Hugh Dickins [Tue, 22 Mar 2011 23:33:06 +0000 (16:33 -0700)]
mm: remove worrying dead code from find_get_pages()
The radix_tree_deref_retry() case in find_get_pages() has a strange little
excrescence, not seen in the other gang lookups: it looks like the start
of an abandoned attempt to guarantee forward progress in a case that
cannot arise.
ret should always be 0 here: if it isn't, then going back to restart will
leak references to pages already gotten. There used to be a comment
saying nr_found is necessarily 1 here: that's not quite true, but the
radix_tree_deref_retry() case is peculiar to the entry at index 0, when we
race with it being moved out of the radix_tree root or back.
Remove the worrisome two lines, add a brief comment here and in
find_get_pages_contig() and find_get_pages_tag(), and a WARN_ON in
find_get_pages() should it ever be seen elsewhere than at 0.
Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Nick Piggin <npiggin@kernel.dk> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Salman Qazi <sqazi@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Petr Holasek [Tue, 22 Mar 2011 23:33:05 +0000 (16:33 -0700)]
hugetlbfs: correct handling of negative input to /proc/sys/vm/nr_hugepages
When the user inserts a negative value into /proc/sys/vm/nr_hugepages it
will cause the kernel to allocate as many hugepages as possible and to
then update /proc/meminfo to reflect this.
This changes the behavior so that the negative input will result in
nr_hugepages value being unchanged.
Signed-off-by: Petr Holasek <pholasek@redhat.com> Signed-off-by: Anton Arapov <anton@redhat.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Eric B Munson <emunson@mgebm.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Tue, 22 Mar 2011 23:33:04 +0000 (16:33 -0700)]
mm: vmscan: kswapd should not free an excessive number of pages when balancing small zones
When reclaiming for order-0 pages, kswapd requires that all zones be
balanced. Each cycle through balance_pgdat() does background ageing on
all zones if necessary and applies equal pressure on the inactive zone
unless a lot of pages are free already.
A "lot of free pages" is defined as a "balance gap" above the high
watermark which is currently 7*high_watermark. Historically this was
reasonable as min_free_kbytes was small. However, on systems using huge
pages, it is recommended that min_free_kbytes is higher and it is tuned
with hugeadm --set-recommended-min_free_kbytes. With the introduction of
transparent huge page support, this recommended value is also applied. On
X86-64 with 4G of memory, min_free_kbytes becomes 67584 so one would
expect around 68M of memory to be free. The Normal zone is approximately
35000 pages so under even normal memory pressure such as copying a large
file, it gets exhausted quickly. As it is getting exhausted, kswapd
applies pressure equally to all zones, including the DMA32 zone. DMA32 is
approximately 700,000 pages with a high watermark of around 23,000 pages.
In this situation, kswapd will reclaim around (23000*8 where 8 is the high
watermark + balance gap of 7 * high watermark) pages or 718M of pages
before the zone is ignored. What the user sees is that free memory far
higher than it should be.
To avoid an excessive number of pages being reclaimed from the larger
zones, explicitely defines the "balance gap" to be either 1% of the zone
or the low watermark for the zone, whichever is smaller. While kswapd
will check all zones to apply pressure, it'll ignore zones that meets the
(high_wmark + balance_gap) watermark.
To test this, 80G were copied from a partition and the amount of memory
being used was recorded. A comparison of a patch and unpatched kernel can
be seen at
http://www.csn.ul.ie/~mel/postings/minfree-20110222/memory-usage-hydra.ps
and shows that kswapd is not reclaiming as much memory with the patch
applied.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: "Chen, Tim C" <tim.c.chen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Namhyung Kim [Tue, 22 Mar 2011 23:33:02 +0000 (16:33 -0700)]
mempolicy: remove redundant check in __mpol_equal()
The 'flags' field is already checked, no need to do it again.
Signed-off-by: Namhyung Kim <namhyung@gmail.com> Cc: Bob Liu <lliubbo@gmail.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Hansen [Tue, 22 Mar 2011 23:33:01 +0000 (16:33 -0700)]
smaps: have smaps show transparent huge pages
Now that the mere act of _looking_ at /proc/$pid/smaps will not destroy
transparent huge pages, tell how much of the VMA is actually mapped with
them.
This way, we can make sure that we're getting THPs where we
expect to see them.
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Tested-by: Eric B Munson <emunson@mgebm.net> Cc: Michael J Wolf <mjwolf@us.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Hansen [Tue, 22 Mar 2011 23:33:00 +0000 (16:33 -0700)]
smaps: teach smaps_pte_range() about THP pmds
This adds code to explicitly detect and handle pmd_trans_huge() pmds. It
then passes HPAGE_SIZE units in to the smap_pte_entry() function instead
of PAGE_SIZE.
This means that using /proc/$pid/smaps now will no longer cause THPs to be
broken down in to small pages.
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Tested-by: Eric B Munson <emunson@mgebm.net> Acked-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michael J Wolf <mjwolf@us.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Hansen [Tue, 22 Mar 2011 23:32:59 +0000 (16:32 -0700)]
smaps: pass pte size argument in to smaps_pte_entry()
Add an argument to the new smaps_pte_entry() function to let it account in
things other than PAGE_SIZE units. I changed all of the PAGE_SIZE sites,
even though not all of them can be reached for transparent huge pages,
just so this will continue to work without changes as THPs are improved.
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Tested-by: Eric B Munson <emunson@mgebm.net> Cc: Michael J Wolf <mjwolf@us.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Hansen [Tue, 22 Mar 2011 23:32:58 +0000 (16:32 -0700)]
smaps: break out smaps_pte_entry() from smaps_pte_range()
We will use smaps_pte_entry() in a moment to handle both small and
transparent large pages. But, we must break it out of smaps_pte_range()
first.
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Tested-by: Eric B Munson <emunson@mgebm.net> Cc: Michael J Wolf <mjwolf@us.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Hansen [Tue, 22 Mar 2011 23:32:56 +0000 (16:32 -0700)]
pagewalk: only split huge pages when necessary
Right now, if a mm_walk has either ->pte_entry or ->pmd_entry set, it will
unconditionally split any transparent huge pages it runs in to. In
practice, that means that anyone doing a
cat /proc/$pid/smaps
will unconditionally break down every huge page in the process and depend
on khugepaged to re-collapse it later. This is fairly suboptimal.
This patch changes that behavior. It teaches each ->pmd_entry handler
(there are five) that they must break down the THPs themselves. Also, the
_generic_ code will never break down a THP unless a ->pte_entry handler is
actually set.
This means that the ->pmd_entry handlers can now choose to deal with THPs
without breaking them down.
[akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Tested-by: Eric B Munson <emunson@mgebm.net> Cc: Michael J Wolf <mjwolf@us.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:54 +0000 (16:32 -0700)]
mm: reclaim invalidated page ASAP
invalidate_mapping_pages is very big hint to reclaimer. It means user
doesn't want to use the page any more. So in order to prevent working set
page eviction, this patch move the page into tail of inactive list by
PG_reclaim.
Please, remember that pages in inactive list are working set as well as
active list. If we don't move pages into inactive list's tail, pages near
by tail of inactive list can be evicted although we have a big clue about
useless pages. It's totally bad.
Now PG_readahead/PG_reclaim is shared. fe3cba17 added ClearPageReclaim
into clear_page_dirty_for_io for preventing fast reclaiming readahead
marker page.
In this series, PG_reclaim is used by invalidated page, too. If VM find
the page is invalidated and it's dirty, it sets PG_reclaim to reclaim
asap. Then, when the dirty page will be writeback,
clear_page_dirty_for_io will clear PG_reclaim unconditionally. It
disturbs this serie's goal.
I think it's okay to clear PG_readahead when the page is dirty, not
writeback time. So this patch moves ClearPageReadahead. In v4,
ClearPageReadahead in set_page_dirty has a problem which is reported by
Steven Barrett. It's due to compound page. Some driver(ex, audio) calls
set_page_dirty with compound page which isn't on LRU. but my patch does
ClearPageRelcaim on compound page. In non-CONFIG_PAGEFLAGS_EXTENDED, it
breaks PageTail flag.
I think it doesn't affect THP and pass my test with THP enabling but Cced
Andrea for double check.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: Steven Barrett <damentz@liquorix.net> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:53 +0000 (16:32 -0700)]
memcg: move memcg reclaimable page into tail of inactive list
The rotate_reclaimable_page function moves just written out pages, which
the VM wanted to reclaim, to the end of the inactive list. That way the
VM will find those pages first next time it needs to free memory.
This patch applies the rule in memcg. It can help to prevent unnecessary
working page eviction of memcg.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:52 +0000 (16:32 -0700)]
mm: deactivate invalidated pages
Recently, there are reported problem about thrashing.
(http://marc.info/?l=rsync&m=128885034930933&w=2) It happens by backup
workloads(ex, nightly rsync). That's because the workload makes just
use-once pages and touches pages twice. It promotes the page into active
list so that it results in working set page eviction.
Some app developer want to support POSIX_FADV_NOREUSE. But other OSes
don't support it, either.
(http://marc.info/?l=linux-mm&m=128928979512086&w=2)
By other approach, app developers use POSIX_FADV_DONTNEED. But it has a
problem. If kernel meets page is writing during invalidate_mapping_pages,
it can't work. It makes for application programmer to use it since they
always have to sync data before calling fadivse(..POSIX_FADV_DONTNEED) to
make sure the pages could be discardable. At last, they can't use
deferred write of kernel so that they could see performance loss.
(http://insights.oetiker.ch/linux/fadvise.html)
In fact, invalidation is very big hint to reclaimer. It means we don't
use the page any more. So let's move the writing page into inactive
list's head if we can't truncate it right now.
Why I move page to head of lru on this patch, Dirty/Writeback page would
be flushed sooner or later. It can prevent writeout of pageout which is
less effective than flusher's writeout.
Originally, I reused lru_demote of Peter with some change so added his
Signed-off-by.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: Ben Gamari <bgamari.foss@gmail.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Richard Kennedy [Tue, 22 Mar 2011 23:32:50 +0000 (16:32 -0700)]
mm: mm_struct: remove 16 bytes of alignment padding on 64 bit builds
Reorder mm_struct to remove 16 bytes of alignment padding on 64 bit
builds. On my config this shrinks mm_struct by enough to fit in one
fewer cache lines and allows more objects per slab in mm_struct
kmem_cache under SLUB.
slabinfo before patch :-
Sizes (bytes) Slabs
--------------------------------
Object : 848 Total : 9
SlabObj: 896 Full : 2
SlabSiz: 16384 Partial: 5
Loss : 48 CpuSlab: 2
Align : 64 Objects: 18
slabinfo after :-
Sizes (bytes) Slabs
--------------------------------
Object : 832 Total : 7
SlabObj: 832 Full : 2
SlabSiz: 16384 Partial: 3
Loss : 0 CpuSlab: 2
Align : 64 Objects: 19
Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
TestSetPageLocked() isn't being used anywhere. Also, using it would
likely be an error, since the proper interface trylock_page() provides
stronger ordering guarantees.
Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Peter Zijlstra [Tue, 22 Mar 2011 23:32:49 +0000 (16:32 -0700)]
mm: simplify anon_vma refcounts
This patch changes the anon_vma refcount to be 0 when the object is free.
It does this by adding 1 ref to being in use in the anon_vma structure
(iow. the anon_vma->head list is not empty).
This allows a simpler release scheme without having to check both the
refcount and the list as well as avoids taking a ref for each entry on the
list.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> 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>
Namhyung Kim [Tue, 22 Mar 2011 23:32:45 +0000 (16:32 -0700)]
mm: batch-free pcp list if possible
free_pcppages_bulk() frees pages from pcp lists in a round-robin fashion
by keeping batch_free counter. But it doesn't need to spin if there is
only one non-empty list. This can be checked by batch_free ==
MIGRATE_PCPTYPES.
[akpm@linux-foundation.org: fix comment] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:44 +0000 (16:32 -0700)]
mm: change __remove_from_page_cache()
Now we renamed remove_from_page_cache with delete_from_page_cache. As
consistency of __remove_from_swap_cache and remove_from_swap_cache, we
change internal page cache handling function name, too.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:43 +0000 (16:32 -0700)]
mm: goodbye remove_from_page_cache()
Now delete_from_page_cache() replaces remove_from_page_cache(). So we
remove remove_from_page_cache so fs or something out of mainline will
notice it when compile time and can fix it.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:41 +0000 (16:32 -0700)]
mm: truncate: change remove_from_page_cache
This patch series changes remove_from_page_cache()'s page ref counting
rule. Page cache ref count is decreased in delete_from_page_cache(). So
we don't need to decrease the page reference in callers.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:32:40 +0000 (16:32 -0700)]
mm: shmem: change remove_from_page_cache
This patch series changes remove_from_page_cache()'s page ref counting
rule. Page cache ref count is decreased in delete_from_page_cache(). So
we don't need to decrease the page reference in callers.
Minchan Kim [Tue, 22 Mar 2011 23:30:54 +0000 (16:30 -0700)]
mm: hugetlbfs: change remove_from_page_cache
This patch series changes remove_from_page_cache()'s page ref counting
rule. Page cache ref count is decreased in delete_from_page_cache(). So
we don't need to decrease the page reference in callers.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: William Irwin <wli@holomorphy.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:30:53 +0000 (16:30 -0700)]
mm: introduce delete_from_page_cache()
Presently we increase the page refcount in add_to_page_cache() but don't
decrease it in remove_from_page_cache(). Such asymmetry adds confusion,
requiring that callers notice it and a comment explaining why they release
a page reference. It's not a good API.
A long time ago, Hugh tried it (http://lkml.org/lkml/2004/10/24/140) but
gave up because reiser4's drop_page() had to unlock the page between
removing it from page cache and doing the page_cache_release(). But now
the situation is changed. I think at least things in current mainline
don't have any obstacles. The problem is for out-of-mainline filesystems
- if they have done such things as reiser4, this patch could be a problem
but they will discover this at compile time since we remove
remove_from_page_cache().
This patch:
This function works as just wrapper remove_from_page_cache(). The
difference is that it decreases page references in itself. So caller have
to make sure it has a page reference before calling.
This patch is ready for removing remove_from_page_cache().
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Edward Shishkin <edward.shishkin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Gleb Natapov [Tue, 22 Mar 2011 23:30:51 +0000 (16:30 -0700)]
mm: allow GUP to fail instead of waiting on a page
GUP user may want to try to acquire a reference to a page if it is already
in memory, but not if IO, to bring it in, is needed. For example KVM may
tell vcpu to schedule another guest process if current one is trying to
access swapped out page. Meanwhile, the page will be swapped in and the
guest process, that depends on it, will be able to run again.
This patch adds FAULT_FLAG_RETRY_NOWAIT (suggested by Linus) and
FOLL_NOWAIT follow_page flags. FAULT_FLAG_RETRY_NOWAIT, when used in
conjunction with VM_FAULT_ALLOW_RETRY, indicates to handle_mm_fault that
it shouldn't drop mmap_sem and wait on a page, but return VM_FAULT_RETRY
instead.
David Rientjes [Tue, 22 Mar 2011 23:30:48 +0000 (16:30 -0700)]
oom: suppress nodes that are not allowed from meminfo on page alloc failure
Displaying extremely verbose meminfo for all nodes on the system is
overkill for page allocation failures when the context restricts that
allocation to only a subset of nodes. We don't particularly care about
the state of all nodes when some are not allowed in the current context,
they can have an abundance of memory but we can't allocate from that part
of memory.
This patch suppresses disallowed nodes from the meminfo dump on a page
allocation failure if the context requires it.
David Rientjes [Tue, 22 Mar 2011 23:30:47 +0000 (16:30 -0700)]
oom: suppress show_mem() for many nodes in irq context on page alloc failure
When a page allocation failure occurs, show_mem() is called to dump the
state of the VM so users may understand what happened to get into that
condition.
This output, however, can be extremely verbose. In irq context, it may
result in significant delays that incur NMI watchdog timeouts when the
machine is large (we use CONFIG_NODES_SHIFT > 8 here to define a "large"
machine since the length of the show_mem() output is proportional to the
number of possible nodes).
This patch suppresses the show_mem() call in irq context when the kernel
has CONFIG_NODES_SHIFT > 8.
David Rientjes [Tue, 22 Mar 2011 23:30:46 +0000 (16:30 -0700)]
oom: suppress nodes that are not allowed from meminfo on oom kill
The oom killer is extremely verbose for machines with a large number of
cpus and/or nodes. This verbosity can often be harmful if it causes other
important messages to be scrolled from the kernel log and incurs a
signicant time delay, specifically for kernels with CONFIG_NODES_SHIFT >
8.
This patch causes only memory information to be displayed for nodes that
are allowed by current's cpuset when dumping the VM state. Information
for all other nodes is irrelevant to the oom condition; we don't care if
there's an abundance of memory elsewhere if we can't access it.
This only affects the behavior of dumping memory information when an oom
is triggered. Other dumps, such as for sysrq+m, still display the
unfiltered form when using the existing show_mem() interface.
Additionally, the per-cpu pageset statistics are extremely verbose in oom
killer output, so it is now suppressed. This removes
Eric Dumazet [Tue, 22 Mar 2011 23:30:45 +0000 (16:30 -0700)]
kthread: use kthread_create_on_node()
ksoftirqd, kworker, migration, and pktgend kthreads can be created with
kthread_create_on_node(), to get proper NUMA affinities for their stack and
task_struct.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: David S. Miller <davem@davemloft.net> Reviewed-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Acked-by: Tejun Heo <tj@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: David Howells <dhowells@redhat.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim [Tue, 22 Mar 2011 23:30:39 +0000 (16:30 -0700)]
mm/compaction: check migrate_pages's return value instead of list_empty()
Many migrate_page's caller check return value instead of list_empy by cf608ac19c ("mm: compaction: fix COMPACTPAGEFAILED counting"). This patch
makes compaction's migrate_pages consistent with others. This patch
should not change old behavior.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andrea Arcangeli [Tue, 22 Mar 2011 23:30:38 +0000 (16:30 -0700)]
mm: compaction: prevent kswapd compacting memory to reduce CPU usage
This patch reverts 5a03b051 ("thp: use compaction in kswapd for GFP_ATOMIC
order > 0") due to reports stating that kswapd CPU usage was higher and
IRQs were being disabled more frequently. This was reported at
http://www.spinics.net/linux/fedora/alsa-user/msg09885.html.
Without this patch applied, CPU usage by kswapd hovers around the 20% mark
according to the tester (Arthur Marsh:
http://www.spinics.net/linux/fedora/alsa-user/msg09899.html). With this
patch applied, it's around 2%.
The problem is not related to THP which specifies __GFP_NO_KSWAPD but is
triggered by high-order allocations hitting the low watermark for their
order and waking kswapd on kernels with CONFIG_COMPACTION set. The most
common trigger for this is network cards configured for jumbo frames but
it's also possible it'll be triggered by fork-heavy workloads (order-1)
and some wireless cards which depend on order-1 allocations.
The symptoms for the user will be high CPU usage by kswapd in low-memory
situations which could be confused with another writeback problem. While
a patch like 5a03b051 may be reintroduced in the future, this patch plays
it safe for now and reverts it.
[mel@csn.ul.ie: Beefed up the changelog] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Arthur Marsh <arthur.marsh@internode.on.net> Tested-by: Arthur Marsh <arthur.marsh@internode.on.net> Cc: <stable@kernel.org> [2.6.38.1] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Nick Piggin [Tue, 22 Mar 2011 23:30:36 +0000 (16:30 -0700)]
mm: vmap area cache
Provide a free area cache for the vmalloc virtual address allocator, based
on the algorithm used by the user virtual memory allocator.
This reduces the number of rbtree operations and linear traversals over
the vmap extents in order to find a free area, by starting off at the last
point that a free area was found.
The free area cache is reset if areas are freed behind it, or if we are
searching for a smaller area or alignment than last time. So allocation
patterns are not changed (verified by corner-case and random test cases in
userspace testing).
This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the
vmap allocator after they are vunmapped, and until a significant number
accumulate that can be flushed in a single batch. So in a workload that
vmalloc/vfree frequently, a chain of extents will build up from
VMALLOC_START address, which have to be iterated over each time (giving an
O(n) type of behaviour).
After this patch, the search will start from where it left off, giving
closer to an amortized O(1).
This is verified to solve regressions reported Steven in GFS2, and Avi in
KVM.
Hugh's update:
: I tried out the recent mmotm, and on one machine was fortunate to hit
: the BUG_ON(first->va_start < addr) which seems to have been stalling
: your vmap area cache patch ever since May.
: I can get you addresses etc, I did dump a few out; but once I stared
: at them, it was easier just to look at the code: and I cannot see how
: you would be so sure that first->va_start < addr, once you've done
: that addr = ALIGN(max(...), align) above, if align is over 0x1000
: (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve).
: I originally got around it by just changing the
: if (first->va_start < addr) {
: to
: while (first->va_start < addr) {
: without thinking about it any further; but that seemed unsatisfactory,
: why would we want to loop here when we've got another very similar
: loop just below it?
: I am never going to admit how long I've spent trying to grasp your
: "while (n)" rbtree loop just above this, the one with the peculiar
: if (!first && tmp->va_start < addr + size)
: in. That's unfamiliar to me, I'm guessing it's designed to save a
: subsequent rb_next() in a few circumstances (at risk of then setting
: a wrong cached_hole_size?); but they did appear few to me, and I didn't
: feel I could sign off something with that in when I don't grasp it,
: and it seems responsible for extra code and mistaken BUG_ON below it.
: I've reverted to the familiar rbtree loop that find_vma() does (but
: with va_end >= addr as you had, to respect the additional guard page):
: and then (given that cached_hole_size starts out 0) I don't see the
: need for any complications below it. If you do want to keep that loop
: as you had it, please add a comment to explain what it's trying to do,
: and where addr is relative to first when you emerge from it.
: Aren't your tests "size <= cached_hole_size" and
: "addr + size > first->va_start" forgetting the guard page we want
: before the next area? I've changed those.
: I have not changed your many "addr + size - 1 < addr" overflow tests,
: but have since come to wonder, shouldn't they be "addr + size < addr"
: tests - won't the vend checks go wrong if addr + size is 0?
: I have added a few comments - Wolfgang Wander's 2.6.13 description of
: 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation
: helped me a lot, perhaps a pointer to that would be good too. And I found
: it easier to understand when I renamed cached_start slightly and moved the
: overflow label down.
: This patch would go after your mm-vmap-area-cache.patch in mmotm.
: Trivially, nobody is going to get that BUG_ON with this patch, and it
: appears to work fine on my machines; but I have not given it anything like
: the testing you did on your original, and may have broken all the
: performance you were aiming for. Please take a look and test it out
: integrate with yours if you're satisfied - thanks.
[akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Robert Morell [Tue, 22 Mar 2011 23:30:31 +0000 (16:30 -0700)]
pwm_backlight: add check_fb() hook
In systems with multiple framebuffer devices, one of the devices might be
blanked while another is unblanked. In order for the backlight blanking
logic to know whether to turn off the backlight for a particular
framebuffer's blanking notification, it needs to be able to check if a
given framebuffer device corresponds to the backlight.
This plumbs the check_fb hook from core backlight through the
pwm_backlight helper to allow platform code to plug in a check_fb hook.
Signed-off-by: Robert Morell <rmorell@nvidia.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Arun Murthy <arun.murthy@stericsson.com> Cc: Linus Walleij <linus.walleij@stericsson.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Axel Lin [Tue, 22 Mar 2011 23:30:30 +0000 (16:30 -0700)]
drivers/video/backlight/jornada720_*.c: make needlessly global symbols static
The following symbols are needlessly defined global: jornada_bl_init,
jornada_bl_exit, jornada_lcd_init, jornada_lcd_exit.
Make them static.
Signed-off-by: Axel Lin <axel.lin@gmail.com> Acked-by: Kristoffer Ericson <kristoffer.ericson@gmail.com> Cc: Richard Purdie <rpurdie@rpsys.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Randy Dunlap [Tue, 22 Mar 2011 23:30:29 +0000 (16:30 -0700)]
backlight: apple_bl depends on ACPI
apple_bl uses ACPI interfaces (data & code), so it should depend on ACPI.
drivers/video/backlight/apple_bl.c:142: warning: 'struct acpi_device' declared inside parameter list
drivers/video/backlight/apple_bl.c:142: warning: its scope is only this definition or declaration, which is probably not what you want
drivers/video/backlight/apple_bl.c:201: warning: 'struct acpi_device' declared inside parameter list
drivers/video/backlight/apple_bl.c:215: error: variable 'apple_bl_driver' has initializer but incomplete type
drivers/video/backlight/apple_bl.c:216: error: unknown field 'name' specified in initializer
...
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Acked-by: Matthew Garrett <mjg@redhat.com> Cc: Richard Purdie <rpurdie@rpsys.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Garrett [Tue, 22 Mar 2011 23:30:28 +0000 (16:30 -0700)]
mbp_nvidia_bl: rename to apple_bl
It works on hardware other than Macbook Pros, and it works on GPUs other
than Nvidia. It should even work on iMacs, so change the name to match
reality more precisely and include an alias so existing users don't get
confused.
Signed-off-by: Matthew Garrett <mjg@redhat.com> Acked-by: Richard Purdie <richard.purdie@linuxfoundation.org> Cc: Mourad De Clerck <mourad@aquazul.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Garrett [Tue, 22 Mar 2011 23:30:27 +0000 (16:30 -0700)]
mbp_nvidia_bl: check that the backlight control functions
The SMI-based backlight control functionality may fail to work if the
system is running under EFI rather than BIOS. Check that the hardware
responds as expected, and exit if it doesn't.
Signed-off-by: Matthew Garrett <mjg@redhat.com> Acked-by: Richard Purdie <richard.purdie@linuxfoundation.org> Cc: Mourad De Clerck <mourad@aquazul.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Garrett [Tue, 22 Mar 2011 23:30:26 +0000 (16:30 -0700)]
mbp_nvidia_bl: remove DMI dependency
This driver only has to deal with two different classes of hardware, but
right now it needs new DMI entries for every new machine. It turns out
that there's an ACPI device that uniquely identifies Apples with backlights,
so this patch reworks the driver into an ACPI one, identifies the hardware
by checking the PCI vendor of the root bridge and strips out all the DMI
code. It also changes the config text to clarify that it works on devices
other than Macbook Pros and GPUs other than nvidia.
Signed-off-by: Matthew Garrett <mjg@redhat.com> Acked-by: Richard Purdie <richard.purdie@linuxfoundation.org> Cc: Mourad De Clerck <mourad@aquazul.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Garrett [Tue, 22 Mar 2011 23:30:25 +0000 (16:30 -0700)]
acpi: tie ACPI backlight devices to PCI devices if possible
Dual-GPU machines may provide more than one ACPI backlight interface. Tie
the backlight device to the GPU in order to allow userspace to identify
the correct interface.
Signed-off-by: Matthew Garrett <mjg@redhat.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: David Airlie <airlied@linux.ie> Cc: Alex Deucher <alexdeucher@gmail.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Len Brown <lenb@kernel.org> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Tested-by: Sedat Dilek <sedat.dilek@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Garrett [Tue, 22 Mar 2011 23:30:24 +0000 (16:30 -0700)]
nouveau: change the backlight parent device to the connector, not the PCI dev
We may eventually end up with per-connector backlights, especially with
ddcci devices. Make sure that the parent node for the backlight device is
the connector rather than the PCI device.
Signed-off-by: Matthew Garrett <mjg@redhat.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: David Airlie <airlied@linux.ie> Cc: Alex Deucher <alexdeucher@gmail.com> Acked-by: Ben Skeggs <bskeggs@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Len Brown <lenb@kernel.org> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Tested-by: Sedat Dilek <sedat.dilek@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michel Dänzer [Tue, 22 Mar 2011 23:30:23 +0000 (16:30 -0700)]
radeon: expose backlight class device for legacy LVDS encoder
Allows e.g. power management daemons to control the backlight level. Inspired
by the corresponding code in radeonfb.
[mjg@redhat.com: updated to add backlight type and make the connector the parent device] Signed-off-by: Michel Dänzer <michel@daenzer.net> Signed-off-by: Matthew Garrett <mjg@redhat.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: David Airlie <airlied@linux.ie> Acked-by: Alex Deucher <alexdeucher@gmail.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Len Brown <lenb@kernel.org> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Tested-by: Sedat Dilek <sedat.dilek@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Garrett [Tue, 22 Mar 2011 23:30:21 +0000 (16:30 -0700)]
backlight: add backlight type
There may be multiple ways of controlling the backlight on a given
machine. Allow drivers to expose the type of interface they are
providing, making it possible for userspace to make appropriate policy
decisions.
Signed-off-by: Matthew Garrett <mjg@redhat.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: David Airlie <airlied@linux.ie> Cc: Alex Deucher <alexdeucher@gmail.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Len Brown <lenb@kernel.org> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mark Brown [Tue, 22 Mar 2011 23:30:14 +0000 (16:30 -0700)]
leds: convert bd2802 driver to dev_pm_ops
There is a move to deprecate bus-specific PM operations and move to using
dev_pm_ops instead in order to reduce the amount of boilerplate code in
buses and facilitiate updates to the PM core. Do this move for the bs2802
driver.
[akpm@linux-foundation.org: fix warnings] Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Cc: Kim Kyuwon <q1.kim@samsung.com> Cc: Kim Kyuwon <chammoru@gmail.com> Cc: Richard Purdie <rpurdie@rpsys.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Phil Carmody [Tue, 22 Mar 2011 23:30:13 +0000 (16:30 -0700)]
cgroups: if you list_empty() a head then don't list_del() it
list_del() leaves poison in the prev and next pointers. The next
list_empty() will compare those poisons, and say the list isn't empty.
Any list operations that assume the node is on a list because of such a
check will be fooled into dereferencing poison. One needs to INIT the
node after the del, and fortunately there's already a wrapper for that -
list_del_init().
Some of the dels are followed by deallocations, so can be ignored, and one
can be merged with an add to make a move. Apart from that, I erred on the
side of caution in making nodes list_empty()-queriable.
Signed-off-by: Phil Carmody <ext-phil.2.carmody@nokia.com> Reviewed-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Rientjes [Tue, 22 Mar 2011 23:30:12 +0000 (16:30 -0700)]
oom: avoid deferring oom killer if exiting task is being traced
The oom killer naturally defers killing anything if it finds an eligible
task that is already exiting and has yet to detach its ->mm. This avoids
unnecessarily killing tasks when one is already in the exit path and may
free enough memory that the oom killer is no longer needed. This is
detected by PF_EXITING since threads that have already detached its ->mm
are no longer considered at all.
The problem with always deferring when a thread is PF_EXITING, however, is
that it may never actually exit when being traced, specifically if another
task is tracing it with PTRACE_O_TRACEEXIT. The oom killer does not want
to defer in this case since there is no guarantee that thread will ever
exit without intervention.
This patch will now only defer the oom killer when a thread is PF_EXITING
and no ptracer has stopped its progress in the exit path. It also ensures
that a child is sacrificed for the chosen parent only if it has a
different ->mm as the comment implies: this ensures that the thread group
leader is always targeted appropriately.
Andrey Vagin [Tue, 22 Mar 2011 23:30:11 +0000 (16:30 -0700)]
oom: skip zombies when iterating tasklist
We shouldn't defer oom killing if a thread has already detached its ->mm
and still has TIF_MEMDIE set. Memory needs to be freed, so find kill
other threads that pin the same ->mm or find another task to kill.
David Rientjes [Tue, 22 Mar 2011 23:30:09 +0000 (16:30 -0700)]
oom: prevent unnecessary oom kills or kernel panics
This patch prevents unnecessary oom kills or kernel panics by reverting
two commits:
495789a5 (oom: make oom_score to per-process value) cef1d352 (oom: multi threaded process coredump don't make deadlock)
First, 495789a5 (oom: make oom_score to per-process value) ignores the
fact that all threads in a thread group do not necessarily exit at the
same time.
It is imperative that select_bad_process() detect threads that are in the
exit path, specifically those with PF_EXITING set, to prevent needlessly
killing additional tasks. If a process is oom killed and the thread group
leader exits, select_bad_process() cannot detect the other threads that
are PF_EXITING by iterating over only processes. Thus, it currently
chooses another task unnecessarily for oom kill or panics the machine when
nothing else is eligible.
By iterating over threads instead, it is possible to detect threads that
are exiting and nominate them for oom kill so they get access to memory
reserves.
Second, cef1d352 (oom: multi threaded process coredump don't make
deadlock) erroneously avoids making the oom killer a no-op when an
eligible thread other than current isfound to be exiting. We want to
detect this situation so that we may allow that exiting thread time to
exit and free its memory; if it is able to exit on its own, that should
free memory so current is no loner oom. If it is not able to exit on its
own, the oom killer will nominate it for oom kill which, in this case,
only means it will get access to memory reserves.
Without this change, it is easy for the oom killer to unnecessarily target
tasks when all threads of a victim don't exit before the thread group
leader or, in the worst case, panic the machine.
Mel Gorman [Tue, 22 Mar 2011 23:30:08 +0000 (16:30 -0700)]
mm: swap: unlock swapfile inode mutex before closing file on bad swapfiles
If an administrator tries to swapon a file backed by NFS, the inode mutex is
taken (as it is for any swapfile) but later identified to be a bad swapfile
due to the lack of bmap and tries to cleanup. During cleanup, an attempt is
made to close the file but with inode->i_mutex still held. Closing an NFS
file syncs it which tries to acquire the inode mutex leading to deadlock. If
lockdep is enabled the following appears on the console;
=============================================
[ INFO: possible recursive locking detected ]
2.6.38-rc8-autobuild #1
---------------------------------------------
swapon/2192 is trying to acquire lock:
(&sb->s_type->i_mutex_key#13){+.+.+.}, at: vfs_fsync_range+0x47/0x7c
but task is already holding lock:
(&sb->s_type->i_mutex_key#13){+.+.+.}, at: sys_swapon+0x28d/0xae7
other info that might help us debug this:
1 lock held by swapon/2192:
#0: (&sb->s_type->i_mutex_key#13){+.+.+.}, at: sys_swapon+0x28d/0xae7
This patch releases the mutex if its held before calling filep_close()
so swapon fails as expected without deadlock when the swapfile is backed
by NFS. If accepted for 2.6.39, it should also be considered a -stable
candidate for 2.6.38 and 2.6.37.
Linus Torvalds [Tue, 22 Mar 2011 23:26:57 +0000 (16:26 -0700)]
Merge branch 'slab/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6
* 'slab/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
slub: Add statistics for this_cmpxchg_double failures
slub: Add missing irq restore for the OOM path
Linus Torvalds [Tue, 22 Mar 2011 23:26:10 +0000 (16:26 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs:
[net/9p]: Introduce basic flow-control for VirtIO transport.
9p: use the updated offset given by generic_write_checks
[net/9p] Don't re-pin pages on retrying virtqueue_add_buf().
[net/9p] Set the condition just before waking up.
[net/9p] unconditional wake_up to proc waiting for space on VirtIO ring
fs/9p: Add v9fs_dentry2v9ses
fs/9p: Attach writeback_fid on first open with WR flag
fs/9p: Open writeback fid in O_SYNC mode
fs/9p: Use truncate_setsize instead of vmtruncate
net/9p: Fix compile warning
net/9p: Convert the in the 9p rpc call path to GFP_NOFS
fs/9p: Fix race in initializing writeback fid
* git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
rbd: use watch/notify for changes in rbd header
libceph: add lingering request and watch/notify event framework
rbd: update email address in Documentation
ceph: rename dentry_release -> d_release, fix comment
ceph: add request to the tail of unsafe write list
ceph: remove request from unsafe list if it is canceled/timed out
ceph: move readahead default to fs/ceph from libceph
ceph: add ino32 mount option
ceph: update common header files
ceph: remove debugfs debug cruft
libceph: fix osd request queuing on osdmap updates
ceph: preserve I_COMPLETE across rename
libceph: Fix base64-decoding when input ends in newline.
Linus Torvalds [Tue, 22 Mar 2011 23:17:32 +0000 (16:17 -0700)]
tty: stop using "delayed_work" in the tty layer
Using delayed-work for tty flip buffers ends up causing us to wait for
the next tick to complete some actions. That's usually not all that
noticeable, but for certain latency-critical workloads it ends up being
totally unacceptable.
As an extreme case of this, passing a token back-and-forth over a pty
will take two ticks per iteration, so even just a thousand iterations
will take 8 seconds assuming a common 250Hz configuration.
Avoiding the whole delayed work issue brings that ping-pong test-case
down to 0.009s on my machine.
In more practical terms, this latency has been a performance problem for
things like dive computer simulators (simulating the serial interface
using the ptys) and for other environments (Alan mentions a CP/M emulator).
[net/9p]: Introduce basic flow-control for VirtIO transport.
Recent zerocopy work in the 9P VirtIO transport maps and pins
user buffers into kernel memory for the server to work on them.
Since the user process can initiate this kind of pinning with a simple
read/write call, thousands of IO threads initiated by the user process can
hog the system resources and could result into denial of service.
This patch introduces flow control to avoid that extreme scenario.
The ceiling limit to avoid denial of service attacks is set to relatively
high (nr_free_pagecache_pages()/4) so that it won't interfere with
regular usage, but can step in extreme cases to limit the total system
hang. Since we don't have a global structure to accommodate this variable,
I choose the virtio_chan as the home for this.
Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Reviewed-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
M. Mohan Kumar [Wed, 16 Mar 2011 16:10:49 +0000 (21:40 +0530)]
9p: use the updated offset given by generic_write_checks
Without this fix, even if a file is opened in O_APPEND mode, data will be
written at current file position instead of end of file.
Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
Given that the sprious wake-ups are common, we need to move the
condition setting right next to the wake_up(). After setting the condition
to req->status = REQ_STATUS_RCVD, sprious wakeups may cause the
virtqueue back on the free list for someone else to use.
This may result in kernel panic while relasing the pinned pages
in p9_release_req_pages().
Also rearranged the while loop in req_done() for better redability.
Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
[net/9p] unconditional wake_up to proc waiting for space on VirtIO ring
Process may wait to get space on VirtIO ring to send a transaction to
VirtFS server. Current code just does a conditional wake_up() which
means only one process will be woken up even if multiple processes
are waiting.
This fix makes the wake_up unconditional. Hence we won't have any
processes waiting for-ever.
Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
convert vmtruncate usage to truncate_setsize. We also writeback
all dirty pages before doing 9p operations and on success call truncate_setsize.
This ensure that we continue sanely on failed truncate on the server. The
disadvantage is that we are now going to write back the content that get
thrown away later as a part of truncate.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
When two process open the same file we can end up with both of them
allocating the writeback_fid. Add a new mutex which can be used
for synchronizing v9fs_inode member values.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
Yehuda Sadeh [Mon, 21 Mar 2011 22:10:11 +0000 (15:10 -0700)]
rbd: use watch/notify for changes in rbd header
Send notifications when we change the rbd header (e.g. create a snapshot)
and wait for such notifications. This allows synchronizing the snapshot
creation between different rbd clients/rools.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
Yehuda Sadeh [Mon, 21 Mar 2011 22:07:16 +0000 (15:07 -0700)]
libceph: add lingering request and watch/notify event framework
Lingering requests are requests that are sent to the OSD normally but
tracked also after we get a successful request. This keeps the OSD
connection open and resends the original request if the object moves to
another OSD. The OSD can then send notification messages back to us
if another client initiates a notify.
This framework will be used by RBD so that the client gets notification
when a snapshot is created by another node or tool.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
Linus Torvalds [Tue, 22 Mar 2011 17:41:36 +0000 (10:41 -0700)]
Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
xen: update mask_rw_pte after kernel page tables init changes
xen: set max_pfn_mapped to the last pfn mapped
x86: Cleanup highmap after brk is concluded
Fix up trivial onflict (added header file includes) in
arch/x86/mm/init_64.c
Linus Torvalds [Tue, 22 Mar 2011 17:06:54 +0000 (10:06 -0700)]
Merge branch 'next-samsung' of git://git.fluff.org/bjdooks/linux
* 'next-samsung' of git://git.fluff.org/bjdooks/linux:
ARM: H1940/RX1950: Change default LED triggers
ARM: S3C2442: RX1950: Add support for LED blinking
ARM: S3C2442: RX1950: Retain LEDs state in suspend
ARM: S3C2410: H1940: Fix lcd_power_set function
ARM: S3C2410: H1940: Add battery support
ARM: S3C2410: H1940: Use leds-gpio driver for LEDs managing
ARM: S3C2410: H1940: Make h1940-bluetooth.c compile again
ARM: S3C2410: H1940: Add keys device
Linus Torvalds [Tue, 22 Mar 2011 17:05:27 +0000 (10:05 -0700)]
Merge branch 'for-linus/2639/i2c-2' of git://git.fluff.org/bjdooks/linux
* 'for-linus/2639/i2c-2' of git://git.fluff.org/bjdooks/linux:
i2c-pxa2xx: Don't clear isr bits too early
i2c-pxa2xx: Fix register offsets
i2c-pxa2xx: pass of_node from platform driver to adapter and publish
i2c-pxa2xx: check timeout correctly
i2c-pxa2xx: add support for shared IRQ handler
i2c-pxa2xx: Add PCI support for PXA I2C controller
ARM: pxa2xx: reorganize I2C files
i2c-pxa2xx: use dynamic register layout
i2c-mxs: set controller to pio queue mode after reset
i2c-eg20t: support new device OKI SEMICONDUCTOR ML7213 IOH
i2c/busses: Add support for Diolan U2C-12 USB-I2C adapter
Linus Torvalds [Tue, 22 Mar 2011 16:36:23 +0000 (09:36 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
slub: Dont define useless label in the !CONFIG_CMPXCHG_LOCAL case
slab,rcu: don't assume the size of struct rcu_head
slub,rcu: don't assume the size of struct rcu_head
slub: automatically reserve bytes at the end of slab
Lockless (and preemptless) fastpaths for slub
slub: Get rid of slab_free_hook_irq()
slub: min_partial needs to be in first cacheline
slub: fix ksize() build error
slub: fix kmemcheck calls to match ksize() hints
Revert "slab: Fix missing DEBUG_SLAB last user"
mm: Remove support for kmem_cache_name()
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (33 commits)
IPVS: Use global mutex in ip_vs_app.c
ipvs: fix a typo in __ip_vs_control_init()
veth: Fix the byte counters
net ipv6: Fix duplicate /proc/sys/net/ipv6/neigh directory entries.
macvlan: Fix use after free of struct macvlan_port.
net: fix incorrect spelling in drop monitor protocol
can: c_can: Do basic c_can configuration _before_ enabling the interrupts
net/appletalk: fix atalk_release use after free
ipx: fix ipx_release()
snmp: SNMP_UPD_PO_STATS_BH() always called from softirq
l2tp: fix possible oops on l2tp_eth module unload
xfrm: Fix initialize repl field of struct xfrm_state
netfilter: ipt_CLUSTERIP: fix buffer overflow
netfilter: xtables: fix reentrancy
netfilter: ipset: fix checking the type revision at create command
netfilter: ipset: fix address ranges at hash:*port* types
niu: Rename NIU parent platform device name to fix conflict.
r8169: fix a bug in rtl8169_init_phy()
bonding: fix a typo in a comment
ftmac100: use resource_size()
...
Simon Horman [Mon, 21 Mar 2011 15:18:01 +0000 (15:18 +0000)]
IPVS: Use global mutex in ip_vs_app.c
As part of the work to make IPVS network namespace aware
__ip_vs_app_mutex was replaced by a per-namespace lock,
ipvs->app_mutex. ipvs->app_key is also supplied for debugging purposes.
Unfortunately this implementation results in ipvs->app_key residing
in non-static storage which at the very least causes a lockdep warning.
This patch takes the rather heavy-handed approach of reinstating
__ip_vs_app_mutex which will cover access to the ipvs->list_head
of all network namespaces.
Signed-off-by: Simon Horman <horms@verge.net.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Hans Schillstrom <hans@schillstrom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 21 Mar 2011 10:15:40 +0000 (10:15 +0000)]
ipvs: fix a typo in __ip_vs_control_init()
Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Simon Horman <horms@verge.net.au> Cc: Julian Anastasov <ja@ssi.bg> Acked-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 44540960 "veth: move loopback logic to common location" introduced
a bug in the packet counters. I don't understand why that happened as it
is not explained in the comments and the mut check in dev_forward_skb
retains the assumption that skb->len is the total length of the packet.
I just measured this emperically by setting up a veth pair between two
noop network namespaces setting and attempting a telnet connection between
the two. I saw three packets in each direction and the byte counters were
exactly 14*3 = 42 bytes high in each direction. I got the actual
packet lengths with tcpdump.
So remove the extra ETH_HLEN from the veth byte count totals.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net ipv6: Fix duplicate /proc/sys/net/ipv6/neigh directory entries.
When I was fixing issues with unregisgtering tables under /proc/sys/net/ipv6/neigh
by adding a mount point it appears I missed a critical ordering issue, in the
ipv6 initialization. I had not realized that ipv6_sysctl_register is called
at the very end of the ipv6 initialization and in particular after we call
neigh_sysctl_register from ndisc_init.
"neigh" needs to be initialized in ipv6_static_sysctl_register which is
the first ipv6 table to initialized, and definitely before ndisc_init.
This removes the weirdness of duplicate tables while still providing a
"neigh" mount point which prevents races in sysctl unregistering.
This was initially reported at https://bugzilla.kernel.org/show_bug.cgi?id=31232 Reported-by: sunkan@zappa.cx Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
macvlan: Fix use after free of struct macvlan_port.
When the macvlan driver was extended to call unregisgter_netdevice_queue
in 23289a37e2b127dfc4de1313fba15bb4c9f0cd5b, a use after free of struct
macvlan_port was introduced. The code in dellink relied on unregister_netdevice
actually unregistering the net device so it would be safe to free macvlan_port.
Since unregister_netdevice_queue can just queue up the unregister instead of
performing the unregiser immediately we free the macvlan_port too soon and
then the code in macvlan_stop removes the macaddress for the set of macaddress
to listen for and uses memory that has already been freed.
To fix this add a reference count to track when it is safe to free the macvlan_port
and move the call of macvlan_port_destroy into macvlan_uninit which is guaranteed
to be called after the final macvlan_port_close.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jan Altenberg [Tue, 22 Mar 2011 01:19:26 +0000 (18:19 -0700)]
can: c_can: Do basic c_can configuration _before_ enabling the interrupts
I ran into some trouble while testing the SocketCAN driver for the BOSCH
C_CAN controller. The interface is not correctly initialized, if I put
some CAN traffic on the line, _while_ the interface is being started
(which means: the interface doesn't come up correcty, if there's some RX
traffic while doing 'ifconfig can0 up').
The current implementation enables the controller interrupts _before_
doing the basic c_can configuration. I think, this should be done the
other way round.
The patch below fixes things for me.
Signed-off-by: Jan Altenberg <jan@linutronix.de> Acked-by: Kurt Van Dijck <kurt.van.dijck@eia.be> Acked-by: Wolfgang Grandegger <wg@grandegger.com> Signed-off-by: David S. Miller <davem@davemloft.net>
James Chapman [Tue, 22 Mar 2011 01:10:25 +0000 (18:10 -0700)]
l2tp: fix possible oops on l2tp_eth module unload
A struct used in the l2tp_eth driver for registering network namespace
ops was incorrectly marked as __net_initdata, leading to oops when
module unloaded.
Wei Yongjun [Tue, 22 Mar 2011 01:08:28 +0000 (18:08 -0700)]
xfrm: Fix initialize repl field of struct xfrm_state
Commit 'xfrm: Move IPsec replay detection functions to a separate file'
(9fdc4883d92d20842c5acea77a4a21bb1574b495)
introduce repl field to struct xfrm_state, and only initialize it
under SA's netlink create path, the other path, such as pf_key,
ipcomp/ipcomp6 etc, the repl field remaining uninitialize. So if
the SA is created by pf_key, any input packet with SA's encryption
algorithm will cause panic.
int xfrm_input()
{
...
x->repl->advance(x, seq);
...
}
This patch fixed it by introduce new function __xfrm_init_state().
projects / karo-tx-linux.git / log