linux.git/mm/page_alloc.c, branch v5.19

page_alloc: fix invalid watermark check on a negative value

2022-07-29T18:33:37+00:00

There was a report that a task is waiting at the
throttle_direct_reclaim. The pgscan_direct_throttle in vmstat was
increasing.

This is a bug where zone_watermark_fast returns true even when the free
is very low. The commit f27ce0e14088 ("page_alloc: consider highatomic
reserve in watermark fast") changed the watermark fast to consider
highatomic reserve. But it did not handle a negative value case which
can be happened when reserved_highatomic pageblock is bigger than the
actual free.

If watermark is considered as ok for the negative value, allocating
contexts for order-0 will consume all free pages without direct reclaim,
and finally free page may become depleted except highatomic free.

Then allocating contexts may fall into throttle_direct_reclaim. This
symptom may easily happen in a system where wmark min is low and other
reclaimers like kswapd does not make free pages quickly.

Handle the negative case by using MIN.

Link: https://lkml.kernel.org/r/20220725095212.25388-1-jaewon31.kim@samsung.com
Fixes: f27ce0e14088 ("page_alloc: consider highatomic reserve in watermark fast")
Signed-off-by: Jaewon Kim 
Reported-by: GyeongHwan Hong 
Acked-by: Mel Gorman 
Cc: Minchan Kim 
Cc: Baoquan He 
Cc: Vlastimil Babka 
Cc: Johannes Weiner 
Cc: Michal Hocko 
Cc: Yong-Taek Lee 
Cc: 
Signed-off-by: Andrew Morton

Merge tag 'mm-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2022-05-27T18:40:49+00:00

Pull more MM updates from Andrew Morton:

 - Two follow-on fixes for the post-5.19 series "Use pageblock_order for
   cma and alloc_contig_range alignment", from Zi Yan.

 - A series of z3fold cleanups and fixes from Miaohe Lin.

 - Some memcg selftests work from Michal Koutný 

 - Some swap fixes and cleanups from Miaohe Lin

 - Several individual minor fixups

* tag 'mm-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (25 commits)
  mm/shmem.c: suppress shift warning
  mm: Kconfig: reorganize misplaced mm options
  mm: kasan: fix input of vmalloc_to_page()
  mm: fix is_pinnable_page against a cma page
  mm: filter out swapin error entry in shmem mapping
  mm/shmem: fix infinite loop when swap in shmem error at swapoff time
  mm/madvise: free hwpoison and swapin error entry in madvise_free_pte_range
  mm/swapfile: fix lost swap bits in unuse_pte()
  mm/swapfile: unuse_pte can map random data if swap read fails
  selftests: memcg: factor out common parts of memory.{low,min} tests
  selftests: memcg: remove protection from top level memcg
  selftests: memcg: adjust expected reclaim values of protected cgroups
  selftests: memcg: expect no low events in unprotected sibling
  selftests: memcg: fix compilation
  mm/z3fold: fix z3fold_page_migrate races with z3fold_map
  mm/z3fold: fix z3fold_reclaim_page races with z3fold_free
  mm/z3fold: always clear PAGE_CLAIMED under z3fold page lock
  mm/z3fold: put z3fold page back into unbuddied list when reclaim or migration fails
  revert "mm/z3fold.c: allow __GFP_HIGHMEM in z3fold_alloc"
  mm/z3fold: throw warning on failure of trylock_page in z3fold_alloc
  ...

Merge tag 'mm-hotfixes-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2022-05-27T18:29:35+00:00

Pull hotfixes from Andrew Morton:
 "Six hotfixes.

  The page_table_check one from Miaohe Lin is considered a minor thing
  so it isn't marked for -stable. The remainder address pre-5.19 issues
  and are cc:stable"

* tag 'mm-hotfixes-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/page_table_check: fix accessing unmapped ptep
  kexec_file: drop weak attribute from arch_kexec_apply_relocations[_add]
  mm/page_alloc: always attempt to allocate at least one page during bulk allocation
  hugetlb: fix huge_pmd_unshare address update
  zsmalloc: fix races between asynchronous zspage free and page migration
  Revert "mm/cma.c: remove redundant cma_mutex lock"

mm: fix is_pinnable_page against a cma page

2022-05-27T16:33:46+00:00

Pages in the CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA so
the current is_pinnable_page() could miss CMA pages which have
MIGRATE_ISOLATE.  It ends up pinning CMA pages as longterm for the
pin_user_pages() API so CMA allocations keep failing until the pin is
released.

     CPU 0                                   CPU 1 - Task B

cma_alloc
alloc_contig_range
                                        pin_user_pages_fast(FOLL_LONGTERM)
change pageblock as MIGRATE_ISOLATE
                                        internal_get_user_pages_fast
                                        lockless_pages_from_mm
                                        gup_pte_range
                                        try_grab_folio
                                        is_pinnable_page
                                          return true;
                                        So, pinned the page successfully.
page migration failure with pinned page
                                        ..
                                        .. After 30 sec
                                        unpin_user_page(page)

CMA allocation succeeded after 30 sec.

The CMA allocation path protects the migration type change race using
zone->lock but what GUP path need to know is just whether the page is on
CMA area or not rather than exact migration type.  Thus, we don't need
zone->lock but just checks migration type in either of (MIGRATE_ISOLATE
and MIGRATE_CMA).

Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause rejecting
of pinning pages on MIGRATE_ISOLATE pageblocks even though it's neither
CMA nor movable zone if the page is temporarily unmovable.  However, such
a migration failure by unexpected temporal refcount holding is general
issue, not only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also
transient state like other temporal elevated refcount problem.

Link: https://lkml.kernel.org/r/20220524171525.976723-1-minchan@kernel.org
Signed-off-by: Minchan Kim 
Reviewed-by: John Hubbard 
Acked-by: Paul E. McKenney 
Cc: David Hildenbrand 
Signed-off-by: Andrew Morton

mm: split free page with properly free memory accounting and without race

2022-05-27T16:33:43+00:00

In isolate_single_pageblock(), free pages are checked without holding zone
lock, but they can go away in split_free_page() when zone lock is held.
Check the free page and its order again in split_free_page() when zone lock
is held. Recheck the page if the free page is gone under zone lock.

In addition, in split_free_page(), the free page was deleted from the page
list without changing free page accounting. Add the missing free page
accounting code.

Fix the type of order parameter in split_free_page().

Link: https://lore.kernel.org/lkml/20220525103621.987185e2ca0079f7b97b856d@linux-foundation.org/
Link: https://lkml.kernel.org/r/20220526231531.2404977-2-zi.yan@sent.com
Fixes: b2c9e2fbba32 ("mm: make alloc_contig_range work at pageblock granularity")
Signed-off-by: Zi Yan 
Reported-by: Doug Berger 
  Link: https://lore.kernel.org/linux-mm/c3932a6f-77fe-29f7-0c29-fe6b1c67ab7b@gmail.com/
Cc: David Hildenbrand 
Cc: Qian Cai 
Cc: Vlastimil Babka 
Cc: Mel Gorman 
Cc: Eric Ren 
Cc: Mike Rapoport 
Cc: Oscar Salvador 
Cc: Christophe Leroy 
Cc: Marek Szyprowski 
Cc: Michael Walle 
Signed-off-by: Andrew Morton

mm/page_alloc: always attempt to allocate at least one page during bulk allocation

2022-05-27T15:55:17+00:00

Peter Pavlisko reported the following problem on kernel bugzilla 216007.

	When I try to extract an uncompressed tar archive (2.6 milion
	files, 760.3 GiB in size) on newly created (empty) XFS file system,
	after first low tens of gigabytes extracted the process hangs in
	iowait indefinitely. One CPU core is 100% occupied with iowait,
	the other CPU core is idle (on 2-core Intel Celeron G1610T).

It was bisected to c9fa563072e1 ("xfs: use alloc_pages_bulk_array() for
buffers") but XFS is only the messenger.  The problem is that nothing is
waking kswapd to reclaim some pages at a time the PCP lists cannot be
refilled until some reclaim happens.  The bulk allocator checks that there
are some pages in the array and the original intent was that a bulk
allocator did not necessarily need all the requested pages and it was best
to return as quickly as possible.

This was fine for the first user of the API but both NFS and XFS require
the requested number of pages be available before making progress.  Both
could be adjusted to call the page allocator directly if a bulk allocation
fails but it puts a burden on users of the API.  Adjust the semantics to
attempt at least one allocation via __alloc_pages() before returning so
kswapd is woken if necessary.

It was reported via bugzilla that the patch addressed the problem and that
the tar extraction completed successfully.  This may also address bug
215975 but has yet to be confirmed.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=216007
BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215975
Link: https://lkml.kernel.org/r/20220526091210.GC3441@techsingularity.net
Fixes: 387ba26fb1cb ("mm/page_alloc: add a bulk page allocator")
Signed-off-by: Mel Gorman 
Cc: "Darrick J. Wong" 
Cc: Dave Chinner 
Cc: Jan Kara 
Cc: Vlastimil Babka 
Cc: Jesper Dangaard Brouer 
Cc: Chuck Lever 
Cc: 	[5.13+]
Signed-off-by: Andrew Morton

mm: fix a potential infinite loop in start_isolate_page_range()

2022-05-25T17:47:47+00:00

In isolate_single_pageblock() called by start_isolate_page_range(), there
are some pageblock isolation issues causing a potential infinite loop when
isolating a page range.  This is reported by Qian Cai.

1. the pageblock was isolated by just changing pageblock migratetype
   without checking unmovable pages. Calling set_migratetype_isolate() to
   isolate pageblock properly.
2. an off-by-one error caused migrating pages unnecessarily, since the page
   is not crossing pageblock boundary.
3. migrating a compound page across pageblock boundary then splitting the
   free page later has a small race window that the free page might be
   allocated again, so that the code will try again, causing an potential
   infinite loop. Temporarily set the to-be-migrated page's pageblock to
   MIGRATE_ISOLATE to prevent that and bail out early if no free page is
   found after page migration.

An additional fix to split_free_page() aims to avoid crashing in
__free_one_page().  When the free page is split at the specified
split_pfn_offset, free_page_order should check both the first bit of
free_page_pfn and the last bit of split_pfn_offset and use the smaller
one.  For example, if free_page_pfn=0x10000, split_pfn_offset=0xc000,
free_page_order should first be 0x8000 then 0x4000, instead of 0x4000 then
0x8000, which the original algorithm did.

[akpm@linux-foundation.org: suppress min() warning]
Link: https://lkml.kernel.org/r/20220524194756.1698351-1-zi.yan@sent.com
Fixes: b2c9e2fbba3253 ("mm: make alloc_contig_range work at pageblock granularity")
Signed-off-by: Zi Yan 
Reported-by: Qian Cai 
Cc: Christophe Leroy 
Cc: David Hildenbrand 
Cc: Eric Ren 
Cc: Mel Gorman 
Cc: Mike Rapoport 
Cc: Minchan Kim 
Cc: Oscar Salvador 
Cc: Vlastimil Babka 
Signed-off-by: Andrew Morton

mm: fix missing handler for __GFP_NOWARN

2022-05-19T21:08:55+00:00

We expect no warnings to be issued when we specify __GFP_NOWARN, but
currently in paths like alloc_pages() and kmalloc(), there are still some
warnings printed, fix it.

But for some warnings that report usage problems, we don't deal with them.
If such warnings are printed, then we should fix the usage problems. 
Such as the following case:

	WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));

[zhengqi.arch@bytedance.com: v2]
 Link: https://lkml.kernel.org/r/20220511061951.1114-1-zhengqi.arch@bytedance.com
Link: https://lkml.kernel.org/r/20220510113809.80626-1-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng 
Cc: Akinobu Mita 
Cc: Vlastimil Babka 
Cc: Greg Kroah-Hartman 
Cc: Jiri Slaby 
Cc: Steven Rostedt (Google) 
Signed-off-by: Andrew Morton

mm/page_alloc: fix tracepoint mm_page_alloc_zone_locked()

2022-05-19T21:08:54+00:00

Currently, trace point mm_page_alloc_zone_locked() doesn't show correct
information.

First, when alloc_flag has ALLOC_HARDER/ALLOC_CMA, page can be allocated
from MIGRATE_HIGHATOMIC/MIGRATE_CMA.  Nevertheless, tracepoint use
requested migration type not MIGRATE_HIGHATOMIC and MIGRATE_CMA.

Second, after commit 44042b4498728 ("mm/page_alloc: allow high-order pages
to be stored on the per-cpu lists") percpu-list can store high order
pages.  But trace point determine whether it is a refiil of percpu-list by
comparing requested order and 0.

To handle these problems, make mm_page_alloc_zone_locked() only be called
by __rmqueue_smallest with correct migration type.  With a new argument
called percpu_refill, it can show roughly whether it is a refill of
percpu-list.

Link: https://lkml.kernel.org/r/20220512025307.57924-1-vvghjk1234@gmail.com
Signed-off-by: Wonhyuk Yang 
Acked-by: Mel Gorman 
Cc: Baik Song An 
Cc: Hong Yeon Kim 
Cc: Taeung Song 
Cc: 
Cc: Steven Rostedt 
Cc: Ingo Molnar 
Signed-off-by: Andrew Morton

mm/memory-failure.c: simplify num_poisoned_pages_dec

2022-05-13T14:20:19+00:00

Don't decrease the number of poisoned pages in page_alloc.c, let the
memory-failure.c do inc/dec poisoned pages only.

Also simplify unpoison_memory(), only decrease the number of
poisoned pages when:
 - TestClearPageHWPoison() succeed
 - put_page_back_buddy succeed

After decreasing, print necessary log.

Finally, remove clear_page_hwpoison() and unpoison_taken_off_page().

Link: https://lkml.kernel.org/r/20220509105641.491313-3-pizhenwei@bytedance.com
Signed-off-by: zhenwei pi 
Acked-by: Naoya Horiguchi 
Signed-off-by: Andrew Morton