mm/process_vm_access: move config option into init/Kconfig
CONFIG_CROSS_MEMORY_ATTACH adds couple syscalls: process_vm_readv and
process_vm_writev, it's a kind of IPC for copying data between processes.
Currently this option is placed inside "Processor type and features".
This patch moves it into "General setup" (where all other arch-independed
syscalls and ipc features are placed) and changes prompt string to less
cryptic.
Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Christopher Yeoh <cyeoh@au1.ibm.com> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Hugh Dickins <hughd@google.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:49 +0000 (16:10 -0700)]
mm: vmscan: use proportional scanning during direct reclaim and full scan at DEF_PRIORITY
Commit "mm: vmscan: obey proportional scanning requirements for kswapd"
ensured that file/anon lists were scanned proportionally for reclaim from
kswapd but ignored it for direct reclaim. The intent was to minimse
direct reclaim latency but Yuanhan Liu pointer out that it substitutes one
long stall for many small stalls and distorts aging for normal workloads
like streaming readers/writers. Hugh Dickins pointed out that a
side-effect of the same commit was that when one LRU list dropped to zero
that the entirety of the other list was shrunk leading to excessive
reclaim in memcgs. This patch scans the file/anon lists proportionally
for direct reclaim to similarly age page whether reclaimed by kswapd or
direct reclaim but takes care to abort reclaim if one LRU drops to zero
after reclaiming the requested number of pages.
Based on ext4 and using the Intel VM scalability test
3.15.0-rc5 3.15.0-rc5
shrinker proportion
Unit lru-file-readonce elapsed 5.3500 ( 0.00%) 5.4200 ( -1.31%)
Unit lru-file-readonce time_range 0.2700 ( 0.00%) 0.1400 ( 48.15%)
Unit lru-file-readonce time_stddv 0.1148 ( 0.00%) 0.0536 ( 53.33%)
Unit lru-file-readtwice elapsed 8.1700 ( 0.00%) 8.1700 ( 0.00%)
Unit lru-file-readtwice time_range 0.4300 ( 0.00%) 0.2300 ( 46.51%)
Unit lru-file-readtwice time_stddv 0.1650 ( 0.00%) 0.0971 ( 41.16%)
The test cases are running multiple dd instances reading sparse files. The results are within
the noise for the small test machine. The impact of the patch is more noticable from the vmstats
3.15.0-rc5 3.15.0-rc5
shrinker proportion
Minor Faults 35154 36784
Major Faults 611 1305
Swap Ins 394 1651
Swap Outs 4394 5891
Allocation stalls 118616 44781
Direct pages scanned 49351714602313
Kswapd pages scanned 1592129216258483
Kswapd pages reclaimed 1591330116248305
Direct pages reclaimed 49333684601133
Kswapd efficiency 99% 99%
Kswapd velocity 670088.047 682555.961
Direct efficiency 99% 99%
Direct velocity 207709.217 193212.133
Percentage direct scans 23% 22%
Page writes by reclaim 4858.000 6232.000
Page writes file 464 341
Page writes anon 4394 5891
Note that there are fewer allocation stalls even though the amount
of direct reclaim scanning is very approximately the same.
Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Dave Chinner <david@fromorbit.com> Tested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tim Chen [Wed, 4 Jun 2014 23:10:47 +0000 (16:10 -0700)]
fs/superblock: avoid locking counting inodes and dentries before reclaiming them
We remove the call to grab_super_passive in call to super_cache_count.
This becomes a scalability bottleneck as multiple threads are trying to do
memory reclamation, e.g. when we are doing large amount of file read and
page cache is under pressure. The cached objects quickly got reclaimed
down to 0 and we are aborting the cache_scan() reclaim. But counting
creates a log jam acquiring the sb_lock.
We are holding the shrinker_rwsem which ensures the safety of call to
list_lru_count_node() and s_op->nr_cached_objects. The shrinker is
unregistered now before ->kill_sb() so the operation is safe when we are
doing unmount.
The impact will depend heavily on the machine and the workload but for a
small machine using postmark tuned to use 4xRAM size the results were
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Chinner <david@fromorbit.com> Tested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Jan Kara <jack@suse.cz> Acked-by: Rik van Riel <riel@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Chinner [Wed, 4 Jun 2014 23:10:46 +0000 (16:10 -0700)]
fs/superblock: unregister sb shrinker before ->kill_sb()
This series is aimed at regressions noticed during reclaim activity. The
first two patches are shrinker patches that were posted ages ago but never
merged for reasons that are unclear to me. I'm posting them again to see
if there was a reason they were dropped or if they just got lost. Dave?
Time? The last patch adjusts proportional reclaim. Yuanhan Liu, can you
retest the vm scalability test cases on a larger machine? Hugh, does this
work for you on the memcg test cases?
Based on ext4, I get the following results but unfortunately my larger
test machines are all unavailable so this is based on a relatively small
machine.
stutter (times mmap latency during large amounts of IO)
3.15.0-rc5 3.15.0-rc5
vanilla proportion-v1r4
Unit >5ms Delays 80252.0000 ( 0.00%) 81523.0000 ( -1.58%)
Unit Mmap min 8.2118 ( 0.00%) 8.3206 ( -1.33%)
Unit Mmap mean 17.4614 ( 0.00%) 17.2868 ( 1.00%)
Unit Mmap stddev 24.9059 ( 0.00%) 34.6771 (-39.23%)
Unit Mmap max 2811.6433 ( 0.00%) 2645.1398 ( 5.92%)
Unit Mmap 90% 20.5098 ( 0.00%) 18.3105 ( 10.72%)
Unit Mmap 93% 22.9180 ( 0.00%) 20.1751 ( 11.97%)
Unit Mmap 95% 25.2114 ( 0.00%) 22.4988 ( 10.76%)
Unit Mmap 99% 46.1430 ( 0.00%) 43.5952 ( 5.52%)
Unit Ideal Tput 85.2623 ( 0.00%) 78.8906 ( 7.47%)
Unit Tput min 44.0666 ( 0.00%) 43.9609 ( 0.24%)
Unit Tput mean 45.5646 ( 0.00%) 45.2009 ( 0.80%)
Unit Tput stddev 0.9318 ( 0.00%) 1.1084 (-18.95%)
Unit Tput max 46.7375 ( 0.00%) 46.7539 ( -0.04%)
This patch (of 3):
We will like to unregister the sb shrinker before ->kill_sb(). This will
allow cached objects to be counted without call to grab_super_passive() to
update ref count on sb. We want to avoid locking during memory
reclamation especially when we are skipping the memory reclaim when we are
out of cached objects.
This is safe because grab_super_passive does a try-lock on the
sb->s_umount now, and so if we are in the unmount process, it won't ever
block. That means what used to be a deadlock and races we were avoiding
by using grab_super_passive() is now:
So it is safe to deregister the shrinker before ->kill_sb().
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Chinner <david@fromorbit.com> Tested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Jan Kara <jack@suse.cz> Acked-by: Rik van Riel <riel@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Wed, 4 Jun 2014 23:10:44 +0000 (16:10 -0700)]
mm/msync.c: sync only the requested range in msync()
msync() currently syncs more than POSIX requires or BSD or Solaris
implement. It is supposed to be equivalent to fdatasync(), not fsync(),
and it is only supposed to sync the portion of the file that overlaps the
range passed to msync.
If the VMA is non-linear, fall back to syncing the entire file, but we
still optimise to only fdatasync() the entire file, not the full fsync().
akpm: there are obvious concerns with bck-compatibility: is anyone relying
on the undocumented side-effect for their data integrity? And how would
they ever know if this change broke their data integrity?
We think the risk is reasonably low, and this patch brings the kernel into
line with other OS's and with what the manpage has always said...
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Chris Mason <clm@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Vlastimil Babka [Wed, 4 Jun 2014 23:10:41 +0000 (16:10 -0700)]
mm, compaction: properly signal and act upon lock and need_sched() contention
Compaction uses compact_checklock_irqsave() function to periodically check
for lock contention and need_resched() to either abort async compaction,
or to free the lock, schedule and retake the lock. When aborting,
cc->contended is set to signal the contended state to the caller. Two
problems have been identified in this mechanism.
First, compaction also calls directly cond_resched() in both scanners when
no lock is yet taken. This call either does not abort async compaction,
or set cc->contended appropriately. This patch introduces a new
compact_should_abort() function to achieve both. In isolate_freepages(),
the check frequency is reduced to once by SWAP_CLUSTER_MAX pageblocks to
match what the migration scanner does in the preliminary page checks. In
case a pageblock is found suitable for calling isolate_freepages_block(),
the checks within there are done on higher frequency.
Second, isolate_freepages() does not check if isolate_freepages_block()
aborted due to contention, and advances to the next pageblock. This
violates the principle of aborting on contention, and might result in
pageblocks not being scanned completely, since the scanning cursor is
advanced. This problem has been noticed in the code by Joonsoo Kim when
reviewing related patches. This patch makes isolate_freepages_block()
check the cc->contended flag and abort.
In case isolate_freepages() has already isolated some pages before
aborting due to contention, page migration will proceed, which is OK since
we do not want to waste the work that has been done, and page migration
has own checks for contention. However, we do not want another isolation
attempt by either of the scanners, so cc->contended flag check is added
also to compaction_alloc() and compact_finished() to make sure compaction
is aborted right after the migration.
The outcome of the patch should be reduced lock contention by async
compaction and lower latencies for higher-order allocations where direct
compaction is involved.
[akpm@linux-foundation.org: fix typo in comment] Reported-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Christoph Lameter <cl@linux.com> Cc: Rik van Riel <riel@redhat.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Tested-by: Shawn Guo <shawn.guo@linaro.org> Tested-by: Kevin Hilman <khilman@linaro.org> Tested-by: Stephen Warren <swarren@nvidia.com> Tested-by: Fabio Estevam <fabio.estevam@freescale.com> Cc: David Rientjes <rientjes@google.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jianyu Zhan [Wed, 4 Jun 2014 23:10:38 +0000 (16:10 -0700)]
mm/vmscan.c: use DIV_ROUND_UP for calculation of zone's balance_gap and correct comments.
Currently, we use (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1)
/ KSWAPD_ZONE_BALANCE_GAP_RATIO to avoid a zero gap value. It's better to
use DIV_ROUND_UP macro for neater code and clear meaning.
Besides, the gap value is calculated against the per-zone "managed pages",
not "present pages". This patch also corrects the comment and do some
rephrasing.
Signed-off-by: Jianyu Zhan <nasa4836@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael Aquini <aquini@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jianyu Zhan [Wed, 4 Jun 2014 23:10:36 +0000 (16:10 -0700)]
mm, hugetlb: move the error handle logic out of normal code path
alloc_huge_page() now mixes normal code path with error handle logic.
This patches move out the error handle logic, to make normal code path
more clean and redue code duplicate.
Signed-off-by: Jianyu Zhan <nasa4836@gmail.com> Acked-by: Davidlohr Bueso <davidlohr@hp.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:34 +0000 (16:10 -0700)]
mm: avoid unnecessary atomic operations during end_page_writeback()
If a page is marked for immediate reclaim then it is moved to the tail of
the LRU list. This occurs when the system is under enough memory pressure
for pages under writeback to reach the end of the LRU but we test for this
using atomic operations on every writeback. This patch uses an optimistic
non-atomic test first. It'll miss some pages in rare cases but the
consequences are not severe enough to warrant such a penalty.
While the function does not dominate profiles during a simple dd test the
cost of it is reduced.
Mel Gorman [Wed, 4 Jun 2014 23:10:31 +0000 (16:10 -0700)]
mm: non-atomically mark page accessed during page cache allocation where possible
aops->write_begin may allocate a new page and make it visible only to have
mark_page_accessed called almost immediately after. Once the page is
visible the atomic operations are necessary which is noticable overhead
when writing to an in-memory filesystem like tmpfs but should also be
noticable with fast storage. The objective of the patch is to initialse
the accessed information with non-atomic operations before the page is
visible.
The bulk of filesystems directly or indirectly use
grab_cache_page_write_begin or find_or_create_page for the initial
allocation of a page cache page. This patch adds an init_page_accessed()
helper which behaves like the first call to mark_page_accessed() but may
called before the page is visible and can be done non-atomically.
The primary APIs of concern in this care are the following and are used
by most filesystems.
All of them are very similar in detail to the patch creates a core helper
pagecache_get_page() which takes a flags parameter that affects its
behavior such as whether the page should be marked accessed or not. Then
old API is preserved but is basically a thin wrapper around this core
function.
Each of the filesystems are then updated to avoid calling
mark_page_accessed when it is known that the VM interfaces have already
done the job. There is a slight snag in that the timing of the
mark_page_accessed() has now changed so in rare cases it's possible a page
gets to the end of the LRU as PageReferenced where as previously it might
have been repromoted. This is expected to be rare but it's worth the
filesystem people thinking about it in case they see a problem with the
timing change. It is also the case that some filesystems may be marking
pages accessed that previously did not but it makes sense that filesystems
have consistent behaviour in this regard.
The test case used to evaulate this is a simple dd of a large file done
multiple times with the file deleted on each iterations. The size of the
file is 1/10th physical memory to avoid dirty page balancing. In the
async case it will be possible that the workload completes without even
hitting the disk and will have variable results but highlight the impact
of mark_page_accessed for async IO. The sync results are expected to be
more stable. The exception is tmpfs where the normal case is for the "IO"
to not hit the disk.
The test machine was single socket and UMA to avoid any scheduling or NUMA
artifacts. Throughput and wall times are presented for sync IO, only wall
times are shown for async as the granularity reported by dd and the
variability is unsuitable for comparison. As async results were variable
do to writback timings, I'm only reporting the maximum figures. The sync
results were stable enough to make the mean and stddev uninteresting.
The performance results are reported based on a run with no profiling.
Profile data is based on a separate run with oprofile running.
Mel Gorman [Wed, 4 Jun 2014 23:10:29 +0000 (16:10 -0700)]
fs: buffer: do not use unnecessary atomic operations when discarding buffers
Discarding buffers uses a bunch of atomic operations when discarding
buffers because ...... I can't think of a reason. Use a cmpxchg loop to
clear all the necessary flags. In most (all?) cases this will be a single
atomic operations.
[akpm@linux-foundation.org: move BUFFER_FLAGS_DISCARD into the .c file] Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:28 +0000 (16:10 -0700)]
mm: do not use unnecessary atomic operations when adding pages to the LRU
When adding pages to the LRU we clear the active bit unconditionally.
As the page could be reachable from other paths we cannot use unlocked
operations without risk of corruption such as a parallel
mark_page_accessed. This patch tests if is necessary to clear the
active flag before using an atomic operation. This potentially opens a
tiny race when PageActive is checked as mark_page_accessed could be
called after PageActive was checked. The race already exists but this
patch changes it slightly. The consequence is that that the page may be
promoted to the active list that might have been left on the inactive
list before the patch. It's too tiny a race and too marginal a
consequence to always use atomic operations for.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:24 +0000 (16:10 -0700)]
mm: shmem: avoid atomic operation during shmem_getpage_gfp
shmem_getpage_gfp uses an atomic operation to set the SwapBacked field
before it's even added to the LRU or visible. This is unnecessary as what
could it possible race against? Use an unlocked variant.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Rik van Riel <riel@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:22 +0000 (16:10 -0700)]
mm: page_alloc: convert hot/cold parameter and immediate callers to bool
cold is a bool, make it one. Make the likely case the "if" part of the
block instead of the else as according to the optimisation manual this is
preferred.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:21 +0000 (16:10 -0700)]
mm: page_alloc: use unsigned int for order in more places
X86 prefers the use of unsigned types for iterators and there is a
tendency to mix whether a signed or unsigned type if used for page order.
This converts a number of sites in mm/page_alloc.c to use unsigned int for
order where possible.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:16 +0000 (16:10 -0700)]
mm: page_alloc: use word-based accesses for get/set pageblock bitmaps
The test_bit operations in get/set pageblock flags are expensive. This
patch reads the bitmap on a word basis and use shifts and masks to isolate
the bits of interest. Similarly masks are used to set a local copy of the
bitmap and then use cmpxchg to update the bitmap if there have been no
other changes made in parallel.
In a test running dd onto tmpfs the overhead of the pageblock-related
functions went from 1.27% in profiles to 0.5%.
In addition to the performance benefits, this patch closes races that are
possible between:
a) get_ and set_pageblock_migratetype(), where get_pageblock_migratetype()
reads part of the bits before and other part of the bits after
set_pageblock_migratetype() has updated them.
b) set_pageblock_migratetype() and set_pageblock_skip(), where the non-atomic
read-modify-update set bit operation in set_pageblock_skip() will cause
lost updates to some bits changed in the set_pageblock_migratetype().
Joonsoo Kim first reported the case a) via code inspection. Vlastimil
Babka's testing with a debug patch showed that either a) or b) occurs
roughly once per mmtests' stress-highalloc benchmark (although not
necessarily in the same pageblock). Furthermore during development of
unrelated compaction patches, it was observed that frequent calls to
{start,undo}_isolate_page_range() the race occurs several thousands of
times and has resulted in NULL pointer dereferences in move_freepages()
and free_one_page() in places where free_list[migratetype] is
manipulated by e.g. list_move(). Further debugging confirmed that
migratetype had invalid value of 6, causing out of bounds access to the
free_list array.
That confirmed that the race exist, although it may be extremely rare,
and currently only fatal where page isolation is performed due to
memory hot remove. Races on pageblocks being updated by
set_pageblock_migratetype(), where both old and new migratetype are
lower MIGRATE_RESERVE, currently cannot result in an invalid value
being observed, although theoretically they may still lead to
unexpected creation or destruction of MIGRATE_RESERVE pageblocks.
Furthermore, things could get suddenly worse when memory isolation is
used more, or when new migratetypes are added.
After this patch, the race has no longer been observed in testing.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reported-and-tested-by: Vlastimil Babka <vbabka@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:14 +0000 (16:10 -0700)]
mm: page_alloc: take the ALLOC_NO_WATERMARK check out of the fast path
ALLOC_NO_WATERMARK is set in a few cases. Always by kswapd, always for
__GFP_MEMALLOC, sometimes for swap-over-nfs, tasks etc. Each of these
cases are relatively rare events but the ALLOC_NO_WATERMARK check is an
unlikely branch in the fast path. This patch moves the check out of the
fast path and after it has been determined that the watermarks have not
been met. This helps the common fast path at the cost of making the slow
path slower and hitting kswapd with a performance cost. It's a reasonable
tradeoff.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:10 +0000 (16:10 -0700)]
mm: page_alloc: only check the zone id check if pages are buddies
A node/zone index is used to check if pages are compatible for merging
but this happens unconditionally even if the buddy page is not free. Defer
the calculation as long as possible. Ideally we would check the zone boundary
but nodes can overlap.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Rik van Riel <riel@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:07 +0000 (16:10 -0700)]
include/linux/jump_label.h: expose the reference count
This patch exposes the jump_label reference count in preparation for the
next patch. cpusets cares about both the jump_label being enabled and how
many users of the cpusets there currently are.
Signed-off-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:06 +0000 (16:10 -0700)]
mm: page_alloc: do not treat a zone that cannot be used for dirty pages as "full"
If a zone cannot be used for a dirty page then it gets marked "full" which
is cached in the zlc and later potentially skipped by allocation requests
that have nothing to do with dirty zones.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:10:05 +0000 (16:10 -0700)]
mm: page_alloc: do not update zlc unless the zlc is active
The zlc is used on NUMA machines to quickly skip over zones that are full.
However it is always updated, even for the first zone scanned when the
zlc might not even be active. As it's a write to a bitmap that
potentially bounces cache line it's deceptively expensive and most
machines will not care. Only update the zlc if it was active.
Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
slab: delete cache from list after __kmem_cache_shutdown succeeds
Currently, on kmem_cache_destroy we delete the cache from the slab_list
before __kmem_cache_shutdown, inserting it back to the list on failure.
Initially, this was done, because we could release the slab_mutex in
__kmem_cache_shutdown to delete sysfs slub entry, but since commit 41a212859a4d ("slub: use sysfs'es release mechanism for kmem_cache") we
remove sysfs entry later in kmem_cache_destroy after dropping the
slab_mutex, so that no implementation of __kmem_cache_shutdown can ever
release the lock. Therefore we can simplify the code a bit by moving
list_del after __kmem_cache_shutdown.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@kernel.org> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Marc Carino [Wed, 4 Jun 2014 23:10:01 +0000 (16:10 -0700)]
cma: increase CMA_ALIGNMENT upper limit to 12
Some systems require a larger maximum PAGE_SIZE order for CMA allocations.
To accommodate such systems, increase the upper-bound of the
CMA_ALIGNMENT range to 12 (which ends up being 16MB on systems with 4K
pages).
Signed-off-by: Marc Carino <marc.ceeeee@gmail.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dan Streetman [Wed, 4 Jun 2014 23:09:59 +0000 (16:09 -0700)]
swap: change swap_list_head to plist, add swap_avail_head
Originally get_swap_page() started iterating through the singly-linked
list of swap_info_structs using swap_list.next or highest_priority_index,
which both were intended to point to the highest priority active swap
target that was not full. The first patch in this series changed the
singly-linked list to a doubly-linked list, and removed the logic to start
at the highest priority non-full entry; it starts scanning at the highest
priority entry each time, even if the entry is full.
Replace the manually ordered swap_list_head with a plist, swap_active_head.
Add a new plist, swap_avail_head. The original swap_active_head plist
contains all active swap_info_structs, as before, while the new
swap_avail_head plist contains only swap_info_structs that are active and
available, i.e. not full. Add a new spinlock, swap_avail_lock, to protect
the swap_avail_head list.
Mel Gorman suggested using plists since they internally handle ordering
the list entries based on priority, which is exactly what swap was doing
manually. All the ordering code is now removed, and swap_info_struct
entries and simply added to their corresponding plist and automatically
ordered correctly.
Using a new plist for available swap_info_structs simplifies and
optimizes get_swap_page(), which no longer has to iterate over full
swap_info_structs. Using a new spinlock for swap_avail_head plist
allows each swap_info_struct to add or remove themselves from the
plist when they become full or not-full; previously they could not
do so because the swap_info_struct->lock is held when they change
from full<->not-full, and the swap_lock protecting the main
swap_active_head must be ordered before any swap_info_struct->lock.
Signed-off-by: Dan Streetman <ddstreet@ieee.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Shaohua Li <shli@fusionio.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com> Cc: Weijie Yang <weijieut@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Bob Liu <bob.liu@oracle.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dan Streetman [Wed, 4 Jun 2014 23:09:57 +0000 (16:09 -0700)]
lib/plist: add plist_requeue
Add plist_requeue(), which moves the specified plist_node after all other
same-priority plist_nodes in the list. This is essentially an optimized
plist_del() followed by plist_add().
This is needed by swap, which (with the next patch in this set) uses a
plist of available swap devices. When a swap device (either a swap
partition or swap file) are added to the system with swapon(), the device
is added to a plist, ordered by the swap device's priority. When swap
needs to allocate a page from one of the swap devices, it takes the page
from the first swap device on the plist, which is the highest priority
swap device. The swap device is left in the plist until all its pages are
used, and then removed from the plist when it becomes full.
However, as described in man 2 swapon, swap must allocate pages from swap
devices with the same priority in round-robin order; to do this, on each
swap page allocation, swap uses a page from the first swap device in the
plist, and then calls plist_requeue() to move that swap device entry to
after any other same-priority swap devices. The next swap page allocation
will again use a page from the first swap device in the plist and requeue
it, and so on, resulting in round-robin usage of equal-priority swap
devices.
Also add plist_test_requeue() test function, for use by plist_test() to
test plist_requeue() function.
Signed-off-by: Dan Streetman <ddstreet@ieee.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Shaohua Li <shli@fusionio.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com> Cc: Weijie Yang <weijieut@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Bob Liu <bob.liu@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dan Streetman [Wed, 4 Jun 2014 23:09:55 +0000 (16:09 -0700)]
lib/plist: add helper functions
Add PLIST_HEAD() to plist.h, equivalent to LIST_HEAD() from list.h, to
define and initialize a struct plist_head.
Add plist_for_each_continue() and plist_for_each_entry_continue(),
equivalent to list_for_each_continue() and list_for_each_entry_continue(),
to iterate over a plist continuing after the current position.
Add plist_prev() and plist_next(), equivalent to (struct list_head*)->prev
and ->next, implemented by list_prev_entry() and list_next_entry(), to
access the prev/next struct plist_node entry. These are needed because
unlike struct list_head, direct access of the prev/next struct plist_node
isn't possible; the list must be navigated via the contained struct
list_head. e.g. instead of accessing the prev by list_prev_entry(node,
node_list) it can be accessed by plist_prev(node).
Signed-off-by: Dan Streetman <ddstreet@ieee.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Shaohua Li <shli@fusionio.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com> Cc: Weijie Yang <weijieut@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Bob Liu <bob.liu@oracle.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dan Streetman [Wed, 4 Jun 2014 23:09:53 +0000 (16:09 -0700)]
swap: change swap_info singly-linked list to list_head
The logic controlling the singly-linked list of swap_info_struct entries
for all active, i.e. swapon'ed, swap targets is rather complex, because:
- it stores the entries in priority order
- there is a pointer to the highest priority entry
- there is a pointer to the highest priority not-full entry
- there is a highest_priority_index variable set outside the swap_lock
- swap entries of equal priority should be used equally
this complexity leads to bugs such as: https://lkml.org/lkml/2014/2/13/181
where different priority swap targets are incorrectly used equally.
That bug probably could be solved with the existing singly-linked lists,
but I think it would only add more complexity to the already difficult to
understand get_swap_page() swap_list iteration logic.
The first patch changes from a singly-linked list to a doubly-linked list
using list_heads; the highest_priority_index and related code are removed
and get_swap_page() starts each iteration at the highest priority
swap_info entry, even if it's full. While this does introduce unnecessary
list iteration (i.e. Schlemiel the painter's algorithm) in the case where
one or more of the highest priority entries are full, the iteration and
manipulation code is much simpler and behaves correctly re: the above bug;
and the fourth patch removes the unnecessary iteration.
The second patch adds some minor plist helper functions; nothing new
really, just functions to match existing regular list functions. These
are used by the next two patches.
The third patch adds plist_requeue(), which is used by get_swap_page() in
the next patch - it performs the requeueing of same-priority entries
(which moves the entry to the end of its priority in the plist), so that
all equal-priority swap_info_structs get used equally.
The fourth patch converts the main list into a plist, and adds a new plist
that contains only swap_info entries that are both active and not full.
As Mel suggested using plists allows removing all the ordering code from
swap - plists handle ordering automatically. The list naming is also
clarified now that there are two lists, with the original list changed
from swap_list_head to swap_active_head and the new list named
swap_avail_head. A new spinlock is also added for the new list, so
swap_info entries can be added or removed from the new list immediately as
they become full or not full.
This patch (of 4):
Replace the singly-linked list tracking active, i.e. swapon'ed,
swap_info_struct entries with a doubly-linked list using struct
list_heads. Simplify the logic iterating and manipulating the list of
entries, especially get_swap_page(), by using standard list_head
functions, and removing the highest priority iteration logic.
The change fixes the bug:
https://lkml.org/lkml/2014/2/13/181
in which different priority swap entries after the highest priority entry
are incorrectly used equally in pairs. The swap behavior is now as
advertised, i.e. different priority swap entries are used in order, and
equal priority swap targets are used concurrently.
Signed-off-by: Dan Streetman <ddstreet@ieee.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Shaohua Li <shli@fusionio.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com> Cc: Weijie Yang <weijieut@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Bob Liu <bob.liu@oracle.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jianyu Zhan [Wed, 4 Jun 2014 23:09:52 +0000 (16:09 -0700)]
mm: fold mlocked_vma_newpage() into its only call site
In previous commit(mm: use the light version __mod_zone_page_state in
mlocked_vma_newpage()) a irq-unsafe __mod_zone_page_state is used. And as
suggested by Andrew, to reduce the risks that new call sites incorrectly
using mlocked_vma_newpage() without knowing they are adding racing, this
patch folds mlocked_vma_newpage() into its only call site,
page_add_new_anon_rmap, to make it open-cocded for people to know what is
going on.
Jianyu Zhan [Wed, 4 Jun 2014 23:09:51 +0000 (16:09 -0700)]
mm: use the light version __mod_zone_page_state in mlocked_vma_newpage()
mlocked_vma_newpage() is called with pte lock held(a spinlock), which
implies preemtion disabled, and the vm stat counter is not modified from
interrupt context, so we need not use an irq-safe mod_zone_page_state()
here, using a light-weight version __mod_zone_page_state() would be OK.
This patch also documents __mod_zone_page_state() and some of its
callsites. The comment above __mod_zone_page_state() is from Hugh
Dickins, and acked by Christoph.
Most credits to Hugh and Christoph for the clarification on the usage of
the __mod_zone_page_state().
[akpm@linux-foundation.org: coding-style fixes] Suggested-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Jianyu Zhan <nasa4836@gmail.com> Reviewed-by: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Vlastimil Babka [Wed, 4 Jun 2014 23:08:34 +0000 (16:08 -0700)]
mm/compaction: avoid rescanning pageblocks in isolate_freepages
The compaction free scanner in isolate_freepages() currently remembers PFN
of the highest pageblock where it successfully isolates, to be used as the
starting pageblock for the next invocation. The rationale behind this is
that page migration might return free pages to the allocator when
migration fails and we don't want to skip them if the compaction
continues.
Since migration now returns free pages back to compaction code where they
can be reused, this is no longer a concern. This patch changes
isolate_freepages() so that the PFN for restarting is updated with each
pageblock where isolation is attempted. Using stress-highalloc from
mmtests, this resulted in 10% reduction of the pages scanned by the free
scanner.
Note that the somewhat similar functionality that records highest
successful pageblock in zone->compact_cached_free_pfn, remains unchanged.
This cache is used when the whole compaction is restarted, not for
multiple invocations of the free scanner during single compaction.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Christoph Lameter <cl@linux.com> Cc: Rik van Riel <riel@redhat.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Vlastimil Babka [Wed, 4 Jun 2014 23:08:32 +0000 (16:08 -0700)]
mm/compaction: do not count migratepages when unnecessary
During compaction, update_nr_listpages() has been used to count remaining
non-migrated and free pages after a call to migrage_pages(). The
freepages counting has become unneccessary, and it turns out that
migratepages counting is also unnecessary in most cases.
The only situation when it's needed to count cc->migratepages is when
migrate_pages() returns with a negative error code. Otherwise, the
non-negative return value is the number of pages that were not migrated,
which is exactly the count of remaining pages in the cc->migratepages
list.
Furthermore, any non-zero count is only interesting for the tracepoint of
mm_compaction_migratepages events, because after that all remaining
unmigrated pages are put back and their count is set to 0.
This patch therefore removes update_nr_listpages() completely, and changes
the tracepoint definition so that the manual counting is done only when
the tracepoint is enabled, and only when migrate_pages() returns a
negative error code.
Furthermore, migrate_pages() and the tracepoints won't be called when
there's nothing to migrate. This potentially avoids some wasted cycles
and reduces the volume of uninteresting mm_compaction_migratepages events
where "nr_migrated=0 nr_failed=0". In the stress-highalloc mmtest, this
was about 75% of the events. The mm_compaction_isolate_migratepages event
is better for determining that nothing was isolated for migration, and
this one was just duplicating the info.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Christoph Lameter <cl@linux.com> Cc: Rik van Riel <riel@redhat.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Rientjes [Wed, 4 Jun 2014 23:08:31 +0000 (16:08 -0700)]
mm, compaction: terminate async compaction when rescheduling
Async compaction terminates prematurely when need_resched(), see
compact_checklock_irqsave(). This can never trigger, however, if the
cond_resched() in isolate_migratepages_range() always takes care of the
scheduling.
If the cond_resched() actually triggers, then terminate this pageblock
scan for async compaction as well.
David Rientjes [Wed, 4 Jun 2014 23:08:30 +0000 (16:08 -0700)]
mm, thp: avoid excessive compaction latency during fault
Synchronous memory compaction can be very expensive: it can iterate an
enormous amount of memory without aborting, constantly rescheduling,
waiting on page locks and lru_lock, etc, if a pageblock cannot be
defragmented.
Unfortunately, it's too expensive for transparent hugepage page faults and
it's much better to simply fallback to pages. On 128GB machines, we find
that synchronous memory compaction can take O(seconds) for a single thp
fault.
Now that async compaction remembers where it left off without strictly
relying on sync compaction, this makes thp allocations best-effort without
causing egregious latency during fault. We still need to retry async
compaction after reclaim, but this won't stall for seconds.
David Rientjes [Wed, 4 Jun 2014 23:08:28 +0000 (16:08 -0700)]
mm, compaction: embed migration mode in compact_control
We're going to want to manipulate the migration mode for compaction in the
page allocator, and currently compact_control's sync field is only a bool.
Currently, we only do MIGRATE_ASYNC or MIGRATE_SYNC_LIGHT compaction
depending on the value of this bool. Convert the bool to enum
migrate_mode and pass the migration mode in directly. Later, we'll want
to avoid MIGRATE_SYNC_LIGHT for thp allocations in the pagefault patch to
avoid unnecessary latency.
This also alters compaction triggered from sysfs, either for the entire
system or for a node, to force MIGRATE_SYNC.
[akpm@linux-foundation.org: fix build]
[iamjoonsoo.kim@lge.com: use MIGRATE_SYNC in alloc_contig_range()] Signed-off-by: David Rientjes <rientjes@google.com> Suggested-by: Mel Gorman <mgorman@suse.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Rientjes [Wed, 4 Jun 2014 23:08:27 +0000 (16:08 -0700)]
mm, compaction: add per-zone migration pfn cache for async compaction
Each zone has a cached migration scanner pfn for memory compaction so that
subsequent calls to memory compaction can start where the previous call
left off.
Currently, the compaction migration scanner only updates the per-zone
cached pfn when pageblocks were not skipped for async compaction. This
creates a dependency on calling sync compaction to avoid having subsequent
calls to async compaction from scanning an enormous amount of non-MOVABLE
pageblocks each time it is called. On large machines, this could be
potentially very expensive.
This patch adds a per-zone cached migration scanner pfn only for async
compaction. It is updated everytime a pageblock has been scanned in its
entirety and when no pages from it were successfully isolated. The cached
migration scanner pfn for sync compaction is updated only when called for
sync compaction.
David Rientjes [Wed, 4 Jun 2014 23:08:26 +0000 (16:08 -0700)]
mm, compaction: return failed migration target pages back to freelist
Greg reported that he found isolated free pages were returned back to the
VM rather than the compaction freelist. This will cause holes behind the
free scanner and cause it to reallocate additional memory if necessary
later.
He detected the problem at runtime seeing that ext4 metadata pages (esp
the ones read by "sbi->s_group_desc[i] = sb_bread(sb, block)") were
constantly visited by compaction calls of migrate_pages(). These pages
had a non-zero b_count which caused fallback_migrate_page() ->
try_to_release_page() -> try_to_free_buffers() to fail.
Memory compaction works by having a "freeing scanner" scan from one end of
a zone which isolates pages as migration targets while another "migrating
scanner" scans from the other end of the same zone which isolates pages
for migration.
When page migration fails for an isolated page, the target page is
returned to the system rather than the freelist built by the freeing
scanner. This may require the freeing scanner to continue scanning memory
after suitable migration targets have already been returned to the system
needlessly.
This patch returns destination pages to the freeing scanner freelist when
page migration fails. This prevents unnecessary work done by the freeing
scanner but also encourages memory to be as compacted as possible at the
end of the zone.
David Rientjes [Wed, 4 Jun 2014 23:08:25 +0000 (16:08 -0700)]
mm, migration: add destination page freeing callback
Memory migration uses a callback defined by the caller to determine how to
allocate destination pages. When migration fails for a source page,
however, it frees the destination page back to the system.
This patch adds a memory migration callback defined by the caller to
determine how to free destination pages. If a caller, such as memory
compaction, builds its own freelist for migration targets, this can reuse
already freed memory instead of scanning additional memory.
If the caller provides a function to handle freeing of destination pages,
it is called when page migration fails. If the caller passes NULL then
freeing back to the system will be handled as usual. This patch
introduces no functional change.
memcg: memcg_kmem_create_cache: make memcg_name_buf statically allocated
It isn't worth complicating the code by allocating it on the first access,
because it only takes 256 bytes.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Instead of calling back to memcontrol.c from kmem_cache_create_memcg in
order to just create the name of a per memcg cache, let's allocate it in
place. We only need to pass the memcg name to kmem_cache_create_memcg for
that - everything else can be done in slab_common.c.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Qiang Huang [Wed, 4 Jun 2014 23:08:21 +0000 (16:08 -0700)]
memcg: fold mem_cgroup_stolen
It is only used in __mem_cgroup_begin_update_page_stat(), the name is
confusing and 2 routines for one thing also confuse people, so fold this
function seems more clear.
[akpm@linux-foundation.org: fix typo, per Michal] Signed-off-by: Qiang Huang <h.huangqiang@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cyrill Gorcunov [Wed, 4 Jun 2014 23:08:16 +0000 (16:08 -0700)]
mm: x86 pgtable: require X86_64 for soft-dirty tracker
Tracking dirty status on 2 level pages requires very ugly macros and
taking into account how old the machines who can operate without PAE
mode only are, lets drop soft dirty tracker from them for code
simplicity (note I can't drop all the macros from 2 level pages by now
since _PAGE_BIT_PROTNONE and _PAGE_BIT_FILE are still used even without
tracker).
Linus proposed to completely rip off softdirty support on x86-32 (even
with PAE) and since for CRIU we're not planning to support native x86-32
mode, lets do that.
(Softdirty tracker is relatively new feature which is mostly used by
CRIU so I don't expect if such API change would cause problems for
userspace).
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Noonan <steven@uplinklabs.net> Cc: Rik van Riel <riel@redhat.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cleanups:
- move pte-related code to separate function. It's about half of the
function;
- get rid of some goto-logic;
- use 'return NULL' instead of 'return page' where page can only be
NULL;
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Hansen [Wed, 4 Jun 2014 23:08:07 +0000 (16:08 -0700)]
mm: shrinker: add nid to tracepoint output
Now that we are doing NUMA-aware shrinking, and can have shrinkers
running in parallel, or working on individual nodes, it seems like we
should also be sticking the node in the output.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Dave Chinner <david@fromorbit.com> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
and noticed that "total_scan" can go negative in some cases. We
used to dump out the "total_scan" variable directly, but some of
the shrinker modifications along the way changed that.
This patch just dumps it out directly, again. It doesn't make
any sense to derive it from new_nr and nr any more since there
are now other shrinkers that can be running in parallel and
mucking with those values.
Here's an example of the negative numbers in the output:
> kswapd0-840 [000] 160.869398: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 10 new scan count 39 total_scan 29 last shrinker return val 256
> kswapd0-840 [000] 160.869618: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 39 new scan count 102 total_scan 63 last shrinker return val 256
> kswapd0-840 [000] 160.870031: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 102 new scan count 47 total_scan -55 last shrinker return val 768
> kswapd0-840 [000] 160.870464: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 47 new scan count 45 total_scan -2 last shrinker return val 768
> kswapd0-840 [000] 163.384144: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 45 new scan count 56 total_scan 11 last shrinker return val 0
> kswapd0-840 [000] 163.384297: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 56 new scan count 15 total_scan -41 last shrinker return val 256
> kswapd0-840 [000] 163.384414: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 15 new scan count 117 total_scan 102 last shrinker return val 0
> kswapd0-840 [000] 163.384657: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 117 new scan count 36 total_scan -81 last shrinker return val 512
> kswapd0-840 [000] 163.384880: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 36 new scan count 111 total_scan 75 last shrinker return val 256
> kswapd0-840 [000] 163.385256: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 111 new scan count 34 total_scan -77 last shrinker return val 768
> kswapd0-840 [000] 163.385598: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 34 new scan count 122 total_scan 88 last shrinker return val 512
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Dave Chinner <david@fromorbit.com> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Daeseok Youn [Wed, 4 Jun 2014 23:08:05 +0000 (16:08 -0700)]
mm/dmapool.c: remove redundant NULL check for dev in dma_pool_create()
"dev" cannot be NULL because it is already checked before calling
dma_pool_create().
If dev ever was NULL, the code would oops in dev_to_node() after enabling
CONFIG_NUMA.
It is possible that some driver is using dev==NULL and has never been run
on a NUMA machine. Such a driver is probably outdated, possibly buggy and
will need some attention if it starts triggering NULL derefs.
Jianyu Zhan [Wed, 4 Jun 2014 23:08:02 +0000 (16:08 -0700)]
mm: introdule compound_head_by_tail()
Currently, in put_compound_page(), we have
======
if (likely(!PageTail(page))) { <------ (1)
if (put_page_testzero(page)) {
/*
¦* By the time all refcounts have been released
¦* split_huge_page cannot run anymore from under us.
¦*/
if (PageHead(page))
__put_compound_page(page);
else
__put_single_page(page);
}
return;
}
/* __split_huge_page_refcount can run under us */
page_head = compound_head(page); <------------ (2)
======
if at (1) , we fail the check, this means page is *likely* a tail page.
Then at (2), as compoud_head(page) is inlined, it is :
smp_rmb();
if (likely(PageTail(page)))
return head;
}
return page;
}
======
here, the (3) unlikely in the case is a negative hint, because it is
*likely* a tail page. So the check (3) in this case is not good, so I
introduce a helper for this case.
So this patch introduces compound_head_by_tail() which deals with a
possible tail page(though it could be spilt by a racy thread), and make
compound_head() a wrapper on it.
This patch has no functional change, and it reduces the object
size slightly:
text data bss dec hex filename
11003 1328 16 12347 303b mm/swap.o.orig
10971 1328 16 12315 301b mm/swap.o.patched
I've ran "perf top -e branch-miss" to observe branch-miss in this case.
As Michael points out, it's a slow path, so only very few times this case
happens. But I grep'ed the code base, and found there still are some
other call sites could be benifited from this helper. And given that it
only bloating up the source by only 5 lines, but with a reduced object
size. I still believe this helper deserves to exsit.
Signed-off-by: Jianyu Zhan <nasa4836@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jianyu Zhan [Wed, 4 Jun 2014 23:08:01 +0000 (16:08 -0700)]
mm/swap.c: split put_compound_page()
Currently, put_compound_page() carefully handles tricky cases to avoid
racing with compound page releasing or splitting, which makes it quite
lenthy (about 200+ lines) and needs deep tab indention, which makes it
quite hard to follow and maintain.
Now based on two helpers introduced in the previous patch ("mm/swap.c:
introduce put_[un]refcounted_compound_page helpers for spliting
put_compound_page"), this patch replaces those two lengthy code paths with
these two helpers, respectively. Also, it has some comment rephrasing.
After this patch, the put_compound_page() is very compact, thus easy to
read and maintain.
After splitting, the object file is of same size as the original one.
Actually, I've diff'ed put_compound_page()'s orginal disassemble code and
the patched disassemble code, the are 100% the same!
This fact shows that this splitting has no functional change, but it
brings readability.
This patch and the previous one blow the code by 32 lines, mostly due to
comments.
Signed-off-by: Jianyu Zhan <nasa4836@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jianyu Zhan [Wed, 4 Jun 2014 23:07:59 +0000 (16:07 -0700)]
mm/swap.c: introduce put_[un]refcounted_compound_page helpers for splitting put_compound_page()
Currently, put_compound_page() carefully handles tricky cases to avoid
racing with compound page releasing or splitting, which makes it quite
lenthy (about 200+ lines) and needs deep tab indention, which makes it
quite hard to follow and maintain.
This patch and the next patch refactor this function.
Based on the code skeleton of put_compound_page:
put_compound_pge:
if !PageTail(page)
put head page fastpath;
return;
/* else PageTail */
page_head = compound_head(page)
if !__compound_tail_refcounted(page_head)
put head page optimal path; <---(1)
return;
else
put head page slowpath; <--- (2)
return;
This patch introduces two helpers, put_[un]refcounted_compound_page,
handling the code path (1) and code path (2), respectively. They both are
tagged __always_inline, thus elmiating function call overhead, making them
operating the same way as before.
They are almost copied verbatim(except one place, a "goto out_put_single"
is expanded), with some comments rephrasing.
Signed-off-by: Jianyu Zhan <nasa4836@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The nmask argument to set_mempolicy() is const according to the user-space
header numaif.h, and since the kernel does indeed not modify it, it might
as well be declared const in the kernel.
The nmask argument to mbind() is const according to the userspace header
numaif.h, and since the kernel does indeed not modify it, it might as well
be declared const in the kernel.
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This doesn't really hurt but unnecessary and misleading. init_task is the
"swapper" thread == current, its ->mm is always NULL. And init_mm can
only be used as ->active_mm, not as ->mm.
mm_init_owner() has a single caller with this patch, perhaps it should
die. mm_init() can initialize ->owner under #ifdef.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Peter Chiang <pchiang@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Oleg Nesterov [Wed, 4 Jun 2014 23:07:54 +0000 (16:07 -0700)]
memcg: optimize the "Search everything else" loop in mm_update_next_owner()
for_each_process_thread() is sub-optimal. All threads share the same
->mm, we can swicth to the next process once we found a thread with
->mm != NULL and ->mm != mm.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Peter Chiang <pchiang@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Oleg Nesterov [Wed, 4 Jun 2014 23:07:52 +0000 (16:07 -0700)]
memcg: mm_update_next_owner() should skip kthreads
"Search through everything else" in mm_update_next_owner() can hit a
kthread which adopted this "mm" via use_mm(), it should not be used as
mm->owner. Add the PF_KTHREAD check.
While at it, change this code to use for_each_process_thread() instead
of deprecated do_each_thread/while_each_thread.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Peter Chiang <pchiang@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Wed, 4 Jun 2014 23:07:50 +0000 (16:07 -0700)]
brd: return -ENOSPC rather than -ENOMEM on page allocation failure
brd is effectively a thinly provisioned device. Thinly provisioned
devices return -ENOSPC when they can't write a new block. -ENOMEM is an
implementation detail that callers shouldn't know.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Acked-by: Dave Chinner <david@fromorbit.com> Cc: Dheeraj Reddy <dheeraj.reddy@intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Wed, 4 Jun 2014 23:07:46 +0000 (16:07 -0700)]
fs/block_dev.c: add bdev_read_page() and bdev_write_page()
A block device driver may choose to provide a rw_page operation. These
will be called when the filesystem is attempting to do page sized I/O to
page cache pages (ie not for direct I/O). This does preclude I/Os that
are larger than page size, so this may only be a performance gain for
some devices.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Tested-by: Dheeraj Reddy <dheeraj.reddy@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Wed, 4 Jun 2014 23:07:45 +0000 (16:07 -0700)]
fs/mpage.c: factor page_endio() out of mpage_end_io()
page_endio() takes care of updating all the appropriate page flags once
I/O has finished to a page. Switch to using mapping_set_error() instead
of setting AS_EIO directly; this will handle thin-provisioned devices
correctly.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dheeraj Reddy <dheeraj.reddy@intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Wed, 4 Jun 2014 23:07:44 +0000 (16:07 -0700)]
fs/mpage.c: factor clean_buffers() out of __mpage_writepage()
__mpage_writepage() is over 200 lines long, has 20 local variables, four
goto labels and could desperately use simplification. Splitting
clean_buffers() into a helper function improves matters a little,
removing 20+ lines from it.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dheeraj Reddy <dheeraj.reddy@intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Wed, 4 Jun 2014 23:07:43 +0000 (16:07 -0700)]
fs/buffer.c: remove block_write_full_page_endio()
The last in-tree caller of block_write_full_page_endio() was removed in
January 2013. It's time to remove the EXPORT_SYMBOL, which leaves
block_write_full_page() as the only caller of
block_write_full_page_endio(), so inline block_write_full_page_endio()
into block_write_full_page().
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dheeraj Reddy <dheeraj.reddy@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
NeilBrown [Wed, 4 Jun 2014 23:07:42 +0000 (16:07 -0700)]
mm/vmscan.c: avoid throttling reclaim for loop-back nfsd threads
When a loopback NFS mount is active and the backing device for the NFS
mount becomes congested, that can impose throttling delays on the nfsd
threads.
These delays significantly reduce throughput and so the NFS mount remains
congested.
This results in a livelock and the reduced throughput persists.
This livelock has been found in testing with the 'wait_iff_congested'
call, and could possibly be caused by the 'congestion_wait' call.
This livelock is similar to the deadlock which justified the introduction
of PF_LESS_THROTTLE, and the same flag can be used to remove this
livelock.
To minimise the impact of the change, we still throttle nfsd when the
filesystem it is writing to is congested, but not when some separate
filesystem (e.g. the NFS filesystem) is congested.
Signed-off-by: NeilBrown <neilb@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:07:41 +0000 (16:07 -0700)]
mm: numa: add migrated transhuge pages to LRU the same way as base pages
Migration of misplaced transhuge pages uses page_add_new_anon_rmap() when
putting the page back as it avoided an atomic operations and added the new
page to the correct LRU. A side-effect is that the page gets marked
activated as part of the migration meaning that transhuge and base pages
are treated differently from an aging perspective than base page
migration.
This patch uses page_add_anon_rmap() and putback_lru_page() on completion
of a transhuge migration similar to base page migration. It would require
fewer atomic operations to use lru_cache_add without taking an additional
reference to the page. The downside would be that it's still different to
base page migration and unevictable pages may be added to the wrong LRU
for cleaning up later. Testing of the usual workloads did not show any
adverse impact to the change.
At present, we have the following mutexes protecting data related to per
memcg kmem caches:
- slab_mutex. This one is held during the whole kmem cache creation
and destruction paths. We also take it when updating per root cache
memcg_caches arrays (see memcg_update_all_caches). As a result, taking
it guarantees there will be no changes to any kmem cache (including per
memcg). Why do we need something else then? The point is it is
private to slab implementation and has some internal dependencies with
other mutexes (get_online_cpus). So we just don't want to rely upon it
and prefer to introduce additional mutexes instead.
- activate_kmem_mutex. Initially it was added to synchronize
initializing kmem limit (memcg_activate_kmem). However, since we can
grow per root cache memcg_caches arrays only on kmem limit
initialization (see memcg_update_all_caches), we also employ it to
protect against memcg_caches arrays relocation (e.g. see
__kmem_cache_destroy_memcg_children).
- We have a convention not to take slab_mutex in memcontrol.c, but we
want to walk over per memcg memcg_slab_caches lists there (e.g. for
destroying all memcg caches on offline). So we have per memcg
slab_caches_mutex's protecting those lists.
Such a syncrhonization scheme has a number of flaws, for instance:
- We can't call kmem_cache_{destroy,shrink} while walking over a
memcg::memcg_slab_caches list due to locking order. As a result, in
mem_cgroup_destroy_all_caches we schedule the
memcg_cache_params::destroy work shrinking and destroying the cache.
- We don't have a mutex to synchronize per memcg caches destruction
between memcg offline (mem_cgroup_destroy_all_caches) and root cache
destruction (__kmem_cache_destroy_memcg_children). Currently we just
don't bother about it.
This patch simplifies it by substituting per memcg slab_caches_mutex's
with the global memcg_slab_mutex. It will be held whenever a new per
memcg cache is created or destroyed, so it protects per root cache
memcg_caches arrays and per memcg memcg_slab_caches lists. The locking
order is following:
This allows us to call kmem_cache_{create,shrink,destroy} under the
memcg_slab_mutex. As a result, we don't need memcg_cache_params::destroy
work any more - we can simply destroy caches while iterating over a per
memcg slab caches list.
Also using the global mutex simplifies synchronization between concurrent
per memcg caches creation/destruction, e.g. mem_cgroup_destroy_all_caches
vs __kmem_cache_destroy_memcg_children.
The downside of this is that we substitute per-memcg slab_caches_mutex's
with a hummer-like global mutex, but since we already take either the
slab_mutex or the cgroup_mutex along with a memcg::slab_caches_mutex, it
shouldn't hurt concurrency a lot.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Glauber Costa <glommer@gmail.com> Cc: Pekka Enberg <penberg@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
memcg, slab: merge memcg_{bind,release}_pages to memcg_{un}charge_slab
Currently we have two pairs of kmemcg-related functions that are called on
slab alloc/free. The first is memcg_{bind,release}_pages that count the
total number of pages allocated on a kmem cache. The second is
memcg_{un}charge_slab that {un}charge slab pages to kmemcg resource
counter. Let's just merge them to keep the code clean.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Glauber Costa <glommer@gmail.com> Cc: Pekka Enberg <penberg@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
memcg, slab: do not schedule cache destruction when last page goes away
This patchset is a part of preparations for kmemcg re-parenting. It
targets at simplifying kmemcg work-flows and synchronization.
First, it removes async per memcg cache destruction (see patches 1, 2).
Now caches are only destroyed on memcg offline. That means the caches
that are not empty on memcg offline will be leaked. However, they are
already leaked, because memcg_cache_params::nr_pages normally never drops
to 0 so the destruction work is never scheduled except kmem_cache_shrink
is called explicitly. In the future I'm planning reaping such dead caches
on vmpressure or periodically.
Second, it substitutes per memcg slab_caches_mutex's with the global
memcg_slab_mutex, which should be taken during the whole per memcg cache
creation/destruction path before the slab_mutex (see patch 3). This
greatly simplifies synchronization among various per memcg cache
creation/destruction paths.
I'm still not quite sure about the end picture, in particular I don't know
whether we should reap dead memcgs' kmem caches periodically or try to
merge them with their parents (see https://lkml.org/lkml/2014/4/20/38 for
more details), but whichever way we choose, this set looks like a
reasonable change to me, because it greatly simplifies kmemcg work-flows
and eases further development.
This patch (of 3):
After a memcg is offlined, we mark its kmem caches that cannot be deleted
right now due to pending objects as dead by setting the
memcg_cache_params::dead flag, so that memcg_release_pages will schedule
cache destruction (memcg_cache_params::destroy) as soon as the last slab
of the cache is freed (memcg_cache_params::nr_pages drops to zero).
I guess the idea was to destroy the caches as soon as possible, i.e.
immediately after freeing the last object. However, it just doesn't work
that way, because kmem caches always preserve some pages for the sake of
performance, so that nr_pages never gets to zero unless the cache is
shrunk explicitly using kmem_cache_shrink. Of course, we could account
the total number of objects on the cache or check if all the slabs
allocated for the cache are empty on kmem_cache_free and schedule
destruction if so, but that would be too costly.
Thus we have a piece of code that works only when we explicitly call
kmem_cache_shrink, but complicates the whole picture a lot. Moreover,
it's racy in fact. For instance, kmem_cache_shrink may free the last slab
and thus schedule cache destruction before it finishes checking that the
cache is empty, which can lead to use-after-free.
So I propose to remove this async cache destruction from
memcg_release_pages, and check if the cache is empty explicitly after
calling kmem_cache_shrink instead. This will simplify things a lot w/o
introducing any functional changes.
And regarding dead memcg caches (i.e. those that are left hanging around
after memcg offline for they have objects), I suppose we should reap them
either periodically or on vmpressure as Glauber suggested initially. I'm
going to implement this later.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Glauber Costa <glommer@gmail.com> Cc: Pekka Enberg <penberg@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Wed, 4 Jun 2014 23:07:36 +0000 (16:07 -0700)]
memcg: do not hang on OOM when killed by userspace OOM access to memory reserves
Eric has reported that he can see task(s) stuck in memcg OOM handler
regularly. The only way out is to
echo 0 > $GROUP/memory.oom_control
His usecase is:
- Setup a hierarchy with memory and the freezer (disable kernel oom and
have a process watch for oom).
- In that memory cgroup add a process with one thread per cpu.
- In one thread slowly allocate once per second I think it is 16M of ram
and mlock and dirty it (just to force the pages into ram and stay
there).
- When oom is achieved loop:
* attempt to freeze all of the tasks.
* if frozen send every task SIGKILL, unfreeze, remove the directory in
cgroupfs.
Eric has then pinpointed the issue to be memcg specific.
All tasks are sitting on the memcg_oom_waitq when memcg oom is disabled.
Those that have received fatal signal will bypass the charge and should
continue on their way out. The tricky part is that the exit path might
trigger a page fault (e.g. exit_robust_list), thus the memcg charge,
while its memcg is still under OOM because nobody has released any charges
yet.
Unlike with the in-kernel OOM handler the exiting task doesn't get
TIF_MEMDIE set so it doesn't shortcut further charges of the killed task
and falls to the memcg OOM again without any way out of it as there are no
fatal signals pending anymore.
This patch fixes the issue by checking PF_EXITING early in
mem_cgroup_try_charge and bypass the charge same as if it had fatal
signal pending or TIF_MEMDIE set.
Normally exiting tasks (aka not killed) will bypass the charge now but
this should be OK as the task is leaving and will release memory and
increasing the memory pressure just to release it in a moment seems
dubious wasting of cycles. Besides that charges after exit_signals should
be rare.
I am bringing this patch again (rebased on the current mmotm tree). I
hope we can move forward finally. If there is still an opposition then
I would really appreciate a concurrent approach so that we can discuss
alternatives.
http://comments.gmane.org/gmane.linux.kernel.stable/77650 is a reference
to the followup discussion when the patch has been dropped from the mmotm
last time.
Reported-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Wed, 4 Jun 2014 23:07:35 +0000 (16:07 -0700)]
mm: vmscan: do not throttle based on pfmemalloc reserves if node has no ZONE_NORMAL
throttle_direct_reclaim() is meant to trigger during swap-over-network
during which the min watermark is treated as a pfmemalloc reserve. It
throttes on the first node in the zonelist but this is flawed.
The user-visible impact is that a process running on CPU whose local
memory node has no ZONE_NORMAL will stall for prolonged periods of time,
possibly indefintely. This is due to throttle_direct_reclaim thinking the
pfmemalloc reserves are depleted when in fact they don't exist on that
node.
On a NUMA machine running a 32-bit kernel (I know) allocation requests
from CPUs on node 1 would detect no pfmemalloc reserves and the process
gets throttled. This patch adjusts throttling of direct reclaim to
throttle based on the first node in the zonelist that has a usable
ZONE_NORMAL or lower zone.
Oleg Nesterov [Wed, 4 Jun 2014 23:07:34 +0000 (16:07 -0700)]
memcg: kill CONFIG_MM_OWNER
CONFIG_MM_OWNER makes no sense. It is not user-selectable, it is only
selected by CONFIG_MEMCG automatically. So we can kill this option in
init/Kconfig and do s/CONFIG_MM_OWNER/CONFIG_MEMCG/ globally.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / karo-tx-linux.git / log