Fix race between swapoff and swapon.  Swapoff used old_block_size from
swap_info outside of swapon_mutex so it could be overwritten by
concurrent swapon.

The race has visible effect only if more than one swap block device
exists with different block sizes (e.g.  /dev/sda1 with block size 4096
and /dev/sdb1 with 512).  In such case it leads to setting the blocksize
of swapped off device with wrong blocksize.

The bug can be triggered with multiple concurrent swapoff and swapon:
0. Swap for some device is on.
1. swapoff:
First the swapoff is called on this device and "struct swap_info_struct
*p" is assigned. This is done under swap_lock however this lock is
released for the call try_to_unuse().

2. swapon:
After the assignment above (and before acquiring swapon_mutex &
swap_lock by swapoff) the swapon is called on the same device.
The p->old_block_size is assigned to the value of block_size the device.
This block size should be the same as previous but sometimes it is not.
The swapon ends successfully.

3. swapoff:
Swapoff resumes, grabs the locks and mutex and continues to disable this
swap device. Now it sets the block size to value taken from swap_info
which was overwritten by swapon in 2.
Signed-off-by: NKrzysztof Kozlowski <k.kozlowski@samsung.com>
Reported-by: NWeijie Yang <weijie.yang.kh@gmail.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Minchan Kim <minchan@kernel.org>
Acked-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

swap cluster allocation is to get better request merge to improve
performance.  But the cluster is shared globally, if multiple tasks are
doing swap, this will cause interleave disk access.  While multiple tasks
swap is quite common, for example, each numa node has a kswapd thread
doing swap and multiple threads/processes doing direct page reclaim.

ioscheduler can't help too much here, because tasks don't send swapout IO
down to block layer in the meantime.  Block layer does merge some IOs, but
a lot not, depending on how many tasks are doing swapout concurrently.  In
practice, I've seen a lot of small size IO in swapout workloads.

We makes the cluster allocation per-cpu here.  The interleave disk access
issue goes away.  All tasks swapout to their own cluster, so swapout will
become sequential, which can be easily merged to big size IO.  If one CPU
can't get its per-cpu cluster (for example, there is no free cluster
anymore in the swap), it will fallback to scan swap_map.  The CPU can
still continue swap.  We don't need recycle free swap entries of other
CPUs.

In my test (swap to a 2-disk raid0 partition), this improves around 10%
swapout throughput, and request size is increased significantly.

How does this impact swap readahead is uncertain though.  On one side,
page reclaim always isolates and swaps several adjancent pages, this will
make page reclaim write the pages sequentially and benefit readahead.  On
the other side, several CPU write pages interleave means the pages don't
live _sequentially_ but relatively _near_.  In the per-cpu allocation
case, if adjancent pages are written by different cpus, they will live
relatively _far_.  So how this impacts swap readahead depends on how many
pages page reclaim isolates and swaps one time.  If the number is big,
this patch will benefit swap readahead.  Of course, this is about
sequential access pattern.  The patch has no impact for random access
pattern, because the new cluster allocation algorithm is just for SSD.

Alternative solution is organizing swap layout to be per-mm instead of
this per-cpu approach.  In the per-mm layout, we allocate a disk range for
each mm, so pages of one mm live in swap disk adjacently.  per-mm layout
has potential issues of lock contention if multiple reclaimers are swap
pages from one mm.  For a sequential workload, per-mm layout is better to
implement swap readahead, because pages from the mm are adjacent in disk.
But per-cpu layout isn't very bad in this workload, as page reclaim always
isolates and swaps several pages one time, such pages will still live in
disk sequentially and readahead can utilize this.  For a random workload,
per-mm layout isn't beneficial of request merge, because it's quite
possible pages from different mm are swapout in the meantime and IO can't
be merged in per-mm layout.  while with per-cpu layout we can merge
requests from any mm.  Considering random workload is more popular in
workloads with swap (and per-cpu approach isn't too bad for sequential
workload too), I'm choosing per-cpu layout.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NShaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The previous patch can expose races, according to Hugh:

swapoff was sometimes failing with "Cannot allocate memory", coming from
try_to_unuse()'s -ENOMEM: it needs to allow for swap_duplicate() failing
on a free entry temporarily SWAP_MAP_BAD while being discarded.

We should use ACCESS_ONCE() there, and whenever accessing swap_map
locklessly; but rather than peppering it throughout try_to_unuse(), just
declare *swap_map with volatile.

try_to_unuse() is accustomed to *swap_map going down racily, but not
necessarily to it jumping up from 0 to SWAP_MAP_BAD: we'll be safer to
prevent that transition once SWP_WRITEOK is switched off, when it's a
waste of time to issue discards anyway (swapon can do a whole discard).

Another issue is:

In swapin_readahead(), read_swap_cache_async() can read a bad swap entry,
because we don't check if readahead swap entry is bad.  This doesn't break
anything but such swapin page is wasteful and can only be freed at page
reclaim.  We should avoid read such swap entry.  And in discard, we mark
swap entry SWAP_MAP_BAD and then switch it to normal when discard is
finished.  If readahead reads such swap entry, we have the same issue, so
we much check if swap entry is bad too.

Thanks Hugh to inspire swapin_readahead could use bad swap entry.

[include Hugh's patch 'swap: fix swapoff ENOMEMs from discard']
Signed-off-by: NShaohua Li <shli@fusionio.com>
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

swap can do cluster discard for SSD, which is good, but there are some
problems here:

1. swap do the discard just before page reclaim gets a swap entry and
   writes the disk sectors.  This is useless for high end SSD, because an
   overwrite to a sector implies a discard to original sector too.  A
   discard + overwrite == overwrite.

2. the purpose of doing discard is to improve SSD firmware garbage
   collection.  Idealy we should send discard as early as possible, so
   firmware can do something smart.  Sending discard just after swap entry
   is freed is considered early compared to sending discard before write.
   Of course, if workload is already bound to gc speed, sending discard
   earlier or later doesn't make

3. block discard is a sync API, which will delay scan_swap_map()
   significantly.

4. Write and discard command can be executed parallel in PCIe SSD.
   Making swap discard async can make execution more efficiently.

This patch makes swap discard async and moves discard to where swap entry
is freed.  Discard and write have no dependence now, so above issues can
be avoided.  Idealy we should do discard for any freed sectors, but some
SSD discard is very slow.  This patch still does discard for a whole
cluster.

My test does a several round of 'mmap, write, unmap', which will trigger a
lot of swap discard.  In a fusionio card, with this patch, the test
runtime is reduced to 18% of the time without it, so around 5.5x faster.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NShaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

I'm using a fast SSD to do swap.  scan_swap_map() sometimes uses up to
20~30% CPU time (when cluster is hard to find, the CPU time can be up to
80%), which becomes a bottleneck.  scan_swap_map() scans a byte array to
search a 256 page cluster, which is very slow.

Here I introduced a simple algorithm to search cluster.  Since we only
care about 256 pages cluster, we can just use a counter to track if a
cluster is free.  Every 256 pages use one int to store the counter.  If
the counter of a cluster is 0, the cluster is free.  All free clusters
will be added to a list, so searching cluster is very efficient.  With
this, scap_swap_map() overhead disappears.

This might help low end SD card swap too.  Because if the cluster is
aligned, SD firmware can do flash erase more efficiently.

We only enable the algorithm for SSD.  Hard disk swap isn't fast enough
and has downside with the algorithm which might introduce regression (see
below).

The patch slightly changes which cluster is choosen.  It always adds free
cluster to list tail.  This can help wear leveling for low end SSD too.
And if no cluster found, the scan_swap_map() will do search from the end
of last cluster.  So if no cluster found, the scan_swap_map() will do
search from the end of last free cluster, which is random.  For SSD, this
isn't a problem at all.

Another downside is the cluster must be aligned to 256 pages, which will
reduce the chance to find a cluster.  I would expect this isn't a big
problem for SSD because of the non-seek penality.  (And this is the reason
I only enable the algorithm for SSD).
Signed-off-by: NShaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

A few 80-col gymnastics were cleaned up as a result.

Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It is possible to swapon a swap area that is too big for the pte width
to handle.

Presently this failure happens silently.

Instead, emit a diagnostic to warn the user.

Testing results, root prompt commands and kernel log messages:

# lvresize /dev/system/swap --size 16G
# mkswap /dev/system/swap
# swapon /dev/system/swap

Jul  7 04:27:22 warfang kernel: Adding 16777212k swap
on /dev/mapper/system-swap.  Priority:-1 extents:1 across:16777212k

# lvresize /dev/system/swap --size 64G
# mkswap /dev/system/swap
# swapon /dev/system/swap

Jul  7 04:27:22 warfang kernel: Truncating oversized swap area, only
using 33554432k out of 67108860k
Jul  7 04:27:22 warfang kernel: Adding 33554428k swap
on /dev/mapper/system-swap.  Priority:-1 extents:1 across:33554428k

[akpm@linux-foundation.org: fix warning]
Signed-off-by: NRaymond Jennings <shentino@gmail.com>
Acked-by: NValdis Kletnieks <valdis.kletnieks@vt.edu>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set
get swapped out, the bit is getting lost and no longer available when
pte read back.

To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in
pte entry for the page being swapped out.  When such page is to be read
back from a swap cache we check for bit presence and if it's there we
clear it and restore the former _PAGE_SOFT_DIRTY bit back.

One of the problem was to find a place in pte entry where we can save
the _PTE_SWP_SOFT_DIRTY bit while page is in swap.  The _PAGE_PSE was
chosen for that, it doesn't intersect with swap entry format stored in
pte.
Reported-by: NAndy Lutomirski <luto@amacapital.net>
Signed-off-by: NCyrill Gorcunov <gorcunov@openvz.org>
Acked-by: NPavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Reviewed-by: NWanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Considering the use cases where the swap device supports discard:
a) and can do it quickly;
b) but it's slow to do in small granularities (or concurrent with other
   I/O);
c) but the implementation is so horrendous that you don't even want to
   send one down;

And assuming that the sysadmin considers it useful to send the discards down
at all, we would (probably) want the following solutions:

  i. do the fine-grained discards for freed swap pages, if device is
     capable of doing so optimally;
 ii. do single-time (batched) swap area discards, either at swapon
     or via something like fstrim (not implemented yet);
iii. allow doing both single-time and fine-grained discards; or
 iv. turn it off completely (default behavior)

As implemented today, one can only enable/disable discards for swap, but
one cannot select, for instance, solution (ii) on a swap device like (b)
even though the single-time discard is regarded to be interesting, or
necessary to the workload because it would imply (1), and the device is
not capable of performing it optimally.

This patch addresses the scenario depicted above by introducing a way to
ensure the (probably) wanted solutions (i, ii, iii and iv) can be flexibly
flagged through swapon(8) to allow a sysadmin to select the best suitable
swap discard policy accordingly to system constraints.

This patch introduces SWAP_FLAG_DISCARD_PAGES and SWAP_FLAG_DISCARD_ONCE
new flags to allow more flexibe swap discard policies being flagged
through swapon(8).  The default behavior is to keep both single-time, or
batched, area discards (SWAP_FLAG_DISCARD_ONCE) and fine-grained discards
for page-clusters (SWAP_FLAG_DISCARD_PAGES) enabled, in order to keep
consistentcy with older kernel behavior, as well as maintain compatibility
with older swapon(8).  However, through the new introduced flags the best
suitable discard policy can be selected accordingly to any given swap
device constraint.

[akpm@linux-foundation.org: tweak comments]
Signed-off-by: NRafael Aquini <aquini@redhat.com>
Acked-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Karel Zak <kzak@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The bitmap accessed by bitops must have enough size to hold the required
numbers of bits rounded up to a multiple of BITS_PER_LONG.  And the
bitmap must not be zeroed by memset() if the number of bits cleared is
not a multiple of BITS_PER_LONG.

This fixes incorrect zeroing and allocation size for frontswap_map.  The
incorrect zeroing part doesn't cause any problem because frontswap_map
is freed just after zeroing.  But the wrongly calculated allocation size
may cause the problem.

For 32bit systems, the allocation size of frontswap_map is about twice
as large as required size.  For 64bit systems, the allocation size is
smaller than requeired if the number of bits is not a multiple of
BITS_PER_LONG.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Frontswap initialization routine depends on swap_lock, which want to be
atomic about frontswap's first appearance.  IOW, frontswap is not present
and will fail all calls OR frontswap is fully functional but if new
swap_info_struct isn't registered by enable_swap_info, swap subsystem
doesn't start I/O so there is no race between init procedure and page I/O
working on frontswap.

So let's remove unnecessary swap_lock dependency.

Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Signed-off-by: NMinchan Kim <minchan@kernel.org>
[v1: Rebased on my branch, reworked to work with backends loading late]
[v2: Added a check for !map]
[v3: Made the invalidate path follow the init path]
[v4: Address comments by Wanpeng Li <liwanp@linux.vnet.ibm.com>]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad@darnok.org>
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andor Daam <andor.daam@googlemail.com>
Cc: Florian Schmaus <fschmaus@gmail.com>
Cc: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Use preferable function name which implies using a pseudo-random
number generator.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Before establishing that KSM page migration was the cause of my
WARN_ON_ONCE(page_mapped(page))s, I suspected that they came from the
lack of a ksm_might_need_to_copy() in swapoff's unuse_pte() - which in
many respects is equivalent to faulting in a page.

In fact I've never caught that as the cause: but in theory it does at
least need the KSM_RUN_UNMERGE check in ksm_might_need_to_copy(), to
avoid bringing a KSM page back in when it's not supposed to be.

I intended to copy how it's done in do_swap_page(), but have a strong
aversion to how "swapcache" ends up being used there: rework it with
"page != swapcache".
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Petr Holasek <pholasek@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Izik Eidus <izik.eidus@ravellosystems.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD).  The main contention comes
from swap_info_get().  This patch tries to fix the gap with adding a new
per-partition lock.

Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.

nr_swap_pages is an atomic now, it can be changed without swap_lock.  In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages.  But sounds not a big problem.

Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.

Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it.  read the
flags is ok with either the locks hold.

If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.

swap_entry_free() can change swap_list.  To delete that code, we add a
new highest_priority_index.  Whenever get_swap_page() is called, we
check it.  If it's valid, we use it.

It's a pity get_swap_page() still holds swap_lock().  But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush).  And
BTW, looks get_swap_page() doesn't really need the lock.  We never free
swap_info[] and we check SWAP_WRITEOK flag.  The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.

"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s.  This patch further improves the
speed to 2.3G/s, so around 15% improvement.  It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.

[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: NShaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When I use several fast SSD to do swap, swapper_space.tree_lock is
heavily contended.  This makes each swap partition have one
address_space to reduce the lock contention.  There is an array of
address_space for swap.  The swap entry type is the index to the array.

In my test with 3 SSD, this increases the swapout throughput 20%.

[akpm@linux-foundation.org: revert unneeded change to  __add_to_swap_cache]
Signed-off-by: NShaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Acked-by: NRik van Riel <riel@redhat.com>
Acked-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

test_set_oom_score_adj() and compare_swap_oom_score_adj() are used to
specify that current should be killed first if an oom condition occurs in
between the two calls.

The usage is

	short oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
	...
	compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);

to store the thread's oom_score_adj, temporarily change it to the maximum
score possible, and then restore the old value if it is still the same.

This happens to still be racy, however, if the user writes
OOM_SCORE_ADJ_MAX to /proc/pid/oom_score_adj in between the two calls.
The compare_swap_oom_score_adj() will then incorrectly reset the old value
prior to the write of OOM_SCORE_ADJ_MAX.

To fix this, introduce a new oom_flags_t member in struct signal_struct
that will be used for per-thread oom killer flags.  KSM and swapoff can
now use a bit in this member to specify that threads should be killed
first in oom conditions without playing around with oom_score_adj.

This also allows the correct oom_score_adj to always be shown when reading
/proc/pid/oom_score.
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: NMichal Hocko <mhocko@suse.cz>
Cc: Anton Vorontsov <anton.vorontsov@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The maximum oom_score_adj is 1000 and the minimum oom_score_adj is -1000,
so this range can be represented by the signed short type with no
functional change.  The extra space this frees up in struct signal_struct
will be used for per-thread oom kill flags in the next patch.
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: NMichal Hocko <mhocko@suse.cz>
Cc: Anton Vorontsov <anton.vorontsov@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The call to frontswap_init() was added within enable_swap_info(), which
was called not only during sys_swapon, but also to reinsert the swap_info
into the swap_list in case of failure of try_to_unuse() within
sys_swapoff.  This means that frontswap_init() might be called more than
once for the same swap area.

While as far as I could see no frontswap implementation has any problem
with it (and in fact, all the ones I found ignore the parameter passed to
frontswap_init), this could change in the future.

To prevent future problems, move the call to frontswap_init() to outside
the code shared between sys_swapon and sys_swapoff.
Signed-off-by: NCesar Eduardo Barros <cesarb@cesarb.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: NDan Magenheimer <dan.magenheimer@oracle.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The block within sys_swapoff() which re-inserts the swap_info into the
swap_list in case of failure of try_to_unuse() reads a few values outside
the swap_lock.  While this is safe at that point, it is subtle code.

Simplify the code by moving the reading of these values to a separate
function, refactoring it a bit so they are read from within the swap_lock.
 This is easier to understand, and matches better the way it worked before
I unified the insertion of the swap_info from both sys_swapon and
sys_swapoff.

This change should make no functional difference.  The only real change is
moving the read of two or three structure fields to within the lock
(frontswap_map_get() is nothing more than a read of p->frontswap_map).
Signed-off-by: NCesar Eduardo Barros <cesarb@cesarb.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There's a name leak introduced by commit 91a27b2a ("vfs: define
struct filename and have getname() return it").  Add the missing
putname.

[akpm@linux-foundation.org: cleanup]
Signed-off-by: NXiaotian Feng <dannyfeng@tencent.com>
Reviewed-by: NJeff Layton <jlayton@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

...and fix up the callers. For do_file_open_root, just declare a
struct filename on the stack and fill out the .name field. For
do_filp_open, make it also take a struct filename pointer, and fix up its
callers to call it appropriately.

For filp_open, add a variant that takes a struct filename pointer and turn
filp_open into a wrapper around it.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

getname() is intended to copy pathname strings from userspace into a
kernel buffer. The result is just a string in kernel space. It would
however be quite helpful to be able to attach some ancillary info to
the string.

For instance, we could attach some audit-related info to reduce the
amount of audit-related processing needed. When auditing is enabled,
we could also call getname() on the string more than once and not
need to recopy it from userspace.

This patchset converts the getname()/putname() interfaces to return
a struct instead of a string. For now, the struct just tracks the
string in kernel space and the original userland pointer for it.

Later, we'll add other information to the struct as it becomes
convenient.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The conditional mem_cgroup_cancel_charge_swapin() is a leftover from when
the function would continue to reestablish the page even after
mem_cgroup_try_charge_swapin() failed.  After 85d9fc89 "memcg: fix refcnt
handling at swapoff", the condition is always true when this code is
reached.
Signed-off-by: NJohannes Weiner <hannes@cmpxchg.org>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Wanpeng Li <liwp.linux@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit b3a27d ("swap: Add swap slot free callback to
block_device_operations") dereferences p->bdev->bd_disk but this is a NULL
dereference if using swap-over-NFS.  This patch checks SWP_BLKDEV on the
swap_info_struct before dereferencing.

With reference to this callback, Christoph Hellwig stated "Please just
remove the callback entirely.  It has no user outside the staging tree and
was added clearly against the rules for that staging tree".  This would
also be my preference but there was not an obvious way of keeping zram in
staging/ happy.
Signed-off-by: NXiaotian Feng <dfeng@redhat.com>
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The version of swap_activate introduced is sufficient for swap-over-NFS
but would not provide enough information to implement a generic handler.
This patch shuffles things slightly to ensure the same information is
available for aops->swap_activate() as is available to the core.

No functionality change.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently swapfiles are managed entirely by the core VM by using ->bmap to
allocate space and write to the blocks directly.  This effectively ensures
that the underlying blocks are allocated and avoids the need for the swap
subsystem to locate what physical blocks store offsets within a file.

If the swap subsystem is to use the filesystem information to locate the
blocks, it is critical that information such as block groups, block
bitmaps and the block descriptor table that map the swap file were
resident in memory.  This patch adds address_space_operations that the VM
can call when activating or deactivating swap backed by a file.

  int swap_activate(struct file *);
  int swap_deactivate(struct file *);

The ->swap_activate() method is used to communicate to the file that the
VM relies on it, and the address_space should take adequate measures such
as reserving space in the underlying device, reserving memory for mempools
and pinning information such as the block descriptor table in memory.  The
->swap_deactivate() method is called on sys_swapoff() if ->swap_activate()
returned success.

After a successful swapfile ->swap_activate, the swapfile is marked
SWP_FILE and swapper_space.a_ops will proxy to
sis->swap_file->f_mappings->a_ops using ->direct_io to write swapcache
pages and ->readpage to read.

It is perfectly possible that direct_IO be used to read the swap pages but
it is an unnecessary complication.  Similarly, it is possible that
->writepage be used instead of direct_io to write the pages but filesystem
developers have stated that calling writepage from the VM is undesirable
for a variety of reasons and using direct_IO opens up the possibility of
writing back batches of swap pages in the future.

[a.p.zijlstra@chello.nl: Original patch]
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In order to teach filesystems to handle swap cache pages, three new page
functions are introduced:

  pgoff_t page_file_index(struct page *);
  loff_t page_file_offset(struct page *);
  struct address_space *page_file_mapping(struct page *);

page_file_index() - gives the offset of this page in the file in
PAGE_CACHE_SIZE blocks.  Like page->index is for mapped pages, this
function also gives the correct index for PG_swapcache pages.

page_file_offset() - uses page_file_index(), so that it will give the
expected result, even for PG_swapcache pages.

page_file_mapping() - gives the mapping backing the actual page; that is
for swap cache pages it will give swap_file->f_mapping.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Minchan Kim reports that when a system has many swap areas, and tmpfs
swaps out to the ninth or more, shmem_getpage_gfp()'s attempts to read
back the page cannot locate it, and the read fails with -ENOMEM.

Whoops.  Yes, I blindly followed read_swap_header()'s pte_to_swp_entry(
swp_entry_to_pte()) technique for determining maximum usable swap
offset, without stopping to realize that that actually depends upon the
pte swap encoding shifting swap offset to the higher bits and truncating
it there.  Whereas our radix_tree swap encoding leaves offset in the
lower bits: it's swap "type" (that is, index of swap area) that was
truncated.

Fix it by reducing the SWP_TYPE_SHIFT() in swapops.h, and removing the
broken radix_to_swp_entry(swp_to_radix_entry()) from read_swap_header().

This does not reduce the usable size of a swap area any further, it
leaves it as claimed when making the original commit: no change from 3.0
on x86_64, nor on i386 without PAE; but 3.0's 512GB is reduced to 128GB
per swapfile on i386 with PAE.  It's not a change I would have risked
five years ago, but with x86_64 supported for ten years, I believe it's
appropriate now.

Hmm, and what if some architecture implements its swap pte with offset
encoded below type? That would equally break the maximum usable swap
offset check.  Happily, they all follow the same tradition of encoding
offset above type, but I'll prepare a check on that for next.
Reported-and-Reviewed-and-Tested-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: stable@vger.kernel.org [3.1, 3.2, 3.3, 3.4]
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch changes memcg's behavior at task_move().

At task_move(), the kernel scans a task's page table and move the changes
for mapped pages from source cgroup to target cgroup.  There has been a
bug at handling shared anonymous pages for a long time.

Before patch:
  - The spec says 'shared anonymous pages are not moved.'
  - The implementation was 'shared anonymoys pages may be moved'.
    If page_mapcount <=2, shared anonymous pages's charge were moved.

After patch:
  - The spec says 'all anonymous pages are moved'.
  - The implementation is 'all anonymous pages are moved'.

Considering usage of memcg, this will not affect user's experience.
'shared anonymous' pages only exists between a tree of processes which
don't do exec().  Moving one of process without exec() seems not sane.
For example, libcgroup will not be affected by this change.  (Anyway, no
one noticed the implementation for a long time...)

Below is a discussion log:

 - current spec/implementation are complex
 - Now, shared file caches are moved
 - It adds unclear check as page_mapcount(). To do correct check,
   we should check swap users, etc.
 - No one notice this implementation behavior. So, no one get benefit
   from the design.
 - In general, once task is moved to a cgroup for running, it will not
   be moved....
 - Finally, we have control knob as memory.move_charge_at_immigrate.

Here is a patch to allow moving shared pages, completely. This makes
memcg simpler and fix current broken code.
Suggested-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Glauber Costa <glommer@parallels.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The GMA500 GPU driver uses GEM shmem objects, but with a new twist: the
backing RAM has to be below 4GB.  Not a problem while the boards
supported only 4GB: but now Intel's D2700MUD boards support 8GB, and
their GMA3600 is managed by the GMA500 driver.

shmem/tmpfs has never pretended to support hardware restrictions on the
backing memory, but it might have appeared to do so before v3.1, and
even now it works fine until a page is swapped out then back in.  When
read_cache_page_gfp() supplied a freshly allocated page for copy, that
compensated for whatever choice might have been made by earlier swapin
readahead; but swapoff was likely to destroy the illusion.

We'd like to continue to support GMA500, so now add a new
shmem_should_replace_page() check on the zone when about to move a page
from swapcache to filecache (in swapin and swapoff cases), with
shmem_replace_page() to allocate and substitute a suitable page (given
gma500/gem.c's mapping_set_gfp_mask GFP_KERNEL | __GFP_DMA32).

This does involve a minor extension to mem_cgroup_replace_page_cache()
(the page may or may not have already been charged); and I've removed a
comment and call to mem_cgroup_uncharge_cache_page(), which in fact is
always a no-op while PageSwapCache.

Also removed optimization of an unlikely path in shmem_getpage_gfp(),
now that we need to check PageSwapCache more carefully (a racing caller
might already have made the copy).  And at one point shmem_unuse_inode()
needs to use the hitherto private page_swapcount(), to guard against
racing with inode eviction.

It would make sense to extend shmem_should_replace_page(), to cover
cpuset and NUMA mempolicy restrictions too, but set that aside for now:
needs a cleanup of shmem mempolicy handling, and more testing, and ought
to handle swap faults in do_swap_page() as well as shmem.
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@infradead.org>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Stephane Marchesin <marcheu@chromium.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Rob Clark <rob.clark@linaro.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch, 2of4, contains the changes to the core swap subsystem.
This includes:

(1) makes available core swap data structures (swap_lock, swap_list and
swap_info) that are needed by frontswap.c but we don't need to expose them
to the dozens of files that include swap.h so we create a new swapfile.h
just to extern-ify these and modify their declarations to non-static

(2) adds frontswap-related elements to swap_info_struct.  Frontswap_map
points to vzalloc'ed one-bit-per-swap-page metadata that indicates
whether the swap page is in frontswap or in the device and frontswap_pages
counts how many pages are in frontswap.

(3) adds hooks in the swap subsystem and extends try_to_unuse so that
frontswap_shrink can do a "partial swapoff".

Note that a failed frontswap_map allocation is safe... failure is noted
by lack of "FS" in the subsequent printk.

---

[v14: rebase to 3.4-rc2]
[v10: no change]
[v9: akpm@linux-foundation.org: mark some statics __read_mostly]
[v9: akpm@linux-foundation.org: add clarifying comments]
[v9: akpm@linux-foundation.org: no need to loop repeating try_to_unuse]
[v9: error27@gmail.com: remove superfluous check for NULL]
[v8: rebase to 3.0-rc4]
[v8: kamezawa.hiroyu@jp.fujitsu.com: change counter to atomic_t to avoid races]
[v8: kamezawa.hiroyu@jp.fujitsu.com: comment to clarify informational counters]
[v7: rebase to 3.0-rc3]
[v7: JBeulich@novell.com: add new swap struct elements only if config'd]
[v6: rebase to 3.0-rc1]
[v6: lliubbo@gmail.com: fix null pointer deref if vzalloc fails]
[v6: konrad.wilk@oracl.com: various checks and code clarifications/comments]
[v5: no change from v4]
[v4: rebase to 2.6.39]
Signed-off-by: NDan Magenheimer <dan.magenheimer@oracle.com>
Reviewed-by: NKamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: NJan Beulich <JBeulich@novell.com>
Acked-by: NSeth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Rik Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
[v11: Rebased, fixed mm/swapfile.c context change]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Most system calls taking flags first check that the flags passed in are
valid, and that helps userspace to detect when new flags are supported.

But swapon never did so: start checking now, to help if we ever want to
support more swap_flags in future.

It's difficult to get stray bits set in an int, and swapon is not widely
used, so this is most unlikely to break any userspace; but we can just
revert if it turns out to do so.
Signed-off-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When swapon() was not passed the SWAP_FLAG_DISCARD option, sys_swapon()
will still perform a discard operation.  This can cause problems if
discard is slow or buggy.

Reverse the order of the check so that a discard operation is performed
only if the sys_swapon() caller is attempting to enable discard.
Signed-off-by: NShaohua Li <shli@fusionio.com>
Reported-by: NHolger Kiehl <Holger.Kiehl@dwd.de>
Tested-by: NHolger Kiehl <Holger.Kiehl@dwd.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Ever since abandoning the virtual scan of processes, for scalability
reasons, swap space has been a little more fragmented than before.  This
can lead to the situation where a large memory user is killed, swap space
ends up full of "holes" and swapin readahead is totally ineffective.

On my home system, after killing a leaky firefox it took over an hour to
page just under 2GB of memory back in, slowing the virtual machines down
to a crawl.

This patch makes swapin readahead simply skip over holes, instead of
stopping at them.  This allows the system to swap things back in at rates
of several MB/second, instead of a few hundred kB/second.

The checks done in valid_swaphandles are already done in
read_swap_cache_async as well, allowing us to remove a fair amount of
code.

[akpm@linux-foundation.org: fix it for page_cluster >= 32]
Signed-off-by: NRik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Acked-by: NMel Gorman <mgorman@suse.de>
Cc: Adrian Drzewiecki <z@drze.net>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In some cases it may happen that pmd_none_or_clear_bad() is called with
the mmap_sem hold in read mode.  In those cases the huge page faults can
allocate hugepmds under pmd_none_or_clear_bad() and that can trigger a
false positive from pmd_bad() that will not like to see a pmd
materializing as trans huge.

It's not khugepaged causing the problem, khugepaged holds the mmap_sem
in write mode (and all those sites must hold the mmap_sem in read mode
to prevent pagetables to go away from under them, during code review it
seems vm86 mode on 32bit kernels requires that too unless it's
restricted to 1 thread per process or UP builds).  The race is only with
the huge pagefaults that can convert a pmd_none() into a
pmd_trans_huge().

Effectively all these pmd_none_or_clear_bad() sites running with
mmap_sem in read mode are somewhat speculative with the page faults, and
the result is always undefined when they run simultaneously.  This is
probably why it wasn't common to run into this.  For example if the
madvise(MADV_DONTNEED) runs zap_page_range() shortly before the page
fault, the hugepage will not be zapped, if the page fault runs first it
will be zapped.

Altering pmd_bad() not to error out if it finds hugepmds won't be enough
to fix this, because zap_pmd_range would then proceed to call
zap_pte_range (which would be incorrect if the pmd become a
pmd_trans_huge()).

The simplest way to fix this is to read the pmd in the local stack
(regardless of what we read, no need of actual CPU barriers, only
compiler barrier needed), and be sure it is not changing under the code
that computes its value.  Even if the real pmd is changing under the
value we hold on the stack, we don't care.  If we actually end up in
zap_pte_range it means the pmd was not none already and it was not huge,
and it can't become huge from under us (khugepaged locking explained
above).

All we need is to enforce that there is no way anymore that in a code
path like below, pmd_trans_huge can be false, but pmd_none_or_clear_bad
can run into a hugepmd.  The overhead of a barrier() is just a compiler
tweak and should not be measurable (I only added it for THP builds).  I
don't exclude different compiler versions may have prevented the race
too by caching the value of *pmd on the stack (that hasn't been
verified, but it wouldn't be impossible considering
pmd_none_or_clear_bad, pmd_bad, pmd_trans_huge, pmd_none are all inlines
and there's no external function called in between pmd_trans_huge and
pmd_none_or_clear_bad).

		if (pmd_trans_huge(*pmd)) {
			if (next-addr != HPAGE_PMD_SIZE) {
				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
				split_huge_page_pmd(vma->vm_mm, pmd);
			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
				continue;
			/* fall through */
		}
		if (pmd_none_or_clear_bad(pmd))

Because this race condition could be exercised without special
privileges this was reported in CVE-2012-1179.

The race was identified and fully explained by Ulrich who debugged it.
I'm quoting his accurate explanation below, for reference.

====== start quote =======
      mapcount 0 page_mapcount 1
      kernel BUG at mm/huge_memory.c:1384!

    At some point prior to the panic, a "bad pmd ..." message similar to the
    following is logged on the console:

      mm/memory.c:145: bad pmd ffff8800376e1f98(80000000314000e7).

    The "bad pmd ..." message is logged by pmd_clear_bad() before it clears
    the page's PMD table entry.

        143 void pmd_clear_bad(pmd_t *pmd)
        144 {
    ->  145         pmd_ERROR(*pmd);
        146         pmd_clear(pmd);
        147 }

    After the PMD table entry has been cleared, there is an inconsistency
    between the actual number of PMD table entries that are mapping the page
    and the page's map count (_mapcount field in struct page). When the page
    is subsequently reclaimed, __split_huge_page() detects this inconsistency.

       1381         if (mapcount != page_mapcount(page))
       1382                 printk(KERN_ERR "mapcount %d page_mapcount %d\n",
       1383                        mapcount, page_mapcount(page));
    -> 1384         BUG_ON(mapcount != page_mapcount(page));

    The root cause of the problem is a race of two threads in a multithreaded
    process. Thread B incurs a page fault on a virtual address that has never
    been accessed (PMD entry is zero) while Thread A is executing an madvise()
    system call on a virtual address within the same 2 MB (huge page) range.

               virtual address space
              .---------------------.
              |                     |
              |                     |
            .-|---------------------|
            | |                     |
            | |                     |<-- B(fault)
            | |                     |
      2 MB  | |/////////////////////|-.
      huge <  |/////////////////////|  > A(range)
      page  | |/////////////////////|-'
            | |                     |
            | |                     |
            '-|---------------------|
              |                     |
              |                     |
              '---------------------'

    - Thread A is executing an madvise(..., MADV_DONTNEED) system call
      on the virtual address range "A(range)" shown in the picture.

    sys_madvise
      // Acquire the semaphore in shared mode.
      down_read(&current->mm->mmap_sem)
      ...
      madvise_vma
        switch (behavior)
        case MADV_DONTNEED:
             madvise_dontneed
               zap_page_range
                 unmap_vmas
                   unmap_page_range
                     zap_pud_range
                       zap_pmd_range
                         //
                         // Assume that this huge page has never been accessed.
                         // I.e. content of the PMD entry is zero (not mapped).
                         //
                         if (pmd_trans_huge(*pmd)) {
                             // We don't get here due to the above assumption.
                         }
                         //
                         // Assume that Thread B incurred a page fault and
             .---------> // sneaks in here as shown below.
             |           //
             |           if (pmd_none_or_clear_bad(pmd))
             |               {
             |                 if (unlikely(pmd_bad(*pmd)))
             |                     pmd_clear_bad
             |                     {
             |                       pmd_ERROR
             |                         // Log "bad pmd ..." message here.
             |                       pmd_clear
             |                         // Clear the page's PMD entry.
             |                         // Thread B incremented the map count
             |                         // in page_add_new_anon_rmap(), but
             |                         // now the page is no longer mapped
             |                         // by a PMD entry (-> inconsistency).
             |                     }
             |               }
             |
             v
    - Thread B is handling a page fault on virtual address "B(fault)" shown
      in the picture.

    ...
    do_page_fault
      __do_page_fault
        // Acquire the semaphore in shared mode.
        down_read_trylock(&mm->mmap_sem)
        ...
        handle_mm_fault
          if (pmd_none(*pmd) && transparent_hugepage_enabled(vma))
              // We get here due to the above assumption (PMD entry is zero).
              do_huge_pmd_anonymous_page
                alloc_hugepage_vma
                  // Allocate a new transparent huge page here.
                ...
                __do_huge_pmd_anonymous_page
                  ...
                  spin_lock(&mm->page_table_lock)
                  ...
                  page_add_new_anon_rmap
                    // Here we increment the page's map count (starts at -1).
                    atomic_set(&page->_mapcount, 0)
                  set_pmd_at
                    // Here we set the page's PMD entry which will be cleared
                    // when Thread A calls pmd_clear_bad().
                  ...
                  spin_unlock(&mm->page_table_lock)

    The mmap_sem does not prevent the race because both threads are acquiring
    it in shared mode (down_read).  Thread B holds the page_table_lock while
    the page's map count and PMD table entry are updated.  However, Thread A
    does not synchronize on that lock.

====== end quote =======

[akpm@linux-foundation.org: checkpatch fixes]
Reported-by: NUlrich Obergfell <uobergfe@redhat.com>
Signed-off-by: NAndrea Arcangeli <aarcange@redhat.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Jones <davej@redhat.com>
Acked-by: NLarry Woodman <lwoodman@redhat.com>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: <stable@vger.kernel.org>		[2.6.38+]
Cc: Mark Salter <msalter@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NCong Wang <amwang@redhat.com>

Collapse security_vm_enough_memory() variants into a single function.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NJames Morris <jmorris@namei.org>

Signed-off-by: NJohannes Weiner <jweiner@redhat.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Colin Cross reported;

  Under the following conditions, __alloc_pages_slowpath can loop forever:
  gfp_mask & __GFP_WAIT is true
  gfp_mask & __GFP_FS is false
  reclaim and compaction make no progress
  order <= PAGE_ALLOC_COSTLY_ORDER

  These conditions happen very often during suspend and resume,
  when pm_restrict_gfp_mask() effectively converts all GFP_KERNEL
  allocations into __GFP_WAIT.

  The oom killer is not run because gfp_mask & __GFP_FS is false,
  but should_alloc_retry will always return true when order is less
  than PAGE_ALLOC_COSTLY_ORDER.

In his fix, he avoided retrying the allocation if reclaim made no progress
and __GFP_FS was not set.  The problem is that this would result in
GFP_NOIO allocations failing that previously succeeded which would be very
unfortunate.

The big difference between GFP_NOIO and suspend converting GFP_KERNEL to
behave like GFP_NOIO is that normally flushers will be cleaning pages and
kswapd reclaims pages allowing GFP_NOIO to succeed after a short delay.
The same does not necessarily apply during suspend as the storage device
may be suspended.

This patch special cases the suspend case to fail the page allocation if
reclaim cannot make progress and adds some documentation on how
gfp_allowed_mask is currently used.  Failing allocations like this may
cause suspend to abort but that is better than a livelock.

[mgorman@suse.de: Rework fix to be suspend specific]
[rientjes@google.com: Move suspended device check to should_alloc_retry]
Reported-by: NColin Cross <ccross@android.com>
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>