linux-stable.git/mm, branch v4.14.95

mm, memcg: fix reclaim deadlock with writeback

2019-01-16T21:07:11+00:00

commit 63f3655f950186752236bb88a22f8252c11ce394 upstream.

Liu Bo has experienced a deadlock between memcg (legacy) reclaim and the
ext4 writeback

  task1:
    wait_on_page_bit+0x82/0xa0
    shrink_page_list+0x907/0x960
    shrink_inactive_list+0x2c7/0x680
    shrink_node_memcg+0x404/0x830
    shrink_node+0xd8/0x300
    do_try_to_free_pages+0x10d/0x330
    try_to_free_mem_cgroup_pages+0xd5/0x1b0
    try_charge+0x14d/0x720
    memcg_kmem_charge_memcg+0x3c/0xa0
    memcg_kmem_charge+0x7e/0xd0
    __alloc_pages_nodemask+0x178/0x260
    alloc_pages_current+0x95/0x140
    pte_alloc_one+0x17/0x40
    __pte_alloc+0x1e/0x110
    alloc_set_pte+0x5fe/0xc20
    do_fault+0x103/0x970
    handle_mm_fault+0x61e/0xd10
    __do_page_fault+0x252/0x4d0
    do_page_fault+0x30/0x80
    page_fault+0x28/0x30

  task2:
    __lock_page+0x86/0xa0
    mpage_prepare_extent_to_map+0x2e7/0x310 [ext4]
    ext4_writepages+0x479/0xd60
    do_writepages+0x1e/0x30
    __writeback_single_inode+0x45/0x320
    writeback_sb_inodes+0x272/0x600
    __writeback_inodes_wb+0x92/0xc0
    wb_writeback+0x268/0x300
    wb_workfn+0xb4/0x390
    process_one_work+0x189/0x420
    worker_thread+0x4e/0x4b0
    kthread+0xe6/0x100
    ret_from_fork+0x41/0x50

He adds
 "task1 is waiting for the PageWriteback bit of the page that task2 has
  collected in mpd->io_submit->io_bio, and tasks2 is waiting for the
  LOCKED bit the page which tasks1 has locked"

More precisely task1 is handling a page fault and it has a page locked
while it charges a new page table to a memcg.  That in turn hits a
memory limit reclaim and the memcg reclaim for legacy controller is
waiting on the writeback but that is never going to finish because the
writeback itself is waiting for the page locked in the #PF path.  So
this is essentially ABBA deadlock:

                                        lock_page(A)
                                        SetPageWriteback(A)
                                        unlock_page(A)
  lock_page(B)
                                        lock_page(B)
  pte_alloc_pne
    shrink_page_list
      wait_on_page_writeback(A)
                                        SetPageWriteback(B)
                                        unlock_page(B)

                                        # flush A, B to clear the writeback

This accumulating of more pages to flush is used by several filesystems
to generate a more optimal IO patterns.

Waiting for the writeback in legacy memcg controller is a workaround for
pre-mature OOM killer invocations because there is no dirty IO
throttling available for the controller.  There is no easy way around
that unfortunately.  Therefore fix this specific issue by pre-allocating
the page table outside of the page lock.  We have that handy
infrastructure for that already so simply reuse the fault-around pattern
which already does this.

There are probably other hidden __GFP_ACCOUNT | GFP_KERNEL allocations
from under a fs page locked but they should be really rare.  I am not
aware of a better solution unfortunately.

[akpm@linux-foundation.org: fix mm/memory.c:__do_fault()]
[akpm@linux-foundation.org: coding-style fixes]
[mhocko@kernel.org: enhance comment, per Johannes]
  Link: http://lkml.kernel.org/r/20181214084948.GA5624@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20181213092221.27270-1-mhocko@kernel.org
Fixes: c3b94f44fcb0 ("memcg: further prevent OOM with too many dirty pages")
Signed-off-by: Michal Hocko 
Reported-by: Liu Bo 
Debugged-by: Liu Bo 
Acked-by: Kirill A. Shutemov 
Acked-by: Johannes Weiner 
Reviewed-by: Liu Bo 
Cc: Jan Kara 
Cc: Dave Chinner 
Cc: Theodore Ts'o 
Cc: Vladimir Davydov 
Cc: Shakeel Butt 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm: page_mapped: don't assume compound page is huge or THP

2019-01-16T21:07:11+00:00

commit 8ab88c7169b7fba98812ead6524b9d05bc76cf00 upstream.

LTP proc01 testcase has been observed to rarely trigger crashes
on arm64:
    page_mapped+0x78/0xb4
    stable_page_flags+0x27c/0x338
    kpageflags_read+0xfc/0x164
    proc_reg_read+0x7c/0xb8
    __vfs_read+0x58/0x178
    vfs_read+0x90/0x14c
    SyS_read+0x60/0xc0

The issue is that page_mapped() assumes that if compound page is not
huge, then it must be THP.  But if this is 'normal' compound page
(COMPOUND_PAGE_DTOR), then following loop can keep running (for
HPAGE_PMD_NR iterations) until it tries to read from memory that isn't
mapped and triggers a panic:

        for (i = 0; i < hpage_nr_pages(page); i++) {
                if (atomic_read(&page[i]._mapcount) >= 0)
                        return true;
	}

I could replicate this on x86 (v4.20-rc4-98-g60b548237fed) only
with a custom kernel module [1] which:
 - allocates compound page (PAGEC) of order 1
 - allocates 2 normal pages (COPY), which are initialized to 0xff (to
   satisfy _mapcount >= 0)
 - 2 PAGEC page structs are copied to address of first COPY page
 - second page of COPY is marked as not present
 - call to page_mapped(COPY) now triggers fault on access to 2nd COPY
   page at offset 0x30 (_mapcount)

[1] https://github.com/jstancek/reproducers/blob/master/kernel/page_mapped_crash/repro.c

Fix the loop to iterate for "1 << compound_order" pages.

Kirrill said "IIRC, sound subsystem can producuce custom mapped compound
pages".

Link: http://lkml.kernel.org/r/c440d69879e34209feba21e12d236d06bc0a25db.1543577156.git.jstancek@redhat.com
Fixes: e1534ae95004 ("mm: differentiate page_mapped() from page_mapcount() for compound pages")
Signed-off-by: Jan Stancek 
Debugged-by: Laszlo Ersek 
Suggested-by: "Kirill A. Shutemov" 
Acked-by: Michal Hocko 
Acked-by: Kirill A. Shutemov 
Reviewed-by: David Hildenbrand 
Reviewed-by: Andrea Arcangeli 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

slab: alien caches must not be initialized if the allocation of the alien cache failed

2019-01-16T21:07:11+00:00

commit 09c2e76ed734a1d36470d257a778aaba28e86531 upstream.

Callers of __alloc_alien() check for NULL.  We must do the same check in
__alloc_alien_cache to avoid NULL pointer dereferences on allocation
failures.

Link: http://lkml.kernel.org/r/010001680f42f192-82b4e12e-1565-4ee0-ae1f-1e98974906aa-000000@email.amazonses.com
Fixes: 49dfc304ba241 ("slab: use the lock on alien_cache, instead of the lock on array_cache")
Fixes: c8522a3a5832b ("Slab: introduce alloc_alien")
Signed-off-by: Christoph Lameter 
Reported-by: syzbot+d6ed4ec679652b4fd4e4@syzkaller.appspotmail.com
Reviewed-by: Andrew Morton 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm, swap: fix swapoff with KSM pages

2019-01-13T09:01:02+00:00

commit 7af7a8e19f0c5425ff639b0f0d2d244c2a647724 upstream.

KSM pages may be mapped to the multiple VMAs that cannot be reached from
one anon_vma.  So during swapin, a new copy of the page need to be
generated if a different anon_vma is needed, please refer to comments of
ksm_might_need_to_copy() for details.

During swapoff, unuse_vma() uses anon_vma (if available) to locate VMA and
virtual address mapped to the page, so not all mappings to a swapped out
KSM page could be found.  So in try_to_unuse(), even if the swap count of
a swap entry isn't zero, the page needs to be deleted from swap cache, so
that, in the next round a new page could be allocated and swapin for the
other mappings of the swapped out KSM page.

But this contradicts with the THP swap support.  Where the THP could be
deleted from swap cache only after the swap count of every swap entry in
the huge swap cluster backing the THP has reach 0.  So try_to_unuse() is
changed in commit e07098294adf ("mm, THP, swap: support to reclaim swap
space for THP swapped out") to check that before delete a page from swap
cache, but this has broken KSM swapoff too.

Fortunately, KSM is for the normal pages only, so the original behavior
for KSM pages could be restored easily via checking PageTransCompound().
That is how this patch works.

The bug is introduced by e07098294adf ("mm, THP, swap: support to reclaim
swap space for THP swapped out"), which is merged by v4.14-rc1.  So I
think we should backport the fix to from 4.14 on.  But Hugh thinks it may
be rare for the KSM pages being in the swap device when swapoff, so nobody
reports the bug so far.

Link: http://lkml.kernel.org/r/20181226051522.28442-1-ying.huang@intel.com
Fixes: e07098294adf ("mm, THP, swap: support to reclaim swap space for THP swapped out")
Signed-off-by: "Huang, Ying" 
Reported-by: Hugh Dickins 
Tested-by: Hugh Dickins 
Acked-by: Hugh Dickins 
Cc: Rik van Riel 
Cc: Johannes Weiner 
Cc: Minchan Kim 
Cc: Shaohua Li 
Cc: Daniel Jordan 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm, hmm: mark hmm_devmem_{add, add_resource} EXPORT_SYMBOL_GPL

2019-01-13T09:01:02+00:00

commit 02917e9f8676207a4c577d4d94eae12bf348e9d7 upstream.

At Maintainer Summit, Greg brought up a topic I proposed around
EXPORT_SYMBOL_GPL usage.  The motivation was considerations for when
EXPORT_SYMBOL_GPL is warranted and the criteria for taking the exceptional
step of reclassifying an existing export.  Specifically, I wanted to make
the case that although the line is fuzzy and hard to specify in abstract
terms, it is nonetheless clear that devm_memremap_pages() and HMM
(Heterogeneous Memory Management) have crossed it.  The
devm_memremap_pages() facility should have been EXPORT_SYMBOL_GPL from the
beginning, and HMM as a derivative of that functionality should have
naturally picked up that designation as well.

Contrary to typical rules, the HMM infrastructure was merged upstream with
zero in-tree consumers.  There was a promise at the time that those users
would be merged "soon", but it has been over a year with no drivers
arriving.  While the Nouveau driver is about to belatedly make good on
that promise it is clear that HMM was targeted first and foremost at an
out-of-tree consumer.

HMM is derived from devm_memremap_pages(), a facility Christoph and I
spearheaded to support persistent memory.  It combines a device lifetime
model with a dynamically created 'struct page' / memmap array for any
physical address range.  It enables coordination and control of the many
code paths in the kernel built to interact with memory via 'struct page'
objects.  With HMM the integration goes even deeper by allowing device
drivers to hook and manipulate page fault and page free events.

One interpretation of when EXPORT_SYMBOL is suitable is when it is
exporting stable and generic leaf functionality.  The
devm_memremap_pages() facility continues to see expanding use cases,
peer-to-peer DMA being the most recent, with no clear end date when it
will stop attracting reworks and semantic changes.  It is not suitable to
export devm_memremap_pages() as a stable 3rd party driver API due to the
fact that it is still changing and manipulates core behavior.  Moreover,
it is not in the best interest of the long term development of the core
memory management subsystem to permit any external driver to effectively
define its own system-wide memory management policies with no
encouragement to engage with upstream.

I am also concerned that HMM was designed in a way to minimize further
engagement with the core-MM.  That, with these hooks in place,
device-drivers are free to implement their own policies without much
consideration for whether and how the core-MM could grow to meet that
need.  Going forward not only should HMM be EXPORT_SYMBOL_GPL, but the
core-MM should be allowed the opportunity and stimulus to change and
address these new use cases as first class functionality.

Original changelog:

hmm_devmem_add(), and hmm_devmem_add_resource() duplicated
devm_memremap_pages() and are now simple now wrappers around the core
facility to inject a dev_pagemap instance into the global pgmap_radix and
hook page-idle events.  The devm_memremap_pages() interface is base
infrastructure for HMM.  HMM has more and deeper ties into the kernel
memory management implementation than base ZONE_DEVICE which is itself a
EXPORT_SYMBOL_GPL facility.

Originally, the HMM page structure creation routines copied the
devm_memremap_pages() code and reused ZONE_DEVICE.  A cleanup to unify the
implementations was discussed during the initial review:
http://lkml.iu.edu/hypermail/linux/kernel/1701.2/00812.html Recent work to
extend devm_memremap_pages() for the peer-to-peer-DMA facility enabled
this cleanup to move forward.

In addition to the integration with devm_memremap_pages() HMM depends on
other GPL-only symbols:

    mmu_notifier_unregister_no_release
    percpu_ref
    region_intersects
    __class_create

It goes further to consume / indirectly expose functionality that is not
exported to any other driver:

    alloc_pages_vma
    walk_page_range

HMM is derived from devm_memremap_pages(), and extends deep core-kernel
fundamentals. Similar to devm_memremap_pages(), mark its entry points
EXPORT_SYMBOL_GPL().

[logang@deltatee.com: PCI/P2PDMA: match interface changes to devm_memremap_pages()]
  Link: http://lkml.kernel.org/r/20181130225911.2900-1-logang@deltatee.com
Link: http://lkml.kernel.org/r/154275560565.76910.15919297436557795278.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams 
Signed-off-by: Logan Gunthorpe 
Reviewed-by: Christoph Hellwig 
Cc: Logan Gunthorpe 
Cc: "Jérôme Glisse" 
Cc: Balbir Singh ,
Cc: Michal Hocko 
Cc: Benjamin Herrenschmidt 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm, hmm: use devm semantics for hmm_devmem_{add, remove}

2019-01-13T09:01:02+00:00

commit 58ef15b765af0d2cbe6799ec564f1dc485010ab8 upstream.

devm semantics arrange for resources to be torn down when
device-driver-probe fails or when device-driver-release completes.
Similar to devm_memremap_pages() there is no need to support an explicit
remove operation when the users properly adhere to devm semantics.

Note that devm_kzalloc() automatically handles allocating node-local
memory.

Link: http://lkml.kernel.org/r/154275559545.76910.9186690723515469051.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Jérôme Glisse 
Cc: "Jérôme Glisse" 
Cc: Logan Gunthorpe 
Cc: Balbir Singh 
Cc: Michal Hocko 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined

2019-01-13T09:01:02+00:00

commit b15c87263a69272423771118c653e9a1d0672caa upstream.

We have received a bug report that an injected MCE about faulty memory
prevents memory offline to succeed on 4.4 base kernel.  The underlying
reason was that the HWPoison page has an elevated reference count and the
migration keeps failing.  There are two problems with that.  First of all
it is dubious to migrate the poisoned page because we know that accessing
that memory is possible to fail.  Secondly it doesn't make any sense to
migrate a potentially broken content and preserve the memory corruption
over to a new location.

Oscar has found out that 4.4 and the current upstream kernels behave
slightly differently with his simply testcase

===

int main(void)
{
        int ret;
        int i;
        int fd;
        char *array = malloc(4096);
        char *array_locked = malloc(4096);

        fd = open("/tmp/data", O_RDONLY);
        read(fd, array, 4095);

        for (i = 0; i < 4096; i++)
                array_locked[i] = 'd';

        ret = mlock((void *)PAGE_ALIGN((unsigned long)array_locked), sizeof(array_locked));
        if (ret)
                perror("mlock");

        sleep (20);

        ret = madvise((void *)PAGE_ALIGN((unsigned long)array_locked), 4096, MADV_HWPOISON);
        if (ret)
                perror("madvise");

        for (i = 0; i < 4096; i++)
                array_locked[i] = 'd';

        return 0;
}
===

+ offline this memory.

In 4.4 kernels he saw the hwpoisoned page to be returned back to the LRU
list
kernel:  [] dump_trace+0x59/0x340
kernel:  [] show_stack_log_lvl+0xea/0x170
kernel:  [] show_stack+0x21/0x40
kernel:  [] dump_stack+0x5c/0x7c
kernel:  [] warn_slowpath_common+0x81/0xb0
kernel:  [] __pagevec_lru_add_fn+0x14c/0x160
kernel:  [] pagevec_lru_move_fn+0xad/0x100
kernel:  [] __lru_cache_add+0x6c/0xb0
kernel:  [] add_to_page_cache_lru+0x46/0x70
kernel:  [] extent_readpages+0xc3/0x1a0 [btrfs]
kernel:  [] __do_page_cache_readahead+0x177/0x200
kernel:  [] ondemand_readahead+0x168/0x2a0
kernel:  [] generic_file_read_iter+0x41f/0x660
kernel:  [] __vfs_read+0xcd/0x140
kernel:  [] vfs_read+0x7a/0x120
kernel:  [] kernel_read+0x3b/0x50
kernel:  [] do_execveat_common.isra.29+0x490/0x6f0
kernel:  [] do_execve+0x28/0x30
kernel:  [] call_usermodehelper_exec_async+0xfb/0x130
kernel:  [] ret_from_fork+0x55/0x80

And that latter confuses the hotremove path because an LRU page is
attempted to be migrated and that fails due to an elevated reference
count.  It is quite possible that the reuse of the HWPoisoned page is some
kind of fixed race condition but I am not really sure about that.

With the upstream kernel the failure is slightly different.  The page
doesn't seem to have LRU bit set but isolate_movable_page simply fails and
do_migrate_range simply puts all the isolated pages back to LRU and
therefore no progress is made and scan_movable_pages finds same set of
pages over and over again.

Fix both cases by explicitly checking HWPoisoned pages before we even try
to get reference on the page, try to unmap it if it is still mapped.  As
explained by Naoya:

: Hwpoison code never unmapped those for no big reason because
: Ksm pages never dominate memory, so we simply didn't have strong
: motivation to save the pages.

Also put WARN_ON(PageLRU) in case there is a race and we can hit LRU
HWPoison pages which shouldn't happen but I couldn't convince myself about
that.  Naoya has noted the following:

: Theoretically no such gurantee, because try_to_unmap() doesn't have a
: guarantee of success and then memory_failure() returns immediately
: when hwpoison_user_mappings fails.
: Or the following code (comes after hwpoison_user_mappings block) also impli=
: es
: that the target page can still have PageLRU flag.
:
:         /*
:          * Torn down by someone else?
:          */
:         if (PageLRU(p) && !PageSwapCache(p) && p->mapping =3D=3D NULL) {
:                 action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED);
:                 res =3D -EBUSY;
:                 goto out;
:         }
:
: So I think it's OK to keep "if (WARN_ON(PageLRU(page)))" block in
: current version of your patch.

Link: http://lkml.kernel.org/r/20181206120135.14079-1-mhocko@kernel.org
Signed-off-by: Michal Hocko 
Reviewed-by: Oscar Salvador 
Debugged-by: Oscar Salvador 
Tested-by: Oscar Salvador 
Acked-by: David Hildenbrand 
Acked-by: Naoya Horiguchi 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm: don't miss the last page because of round-off error

2018-12-29T12:39:11+00:00

commit 68600f623d69da428c6163275f97ca126e1a8ec5 upstream.

I've noticed, that dying memory cgroups are often pinned in memory by a
single pagecache page.  Even under moderate memory pressure they sometimes
stayed in such state for a long time.  That looked strange.

My investigation showed that the problem is caused by applying the LRU
pressure balancing math:

  scan = div64_u64(scan * fraction[lru], denominator),

where

  denominator = fraction[anon] + fraction[file] + 1.

Because fraction[lru] is always less than denominator, if the initial scan
size is 1, the result is always 0.

This means the last page is not scanned and has
no chances to be reclaimed.

Fix this by rounding up the result of the division.

In practice this change significantly improves the speed of dying cgroups
reclaim.

[guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments]
  Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle
Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com
Signed-off-by: Roman Gushchin 
Reviewed-by: Andrew Morton 
Cc: Johannes Weiner 
Cc: Michal Hocko 
Cc: Tejun Heo 
Cc: Rik van Riel 
Cc: Konstantin Khlebnikov 
Cc: Matthew Wilcox 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm/page_alloc.c: fix calculation of pgdat->nr_zones

2018-12-17T08:28:54+00:00

[ Upstream commit 8f416836c0d50b198cad1225132e5abebf8980dc ]

init_currently_empty_zone() will adjust pgdat->nr_zones and set it to
'zone_idx(zone) + 1' unconditionally.  This is correct in the normal
case, while not exact in hot-plug situation.

This function is used in two places:

  * free_area_init_core()
  * move_pfn_range_to_zone()

In the first case, we are sure zone index increase monotonically.  While
in the second one, this is under users control.

One way to reproduce this is:
----------------------------

1. create a virtual machine with empty node1

   -m 4G,slots=32,maxmem=32G \
   -smp 4,maxcpus=8          \
   -numa node,nodeid=0,mem=4G,cpus=0-3 \
   -numa node,nodeid=1,mem=0G,cpus=4-7

2. hot-add cpu 3-7

   cpu-add [3-7]

2. hot-add memory to nod1

   object_add memory-backend-ram,id=ram0,size=1G
   device_add pc-dimm,id=dimm0,memdev=ram0,node=1

3. online memory with following order

   echo online_movable > memory47/state
   echo online > memory40/state

After this, node1 will have its nr_zones equals to (ZONE_NORMAL + 1)
instead of (ZONE_MOVABLE + 1).

Michal said:
 "Having an incorrect nr_zones might result in all sorts of problems
  which would be quite hard to debug (e.g. reclaim not considering the
  movable zone). I do not expect many users would suffer from this it
  but still this is trivial and obviously right thing to do so
  backporting to the stable tree shouldn't be harmful (last famous
  words)"

Link: http://lkml.kernel.org/r/20181117022022.9956-1-richard.weiyang@gmail.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")
Signed-off-by: Wei Yang 
Acked-by: Michal Hocko 
Reviewed-by: Oscar Salvador 
Cc: Anshuman Khandual 
Cc: Dave Hansen 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 

Signed-off-by: Sasha Levin

mm: don't warn about allocations which stall for too long

2018-12-13T08:18:50+00:00

[ Upstream commit 400e22499dd92613821374c8c6c88c7225359980 ]

Commit 63f53dea0c98 ("mm: warn about allocations which stall for too
long") was a great step for reducing possibility of silent hang up
problem caused by memory allocation stalls.  But this commit reverts it,
for it is possible to trigger OOM lockup and/or soft lockups when many
threads concurrently called warn_alloc() (in order to warn about memory
allocation stalls) due to current implementation of printk(), and it is
difficult to obtain useful information due to limitation of synchronous
warning approach.

Current printk() implementation flushes all pending logs using the
context of a thread which called console_unlock().  printk() should be
able to flush all pending logs eventually unless somebody continues
appending to printk() buffer.

Since warn_alloc() started appending to printk() buffer while waiting
for oom_kill_process() to make forward progress when oom_kill_process()
is processing pending logs, it became possible for warn_alloc() to force
oom_kill_process() loop inside printk().  As a result, warn_alloc()
significantly increased possibility of preventing oom_kill_process()
from making forward progress.

---------- Pseudo code start ----------
Before warn_alloc() was introduced:

  retry:
    if (mutex_trylock(&oom_lock)) {
      while (atomic_read(&printk_pending_logs) > 0) {
        atomic_dec(&printk_pending_logs);
        print_one_log();
      }
      // Send SIGKILL here.
      mutex_unlock(&oom_lock)
    }
    goto retry;

After warn_alloc() was introduced:

  retry:
    if (mutex_trylock(&oom_lock)) {
      while (atomic_read(&printk_pending_logs) > 0) {
        atomic_dec(&printk_pending_logs);
        print_one_log();
      }
      // Send SIGKILL here.
      mutex_unlock(&oom_lock)
    } else if (waited_for_10seconds()) {
      atomic_inc(&printk_pending_logs);
    }
    goto retry;
---------- Pseudo code end ----------

Although waited_for_10seconds() becomes true once per 10 seconds,
unbounded number of threads can call waited_for_10seconds() at the same
time.  Also, since threads doing waited_for_10seconds() keep doing
almost busy loop, the thread doing print_one_log() can use little CPU
resource.  Therefore, this situation can be simplified like

---------- Pseudo code start ----------
  retry:
    if (mutex_trylock(&oom_lock)) {
      while (atomic_read(&printk_pending_logs) > 0) {
        atomic_dec(&printk_pending_logs);
        print_one_log();
      }
      // Send SIGKILL here.
      mutex_unlock(&oom_lock)
    } else {
      atomic_inc(&printk_pending_logs);
    }
    goto retry;
---------- Pseudo code end ----------

when printk() is called faster than print_one_log() can process a log.

One of possible mitigation would be to introduce a new lock in order to
make sure that no other series of printk() (either oom_kill_process() or
warn_alloc()) can append to printk() buffer when one series of printk()
(either oom_kill_process() or warn_alloc()) is already in progress.

Such serialization will also help obtaining kernel messages in readable
form.

---------- Pseudo code start ----------
  retry:
    if (mutex_trylock(&oom_lock)) {
      mutex_lock(&oom_printk_lock);
      while (atomic_read(&printk_pending_logs) > 0) {
        atomic_dec(&printk_pending_logs);
        print_one_log();
      }
      // Send SIGKILL here.
      mutex_unlock(&oom_printk_lock);
      mutex_unlock(&oom_lock)
    } else {
      if (mutex_trylock(&oom_printk_lock)) {
        atomic_inc(&printk_pending_logs);
        mutex_unlock(&oom_printk_lock);
      }
    }
    goto retry;
---------- Pseudo code end ----------

But this commit does not go that direction, for we don't want to
introduce a new lock dependency, and we unlikely be able to obtain
useful information even if we serialized oom_kill_process() and
warn_alloc().

Synchronous approach is prone to unexpected results (e.g.  too late [1],
too frequent [2], overlooked [3]).  As far as I know, warn_alloc() never
helped with providing information other than "something is going wrong".
I want to consider asynchronous approach which can obtain information
during stalls with possibly relevant threads (e.g.  the owner of
oom_lock and kswapd-like threads) and serve as a trigger for actions
(e.g.  turn on/off tracepoints, ask libvirt daemon to take a memory dump
of stalling KVM guest for diagnostic purpose).

This commit temporarily loses ability to report e.g.  OOM lockup due to
unable to invoke the OOM killer due to !__GFP_FS allocation request.
But asynchronous approach will be able to detect such situation and emit
warning.  Thus, let's remove warn_alloc().

[1] https://bugzilla.kernel.org/show_bug.cgi?id=192981
[2] http://lkml.kernel.org/r/CAM_iQpWuPVGc2ky8M-9yukECtS+zKjiDasNymX7rMcBjBFyM_A@mail.gmail.com
[3] commit db73ee0d46379922 ("mm, vmscan: do not loop on too_many_isolated for ever"))

Link: http://lkml.kernel.org/r/1509017339-4802-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp
Signed-off-by: Tetsuo Handa 
Reported-by: Cong Wang 
Reported-by: yuwang.yuwang 
Reported-by: Johannes Weiner 
Acked-by: Michal Hocko 
Acked-by: Johannes Weiner 
Cc: Vlastimil Babka 
Cc: Mel Gorman 
Cc: Dave Hansen 
Cc: Sergey Senozhatsky 
Cc: Petr Mladek 
Cc: Steven Rostedt 
Signed-off-by: Andrew Morton 

Signed-off-by: Linus Torvalds 

Signed-off-by: Sasha Levin