define ___GFP_COMP 0x4000u
|
|
|
|
|
#define ___GFP_ZERO 0x8000u
|
|
|
|
|
#define ___GFP_NOMEMALLOC 0x10000u
|
|
|
|
|
#define ___GFP_HARDWALL 0x20000u
|
|
|
|
|
#define ___GFP_THISNODE 0x40000u
|
2015-11-07 08:28:21 +08:00
|
|
|
#define ___GFP_ATOMIC 0x80000u
|
2015-05-15 06:16:55 +08:00
|
|
|
#define ___GFP_NOACCOUNT 0x100000u
|
Revert "revert "Revert "mm: remove __GFP_NO_KSWAPD""" and associated damage
This reverts commits a50915394f1fc02c2861d3b7ce7014788aa5066e and
d7c3b937bdf45f0b844400b7bf6fd3ed50bac604.
This is a revert of a revert of a revert. In addition, it reverts the
even older i915 change to stop using the __GFP_NO_KSWAPD flag due to the
original commits in linux-next.
It turns out that the original patch really was bogus, and that the
original revert was the correct thing to do after all. We thought we
had fixed the problem, and then reverted the revert, but the problem
really is fundamental: waking up kswapd simply isn't the right thing to
do, and direct reclaim sometimes simply _is_ the right thing to do.
When certain allocations fail, we simply should try some direct reclaim,
and if that fails, fail the allocation. That's the right thing to do
for THP allocations, which can easily fail, and the GPU allocations want
to do that too.
So starting kswapd is sometimes simply wrong, and removing the flag that
said "don't start kswapd" was a mistake. Let's hope we never revisit
this mistake again - and certainly not this many times ;)
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-11 02:51:16 +08:00
|
|
|
#define ___GFP_NOTRACK 0x200000u
|
2015-11-07 08:28:21 +08:00
|
|
|
#define ___GFP_DIRECT_RECLAIM 0x400000u
|
Revert "revert "Revert "mm: remove __GFP_NO_KSWAPD""" and associated damage
This reverts commits a50915394f1fc02c2861d3b7ce7014788aa5066e and
d7c3b937bdf45f0b844400b7bf6fd3ed50bac604.
This is a revert of a revert of a revert. In addition, it reverts the
even older i915 change to stop using the __GFP_NO_KSWAPD flag due to the
original commits in linux-next.
It turns out that the original patch really was bogus, and that the
original revert was the correct thing to do after all. We thought we
had fixed the problem, and then reverted the revert, but the problem
really is fundamental: waking up kswapd simply isn't the right thing to
do, and direct reclaim sometimes simply _is_ the right thing to do.
When certain allocations fail, we simply should try some direct reclaim,
and if that fails, fail the allocation. That's the right thing to do
for THP allocations, which can easily fail, and the GPU allocations want
to do that too.
So starting kswapd is sometimes simply wrong, and removing the flag that
said "don't start kswapd" was a mistake. Let's hope we never revisit
this mistake again - and certainly not this many times ;)
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-11 02:51:16 +08:00
|
|
|
#define ___GFP_OTHER_NODE 0x800000u
|
|
|
|
|
#define ___GFP_WRITE 0x1000000u
|
2015-11-07 08:28:21 +08:00
|
|
|
#define ___GFP_KSWAPD_RECLAIM 0x2000000u
|
2012-12-13 05:51:56 +08:00
|
|
|
/* If the above are modified, __GFP_BITS_SHIFT may need updating */
|
2010-10-27 05:22:04 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* GFP bitmasks..
|
2006-09-26 14:31:14 +08:00
|
|
|
*
|
|
|
|
|
* Zone modifiers (see linux/mmzone.h - low three bits)
|
|
|
|
|
*
|
|
|
|
|
* Do not put any conditional on these. If necessary modify the definitions
|
2010-05-25 05:32:44 +08:00
|
|
|
* without the underscores and use them consistently. The definitions here may
|
2006-09-26 14:31:14 +08:00
|
|
|
* be used in bit comparisons.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2010-10-27 05:22:04 +08:00
|
|
|
#define __GFP_DMA ((__force gfp_t)___GFP_DMA)
|
|
|
|
|
#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM)
|
|
|
|
|
#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32)
|
|
|
|
|
#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* Page is movable */
|
2009-06-17 06:32:46 +08:00
|
|
|
#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* Action modifiers - doesn't change the zoning
|
|
|
|
|
*
|
|
|
|
|
* __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
|
|
|
|
|
* _might_ fail. This depends upon the particular VM implementation.
|
|
|
|
|
*
|
|
|
|
|
* __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
|
2015-04-15 06:47:07 +08:00
|
|
|
* cannot handle allocation failures. New users should be evaluated carefully
|
|
|
|
|
* (and the flag should be used only when there is no reasonable failure policy)
|
|
|
|
|
* but it is definitely preferable to use the flag rather than opencode endless
|
|
|
|
|
* loop around allocator.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2015-09-09 06:00:31 +08:00
|
|
|
* __GFP_NORETRY: The VM implementation must not retry indefinitely and will
|
|
|
|
|
* return NULL when direct reclaim and memory compaction have failed to allow
|
|
|
|
|
* the allocation to succeed. The OOM killer is not called with the current
|
|
|
|
|
* implementation.
|
2007-07-17 19:03:05 +08:00
|
|
|
*
|
|
|
|
|
* __GFP_MOVABLE: Flag that this page will be movable by the page migration
|
|
|
|
|
* mechanism or reclaimed
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2015-11-07 08:28:21 +08:00
|
|
|
#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) /* Caller cannot wait or reschedule */
|
2010-10-27 05:22:04 +08:00
|
|
|
#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) /* Should access emergency pools? */
|
|
|
|
|
#define __GFP_IO ((__force gfp_t)___GFP_IO) /* Can start physical IO? */
|
|
|
|
|
#define __GFP_FS ((__force gfp_t)___GFP_FS) /* Can call down to low-level FS? */
|
|
|
|
|
#define __GFP_COLD ((__force gfp_t)___GFP_COLD) /* Cache-cold page required */
|
|
|
|
|
#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) /* Suppress page allocation failure warning */
|
|
|
|
|
#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) /* See above */
|
|
|
|
|
#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) /* See above */
|
|
|
|
|
#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /* See above */
|
2012-08-01 07:44:03 +08:00
|
|
|
#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */
|
2010-10-27 05:22:04 +08:00
|
|
|
#define __GFP_COMP ((__force gfp_t)___GFP_COMP) /* Add compound page metadata */
|
|
|
|
|
#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Return zeroed page on success */
|
2012-08-01 07:44:03 +08:00
|
|
|
#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves.
|
|
|
|
|
* This takes precedence over the
|
|
|
|
|
* __GFP_MEMALLOC flag if both are
|
|
|
|
|
* set
|
|
|
|
|
*/
|
2010-10-27 05:22:04 +08:00
|
|
|
#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
|
|
|
|
|
#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
|
|
|
|
|
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
|
2015-05-15 06:16:55 +08:00
|
|
|
#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */
|
2010-10-27 05:22:04 +08:00
|
|
|
#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-03-23 07:33:12 +08:00
|
|
|
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
|
mm: try to distribute dirty pages fairly across zones
The maximum number of dirty pages that exist in the system at any time is
determined by a number of pages considered dirtyable and a user-configured
percentage of those, or an absolute number in bytes.
This number of dirtyable pages is the sum of memory provided by all the
zones in the system minus their lowmem reserves and high watermarks, so
that the system can retain a healthy number of free pages without having
to reclaim dirty pages.
But there is a flaw in that we have a zoned page allocator which does not
care about the global state but rather the state of individual memory
zones. And right now there is nothing that prevents one zone from filling
up with dirty pages while other zones are spared, which frequently leads
to situations where kswapd, in order to restore the watermark of free
pages, does indeed have to write pages from that zone's LRU list. This
can interfere so badly with IO from the flusher threads that major
filesystems (btrfs, xfs, ext4) mostly ignore write requests from reclaim
already, taking away the VM's only possibility to keep such a zone
balanced, aside from hoping the flushers will soon clean pages from that
zone.
Enter per-zone dirty limits. They are to a zone's dirtyable memory what
the global limit is to the global amount of dirtyable memory, and try to
make sure that no single zone receives more than its fair share of the
globally allowed dirty pages in the first place. As the number of pages
considered dirtyable excludes the zones' lowmem reserves and high
watermarks, the maximum number of dirty pages in a zone is such that the
zone can always be balanced without requiring page cleaning.
As this is a placement decision in the page allocator and pages are
dirtied only after the allocation, this patch allows allocators to pass
__GFP_WRITE when they know in advance that the page will be written to and
become dirty soon. The page allocator will then attempt to allocate from
the first zone of the zonelist - which on NUMA is determined by the task's
NUMA memory policy - that has not exceeded its dirty limit.
At first glance, it would appear that the diversion to lower zones can
increase pressure on them, but this is not the case. With a full high
zone, allocations will be diverted to lower zones eventually, so it is
more of a shift in timing of the lower zone allocations. Workloads that
previously could fit their dirty pages completely in the higher zone may
be forced to allocate from lower zones, but the amount of pages that
"spill over" are limited themselves by the lower zones' dirty constraints,
and thus unlikely to become a problem.
For now, the problem of unfair dirty page distribution remains for NUMA
configurations where the zones allowed for allocation are in sum not big
enough to trigger the global dirty limits, wake up the flusher threads and
remedy the situation. Because of this, an allocation that could not
succeed on any of the considered zones is allowed to ignore the dirty
limits before going into direct reclaim or even failing the allocation,
until a future patch changes the global dirty throttling and flusher
thread activation so that they take individual zone states into account.
Test results
15M DMA + 3246M DMA32 + 504 Normal = 3765M memory
40% dirty ratio
16G USB thumb drive
10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15))
seconds nr_vmscan_write
(stddev) min| median| max
xfs
vanilla: 549.747( 3.492) 0.000| 0.000| 0.000
patched: 550.996( 3.802) 0.000| 0.000| 0.000
fuse-ntfs
vanilla: 1183.094(53.178) 54349.000| 59341.000| 65163.000
patched: 558.049(17.914) 0.000| 0.000| 43.000
btrfs
vanilla: 573.679(14.015) 156657.000| 460178.000| 606926.000
patched: 563.365(11.368) 0.000| 0.000| 1362.000
ext4
vanilla: 561.197(15.782) 0.000|2725438.000|4143837.000
patched: 568.806(17.496) 0.000| 0.000| 0.000
Signed-off-by: Johannes Weiner <jweiner@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:07:49 +08:00
|
|
|
#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */
|
2011-01-14 07:46:49 +08:00
|
|
|
|
2015-11-07 08:28:21 +08:00
|
|
|
/*
|
|
|
|
|
* A caller that is willing to wait may enter direct reclaim and will
|
|
|
|
|
* wake kswapd to reclaim pages in the background until the high
|
|
|
|
|
* watermark is met. A caller may wish to clear __GFP_DIRECT_RECLAIM to
|
|
|
|
|
* avoid unnecessary delays when a fallback option is available but
|
|
|
|
|
* still allow kswapd to reclaim in the background. The kswapd flag
|
|
|
|
|
* can be cleared when the reclaiming of pages would cause unnecessary
|
|
|
|
|
* disruption.
|
|
|
|
|
*/
|
2015-11-07 08:28:28 +08:00
|
|
|
#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
|
2015-11-07 08:28:21 +08:00
|
|
|
#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
|
|
|
|
|
#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
|
|
|
|
|
|
kmemcheck: add mm functions
With kmemcheck enabled, the slab allocator needs to do this:
1. Tell kmemcheck to allocate the shadow memory which stores the status of
each byte in the allocation proper, e.g. whether it is initialized or
uninitialized.
2. Tell kmemcheck which parts of memory that should be marked uninitialized.
There are actually a few more states, such as "not yet allocated" and
"recently freed".
If a slab cache is set up using the SLAB_NOTRACK flag, it will never return
memory that can take page faults because of kmemcheck.
If a slab cache is NOT set up using the SLAB_NOTRACK flag, callers can still
request memory with the __GFP_NOTRACK flag. This does not prevent the page
faults from occuring, however, but marks the object in question as being
initialized so that no warnings will ever be produced for this object.
In addition to (and in contrast to) __GFP_NOTRACK, the
__GFP_NOTRACK_FALSE_POSITIVE flag indicates that the allocation should
not be tracked _because_ it would produce a false positive. Their values
are identical, but need not be so in the future (for example, we could now
enable/disable false positives with a config option).
Parts of this patch were contributed by Pekka Enberg but merged for
atomicity.
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
[rebased for mainline inclusion]
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
2008-05-31 21:56:17 +08:00
|
|
|
/*
|
|
|
|
|
* This may seem redundant, but it's a way of annotating false positives vs.
|
|
|
|
|
* allocations that simply cannot be supported (e.g. page tables).
|
|
|
|
|
*/
|
|
|
|
|
#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
|
|
|
|
|
|
2015-11-07 08:28:21 +08:00
|
|
|
#define __GFP_BITS_SHIFT 26 /* Room for N __GFP_FOO bits */
|
2005-10-21 14:55:38 +08:00
|
|
|
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2015-11-07 08:28:21 +08:00
|
|
|
/*
|
|
|
|
|
* GFP_ATOMIC callers can not sleep, need the allocation to succeed.
|
|
|
|
|
* A lower watermark is applied to allow access to "atomic reserves"
|
|
|
|
|
*/
|
|
|
|
|
#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
|
|
|
|
|
#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
|
2015-11-07 08:28:28 +08:00
|
|
|
#define GFP_NOIO (__GFP_RECLAIM)
|
|
|
|
|
#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO)
|
|
|
|
|
#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
|
|
|
|
|
#define GFP_TEMPORARY (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \
|
2007-10-16 16:25:52 +08:00
|
|
|
__GFP_RECLAIMABLE)
|
2015-11-07 08:28:28 +08:00
|
|
|
#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
|
2014-12-13 08:55:43 +08:00
|
|
|
#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM)
|
|
|
|
|
#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE)
|
2015-11-07 08:28:21 +08:00
|
|
|
#define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
|
|
|
|
|
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
|
|
|
|
|
~__GFP_KSWAPD_RECLAIM)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-16 16:25:41 +08:00
|
|
|
/* This mask makes up all the page movable related flags */
|
2007-10-16 16:25:52 +08:00
|
|
|
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
|
2015-11-07 08:28:18 +08:00
|
|
|
#define GFP_MOVABLE_SHIFT 3
|
2007-10-16 16:25:41 +08:00
|
|
|
|
|
|
|
|
/* Control page allocator reclaim behavior */
|
2015-11-07 08:28:28 +08:00
|
|
|
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
|
2007-10-16 16:25:41 +08:00
|
|
|
__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
|
2012-08-01 07:44:03 +08:00
|
|
|
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
|
2007-10-16 16:25:41 +08:00
|
|
|
|
2009-06-12 19:03:06 +08:00
|
|
|
/* Control slab gfp mask during early boot */
|
2015-11-07 08:28:28 +08:00
|
|
|
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
|
2009-06-12 19:03:06 +08:00
|
|
|
|
2007-10-16 16:25:41 +08:00
|
|
|
/* Control allocation constraints */
|
|
|
|
|
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)
|
|
|
|
|
|
|
|
|
|
/* Do not use these with a slab allocator */
|
|
|
|
|
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
|
2006-09-26 14:31:46 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Flag - indicates that the buffer will be suitable for DMA. Ignored on some
|
|
|
|
|
platforms, used as appropriate on others */
|
|
|
|
|
|
|
|
|
|
#define GFP_DMA __GFP_DMA
|
|
|
|
|
|
2005-11-06 00:25:53 +08:00
|
|
|
/* 4GB DMA on some platforms */
|
|
|
|
|
#define GFP_DMA32 __GFP_DMA32
|
|
|
|
|
|
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo
This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo.
The information is collected only on request so there is no runtime overhead.
The statistics are in three parts:
The first part prints information on the size of blocks that pages are
being grouped on and looks like
Page block order: 10
Pages per block: 1024
The second part is a more detailed version of /proc/buddyinfo and looks like
Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0
Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0
Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0
Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0
Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4
The third part looks like
Number of blocks type Unmovable Reclaimable Movable Reserve
Node 0, zone DMA 0 1 2 1
Node 0, zone Normal 3 17 94 4
To walk the zones within a node with interrupts disabled, walk_zones_in_node()
is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and
/proc/pagetypeinfo to reduce code duplication. It seems specific to what
vmstat.c requires but could be broken out as a general utility function in
mmzone.c if there were other other potential users.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:02 +08:00
|
|
|
/* Convert GFP flags to their corresponding migrate type */
|
2014-10-10 06:27:25 +08:00
|
|
|
static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
|
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo
This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo.
The information is collected only on request so there is no runtime overhead.
The statistics are in three parts:
The first part prints information on the size of blocks that pages are
being grouped on and looks like
Page block order: 10
Pages per block: 1024
The second part is a more detailed version of /proc/buddyinfo and looks like
Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0
Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0
Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0
Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0
Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4
The third part looks like
Number of blocks type Unmovable Reclaimable Movable Reserve
Node 0, zone DMA 0 1 2 1
Node 0, zone Normal 3 17 94 4
To walk the zones within a node with interrupts disabled, walk_zones_in_node()
is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and
/proc/pagetypeinfo to reduce code duplication. It seems specific to what
vmstat.c requires but could be broken out as a general utility function in
mmzone.c if there were other other potential users.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:02 +08:00
|
|
|
{
|
2015-11-07 08:28:18 +08:00
|
|
|
VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
|
|
|
|
|
BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
|
|
|
|
|
BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE);
|
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo
This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo.
The information is collected only on request so there is no runtime overhead.
The statistics are in three parts:
The first part prints information on the size of blocks that pages are
being grouped on and looks like
Page block order: 10
Pages per block: 1024
The second part is a more detailed version of /proc/buddyinfo and looks like
Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0
Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0
Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0
Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0
Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4
The third part looks like
Number of blocks type Unmovable Reclaimable Movable Reserve
Node 0, zone DMA 0 1 2 1
Node 0, zone Normal 3 17 94 4
To walk the zones within a node with interrupts disabled, walk_zones_in_node()
is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and
/proc/pagetypeinfo to reduce code duplication. It seems specific to what
vmstat.c requires but could be broken out as a general utility function in
mmzone.c if there were other other potential users.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:02 +08:00
|
|
|
|
|
|
|
|
if (unlikely(page_group_by_mobility_disabled))
|
|
|
|
|
return MIGRATE_UNMOVABLE;
|
|
|
|
|
|
|
|
|
|
/* Group based on mobility */
|
2015-11-07 08:28:18 +08:00
|
|
|
return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
|
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo
This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo.
The information is collected only on request so there is no runtime overhead.
The statistics are in three parts:
The first part prints information on the size of blocks that pages are
being grouped on and looks like
Page block order: 10
Pages per block: 1024
The second part is a more detailed version of /proc/buddyinfo and looks like
Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0
Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0
Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0
Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0
Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4
The third part looks like
Number of blocks type Unmovable Reclaimable Movable Reserve
Node 0, zone DMA 0 1 2 1
Node 0, zone Normal 3 17 94 4
To walk the zones within a node with interrupts disabled, walk_zones_in_node()
is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and
/proc/pagetypeinfo to reduce code duplication. It seems specific to what
vmstat.c requires but could be broken out as a general utility function in
mmzone.c if there were other other potential users.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:02 +08:00
|
|
|
}
|
2005-11-06 00:25:53 +08:00
|
|
|
|
2015-11-07 08:28:21 +08:00
|
|
|
static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
|
|
|
|
|
{
|
|
|
|
|
return gfp_flags & __GFP_DIRECT_RECLAIM;
|
|
|
|
|
}
|
|
|
|
|
|
2009-06-17 06:32:46 +08:00
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
|
#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
|
|
|
|
|
#else
|
|
|
|
|
#define OPT_ZONE_HIGHMEM ZONE_NORMAL
|
|
|
|
|
#endif
|
|
|
|
|
|
2007-02-10 17:43:10 +08:00
|
|
|
#ifdef CONFIG_ZONE_DMA
|
2009-06-17 06:32:46 +08:00
|
|
|
#define OPT_ZONE_DMA ZONE_DMA
|
|
|
|
|
#else
|
|
|
|
|
#define OPT_ZONE_DMA ZONE_NORMAL
|
2007-02-10 17:43:10 +08:00
|
|
|
#endif
|
2009-06-17 06:32:46 +08:00
|
|
|
|
2006-09-26 14:31:17 +08:00
|
|
|
#ifdef CONFIG_ZONE_DMA32
|
2009-06-17 06:32:46 +08:00
|
|
|
#define OPT_ZONE_DMA32 ZONE_DMA32
|
|
|
|
|
#else
|
|
|
|
|
#define OPT_ZONE_DMA32 ZONE_NORMAL
|
2006-09-26 14:31:17 +08:00
|
|
|
#endif
|
2009-06-17 06:32:46 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* GFP_ZONE_TABLE is a word size bitstring that is used for looking up the
|
|
|
|
|
* zone to use given the lowest 4 bits of gfp_t. Entries are ZONE_SHIFT long
|
|
|
|
|
* and there are 16 of them to cover all possible combinations of
|
2010-05-25 05:32:44 +08:00
|
|
|
* __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM.
|
2009-06-17 06:32:46 +08:00
|
|
|
*
|
|
|
|
|
* The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA.
|
|
|
|
|
* But GFP_MOVABLE is not only a zone specifier but also an allocation
|
|
|
|
|
* policy. Therefore __GFP_MOVABLE plus another zone selector is valid.
|
2010-05-25 05:32:44 +08:00
|
|
|
* Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1".
|
2009-06-17 06:32:46 +08:00
|
|
|
*
|
|
|
|
|
* bit result
|
|
|
|
|
* =================
|
|
|
|
|
* 0x0 => NORMAL
|
|
|
|
|
* 0x1 => DMA or NORMAL
|
|
|
|
|
* 0x2 => HIGHMEM or NORMAL
|
|
|
|
|
* 0x3 => BAD (DMA+HIGHMEM)
|
|
|
|
|
* 0x4 => DMA32 or DMA or NORMAL
|
|
|
|
|
* 0x5 => BAD (DMA+DMA32)
|
|
|
|
|
* 0x6 => BAD (HIGHMEM+DMA32)
|
|
|
|
|
* 0x7 => BAD (HIGHMEM+DMA32+DMA)
|
|
|
|
|
* 0x8 => NORMAL (MOVABLE+0)
|
|
|
|
|
* 0x9 => DMA or NORMAL (MOVABLE+DMA)
|
|
|
|
|
* 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too)
|
|
|
|
|
* 0xb => BAD (MOVABLE+HIGHMEM+DMA)
|
2013-07-09 07:00:02 +08:00
|
|
|
* 0xc => DMA32 (MOVABLE+DMA32)
|
2009-06-17 06:32:46 +08:00
|
|
|
* 0xd => BAD (MOVABLE+DMA32+DMA)
|
|
|
|
|
* 0xe => BAD (MOVABLE+DMA32+HIGHMEM)
|
|
|
|
|
* 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
|
|
|
|
|
*
|
|
|
|
|
* ZONES_SHIFT must be <= 2 on 32 bit platforms.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#if 16 * ZONES_SHIFT > BITS_PER_LONG
|
|
|
|
|
#error ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#define GFP_ZONE_TABLE ( \
|
2010-10-27 05:22:04 +08:00
|
|
|
(ZONE_NORMAL << 0 * ZONES_SHIFT) \
|
|
|
|
|
| (OPT_ZONE_DMA << ___GFP_DMA * ZONES_SHIFT) \
|
|
|
|
|
| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * ZONES_SHIFT) \
|
|
|
|
|
| (OPT_ZONE_DMA32 << ___GFP_DMA32 * ZONES_SHIFT) \
|
|
|
|
|
| (ZONE_NORMAL << ___GFP_MOVABLE * ZONES_SHIFT) \
|
|
|
|
|
| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * ZONES_SHIFT) \
|
|
|
|
|
| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * ZONES_SHIFT) \
|
|
|
|
|
| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * ZONES_SHIFT) \
|
2009-06-17 06:32:46 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
/*
|
2010-05-25 05:32:44 +08:00
|
|
|
* GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32
|
2009-06-17 06:32:46 +08:00
|
|
|
* __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per
|
|
|
|
|
* entry starting with bit 0. Bit is set if the combination is not
|
|
|
|
|
* allowed.
|
|
|
|
|
*/
|
|
|
|
|
#define GFP_ZONE_BAD ( \
|
2010-10-27 05:22:04 +08:00
|
|
|
1 << (___GFP_DMA | ___GFP_HIGHMEM) \
|
|
|
|
|
| 1 << (___GFP_DMA | ___GFP_DMA32) \
|
|
|
|
|
| 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \
|
|
|
|
|
| 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \
|
|
|
|
|
| 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \
|
|
|
|
|
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \
|
|
|
|
|
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \
|
|
|
|
|
| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \
|
2009-06-17 06:32:46 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
static inline enum zone_type gfp_zone(gfp_t flags)
|
|
|
|
|
{
|
|
|
|
|
enum zone_type z;
|
2010-10-27 05:22:04 +08:00
|
|
|
int bit = (__force int) (flags & GFP_ZONEMASK);
|
2009-06-17 06:32:46 +08:00
|
|
|
|
|
|
|
|
z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) &
|
|
|
|
|
((1 << ZONES_SHIFT) - 1);
|
2011-05-25 08:11:42 +08:00
|
|
|
VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
|
2009-06-17 06:32:46 +08:00
|
|
|
return z;
|
2006-09-26 14:31:17 +08:00
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* There is only one page-allocator function, and two main namespaces to
|
|
|
|
|
* it. The alloc_page*() variants return 'struct page *' and as such
|
|
|
|
|
* can allocate highmem pages, the *get*page*() variants return
|
|
|
|
|
* virtual kernel addresses to the allocated page(s).
|
|
|
|
|
*/
|
|
|
|
|
|
2008-04-28 17:12:16 +08:00
|
|
|
static inline int gfp_zonelist(gfp_t flags)
|
|
|
|
|
{
|
2012-12-12 08:00:29 +08:00
|
|
|
if (IS_ENABLED(CONFIG_NUMA) && unlikely(flags & __GFP_THISNODE))
|
2008-04-28 17:12:16 +08:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* We get the zone list from the current node and the gfp_mask.
|
|
|
|
|
* This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones.
|
2008-04-28 17:12:16 +08:00
|
|
|
* There are two zonelists per node, one for all zones with memory and
|
|
|
|
|
* one containing just zones from the node the zonelist belongs to.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
|
|
|
|
|
* optimized to &contig_page_data at compile-time.
|
|
|
|
|
*/
|
2008-04-28 17:12:14 +08:00
|
|
|
static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
|
|
|
|
|
{
|
2008-04-28 17:12:16 +08:00
|
|
|
return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
|
2008-04-28 17:12:14 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#ifndef HAVE_ARCH_FREE_PAGE
|
|
|
|
|
static inline void arch_free_page(struct page *page, int order) { }
|
|
|
|
|
#endif
|
2006-12-07 12:32:00 +08:00
|
|
|
#ifndef HAVE_ARCH_ALLOC_PAGE
|
|
|
|
|
static inline void arch_alloc_page(struct page *page, int order) { }
|
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-07-24 12:27:01 +08:00
|
|
|
struct page *
|
2009-06-17 06:31:52 +08:00
|
|
|
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
|
2008-07-24 12:27:01 +08:00
|
|
|
struct zonelist *zonelist, nodemask_t *nodemask);
|
|
|
|
|
|
|
|
|
|
static inline struct page *
|
|
|
|
|
__alloc_pages(gfp_t gfp_mask, unsigned int order,
|
|
|
|
|
struct zonelist *zonelist)
|
|
|
|
|
{
|
2009-06-17 06:31:52 +08:00
|
|
|
return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
|
2008-07-24 12:27:01 +08:00
|
|
|
}
|
|
|
|
|
|
mm: rename alloc_pages_exact_node() to __alloc_pages_node()
alloc_pages_exact_node() was introduced in commit 6484eb3e2a81 ("page
allocator: do not check NUMA node ID when the caller knows the node is
valid") as an optimized variant of alloc_pages_node(), that doesn't
fallback to current node for nid == NUMA_NO_NODE. Unfortunately the
name of the function can easily suggest that the allocation is
restricted to the given node and fails otherwise. In truth, the node is
only preferred, unless __GFP_THISNODE is passed among the gfp flags.
The misleading name has lead to mistakes in the past, see for example
commits 5265047ac301 ("mm, thp: really limit transparent hugepage
allocation to local node") and b360edb43f8e ("mm, mempolicy:
migrate_to_node should only migrate to node").
Another issue with the name is that there's a family of
alloc_pages_exact*() functions where 'exact' means exact size (instead
of page order), which leads to more confusion.
To prevent further mistakes, this patch effectively renames
alloc_pages_exact_node() to __alloc_pages_node() to better convey that
it's an optimized variant of alloc_pages_node() not intended for general
usage. Both functions get described in comments.
It has been also considered to really provide a convenience function for
allocations restricted to a node, but the major opinion seems to be that
__GFP_THISNODE already provides that functionality and we shouldn't
duplicate the API needlessly. The number of users would be small
anyway.
Existing callers of alloc_pages_exact_node() are simply converted to
call __alloc_pages_node(), with the exception of sba_alloc_coherent()
which open-codes the check for NUMA_NO_NODE, so it is converted to use
alloc_pages_node() instead. This means it no longer performs some
VM_BUG_ON checks, and since the current check for nid in
alloc_pages_node() uses a 'nid < 0' comparison (which includes
NUMA_NO_NODE), it may hide wrong values which would be previously
exposed.
Both differences will be rectified by the next patch.
To sum up, this patch makes no functional changes, except temporarily
hiding potentially buggy callers. Restricting the checks in
alloc_pages_node() is left for the next patch which can in turn expose
more existing buggy callers.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Robin Holt <robinmholt@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Cliff Whickman <cpw@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 06:03:50 +08:00
|
|
|
/*
|
|
|
|
|
* Allocate pages, preferring the node given as nid. The node must be valid and
|
|
|
|
|
* online. For more general interface, see alloc_pages_node().
|
|
|
|
|
*/
|
|
|
|
|
static inline struct page *
|
|
|
|
|
__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2015-09-09 06:03:53 +08:00
|
|
|
VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
|
|
|
|
|
VM_WARN_ON(!node_online(nid));
|
2006-01-12 05:43:45 +08:00
|
|
|
|
2008-04-28 17:12:14 +08:00
|
|
|
return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
mm: rename alloc_pages_exact_node() to __alloc_pages_node()
alloc_pages_exact_node() was introduced in commit 6484eb3e2a81 ("page
allocator: do not check NUMA node ID when the caller knows the node is
valid") as an optimized variant of alloc_pages_node(), that doesn't
fallback to current node for nid == NUMA_NO_NODE. Unfortunately the
name of the function can easily suggest that the allocation is
restricted to the given node and fails otherwise. In truth, the node is
only preferred, unless __GFP_THISNODE is passed among the gfp flags.
The misleading name has lead to mistakes in the past, see for example
commits 5265047ac301 ("mm, thp: really limit transparent hugepage
allocation to local node") and b360edb43f8e ("mm, mempolicy:
migrate_to_node should only migrate to node").
Another issue with the name is that there's a family of
alloc_pages_exact*() functions where 'exact' means exact size (instead
of page order), which leads to more confusion.
To prevent further mistakes, this patch effectively renames
alloc_pages_exact_node() to __alloc_pages_node() to better convey that
it's an optimized variant of alloc_pages_node() not intended for general
usage. Both functions get described in comments.
It has been also considered to really provide a convenience function for
allocations restricted to a node, but the major opinion seems to be that
__GFP_THISNODE already provides that functionality and we shouldn't
duplicate the API needlessly. The number of users would be small
anyway.
Existing callers of alloc_pages_exact_node() are simply converted to
call __alloc_pages_node(), with the exception of sba_alloc_coherent()
which open-codes the check for NUMA_NO_NODE, so it is converted to use
alloc_pages_node() instead. This means it no longer performs some
VM_BUG_ON checks, and since the current check for nid in
alloc_pages_node() uses a 'nid < 0' comparison (which includes
NUMA_NO_NODE), it may hide wrong values which would be previously
exposed.
Both differences will be rectified by the next patch.
To sum up, this patch makes no functional changes, except temporarily
hiding potentially buggy callers. Restricting the checks in
alloc_pages_node() is left for the next patch which can in turn expose
more existing buggy callers.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Robin Holt <robinmholt@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Cliff Whickman <cpw@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 06:03:50 +08:00
|
|
|
/*
|
|
|
|
|
* Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
|
2015-09-09 06:03:56 +08:00
|
|
|
* prefer the current CPU's closest node. Otherwise node must be valid and
|
|
|
|
|
* online.
|
mm: rename alloc_pages_exact_node() to __alloc_pages_node()
alloc_pages_exact_node() was introduced in commit 6484eb3e2a81 ("page
allocator: do not check NUMA node ID when the caller knows the node is
valid") as an optimized variant of alloc_pages_node(), that doesn't
fallback to current node for nid == NUMA_NO_NODE. Unfortunately the
name of the function can easily suggest that the allocation is
restricted to the given node and fails otherwise. In truth, the node is
only preferred, unless __GFP_THISNODE is passed among the gfp flags.
The misleading name has lead to mistakes in the past, see for example
commits 5265047ac301 ("mm, thp: really limit transparent hugepage
allocation to local node") and b360edb43f8e ("mm, mempolicy:
migrate_to_node should only migrate to node").
Another issue with the name is that there's a family of
alloc_pages_exact*() functions where 'exact' means exact size (instead
of page order), which leads to more confusion.
To prevent further mistakes, this patch effectively renames
alloc_pages_exact_node() to __alloc_pages_node() to better convey that
it's an optimized variant of alloc_pages_node() not intended for general
usage. Both functions get described in comments.
It has been also considered to really provide a convenience function for
allocations restricted to a node, but the major opinion seems to be that
__GFP_THISNODE already provides that functionality and we shouldn't
duplicate the API needlessly. The number of users would be small
anyway.
Existing callers of alloc_pages_exact_node() are simply converted to
call __alloc_pages_node(), with the exception of sba_alloc_coherent()
which open-codes the check for NUMA_NO_NODE, so it is converted to use
alloc_pages_node() instead. This means it no longer performs some
VM_BUG_ON checks, and since the current check for nid in
alloc_pages_node() uses a 'nid < 0' comparison (which includes
NUMA_NO_NODE), it may hide wrong values which would be previously
exposed.
Both differences will be rectified by the next patch.
To sum up, this patch makes no functional changes, except temporarily
hiding potentially buggy callers. Restricting the checks in
alloc_pages_node() is left for the next patch which can in turn expose
more existing buggy callers.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Robin Holt <robinmholt@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Cliff Whickman <cpw@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 06:03:50 +08:00
|
|
|
*/
|
|
|
|
|
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
|
2009-06-17 06:31:54 +08:00
|
|
|
unsigned int order)
|
|
|
|
|
{
|
2015-09-09 06:03:53 +08:00
|
|
|
if (nid == NUMA_NO_NODE)
|
2015-09-09 06:03:56 +08:00
|
|
|
nid = numa_mem_id();
|
2009-06-17 06:31:54 +08:00
|
|
|
|
2015-09-09 06:03:53 +08:00
|
|
|
return __alloc_pages_node(nid, gfp_mask, order);
|
2009-06-17 06:31:54 +08:00
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
2005-10-07 14:46:04 +08:00
|
|
|
extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
static inline struct page *
|
2005-10-07 14:46:04 +08:00
|
|
|
alloc_pages(gfp_t gfp_mask, unsigned int order)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
return alloc_pages_current(gfp_mask, order);
|
|
|
|
|
}
|
2011-01-14 07:47:05 +08:00
|
|
|
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
|
2011-03-05 09:36:29 +08:00
|
|
|
struct vm_area_struct *vma, unsigned long addr,
|
2015-02-12 07:27:15 +08:00
|
|
|
int node, bool hugepage);
|
|
|
|
|
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
|
|
|
|
|
alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
|
2005-04-17 06:20:36 +08:00
|
|
|
#else
|
|
|
|
|
#define alloc_pages(gfp_mask, order) \
|
|
|
|
|
alloc_pages_node(numa_node_id(), gfp_mask, order)
|
2015-02-12 07:27:15 +08:00
|
|
|
#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
|
2011-01-14 07:47:05 +08:00
|
|
|
alloc_pages(gfp_mask, order)
|
2015-02-12 07:27:12 +08:00
|
|
|
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
|
|
|
|
|
alloc_pages(gfp_mask, order)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
|
2011-03-05 09:36:29 +08:00
|
|
|
#define alloc_page_vma(gfp_mask, vma, addr) \
|
2015-02-12 07:27:15 +08:00
|
|
|
alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
|
2011-03-05 09:36:30 +08:00
|
|
|
#define alloc_page_vma_node(gfp_mask, vma, addr, node) \
|
2015-02-12 07:27:15 +08:00
|
|
|
alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2014-06-05 07:06:39 +08:00
|
|
|
extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order);
|
|
|
|
|
extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask,
|
|
|
|
|
unsigned int order);
|
|
|
|
|
|
2008-02-14 07:03:15 +08:00
|
|
|
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
|
|
|
|
|
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-07-24 12:28:11 +08:00
|
|
|
void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
|
|
|
|
|
void free_pages_exact(void *virt, size_t size);
|
2014-08-07 07:04:59 +08:00
|
|
|
void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
|
2008-07-24 12:28:11 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#define __get_free_page(gfp_mask) \
|
2010-05-25 05:32:45 +08:00
|
|
|
__get_free_pages((gfp_mask), 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#define __get_dma_pages(gfp_mask, order) \
|
2010-05-25 05:32:45 +08:00
|
|
|
__get_free_pages((gfp_mask) | GFP_DMA, (order))
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-02-14 07:03:15 +08:00
|
|
|
extern void __free_pages(struct page *page, unsigned int order);
|
|
|
|
|
extern void free_pages(unsigned long addr, unsigned int order);
|
2014-06-05 07:10:22 +08:00
|
|
|
extern void free_hot_cold_page(struct page *page, bool cold);
|
|
|
|
|
extern void free_hot_cold_page_list(struct list_head *list, bool cold);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2015-05-07 12:11:57 +08:00
|
|
|
struct page_frag_cache;
|
|
|
|
|
extern void *__alloc_page_frag(struct page_frag_cache *nc,
|
|
|
|
|
unsigned int fragsz, gfp_t gfp_mask);
|
|
|
|
|
extern void __free_page_frag(void *addr);
|
|
|
|
|
|
2014-06-05 07:06:39 +08:00
|
|
|
extern void __free_kmem_pages(struct page *page, unsigned int order);
|
|
|
|
|
extern void free_kmem_pages(unsigned long addr, unsigned int order);
|
2012-12-19 06:22:00 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#define __free_page(page) __free_pages((page), 0)
|
2010-05-25 05:32:45 +08:00
|
|
|
#define free_page(addr) free_pages((addr), 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
void page_alloc_init(void);
|
2007-05-09 17:35:14 +08:00
|
|
|
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
|
2014-12-11 07:43:01 +08:00
|
|
|
void drain_all_pages(struct zone *zone);
|
|
|
|
|
void drain_local_pages(struct zone *zone);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2015-07-01 05:57:27 +08:00
|
|
|
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
|
|
|
|
|
void page_alloc_init_late(void);
|
|
|
|
|
#else
|
|
|
|
|
static inline void page_alloc_init_late(void)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
2012-01-11 07:07:15 +08:00
|
|
|
/*
|
|
|
|
|
* gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
|
|
|
|
|
* GFP flags are used before interrupts are enabled. Once interrupts are
|
|
|
|
|
* enabled, it is set to __GFP_BITS_MASK while the system is running. During
|
|
|
|
|
* hibernation, it is used by PM to avoid I/O during memory allocation while
|
|
|
|
|
* devices are suspended.
|
|
|
|
|
*/
|
2009-06-18 11:24:12 +08:00
|
|
|
extern gfp_t gfp_allowed_mask;
|
|
|
|
|
|
2012-08-01 07:44:19 +08:00
|
|
|
/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
|
|
|
|
|
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
|
|
|
|
|
|
2010-12-04 05:57:45 +08:00
|
|
|
extern void pm_restrict_gfp_mask(void);
|
|
|
|
|
extern void pm_restore_gfp_mask(void);
|
2009-06-18 11:24:12 +08:00
|
|
|
|
2012-01-11 07:07:15 +08:00
|
|
|
#ifdef CONFIG_PM_SLEEP
|
|
|
|
|
extern bool pm_suspended_storage(void);
|
|
|
|
|
#else
|
|
|
|
|
static inline bool pm_suspended_storage(void)
|
|
|
|
|
{
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
#endif /* CONFIG_PM_SLEEP */
|
|
|
|
|
|
2011-12-29 20:09:50 +08:00
|
|
|
#ifdef CONFIG_CMA
|
|
|
|
|
|
|
|
|
|
/* The below functions must be run on a range from a single zone. */
|
2012-04-03 21:06:15 +08:00
|
|
|
extern int alloc_contig_range(unsigned long start, unsigned long end,
|
|
|
|
|
unsigned migratetype);
|
2011-12-29 20:09:50 +08:00
|
|
|
extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
|
|
|
|
|
|
2011-12-29 20:09:50 +08:00
|
|
|
/* CMA stuff */
|
|
|
|
|
extern void init_cma_reserved_pageblock(struct page *page);
|
|
|
|
|
|
2011-12-29 20:09:50 +08:00
|
|
|
#endif
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* __LINUX_GFP_H */
|