linux-2.6-block.git
3 years agomm/migration: add trace events for THP migrations
Anshuman Khandual [Mon, 28 Feb 2022 23:05:42 +0000 (10:05 +1100)]
mm/migration: add trace events for THP migrations

Patch series "mm/migration: Add trace events", v3.

This adds trace events for all migration scenarios including base page,
THP and HugeTLB.

This patch (of 3):

This adds two trace events for PMD based THP migration without split.
These events closely follow the implementation details like setting and
removing of PMD migration entries, which are essential operations for THP
migration.  This moves CREATE_TRACE_POINTS into generic THP from powerpc
for these new trace events to be available on other platforms as well.

Link: https://lkml.kernel.org/r/1643368182-9588-1-git-send-email-anshuman.khandual@arm.com
Link: https://lkml.kernel.org/r/1643368182-9588-2-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
3 years agomm-fix-race-between-madv_free-reclaim-and-blkdev-direct-io-read-v4
Mauricio Faria de Oliveira [Mon, 28 Feb 2022 23:05:38 +0000 (10:05 +1100)]
mm-fix-race-between-madv_free-reclaim-and-blkdev-direct-io-read-v4

v4: - fixed Fixes: tag to first support, after tests on v4.5;
      updated commit message/reproducer section with results.
    - tested on v5.17-rc3 and v4.5.
    - shorten comment line; remove inner braces in the check.
      (Thanks: Christoph Hellwig <hch@infradead.org>)
    - clarify comment about __remove_mapping()
      (Thanks: Yu Zhao <yuzhao@google.com>)

Link: https://lkml.kernel.org/r/20220209202659.183418-1-mfo@canonical.com
Fixes: 854e9ed09ded ("mm: support madvise(MADV_FREE)")
Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Dan Hill <daniel.hill@canonical.com>
Cc: Dan Streetman <dan.streetman@canonical.com>
Cc: Dongdong Tao <dongdong.tao@canonical.com>
Cc: Gavin Guo <gavin.guo@canonical.com>
Cc: Gerald Yang <gerald.yang@canonical.com>
Cc: Heitor Alves de Siqueira <halves@canonical.com>
Cc: Ioanna Alifieraki <ioanna-maria.alifieraki@canonical.com>
Cc: Jay Vosburgh <jay.vosburgh@canonical.com>
Cc: Matthew Ruffell <matthew.ruffell@canonical.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Ponnuvel Palaniyappan <ponnuvel.palaniyappan@canonical.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
3 years agomm: fix race between MADV_FREE reclaim and blkdev direct IO read
Mauricio Faria de Oliveira [Mon, 28 Feb 2022 23:05:37 +0000 (10:05 +1100)]
mm: fix race between MADV_FREE reclaim and blkdev direct IO read

Problem:
=======

Userspace might read the zero-page instead of actual data from a direct IO
read on a block device if the buffers have been called madvise(MADV_FREE)
on earlier (this is discussed below) due to a race between page reclaim on
MADV_FREE and blkdev direct IO read.

- Race condition:
  ==============

During page reclaim, the MADV_FREE page check in try_to_unmap_one() checks
if the page is not dirty, then discards its rmap PTE(s) (vs.  remap back
if the page is dirty).

However, after try_to_unmap_one() returns to shrink_page_list(), it might
keep the page _anyway_ if page_ref_freeze() fails (it expects exactly
_one_ page reference, from the isolation for page reclaim).

Well, blkdev_direct_IO() gets references for all pages, and on READ
operations it only sets them dirty _later_.

So, if MADV_FREE'd pages (i.e., not dirty) are used as buffers for direct
IO read from block devices, and page reclaim happens during
__blkdev_direct_IO[_simple]() exactly AFTER bio_iov_iter_get_pages()
returns, but BEFORE the pages are set dirty, the situation happens.

The direct IO read eventually completes.  Now, when userspace reads the
buffers, the PTE is no longer there and the page fault handler
do_anonymous_page() services that with the zero-page, NOT the data!

A synthetic reproducer is provided.

- Page faults:
  ===========

If page reclaim happens BEFORE bio_iov_iter_get_pages() the issue doesn't
happen, because that faults-in all pages as writeable, so
do_anonymous_page() sets up a new page/rmap/PTE, and that is used by
direct IO.  The userspace reads don't fault as the PTE is there (thus
zero-page is not used/setup).

But if page reclaim happens AFTER it / BEFORE setting pages dirty, the PTE
is no longer there; the subsequent page faults can't help:

The data-read from the block device probably won't generate faults due to
DMA (no MMU) but even in the case it wouldn't use DMA, that happens on
different virtual addresses (not user-mapped addresses) because `struct
bio_vec` stores `struct page` to figure addresses out (which are different
from user-mapped addresses) for the read.

Thus userspace reads (to user-mapped addresses) still fault, then
do_anonymous_page() gets another `struct page` that would address/ map to
other memory than the `struct page` used by `struct bio_vec` for the read.
(The original `struct page` is not available, since it wasn't freed, as
page_ref_freeze() failed due to more page refs.  And even if it were
available, its data cannot be trusted anymore.)

Solution:
========

One solution is to check for the expected page reference count in
try_to_unmap_one().

There should be one reference from the isolation (that is also checked in
shrink_page_list() with page_ref_freeze()) plus one or more references
from page mapping(s) (put in discard: label).  Further references mean
that rmap/PTE cannot be unmapped/nuked.

(Note: there might be more than one reference from mapping due to
fork()/clone() without CLONE_VM, which use the same `struct page` for
references, until the copy-on-write page gets copied.)

So, additional page references (e.g., from direct IO read) now prevent the
rmap/PTE from being unmapped/dropped; similarly to the page is not freed
per shrink_page_list()/page_ref_freeze()).

- Races and Barriers:
  ==================

The new check in try_to_unmap_one() should be safe in races with
bio_iov_iter_get_pages() in get_user_pages() fast and slow paths, as it's
done under the PTE lock.

The fast path doesn't take the lock, but it checks if the PTE has changed
and if so, it drops the reference and leaves the page for the slow path
(which does take that lock).

The fast path requires synchronization w/ full memory barrier: it writes
the page reference count first then it reads the PTE later, while
try_to_unmap() writes PTE first then it reads page refcount.

And a second barrier is needed, as the page dirty flag should not be read
before the page reference count (as in __remove_mapping()).  (This can be
a load memory barrier only; no writes are involved.)

Call stack/comments:

- try_to_unmap_one()
  - page_vma_mapped_walk()
    - map_pte() # see pte_offset_map_lock():
        pte_offset_map()
        spin_lock()

  - ptep_get_and_clear() # write PTE
  - smp_mb() # (new barrier) GUP fast path
  - page_ref_count() # (new check) read refcount

  - page_vma_mapped_walk_done() # see pte_unmap_unlock():
      pte_unmap()
      spin_unlock()

- bio_iov_iter_get_pages()
  - __bio_iov_iter_get_pages()
    - iov_iter_get_pages()
      - get_user_pages_fast()
        - internal_get_user_pages_fast()

          # fast path
          - lockless_pages_from_mm()
            - gup_{pgd,p4d,pud,pmd,pte}_range()
                ptep = pte_offset_map() # not _lock()
                pte = ptep_get_lockless(ptep)

                page = pte_page(pte)
                try_grab_compound_head(page) # inc refcount
                                             # (RMW/barrier
                                              #  on success)

                if (pte_val(pte) != pte_val(*ptep)) # read PTE
                        put_compound_head(page) # dec refcount
                         # go slow path

          # slow path
          - __gup_longterm_unlocked()
            - get_user_pages_unlocked()
              - __get_user_pages_locked()
                - __get_user_pages()
                  - follow_{page,p4d,pud,pmd}_mask()
                    - follow_page_pte()
                        ptep = pte_offset_map_lock()
                        pte = *ptep
                        page = vm_normal_page(pte)
                        try_grab_page(page) # inc refcount
                        pte_unmap_unlock()

- Huge Pages:
  ==========

Regarding transparent hugepages, that logic shouldn't change, as MADV_FREE
(aka lazyfree) pages are PageAnon() && !PageSwapBacked()
(madvise_free_pte_range() -> mark_page_lazyfree() -> lru_lazyfree_fn())
thus should reach shrink_page_list() -> split_huge_page_to_list() before
try_to_unmap[_one](), so it deals with normal pages only.

(And in case unlikely/TTU_SPLIT_HUGE_PMD/split_huge_pmd_address() happens,
which should not or be rare, the page refcount should be greater than
mapcount: the head page is referenced by tail pages.  That also prevents
checking the head `page` then incorrectly call page_remove_rmap(subpage)
for a tail page, that isn't even in the shrink_page_list()'s page_list (an
effect of split huge pmd/pmvw), as it might happen today in this unlikely
scenario.)

MADV_FREE'd buffers:
===================

So, back to the "if MADV_FREE pages are used as buffers" note.  The case
is arguable, and subject to multiple interpretations.

The madvise(2) manual page on the MADV_FREE advice value says:

1) 'After a successful MADV_FREE ... data will be lost when
   the kernel frees the pages.'
2) 'the free operation will be canceled if the caller writes
   into the page' / 'subsequent writes ... will succeed and
   then [the] kernel cannot free those dirtied pages'
3) 'If there is no subsequent write, the kernel can free the
   pages at any time.'

Thoughts, questions, considerations... respectively:

1) Since the kernel didn't actually free the page (page_ref_freeze()
   failed), should the data not have been lost? (on userspace read.)
2) Should writes performed by the direct IO read be able to cancel
   the free operation?
   - Should the direct IO read be considered as 'the caller' too,
     as it's been requested by 'the caller'?
   - Should the bio technique to dirty pages on return to userspace
     (bio_check_pages_dirty() is called/used by __blkdev_direct_IO())
     be considered in another/special way here?
3) Should an upcoming write from a previously requested direct IO
   read be considered as a subsequent write, so the kernel should
   not free the pages? (as it's known at the time of page reclaim.)

And lastly:

Technically, the last point would seem a reasonable consideration and
balance, as the madvise(2) manual page apparently (and fairly) seem to
assume that 'writes' are memory access from the userspace process (not
explicitly considering writes from the kernel or its corner cases; again,
fairly)..  plus the kernel fix implementation for the corner case of the
largely 'non-atomic write' encompassed by a direct IO read operation, is
relatively simple; and it helps.

Reproducer:
==========

@ test.c (simplified, but works)

#define _GNU_SOURCE
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/mman.h>

int main() {
int fd, i;
char *buf;

fd = open(DEV, O_RDONLY | O_DIRECT);

buf = mmap(NULL, BUF_SIZE, PROT_READ | PROT_WRITE,
                    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);

for (i = 0; i < BUF_SIZE; i += PAGE_SIZE)
buf[i] = 1; // init to non-zero

madvise(buf, BUF_SIZE, MADV_FREE);

read(fd, buf, BUF_SIZE);

for (i = 0; i < BUF_SIZE; i += PAGE_SIZE)
printf("%p: 0x%x\n", &buf[i], buf[i]);

return 0;
}

@ block/fops.c (formerly fs/block_dev.c)

+#include <linux/swap.h>
...
... __blkdev_direct_IO[_simple](...)
{
...
+ if (!strcmp(current->comm, "good"))
+ shrink_all_memory(ULONG_MAX);
+
          ret = bio_iov_iter_get_pages(...);
+
+ if (!strcmp(current->comm, "bad"))
+ shrink_all_memory(ULONG_MAX);
...
}

@ shell

        # NUM_PAGES=4
        # PAGE_SIZE=$(getconf PAGE_SIZE)

        # yes | dd of=test.img bs=${PAGE_SIZE} count=${NUM_PAGES}
        # DEV=$(losetup -f --show test.img)

        # gcc -DDEV=\"$DEV\" \
              -DBUF_SIZE=$((PAGE_SIZE * NUM_PAGES)) \
              -DPAGE_SIZE=${PAGE_SIZE} \
               test.c -o test

        # od -tx1 $DEV
        0000000 79 0a 79 0a 79 0a 79 0a 79 0a 79 0a 79 0a 79 0a
        *
        0040000

        # mv test good
        # ./good
        0x7f7c10418000: 0x79
        0x7f7c10419000: 0x79
        0x7f7c1041a000: 0x79
        0x7f7c1041b000: 0x79

        # mv good bad
        # ./bad
        0x7fa1b8050000: 0x0
        0x7fa1b8051000: 0x0
        0x7fa1b8052000: 0x0
        0x7fa1b8053000: 0x0

Note: the issue is consistent on v5.17-rc3, but it's intermittent with the
support of MADV_FREE on v4.5 (60%-70% error; needs swap).  [wrap
do_direct_IO() in do_blockdev_direct_IO() @ fs/direct-io.c].

- v5.17-rc3:

        # for i in {1..1000}; do ./good; done \
            | cut -d: -f2 | sort | uniq -c
           4000  0x79

        # mv good bad
        # for i in {1..1000}; do ./bad; done \
            | cut -d: -f2 | sort | uniq -c
           4000  0x0

        # free | grep Swap
        Swap:             0           0           0

- v4.5:

        # for i in {1..1000}; do ./good; done \
            | cut -d: -f2 | sort | uniq -c
           4000  0x79

        # mv good bad
        # for i in {1..1000}; do ./bad; done \
            | cut -d: -f2 | sort | uniq -c
           2702  0x0
           1298  0x79

        # swapoff -av
        swapoff /swap

        # for i in {1..1000}; do ./bad; done \
            | cut -d: -f2 | sort | uniq -c
           4000  0x79

Ceph/TCMalloc:
=============

For documentation purposes, the use case driving the analysis/fix is Ceph
on Ubuntu 18.04, as the TCMalloc library there still uses MADV_FREE to
release unused memory to the system from the mmap'ed page heap (might be
committed back/used again; it's not munmap'ed.) - PageHeap::DecommitSpan()
-> TCMalloc_SystemRelease() -> madvise() - PageHeap::CommitSpan() ->
TCMalloc_SystemCommit() -> do nothing.

Note: TCMalloc switched back to MADV_DONTNEED a few commits after the
release in Ubuntu 18.04 (google-perftools/gperftools 2.5), so the issue
just 'disappeared' on Ceph on later Ubuntu releases but is still present
in the kernel, and can be hit by other use cases.

The observed issue seems to be the old Ceph bug #22464 [1], where checksum
mismatches are observed (and instrumentation with buffer dumps shows
zero-pages read from mmap'ed/MADV_FREE'd page ranges).

The issue in Ceph was reasonably deemed a kernel bug (comment #50) and
mostly worked around with a retry mechanism, but other parts of Ceph could
still hit that (rocksdb).  Anyway, it's less likely to be hit again as
TCMalloc switched out of MADV_FREE by default.

(Some kernel versions/reports from the Ceph bug, and relation with
the MADV_FREE introduction/changes; TCMalloc versions not checked.)
- 4.4 good
- 4.5 (madv_free: introduction)
- 4.9 bad
- 4.10 good? maybe a swapless system
- 4.12 (madv_free: no longer free instantly on swapless systems)
- 4.13 bad

[1] https://tracker.ceph.com/issues/22464

Thanks:
======

Several people contributed to analysis/discussions/tests/reproducers in
the first stages when drilling down on ceph/tcmalloc/linux kernel:

- Dan Hill
- Dan Streetman
- Dongdong Tao
- Gavin Guo
- Gerald Yang
- Heitor Alves de Siqueira
- Ioanna Alifieraki
- Jay Vosburgh
- Matthew Ruffell
- Ponnuvel Palaniyappan

Reviews, suggestions, corrections, comments:

- Minchan Kim
- Yu Zhao
- Huang, Ying
- John Hubbard
- Christoph Hellwig

Link: https://lkml.kernel.org/r/20220131230255.789059-1-mfo@canonical.com
Fixes: 802a3a92ad7a ("mm: reclaim MADV_FREE pages")
Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Dan Hill <daniel.hill@canonical.com>
Cc: Dan Streetman <dan.streetman@canonical.com>
Cc: Dongdong Tao <dongdong.tao@canonical.com>
Cc: Gavin Guo <gavin.guo@canonical.com>
Cc: Gerald Yang <gerald.yang@canonical.com>
Cc: Heitor Alves de Siqueira <halves@canonical.com>
Cc: Ioanna Alifieraki <ioanna-maria.alifieraki@canonical.com>
Cc: Jay Vosburgh <jay.vosburgh@canonical.com>
Cc: Matthew Ruffell <matthew.ruffell@canonical.com>
Cc: Ponnuvel Palaniyappan <ponnuvel.palaniyappan@canonical.com>
Cc: <stable@vger.kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
3 years agomm/oom_kill.c: fix vm_oom_kill_table[] ifdeffery
Andrew Morton [Mon, 28 Feb 2022 23:05:36 +0000 (10:05 +1100)]
mm/oom_kill.c: fix vm_oom_kill_table[] ifdeffery

arm allnoconfig:

mm/oom_kill.c:60:25: warning: 'vm_oom_kill_table' defined but not used [-Wunused-variable]
   60 | static struct ctl_table vm_oom_kill_table[] = {
      |                         ^~~~~~~~~~~~~~~~~

Cc: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
3 years agoarch/x86/kernel/resource.c: needs spinlock.h
Andrew Morton [Mon, 28 Feb 2022 23:05:35 +0000 (10:05 +1100)]
arch/x86/kernel/resource.c: needs spinlock.h

fix recent breaking in -next.  x86_64 allnoconfig.

In file included from arch/x86/kernel/resource.c:4:
./arch/x86/include/asm/pci_x86.h:105:8: error: unknown type name 'raw_spinlock_t'
  105 | extern raw_spinlock_t pci_config_lock;
      |        ^~~~~~~~~~~~~~

am too lazy to hunt down the offending commit.

Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
3 years agoMerge branch 'akpm-current/current'
Stephen Rothwell [Tue, 1 Mar 2022 09:08:57 +0000 (20:08 +1100)]
Merge branch 'akpm-current/current'

3 years agoMerge branch 'for-next/execve' of git://git.kernel.org/pub/scm/linux/kernel/git/kees...
Stephen Rothwell [Tue, 1 Mar 2022 08:25:29 +0000 (19:25 +1100)]
Merge branch 'for-next/execve' of git://git./linux/kernel/git/kees/linux.git

3 years agoMerge branch 'for-next' of git://git.infradead.org/users/willy/pagecache.git
Stephen Rothwell [Tue, 1 Mar 2022 08:09:04 +0000 (19:09 +1100)]
Merge branch 'for-next' of git://git.infradead.org/users/willy/pagecache.git

# Conflicts:
# drivers/gpu/drm/drm_cache.c

3 years agoMerge branch 'sysctl-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof...
Stephen Rothwell [Tue, 1 Mar 2022 07:52:37 +0000 (18:52 +1100)]
Merge branch 'sysctl-next' of git://git./linux/kernel/git/mcgrof/linux.git

# Conflicts:
# include/linux/sched/sysctl.h
# kernel/sysctl.c

3 years agoMerge branch 'rust-next' of https://github.com/Rust-for-Linux/linux.git
Stephen Rothwell [Tue, 1 Mar 2022 07:36:12 +0000 (18:36 +1100)]
Merge branch 'rust-next' of https://github.com/Rust-for-Linux/linux.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/mic/linux.git
Stephen Rothwell [Tue, 1 Mar 2022 07:19:49 +0000 (18:19 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/mic/linux.git

3 years agoMerge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git
Stephen Rothwell [Tue, 1 Mar 2022 07:10:19 +0000 (18:10 +1100)]
Merge branch 'master' of git://git./linux/kernel/git/crng/random.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git
Stephen Rothwell [Tue, 1 Mar 2022 07:08:09 +0000 (18:08 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/vbabka/slab.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
Stephen Rothwell [Tue, 1 Mar 2022 07:08:08 +0000 (18:08 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/efi/efi.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl.git
Stephen Rothwell [Tue, 1 Mar 2022 07:06:30 +0000 (18:06 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/cxl/cxl.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/membloc...
Stephen Rothwell [Tue, 1 Mar 2022 06:54:32 +0000 (17:54 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/rppt/memblock.git

3 years agoMerge branch 'mhi-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mani/mhi.git
Stephen Rothwell [Tue, 1 Mar 2022 06:52:57 +0000 (17:52 +1100)]
Merge branch 'mhi-next' of git://git./linux/kernel/git/mani/mhi.git

3 years agoMerge branch 'kunit' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux...
Stephen Rothwell [Tue, 1 Mar 2022 06:50:36 +0000 (17:50 +1100)]
Merge branch 'kunit' of git://git./linux/kernel/git/shuah/linux-kselftest.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mdf/linux...
Stephen Rothwell [Tue, 1 Mar 2022 06:49:01 +0000 (17:49 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/mdf/linux-fpga.git

3 years agoMerge branch 'hyperv-next' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv...
Stephen Rothwell [Tue, 1 Mar 2022 06:46:35 +0000 (17:46 +1100)]
Merge branch 'hyperv-next' of git://git./linux/kernel/git/hyperv/linux.git

3 years agoMerge branch 'main' of git://git.infradead.org/users/willy/xarray.git
Stephen Rothwell [Tue, 1 Mar 2022 06:30:28 +0000 (17:30 +1100)]
Merge branch 'main' of git://git.infradead.org/users/willy/xarray.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/srini/nvmem.git
Stephen Rothwell [Tue, 1 Mar 2022 06:28:51 +0000 (17:28 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/srini/nvmem.git

# Conflicts:
# MAINTAINERS
# drivers/nvmem/Kconfig
# drivers/nvmem/Makefile

3 years agoMerge branch 'ntb-next' of https://github.com/jonmason/ntb.git
Stephen Rothwell [Tue, 1 Mar 2022 06:27:16 +0000 (17:27 +1100)]
Merge branch 'ntb-next' of https://github.com/jonmason/ntb.git

3 years agoMerge branch 'libnvdimm-for-next' of git://git.kernel.org/pub/scm/linux/kernel/git...
Stephen Rothwell [Tue, 1 Mar 2022 06:25:06 +0000 (17:25 +1100)]
Merge branch 'libnvdimm-for-next' of git://git./linux/kernel/git/nvdimm/nvdimm.git

3 years agoMerge branch 'rtc-next' of git://git.kernel.org/pub/scm/linux/kernel/git/abelloni...
Stephen Rothwell [Tue, 1 Mar 2022 06:22:45 +0000 (17:22 +1100)]
Merge branch 'rtc-next' of git://git./linux/kernel/git/abelloni/linux.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/coresight/linux.git
Stephen Rothwell [Tue, 1 Mar 2022 06:21:00 +0000 (17:21 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/coresight/linux.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/livepatching...
Stephen Rothwell [Tue, 1 Mar 2022 06:19:46 +0000 (17:19 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/livepatching/livepatching

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux...
Stephen Rothwell [Tue, 1 Mar 2022 06:18:32 +0000 (17:18 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/shuah/linux-kselftest.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm...
Stephen Rothwell [Tue, 1 Mar 2022 06:16:21 +0000 (17:16 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/ebiederm/user-namespace.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry...
Stephen Rothwell [Tue, 1 Mar 2022 06:14:08 +0000 (17:14 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/thierry.reding/linux-pwm.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux...
Stephen Rothwell [Tue, 1 Mar 2022 06:11:43 +0000 (17:11 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/linusw/linux-pinctrl.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/andy/linux...
Stephen Rothwell [Tue, 1 Mar 2022 06:09:30 +0000 (17:09 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/andy/linux-gpio-intel.git

3 years agoMerge branch 'gpio/for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl...
Stephen Rothwell [Tue, 1 Mar 2022 06:05:54 +0000 (17:05 +1100)]
Merge branch 'gpio/for-next' of git://git./linux/kernel/git/brgl/linux.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/remoteproc...
Stephen Rothwell [Tue, 1 Mar 2022 06:03:42 +0000 (17:03 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/remoteproc/linux.git

3 years agoMerge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git
Stephen Rothwell [Tue, 1 Mar 2022 06:01:21 +0000 (17:01 +1100)]
Merge branch 'linux-next' of git://git./linux/kernel/git/mst/vhost.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git
Stephen Rothwell [Tue, 1 Mar 2022 05:58:42 +0000 (16:58 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/mkp/scsi.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git
Stephen Rothwell [Tue, 1 Mar 2022 05:48:04 +0000 (16:48 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/jejb/scsi.git

# Conflicts:
# block/blk-lib.c
# drivers/block/rnbd/rnbd-clt.c

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
Stephen Rothwell [Tue, 1 Mar 2022 05:48:03 +0000 (16:48 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/tj/cgroup.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine.git
Stephen Rothwell [Tue, 1 Mar 2022 05:45:53 +0000 (16:45 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/vkoul/dmaengine.git

3 years agoMerge branch 'icc-next' of git://git.kernel.org/pub/scm/linux/kernel/git/djakov/icc.git
Stephen Rothwell [Tue, 1 Mar 2022 05:44:17 +0000 (16:44 +1100)]
Merge branch 'icc-next' of git://git./linux/kernel/git/djakov/icc.git

3 years agoMerge branch 'togreg' of git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio.git
Stephen Rothwell [Tue, 1 Mar 2022 05:28:05 +0000 (16:28 +1100)]
Merge branch 'togreg' of git://git./linux/kernel/git/jic23/iio.git

# Conflicts:
# .mailmap
# drivers/iio/accel/fxls8962af-core.c

3 years agoMerge branch 'staging-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh...
Stephen Rothwell [Tue, 1 Mar 2022 05:25:36 +0000 (16:25 +1100)]
Merge branch 'staging-next' of git://git./linux/kernel/git/gregkh/staging.git

# Conflicts:
# drivers/staging/fbtft/fbtft.h

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderb...
Stephen Rothwell [Tue, 1 Mar 2022 05:24:00 +0000 (16:24 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/westeri/thunderbolt.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/soundwire.git
Stephen Rothwell [Tue, 1 Mar 2022 05:22:26 +0000 (16:22 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/vkoul/soundwire.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git
Stephen Rothwell [Tue, 1 Mar 2022 05:20:12 +0000 (16:20 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/phy/linux-phy.git

3 years agoMerge branch 'extcon-next' of git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo...
Stephen Rothwell [Tue, 1 Mar 2022 05:17:50 +0000 (16:17 +1100)]
Merge branch 'extcon-next' of git://git./linux/kernel/git/chanwoo/extcon.git

# Conflicts:
# drivers/power/supply/max8997_charger.c

3 years agonext-20220224/char-misc
Stephen Rothwell [Tue, 1 Mar 2022 05:14:42 +0000 (16:14 +1100)]
next-20220224/char-misc

3 years agoMerge branch 'tty-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty.git
Stephen Rothwell [Tue, 1 Mar 2022 04:54:17 +0000 (15:54 +1100)]
Merge branch 'tty-next' of git://git./linux/kernel/git/gregkh/tty.git

# Conflicts:
# MAINTAINERS

3 years agoMerge branch 'for-usb-next' of git://git.kernel.org/pub/scm/linux/kernel/git/peter...
Stephen Rothwell [Tue, 1 Mar 2022 04:54:16 +0000 (15:54 +1100)]
Merge branch 'for-usb-next' of git://git./linux/kernel/git/peter.chen/usb.git

3 years agoMerge branch 'usb-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git
Stephen Rothwell [Tue, 1 Mar 2022 04:51:50 +0000 (15:51 +1100)]
Merge branch 'usb-next' of git://git./linux/kernel/git/gregkh/usb.git

# Conflicts:
# arch/arm64/boot/dts/qcom/ipq6018.dtsi
# arch/arm64/boot/dts/xilinx/zynqmp.dtsi

3 years agoMerge branch 'driver-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git...
Stephen Rothwell [Tue, 1 Mar 2022 04:35:42 +0000 (15:35 +1100)]
Merge branch 'driver-core-next' of git://git./linux/kernel/git/gregkh/driver-core.git

# Conflicts:
# drivers/power/supply/ab8500_chargalg.c

3 years agoMerge branch 'for-next' of git://github.com/cminyard/linux-ipmi.git
Stephen Rothwell [Tue, 1 Mar 2022 04:34:07 +0000 (15:34 +1100)]
Merge branch 'for-next' of git://github.com/cminyard/linux-ipmi.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux...
Stephen Rothwell [Tue, 1 Mar 2022 04:32:32 +0000 (15:32 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/pavel/linux-leds.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/chrome-platf...
Stephen Rothwell [Tue, 1 Mar 2022 04:30:58 +0000 (15:30 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/chrome-platform/linux.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platfo...
Stephen Rothwell [Tue, 1 Mar 2022 04:29:19 +0000 (15:29 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/pdx86/platform-drivers-x86.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git
Stephen Rothwell [Tue, 1 Mar 2022 04:27:09 +0000 (15:27 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/tj/wq.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percp...
Stephen Rothwell [Tue, 1 Mar 2022 04:27:09 +0000 (15:27 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/dennis/percpu.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
Stephen Rothwell [Tue, 1 Mar 2022 04:25:56 +0000 (15:25 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/kvms390/linux.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
Stephen Rothwell [Tue, 1 Mar 2022 04:22:54 +0000 (15:22 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/kvmarm/kvmarm.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm.git
Stephen Rothwell [Tue, 1 Mar 2022 04:20:25 +0000 (15:20 +1100)]
Merge branch 'next' of git://git./virt/kvm/kvm.git

# Conflicts:
# arch/x86/kvm/x86.c

3 years agoMerge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck...
Stephen Rothwell [Tue, 1 Mar 2022 04:04:05 +0000 (15:04 +1100)]
Merge branch 'rcu/next' of git://git./linux/kernel/git/paulmck/linux-rcu.git

# Conflicts:
# kernel/rcu/tree_plugin.h

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt...
Stephen Rothwell [Tue, 1 Mar 2022 04:01:40 +0000 (15:01 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/rostedt/linux-trace.git

3 years agoMerge branch 'irq/irqchip-next' of git://git.kernel.org/pub/scm/linux/kernel/git...
Stephen Rothwell [Tue, 1 Mar 2022 03:52:55 +0000 (14:52 +1100)]
Merge branch 'irq/irqchip-next' of git://git./linux/kernel/git/maz/arm-platforms.git

# Conflicts:
# drivers/pinctrl/pinctrl-starfive.c

3 years agoMerge branch 'edac-for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/ras...
Stephen Rothwell [Tue, 1 Mar 2022 03:51:20 +0000 (14:51 +1100)]
Merge branch 'edac-for-next' of git://git./linux/kernel/git/ras/ras.git

3 years agoMerge branch 'timers/drivers/next' of git://git.linaro.org/people/daniel.lezcano...
Stephen Rothwell [Tue, 1 Mar 2022 03:49:08 +0000 (14:49 +1100)]
Merge branch 'timers/drivers/next' of git://git.linaro.org/people/daniel.lezcano/linux.git

3 years agoMerge branch 'auto-latest' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git
Stephen Rothwell [Tue, 1 Mar 2022 03:32:40 +0000 (14:32 +1100)]
Merge branch 'auto-latest' of git://git./linux/kernel/git/tip/tip.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie...
Stephen Rothwell [Tue, 1 Mar 2022 03:29:32 +0000 (14:29 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/broonie/spi.git

# Conflicts:
# arch/arm/mach-pxa/stargate2.c

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
Stephen Rothwell [Tue, 1 Mar 2022 03:24:55 +0000 (14:24 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/robh/linux.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
Stephen Rothwell [Tue, 1 Mar 2022 03:22:47 +0000 (14:22 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/pcmoore/audit.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
Stephen Rothwell [Tue, 1 Mar 2022 03:20:20 +0000 (14:20 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/joro/iommu.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux...
Stephen Rothwell [Tue, 1 Mar 2022 03:17:58 +0000 (14:17 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/jarkko/linux-tpmdd.git

3 years agoMerge branch 'master' of https://scm.osdn.net/gitroot/tomoyo/tomoyo-test1.git
Stephen Rothwell [Tue, 1 Mar 2022 03:01:35 +0000 (14:01 +1100)]
Merge branch 'master' of https://scm.osdn.net/gitroot/tomoyo/tomoyo-test1.git

3 years agoMerge branch 'next' of git://github.com/cschaufler/smack-next
Stephen Rothwell [Tue, 1 Mar 2022 02:59:25 +0000 (13:59 +1100)]
Merge branch 'next' of git://github.com/cschaufler/smack-next

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
Stephen Rothwell [Tue, 1 Mar 2022 02:52:05 +0000 (13:52 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/pcmoore/selinux.git

3 years agoMerge branch 'next-integrity' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar...
Stephen Rothwell [Tue, 1 Mar 2022 02:49:52 +0000 (13:49 +1100)]
Merge branch 'next-integrity' of git://git./linux/kernel/git/zohar/linux-integrity

3 years agoMerge branch 'apparmor-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jj...
Stephen Rothwell [Tue, 1 Mar 2022 02:47:38 +0000 (13:47 +1100)]
Merge branch 'apparmor-next' of git://git./linux/kernel/git/jj/linux-apparmor

3 years agoMerge branch 'next-testing' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris...
Stephen Rothwell [Tue, 1 Mar 2022 02:47:37 +0000 (13:47 +1100)]
Merge branch 'next-testing' of git://git./linux/kernel/git/jmorris/linux-security.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie...
Stephen Rothwell [Tue, 1 Mar 2022 02:45:49 +0000 (13:45 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/broonie/regulator.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/sre/linux...
Stephen Rothwell [Tue, 1 Mar 2022 02:43:10 +0000 (13:43 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/sre/linux-power-supply.git

3 years agoMerge branch 'for-mfd-next' of git://git.kernel.org/pub/scm/linux/kernel/git/lee...
Stephen Rothwell [Tue, 1 Mar 2022 02:40:45 +0000 (13:40 +1100)]
Merge branch 'for-mfd-next' of git://git./linux/kernel/git/lee/mfd.git

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
Stephen Rothwell [Tue, 1 Mar 2022 02:39:08 +0000 (13:39 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/ulfh/mmc.git

3 years agoMerge branch 'pcmcia-next' of git://git.kernel.org/pub/scm/linux/kernel/git/brodo...
Stephen Rothwell [Tue, 1 Mar 2022 02:37:31 +0000 (13:37 +1100)]
Merge branch 'pcmcia-next' of git://git./linux/kernel/git/brodo/linux.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal...
Stephen Rothwell [Tue, 1 Mar 2022 02:35:40 +0000 (13:35 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/dlemoal/libata.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mappe...
Stephen Rothwell [Tue, 1 Mar 2022 02:33:19 +0000 (13:33 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/device-mapper/linux-dm.git

3 years agoMerge branch 'for-next' of git://git.kernel.dk/linux-block.git
Stephen Rothwell [Tue, 1 Mar 2022 02:22:37 +0000 (13:22 +1100)]
Merge branch 'for-next' of git://git.kernel.dk/linux-block.git

# Conflicts:
# fs/iomap/direct-io.c

3 years agoMerge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input.git
Stephen Rothwell [Tue, 1 Mar 2022 02:21:03 +0000 (13:21 +1100)]
Merge branch 'next' of git://git./linux/kernel/git/dtor/input.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie...
Stephen Rothwell [Tue, 1 Mar 2022 02:19:10 +0000 (13:19 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/broonie/sound.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
Stephen Rothwell [Tue, 1 Mar 2022 02:16:03 +0000 (13:16 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/tiwai/sound.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie...
Stephen Rothwell [Tue, 1 Mar 2022 02:13:54 +0000 (13:13 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/broonie/regmap.git

3 years agoMerge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/linux...
Stephen Rothwell [Tue, 1 Mar 2022 02:12:17 +0000 (13:12 +1100)]
Merge branch 'for-next' of git://git./linux/kernel/git/deller/linux-fbdev.git

3 years agoMerge branch 'imx-drm/next' of https://git.pengutronix.de/git/pza/linux
Stephen Rothwell [Tue, 1 Mar 2022 02:10:43 +0000 (13:10 +1100)]
Merge branch 'imx-drm/next' of https://git.pengutronix.de/git/pza/linux

3 years agoMerge branch 'msm-next' of https://gitlab.freedesktop.org/drm/msm.git
Stephen Rothwell [Tue, 1 Mar 2022 02:09:05 +0000 (13:09 +1100)]
Merge branch 'msm-next' of https://gitlab.freedesktop.org/drm/msm.git

3 years agoMerge branch 'drm/tegra/for-next' of git://anongit.freedesktop.org/tegra/linux.git
Stephen Rothwell [Tue, 1 Mar 2022 02:07:54 +0000 (13:07 +1100)]
Merge branch 'drm/tegra/for-next' of git://anongit.freedesktop.org/tegra/linux.git

3 years agoMerge branch 'for-linux-next' of git://anongit.freedesktop.org/drm-intel
Stephen Rothwell [Tue, 1 Mar 2022 02:04:37 +0000 (13:04 +1100)]
Merge branch 'for-linux-next' of git://anongit.freedesktop.org/drm-intel

# Conflicts:
# drivers/gpu/drm/dp/drm_dp.c
# drivers/gpu/drm/i915/display/intel_bw.c
# drivers/gpu/drm/i915/display/intel_snps_phy.c

3 years agoMerge branch 'drm-next' of https://gitlab.freedesktop.org/agd5f/linux
Stephen Rothwell [Tue, 1 Mar 2022 02:02:42 +0000 (13:02 +1100)]
Merge branch 'drm-next' of https://gitlab.freedesktop.org/agd5f/linux

3 years agoselftests/vm/transhuge-stress: Support file-backed PMD folios
Matthew Wilcox (Oracle) [Sun, 25 Jul 2021 03:43:58 +0000 (23:43 -0400)]
selftests/vm/transhuge-stress: Support file-backed PMD folios

Add a -f <filename> option to test PMD folios on files

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
3 years agomm/filemap: Support VM_HUGEPAGE for file mappings
Matthew Wilcox (Oracle) [Sun, 25 Jul 2021 03:37:13 +0000 (23:37 -0400)]
mm/filemap: Support VM_HUGEPAGE for file mappings

If the VM_HUGEPAGE flag is set, attempt to allocate PMD-sized folios
during readahead, even if we have no history of readahead being
successful.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
3 years agomm/readahead: Switch to page_cache_ra_order
Matthew Wilcox (Oracle) [Sun, 25 Jul 2021 03:26:14 +0000 (23:26 -0400)]
mm/readahead: Switch to page_cache_ra_order

do_page_cache_ra() was being exposed for the benefit of
do_sync_mmap_readahead().  Switch it over to page_cache_ra_order()
partly because it's a better interface but mostly for the benefit of
the next patch.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
3 years agomm/readahead: Align file mappings for non-DAX
William Kucharski [Sun, 22 Sep 2019 12:43:15 +0000 (08:43 -0400)]
mm/readahead: Align file mappings for non-DAX

When we have the opportunity to use PMDs to map a file, we want to follow
the same rules as DAX.

Signed-off-by: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
3 years agomm/readahead: Add large folio readahead
Matthew Wilcox (Oracle) [Wed, 5 Feb 2020 16:27:01 +0000 (11:27 -0500)]
mm/readahead: Add large folio readahead

Allocate large folios in the readahead code when the filesystem supports
them and it seems worth doing.  The heuristic for choosing which folio
sizes will surely need some tuning, but this aggressive ramp-up has been
good for testing.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>