Implement the uABI of UFFDIO_MOVE ioctl.
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [2].
We see over 40% reduction (on a Google pixel 6 device) in the compacting
thread's completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was
measured using a benchmark that emulates a heap compaction implementation
using userfaultfd (to allow concurrent accesses by application threads).
More details of the usecase are explained in [2]. Furthermore,
UFFDIO_MOVE enables moving swapped-out pages without touching them within
the same vma. Today, it can only be done by mremap, however it forces
splitting the vma.
[1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/
[2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/
Update for the ioctl_userfaultfd(2) manpage:
UFFDIO_MOVE
(Since Linux xxx) Move a continuous memory chunk into the
userfault registered range and optionally wake up the blocked
thread. The source and destination addresses and the number of
bytes to move are specified by the src, dst, and len fields of
the uffdio_move structure pointed to by argp:
struct uffdio_move {
__u64 dst; /* Destination of move */
__u64 src; /* Source of move */
__u64 len; /* Number of bytes to move */
__u64 mode; /* Flags controlling behavior of move */
__s64 move; /* Number of bytes moved, or negated error */
};
The following value may be bitwise ORed in mode to change the
behavior of the UFFDIO_MOVE operation:
UFFDIO_MOVE_MODE_DONTWAKE
Do not wake up the thread that waits for page-fault
resolution
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES
Allow holes in the source virtual range that is being moved.
When not specified, the holes will result in ENOENT error.
When specified, the holes will be accounted as successfully
moved memory. This is mostly useful to move hugepage aligned
virtual regions without knowing if there are transparent
hugepages in the regions or not, but preventing the risk of
having to split the hugepage during the operation.
The move field is used by the kernel to return the number of
bytes that was actually moved, or an error (a negated errno-
style value). If the value returned in move doesn't match the
value that was specified in len, the operation fails with the
error EAGAIN. The move field is output-only; it is not read by
the UFFDIO_MOVE operation.
The operation may fail for various reasons. Usually, remapping of
pages that are not exclusive to the given process fail; once KSM
might deduplicate pages or fork() COW-shares pages during fork()
with child processes, they are no longer exclusive. Further, the
kernel might only perform lightweight checks for detecting whether
the pages are exclusive, and return -EBUSY in case that check fails.
To make the operation more likely to succeed, KSM should be
disabled, fork() should be avoided or MADV_DONTFORK should be
configured for the source VMA before fork().
This ioctl(2) operation returns 0 on success. In this case, the
entire area was moved. On error, -1 is returned and errno is
set to indicate the error. Possible errors include:
EAGAIN The number of bytes moved (i.e., the value returned in
the move field) does not equal the value that was
specified in the len field.
EINVAL Either dst or len was not a multiple of the system page
size, or the range specified by src and len or dst and len
was invalid.
EINVAL An invalid bit was specified in the mode field.
ENOENT
The source virtual memory range has unmapped holes and
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set.
EEXIST
The destination virtual memory range is fully or partially
mapped.
EBUSY
The pages in the source virtual memory range are either
pinned or not exclusive to the process. The kernel might
only perform lightweight checks for detecting whether the
pages are exclusive. To make the operation more likely to
succeed, KSM should be disabled, fork() should be avoided
or MADV_DONTFORK should be configured for the source virtual
memory area before fork().
ENOMEM Allocating memory needed for the operation failed.
ESRCH
The target process has exited at the time of a UFFDIO_MOVE
operation.
Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "userfaultfd move option", v6.
This patch series introduces UFFDIO_MOVE feature to userfaultfd, which has
long been implemented and maintained by Andrea in his local tree [1], but
was not upstreamed due to lack of use cases where this approach would be
better than allocating a new page and copying the contents. Previous
upstraming attempts could be found at [6] and [7].
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [2]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [3]. We see over 40% reduction (on a Google pixel 6 device) in
the compacting thread's completion time by using UFFDIO_MOVE vs.
UFFDIO_COPY. This was measured using a benchmark that emulates a heap
compaction implementation using userfaultfd (to allow concurrent accesses
by application threads). More details of the usecase are explained in
[3].
Furthermore, UFFDIO_MOVE enables moving swapped-out pages without
touching them within the same vma. Today, it can only be done by mremap,
however it forces splitting the vma.
TODOs for follow-up improvements:
- cross-mm support. Known differences from single-mm and missing pieces:
- memcg recharging (might need to isolate pages in the process)
- mm counters
- cross-mm deposit table moves
- cross-mm test
- document the address space where src and dest reside in struct
uffdio_move
- TLB flush batching. Will require extensive changes to PTL locking in
move_pages_pte(). OTOH that might let us reuse parts of mremap code.
This patch (of 5):
For now, folio_move_anon_rmap() was only used to move a folio to a
different anon_vma after fork(), whereby the root anon_vma stayed
unchanged. For that, it was sufficient to hold the folio lock when
calling folio_move_anon_rmap().
However, we want to make use of folio_move_anon_rmap() to move folios
between VMAs that have a different root anon_vma. As folio_referenced()
performs an RMAP walk without holding the folio lock but only holding the
anon_vma in read mode, holding the folio lock is insufficient.
When moving to an anon_vma with a different root anon_vma, we'll have to
hold both, the folio lock and the anon_vma lock in write mode.
Consequently, whenever we succeeded in folio_lock_anon_vma_read() to
read-lock the anon_vma, we have to re-check if the mapping was changed in
the meantime. If that was the case, we have to retry.
Note that folio_move_anon_rmap() must only be called if the anon page is
exclusive to a process, and must not be called on KSM folios.
This is a preparation for UFFDIO_MOVE, which will hold the folio lock, the
anon_vma lock in write mode, and the mmap_lock in read mode.
Link: https://lkml.kernel.org/r/20231206103702.3873743-1-surenb@google.com
Link: https://lkml.kernel.org/r/20231206103702.3873743-2-surenb@google.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: kernel-team@android.com
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Both __block_write_full_folio() and block_read_full_folio() assumed that
block size <= PAGE_SIZE. Replace the shift with a divide, which is
probably cheaper than first calculating the shift. That lets us remove
block_size_bits() as these were the last callers.
Link: https://lkml.kernel.org/r/20231109210608.2252323-8-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When __block_write_begin_int() was converted to support folios, we did not
expect large folios to be passed to it. With the current work to support
large block size storage devices, this will no longer be true so change
the checks on 'from' and 'to' to be related to the size of the folio
instead of PAGE_SIZE. Also remove an assumption that the block size is
smaller than PAGE_SIZE.
Link: https://lkml.kernel.org/r/20231109210608.2252323-7-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reported-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
If i_blkbits is larger than PAGE_SHIFT, we shift by a negative number,
which is undefined. It is safe to shift the block left as a block device
must be smaller than MAX_LFS_FILESIZE, which is guaranteed to fit in
loff_t.
Link: https://lkml.kernel.org/r/20231109210608.2252323-6-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Pankaj Raghav <p.raghav@samsung.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
While sector_t is always defined as a u64 today, that hasn't always been
the case and it might not always be the same size as loff_t in the future.
Link: https://lkml.kernel.org/r/20231109210608.2252323-5-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
We must not shift by a negative number so work in terms of a byte offset
to avoid the awkward shift left-or-right-depending-on-sign option. This
means we need to use check_mul_overflow() to ensure that a large block
number does not result in a wrap.
Link: https://lkml.kernel.org/r/20231109210608.2252323-4-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
[nathan@kernel.org: add cast in grow_buffers() to avoid a multiplication libcall]
Link: https://lkml.kernel.org/r/20231128-avoid-muloti4-grow_buffers-v1-1-bc3d0f0ec483@kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The calculation of block from index doesn't work for devices with a block
size larger than PAGE_SIZE as we end up shifting by a negative number.
Instead, calculate the number of the first block from the folio's position
in the block device. We no longer need to pass sizebits to
grow_dev_folio().
Link: https://lkml.kernel.org/r/20231109210608.2252323-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Pankaj Raghav <p.raghav@samsung.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "More buffer_head cleanups", v2.
The first patch is a left-over from last cycle. The rest fix "obvious"
block size > PAGE_SIZE problems. I haven't tested with a large block size
setup (but I have done an ext4 xfstests run).
This patch (of 7):
Rename grow_dev_page() to grow_dev_folio() and make it return a bool.
Document what that bool means; it's more subtle than it first appears.
Also rename the 'failed' label to 'unlock' beacuse it's not exactly
'failed'. It just hasn't succeeded.
Link: https://lkml.kernel.org/r/20231109210608.2252323-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
- Andy steps down as GPIO reviewer
- Kent becomes a reviewer for GPIO uAPI
- add missing intel file to the relevant MAINTAINERS section
-----BEGIN PGP SIGNATURE-----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=bdYK
-----END PGP SIGNATURE-----
Merge tag 'gpio-fixes-for-v6.7-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux
Pull gpio fixes from Bartosz Golaszewski:
- Andy steps down as GPIO reviewer
- Kent becomes a reviewer for GPIO uAPI
- add missing intel file to the relevant MAINTAINERS section
* tag 'gpio-fixes-for-v6.7-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux:
MAINTAINERS: Add a missing file to the INTEL GPIO section
MAINTAINERS: Remove Andy from GPIO maintainers
MAINTAINERS: split out the uAPI into a new section
-----BEGIN PGP SIGNATURE-----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=wPUa
-----END PGP SIGNATURE-----
Merge tag 'block-6.7-2023-12-29' of git://git.kernel.dk/linux
Pull block fixes from Jens Axboe:
"Fix for a badly numbered flag, and a regression fix for the badblocks
updates from this merge window"
* tag 'block-6.7-2023-12-29' of git://git.kernel.dk/linux:
block: renumber QUEUE_FLAG_HW_WC
badblocks: avoid checking invalid range in badblocks_check()
Update the email addresses for vmwgfx and vmmouse to reflect the fact that
VMware is now part of Broadcom.
Add a .mailmap entry because the vmware.com address will start bouncing
soon.
Link: https://lkml.kernel.org/r/20231224052036.603621-1-zack.rusin@broadcom.com
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Ian Forbes <ian.forbes@broadcom.com>
Cc: Martin Krastev <martin.krastev@broadcom.com>
Cc: Maaz Mombasawala <maaz.mombasawala@broadcom.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
A test [1] in Android test suite started failing after [2] was merged. It
turns out that after handling a major fault under per-VMA lock, the
process major fault counter does not register that fault as major. Before
[2] read faults would be done under mmap_lock, in which case
FAULT_FLAG_TRIED flag is set before retrying. That in turn causes
mm_account_fault() to account the fault as major once retry completes.
With per-VMA locks we often retry because a fault can't be handled without
locking the whole mm using mmap_lock. Therefore such retries do not set
FAULT_FLAG_TRIED flag. This logic does not work after [2] because we can
now handle read major faults under per-VMA lock and upon retry the fact
there was a major fault gets lost. Fix this by setting FAULT_FLAG_TRIED
after retrying under per-VMA lock if VM_FAULT_MAJOR was returned. Ideally
we would use an additional VM_FAULT bit to indicate the reason for the
retry (could not handle under per-VMA lock vs other reason) but this
simpler solution seems to work, so keeping it simple.
[1] https://cs.android.com/android/platform/superproject/+/master:test/vts-testcase/kernel/api/drop_caches_prop/drop_caches_test.cpp
[2] https://lore.kernel.org/all/20231006195318.4087158-6-willy@infradead.org/
Link: https://lkml.kernel.org/r/20231226214610.109282-1-surenb@google.com
Fixes: 12214eba19 ("mm: handle read faults under the VMA lock")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Miaohe Lin has contributed to hwpoison subsystem as a reviewer for more
than 1.5 year, and has made many patch contributions in hwpoison subsystem
and the memory management subsystem. So I'd like to pass on the hwpoison
maintainership to Miaohe.
[nao.horiguchi@gmail.com: update to keep myself as a reviewer]
Link: https://lkml.kernel.org/r/20231223031115.GA2883156@u2004
Link: https://lkml.kernel.org/r/20231222024024.1601043-1-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
I am stepping away from my role as hugetlb maintainer. There should be no
gap in coverage as Muchun Song is also a hugetlb maintainer.
[akpm@linux-foundation.org: update CREDITS]
Link: https://lkml.kernel.org/r/20231220220843.73586-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The bug happens when highest bit of holebegin is 1, suppose holebegin is
0x8000000111111000, after shift, hba would be 0xfff8000000111111, then
vma_interval_tree_foreach would look it up fail or leads to the wrong
result.
error call seq e.g.:
- mmap(..., offset=0x8000000111111000)
|- syscall(mmap, ... unsigned long, off):
|- ksys_mmap_pgoff( ... , off >> PAGE_SHIFT);
here pgoff is correctly shifted to 0x8000000111111,
but pass 0x8000000111111000 as holebegin to unmap
would then cause terrible result, as shown below:
- unmap_mapping_range(..., loff_t const holebegin)
|- pgoff_t hba = holebegin >> PAGE_SHIFT;
/* hba = 0xfff8000000111111 unexpectedly */
The issue happens in Heterogeneous computing, where the device(e.g.
gpu) and host share the same virtual address space.
A simple workflow pattern which hit the issue is:
/* host */
1. userspace first mmap a file backed VA range with specified offset.
e.g. (offset=0x800..., mmap return: va_a)
2. write some data to the corresponding sys page
e.g. (va_a = 0xAABB)
/* device */
3. gpu workload touches VA, triggers gpu fault and notify the host.
/* host */
4. reviced gpu fault notification, then it will:
4.1 unmap host pages and also takes care of cpu tlb
(use unmap_mapping_range with offset=0x800...)
4.2 migrate sys page to device
4.3 setup device page table and resolve device fault.
/* device */
5. gpu workload continued, it accessed va_a and got 0xAABB.
6. gpu workload continued, it wrote 0xBBCC to va_a.
/* host */
7. userspace access va_a, as expected, it will:
7.1 trigger cpu vm fault.
7.2 driver handling fault to migrate gpu local page to host.
8. userspace then could correctly get 0xBBCC from va_a
9. done
But in step 4.1, if we hit the bug this patch mentioned, then userspace
would never trigger cpu fault, and still get the old value: 0xAABB.
Making holebegin unsigned first fixes the bug.
Link: https://lkml.kernel.org/r/20231220052839.26970-1-jiajun.xie.sh@gmail.com
Signed-off-by: Jiajun Xie <jiajun.xie.sh@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When running autonuma with enabling multi-size THP, I encountered the
following kernel crash issue:
[ 134.290216] list_del corruption. prev->next should be fffff9ad42e1c490,
but was dead000000000100. (prev=fffff9ad42399890)
[ 134.290877] kernel BUG at lib/list_debug.c:62!
[ 134.291052] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[ 134.291210] CPU: 56 PID: 8037 Comm: numa01 Kdump: loaded Tainted:
G E 6.7.0-rc4+ #20
[ 134.291649] RIP: 0010:__list_del_entry_valid_or_report+0x97/0xb0
......
[ 134.294252] Call Trace:
[ 134.294362] <TASK>
[ 134.294440] ? die+0x33/0x90
[ 134.294561] ? do_trap+0xe0/0x110
......
[ 134.295681] ? __list_del_entry_valid_or_report+0x97/0xb0
[ 134.295842] folio_undo_large_rmappable+0x99/0x100
[ 134.296003] destroy_large_folio+0x68/0x70
[ 134.296172] migrate_folio_move+0x12e/0x260
[ 134.296264] ? __pfx_remove_migration_pte+0x10/0x10
[ 134.296389] migrate_pages_batch+0x495/0x6b0
[ 134.296523] migrate_pages+0x1d0/0x500
[ 134.296646] ? __pfx_alloc_misplaced_dst_folio+0x10/0x10
[ 134.296799] migrate_misplaced_folio+0x12d/0x2b0
[ 134.296953] do_numa_page+0x1f4/0x570
[ 134.297121] __handle_mm_fault+0x2b0/0x6c0
[ 134.297254] handle_mm_fault+0x107/0x270
[ 134.300897] do_user_addr_fault+0x167/0x680
[ 134.304561] exc_page_fault+0x65/0x140
[ 134.307919] asm_exc_page_fault+0x22/0x30
The reason for the crash is that, the commit 85ce2c517a ("memcontrol:
only transfer the memcg data for migration") removed the charging and
uncharging operations of the migration folios and cleared the memcg data
of the old folio.
During the subsequent release process of the old large folio in
destroy_large_folio(), if the large folio needs to be removed from the
split queue, an incorrect split queue can be obtained (which is
pgdat->deferred_split_queue) because the old folio's memcg is NULL now.
This can lead to list operations being performed under the wrong split
queue lock protection, resulting in a list crash as above.
After the migration, the old folio is going to be freed, so we can remove
it from the split queue in mem_cgroup_migrate() a bit earlier before
clearing the memcg data to avoid getting incorrect split queue.
[akpm@linux-foundation.org: fix comment, per Zi Yan]
Link: https://lkml.kernel.org/r/61273e5e9b490682388377c20f52d19de4a80460.1703054559.git.baolin.wang@linux.alibaba.com
Fixes: 85ce2c517a ("memcontrol: only transfer the memcg data for migration")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Since now bdi->max_ratio is part per million, fix the wrong arithmetic for
max_prop_frac when setting max_ratio. Otherwise the miscalculated
max_prop_frac will affect the incrementing of writeout completion count
when max_ratio is not 100%.
Link: https://lkml.kernel.org/r/20231219142508.86265-3-jefflexu@linux.alibaba.com
Fixes: efc3e6ad53 ("mm: split off __bdi_set_max_ratio() function")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Stefan Roesch <shr@devkernel.io>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Since now bdi->min_ratio is part per million, fix the wrong arithmetic.
Otherwise it will fail with -EINVAL when setting a reasonable min_ratio,
as it tries to set min_ratio to (min_ratio * BDI_RATIO_SCALE) in
percentage unit, which exceeds 100% anyway.
# cat /sys/class/bdi/253\:0/min_ratio
0
# cat /sys/class/bdi/253\:0/max_ratio
100
# echo 1 > /sys/class/bdi/253\:0/min_ratio
-bash: echo: write error: Invalid argument
Link: https://lkml.kernel.org/r/20231219142508.86265-2-jefflexu@linux.alibaba.com
Fixes: 8021fb3232 ("mm: split off __bdi_set_min_ratio() function")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reported-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Stefan Roesch <shr@devkernel.io>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Align larger anonymous memory mappings on THP boundaries by going through
thp_get_unmapped_area if THPs are enabled for the current process.
With this patch, larger anonymous mappings are now THP aligned. When a
malloc library allocates a 2MB or larger arena, that arena can now be
mapped with THPs right from the start, which can result in better TLB hit
rates and execution time.
Link: https://lkml.kernel.org/r/20220809142457.4751229f@imladris.surriel.com
Link: https://lkml.kernel.org/r/20231214223423.1133074-1-yang@os.amperecomputing.com
Signed-off-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christopher Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Andorid can wakeup from various wakeup sources, but only several wakeup
sources can wake up screen with right events(POWER, WAKEUP) from input
device.
Regarding pressing acpi power button, it can resume system and
ACPI_BITMASK_WAKE_STATUS and ACPI_BITMASK_POWER_BUTTON_STATUS are set in
pm1a_sts, but kernel does not report any key event to user space during
resuming by default.
So, send wakeup key event to user space during resume from power button.
Signed-off-by: Ken Xue <Ken.Xue@amd.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
[ rjw: Subject edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The TongFang GMxXGxx, which needs IRQ overriding for the keyboard to work,
is also sold as the Eluktronics RP-15 which does not use the standard
TongFang GMxXGxx DMI board_name.
Add an entry for this laptop to the irq1_edge_low_force_override[] DMI
table to make the internal keyboard functional.
Reported-by: Luis Acuna <ldacuna@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The cpuidle drivers' ->enter() methods are supposed to be IRQ invariant:
5e26aa9339 ("cpuidle/poll: Ensure IRQs stay disabled after cpuidle_state::enter() calls")
bb7b112585 ("cpuidle: Move IRQ state validation")
Do that in the haltpoll driver too.
Fixes: 5e26aa9339 ("cpuidle/poll: Ensure IRQs stay disabled after cpuidle_state::enter() calls")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218245
Reported-by: <forza@tnonline.net>
Tested-by: <forza@tnonline.net>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
AUD_PAD_TOP widget's correct register is AFE_AUD_PAD_TOP , and not zero.
Having a zero as register, it would mean that the `snd_soc_dapm_new_widgets`
would try to read the register at offset zero when trying to get the power
status of this widget, which is incorrect.
Fixes: b65c466220 ("ASoC: mediatek: mt8186: support adda in platform driver")
Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
Link: https://lore.kernel.org/r/20231229114342.195867-1-eugen.hristev@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
When the thermal instance's weight is updated from the sysfs the governor
update_tz() callback is triggered. Implement proper reaction to this
event in the IPA, which would save CPU cycles spent in throttle().
This will speed-up the main throttle() IPA function and clean it up
a bit.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Support governors update when the thermal instance's weight has changed.
This allows to adjust internal state for the governor.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
[ rjw: Add two empty code lines aroung the locking ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
User space can change the weight of a thermal instance via sysfs while the
.throttle() callback is running for a governor, because weight_store()
does not use the zone lock.
The IPA governor uses instance weight values for power calculations and
caches the sum of them as total_weight, so it gets confused when one of
them changes while its .throttle() callback is running.
To prevent that from happening, use thermal zone locking in
weight_store().
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
There is a need to check if the cooling device in the thermal zone
supports IPA callback and is set for control trip point.
Refactor the code which validates the power actor capabilities and
make it more consistent in all places.
No intentional functional impact.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The new thermal callback allows to react to the change of cooling
instances in the thermal zone. Move the memory allocation to that new
callback and save CPU cycles in the throttle() code path.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Change trace event trace_thermal_power_allocator() to not use dynamic
array for requested power and granted power for all power actors.
Instead, simplify the trace event and print other simple values.
Add new trace event to print power actor information of requested power
and granted power. That trace event would be called in a loop for each
power actor. The trace data would be easier to parse comparing to the
dynamic array implementation.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Simplify the code and remove one extra 'if' block.
No intentional functional impact.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
In preparation for a subsequent change, rearrange check_power_actors().
No intentional functional impact.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Add a new callback to the struct thermal_governor. It can be used for
updating governors when there is a change in the thermal zone internals,
e.g. thermal cooling device is bind to the thermal zone.
That makes possible to move some heavy operations like memory allocations
related to the number of cooling instances out of the throttle() callback.
Both callback code paths (throttle() and update_tz()) are protected with
the same thermal zone lock, which guaranties the consistency.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The discard granularity now defaults to a single sector, so don't set
that value explicitly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Richard Weinberger <richard@nod.at>
Link: https://lore.kernel.org/r/20231228075545.362768-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The discard granularity now defaults to a single sector, so don't set
that value explicitly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-9-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The discard granularity now defaults to a single sector, so don't set
that value explicitly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-8-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The discard granularity now defaults to a single sector, so don't set
that value explicitly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-7-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The discard granularity now defaults to a single sector, so don't set
that value explicitly. Also don't bother clearing it as a discard
granularity without discard_sectors doesn't mean anything.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-6-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The discard granularity now defaults to a single sector, so don't set
that value explicitly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Richard Weinberger <richard@nod.at>
Link: https://lore.kernel.org/r/20231228075545.362768-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Current the discard granularity defaults to 0 and must be initialized by
any driver that wants to support discard. Default to the sector size
instead, which is the smallest possible value, and a very useful default.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Just like all block I/O, discards are in units of sectors. Thus setting a
smaller than sector size discard limit in case of > 512 byte sectors in
bcache doesn't make sense. Always set the discard granularity to 512
bytes instead.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A zero discard_granularity is not treated the same as a single-block one,
and not having any segments after taking alignment is perfectly fine
and does not need a warning.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231228075545.362768-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
parse_server_interfaces should be in complete charge of maintaining
the iface_list linked list. Today, iface entries are removed
from the list only when the last refcount is dropped.
i.e. in release_iface. However, this can result in undercounting
of refcount if the server stops advertising interfaces (which
Azure SMB server does).
This change puts parse_server_interfaces in full charge of
maintaining the iface_list. So if an empty list is returned
by the server, the entries in the list will immediately be
removed. This way, a following call to the same function will
not find entries in the list.
Fixes: aa45dadd34 ("cifs: change iface_list from array to sorted linked list")
Cc: stable@vger.kernel.org
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
cifs_chan_is_iface_active checks the channels of a session to see
if the associated iface is active. This should always happen
with chan_lock held. However, these two callers of this function
were missing this locking.
This change makes sure the function calls are protected with
proper locking.
Fixes: b54034a73b ("cifs: during reconnect, update interface if necessary")
Fixes: fa1d0508bd ("cifs: account for primary channel in the interface list")
Cc: stable@vger.kernel.org
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Once the server disables multichannel for an active multichannel
session, on the following reconnect, the client would reduce
the number of channels to 1. However, it could be the case that
the tree connect was active on one of these disabled channels.
This results in an unrecoverable state.
This change fixes that by making sure that whenever a channel
is being terminated, the session and tcon are marked for
reconnect too. This could mean a few redundant tree connect
calls to the server, but considering that this is not a frequent
event, we should be okay.
Fixes: ee1d21794e ("cifs: handle when server stops supporting multichannel")
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>