linux-stable.git/include/linux/swap.h, branch v7.3-rc2

mm/swap: move swap_ops into file systems for file system-based swap

2026-08-25T01:43:20+00:00

Currently swap to and from file systems goes through two indirect calls
between the swap ops and the swap_rw method.  Reduce this by directly
providing the swap_ops from the file system.

For this refactor swap_fs_submit into a swap_fs_prepare_rw helper that
initializes the iov_iter on the callers stack so that file systems can
call it directly, and use that to initialize file system specific ops in
the NFS and SMB clients, which then get passed to swap_fs_activate.

Link: https://lore.kernel.org/20260723054622.3460249-4-hch@lst.de
Signed-off-by: Christoph Hellwig 
Acked-by: Chris Li 
Cc: Baoquan He 
Cc: Kairui Song 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Nhat Pham 
Cc: Steve French 
Cc: Usama Arif 
Signed-off-by: Andrew Morton

mm/swap: remove SWP_FS_OPS

2026-08-25T01:43:15+00:00

Provide a swap_fs_activate helper that directly sets up swap_fs_ops, and a
flag in struct swap_ops to indicate of NOFS swapping is allowed.

Link: https://lore.kernel.org/20260713093350.2154226-7-hch@lst.de
Signed-off-by: Christoph Hellwig 
Cc: Baolin Wang 
Cc: Baoquan He 
Cc: Barry Song 
Cc: Chris Li 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Nhat Pham 
Cc: Youngjun Park 
Signed-off-by: Andrew Morton

mm/swap: use swap_ops to register swap device's methods

2026-08-25T01:43:15+00:00

This simplifies codes and makes logic clearer.  And also makes later any
new swap device type being added easier to handle.

Currently there are two types of swap devices: fs and bdev.

[hch@lst.de: updated for the new submit and can_merge abstraction]
Link: https://lore.kernel.org/20260713093350.2154226-6-hch@lst.de
Signed-off-by: Baoquan He 
Signed-off-by: Christoph Hellwig 
Suggested-by: Chris Li 
Reviewed-by: Nhat Pham 
Cc: Baolin Wang 
Cc: Barry Song 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Youngjun Park 
Signed-off-by: Andrew Morton

mm/gup: factor out LRU cache draining for folio into lru_cache_drain_for_folio()

2026-08-25T01:43:00+00:00

KVM with guest_memfd wants to remove any folio references due to LRU
caches, as it really must only allow to convert folios from shared to
private when there are no unexpected folio references (e.g., from GUP
references).

So, to drive the refcount down, it needs a way to flush the LRU caches. 
Let's factor out what we have in lru_cache_drain_for_folio().  Document
it, and also mention that concurrent folio (un)mapping might, in theory,
miss detecting LRU cache references.  Keep obtaining the expected refcount
twice to minimize the possibility.  For the current and future user that
should work, and we don't really have a better alternative: we could
detect if the mapcount changed, but it would still be racy and add more
complexity with questionable benefit.

Maybe there is a chance to avoid the draining entirely in the future, by
avoiding extra references from the LRU cache: Hugh thinks there might be a
way.  But for the time being, this handling is unfortunately required.

Make folio_may_be_lru_cached() accept a const pointer so
lru_cache_drain_for_folio() can accept a const pointer as well.

Link: https://lore.kernel.org/20260806-lru_cache_drain_for_folio-v1-1-c6287d295e99@kernel.org
Signed-off-by: David Hildenbrand (Arm) 
Reviewed-by: Fuad Tabba 
Cc: Ackerley Tng 
Cc: Baoquan He 
Cc: Barry Song 
Cc: Chris Li 
Cc: Jason Gunthorpe 
Cc: John Hubbard 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Liam R. Howlett 
Cc: Lorenzo Stoakes 
Cc: Michal Hocko 
Cc: Mike Rapoport 
Cc: Nhat Pham 
Cc: Peter Xu 
Cc: Sean Christopherson 
Cc: Suren Baghdasaryan 
Cc: Vlastimil Babka 
Signed-off-by: Andrew Morton

memcg: move mem_cgroup_swappiness and vm_swappiness to mm/swap.h

2026-08-25T01:42:55+00:00

Patch series "mm: vmscan: fix node reclaim ignoring swappiness parameter",
v4.

The per-node proactive reclaim interface
(/sys/devices/system/node/nodeX/reclaim) accepts a swappiness parameter,
but it is silently ignored when CONFIG_MEMCG is disabled.  The root cause
is that sc_swappiness() has separate implementations for CONFIG_MEMCG and
!CONFIG_MEMCG, and the latter never checks proactive_swappiness.

Patch 1 moves mem_cgroup_swappiness() and vm_swappiness out of the public
include/linux/swap.h into the mm-private mm/swap.h, and makes the helper
handle both CONFIG_MEMCG and !CONFIG_MEMCG in a single inline function. 
This is a prerequisite for unifying sc_swappiness().

Patch 2 consolidates sc_swappiness() into a single definition that works
regardless of CONFIG_MEMCG, fixing the node reclaim swappiness bug.


This patch (of 2):

The per-memcg swappiness knob is v1-only; v2 always uses global
vm_swappiness and ignores the per-cgroup field.

Both mem_cgroup_swappiness() and vm_swappiness are only used within mm/
(memcontrol.c, memcontrol-v1.c, vmscan.c), so move them out of the public
include/linux/swap.h into the mm-private mm/swap.h.  This keeps unrelated
declarations out of include/linux/swap.h.

Guard memcg->swappiness with CONFIG_MEMCG_V1 as well, so v2-only
kernels drop the unused field.

No functional change for v1; v2-only kernels drop the unused field.

Link: https://lore.kernel.org/20260723032434.2016749-1-ridong.chen@linux.dev
Link: https://lore.kernel.org/20260723032434.2016749-2-ridong.chen@linux.dev
Signed-off-by: Ridong Chen 
Acked-by: Johannes Weiner 
Reviewed-by: Barry Song 
Reviewed-by: Song Hu 
Acked-by: Shakeel Butt 
Cc: Axel Rasmussen 
Cc: Baoquan He 
Cc: Chris Li 
Cc: David Hildenbrand 
Cc: Davidlohr Bueso 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Lorenzo Stoakes 
Cc: Michal Hocko 
Cc: Muchun Song 
Cc: Nhat Pham 
Cc: Roman Gushchin 
Cc: Wei Xu 
Cc: Yuanchu Xie 
Cc: Qi Zheng 
Signed-off-by: Andrew Morton

mm: move reclaim-internal declarations out of swap.h

2026-08-05T02:18:35+00:00

Keep include/linux/swap.h focused on swap-facing interfaces by moving
MM-internal reclaim and workingset declarations into mm/internal.h.

Leave the small set of LRU helper declarations that are used outside mm/
in swap.h so this cleanup does not need a new public header under
include/linux/.

Link: https://lore.kernel.org/20260708-ch-swap-series-plus-folio-lru-cleanup-v9-3-2bc72b4f8730@gmail.com
Signed-off-by: Jianyue Wu 
Suggested-by: Barry Song 
Suggested-by: Baoquan He 
Acked-by: Johannes Weiner 
Cc: Axel Rasmussen 
Cc: Baolin Wang 
Cc: Chris Li 
Cc: David Hildenbrand 
Cc: Hugh Dickins 
Cc: Jonathan Corbet 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Liam R. Howlett 
Cc: Lorenzo Stoakes 
Cc: Matthew Wilcox (Oracle) 
Cc: Michal Hocko 
Cc: Michal Hocko 
Cc: Mike Rapoport 
Cc: Nhat Pham 
Cc: Shakeel Butt 
Cc: Suren Baghdasaryan 
Cc: Vlastimil Babka 
Cc: Wei Xu 
Cc: Yuanchu Xie 
Signed-off-by: Andrew Morton

mm/swap: colocate page-cluster sysctl with swap readahead

2026-08-05T02:18:34+00:00

Patch series "mm: clean up folio LRU and swap declarations", v9.

This series splits folio LRU and swap cleanup into three steps:

  - move the page-cluster sysctl next to swap readahead in
    mm/swap_state.c
  - rename mm/swap.c to mm/folio.c after the swap-specific code
    moves out
  - move MM-internal reclaim declarations out of include/linux/swap.h

After this series, swap cache and swap-in readahead stay in
mm/swap_state.c.  Folio LRU helpers live in mm/folio.c, and MM-internal
reclaim/workingset declarations move from include/linux/swap.h to
mm/internal.h (public LRU helpers used outside mm/ remain in swap.h).

The first patch handles the swap-specific page-cluster state before the
file rename, so the rename commit only carries folio LRU code.  The last
patch keeps the LRU helpers used outside mm/ in include/linux/swap.h and
moves the internal reclaim/workingset declarations to mm/internal.h.


This patch (of 3):

page_cluster and the vm.page-cluster sysctl are only used by swap-in
readahead in swap_state.c.  Move them out of swap.c together with
swap_readahead_setup(), and make page_cluster static to that file.

Rename swap_setup() while moving it as well.  The helper is internal to MM
and now only sets up swap readahead defaults and its sysctl hook, so the
more specific name matches its reduced scope.

Call swap_readahead_setup() from swap_init() after moving it, keeping the
readahead defaults and sysctl registration with swap_state.c
initialization.

swap_setup() previously lived in mm/swap.c, which is built
unconditionally, so the vm.page-cluster sysctl was registered also on
CONFIG_SWAP=n kernels.  After moving the setup into swap_state.c, which is
built only when CONFIG_SWAP is enabled, vm.page-cluster is no longer
registered there.  The knob only tunes swap-in readahead and had no effect
without swap.

Link: https://lore.kernel.org/20260708-ch-swap-series-plus-folio-lru-cleanup-v9-0-2bc72b4f8730@gmail.com
Link: https://lore.kernel.org/20260708-ch-swap-series-plus-folio-lru-cleanup-v9-1-2bc72b4f8730@gmail.com
Signed-off-by: Jianyue Wu 
Suggested-by: Baoquan He 
Suggested-by: Barry Song 
Suggested-by: Johannes Weiner 
Suggested-by: Matthew Wilcox 
Reviewed-by: Kairui Song 
Acked-by: Johannes Weiner 
Acked-by: David Hildenbrand (Arm) 
Cc: Axel Rasmussen 
Cc: Baolin Wang 
Cc: Chris Li 
Cc: Hugh Dickins 
Cc: Jonathan Corbet 
Cc: Kemeng Shi 
Cc: Liam R. Howlett 
Cc: Lorenzo Stoakes 
Cc: Michal Hocko 
Cc: Michal Hocko 
Cc: Mike Rapoport 
Cc: Nhat Pham 
Cc: Shakeel Butt 
Cc: Suren Baghdasaryan 
Cc: Vlastimil Babka 
Cc: Wei Xu 
Cc: Yuanchu Xie 
Signed-off-by: Andrew Morton

mm: constify oom_control, scan_control, and alloc_context nodemask

2026-07-29T04:12:04+00:00

The nodemasks in these structures may come from a variety of sources,
including tasks and cpusets - and should never be modified by any code
when being passed around inside another context.

Link: https://lore.kernel.org/20260609002919.3967782-1-gourry@gourry.net
Signed-off-by: Gregory Price 
Reviewed-by: Lorenzo Stoakes 
Acked-by: David Hildenbrand (Arm) 
Reviewed-by: Barry Song 
Acked-by: Vlastimil Babka (SUSE) 
Tested-by: SeongJae Park 
Acked-by: SeongJae Park 
Acked-by: Waiman Long 
Acked-by: Zi Yan 
Cc: Axel Rasmussen 
Cc: Baoquan He 
Cc: Brendan Jackman 
Cc: Chris Li 
Cc: David Rientjes 
Cc: Johannes Weiner 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Liam R. Howlett 
Cc: Michal Hocko 
Cc: Michal Koutný 
Cc: Mike Rapoport 
Cc: Nhat Pham 
Cc: Shakeel Butt 
Cc: Suren Baghdasaryan 
Cc: Tejun Heo 
Cc: Wei Xu 
Cc: Yuanchu Xie 
Signed-off-by: Andrew Morton

include/linux/swap.h: remove unused leftovers

2026-07-29T04:12:04+00:00

This removed unused leftovers, most of them are forward structure
declarations.  Also removes SWAP_BATCH macro which isn't used any where in
the code.

Found these during manual code review.

Link: https://lore.kernel.org/68591daf0d679e5a0072d63751f187d14613e2b0.1781146877.git.ritesh.list@gmail.com
Signed-off-by: Ritesh Harjani (IBM) 
Reviewed-by: Barry Song 
Acked-by: Chris Li 
Acked-by: David Hildenbrand (Arm) 
Cc: Baoquan He 
Cc: Kairui Song 
Cc: Kemeng Shi 
Cc: Nhat Pham 
Signed-off-by: Andrew Morton

mm/swap, PM: hibernate: fix swapoff race in uswsusp by pinning swap device

2026-06-09T01:21:31+00:00

Patch series "mm/swap, PM: hibernate: fix swapoff race in uswsusp by
pinning swap device", v8.

Currently, in the uswsusp path, only the swap type value is retrieved at
lookup time without holding a reference. If swapoff races after the type
is acquired, subsequent slot allocations operate on a stale swap device.

Additionally, grabbing and releasing the swap device reference on every
slot allocation is inefficient across the entire hibernation swap path.

This patch series addresses these issues:
- Patch 1: Fixes the swapoff race in uswsusp by pinning the swap device
  from the point it is looked up until the session completes.
- Patch 2: Removes the overhead of per-slot reference counting in alloc/free
  paths and cleans up the redundant SWP_WRITEOK check.


This patch (of 2):

Hibernation via uswsusp (/dev/snapshot ioctls) has a race window: after
selecting the resume swap area but before user space is frozen, swapoff
may run and invalidate the selected swap device.

Fix this by pinning the swap device with SWP_HIBERNATION while it is in
use.  The pin is exclusive, which is sufficient since hibernate_acquire()
already prevents concurrent hibernation sessions.

The kernel swsusp path (sysfs-based hibernate/resume) uses
find_hibernation_swap_type() which is not affected by the pin.  It freezes
user space before touching swap, so swapoff cannot race.

Introduce dedicated helpers:
- pin_hibernation_swap_type(): Look up and pin the swap device.
  Used by the uswsusp path.
- find_hibernation_swap_type(): Lookup without pinning.
  Used by the kernel swsusp path.
- unpin_hibernation_swap_type(): Clear the hibernation pin.

While a swap device is pinned, swapoff is prevented from proceeding.

Link: https://lore.kernel.org/20260323160822.1409904-1-youngjun.park@lge.com
Link: https://lore.kernel.org/20260323160822.1409904-2-youngjun.park@lge.com
Signed-off-by: Youngjun Park 
Reviewed-by: Kairui Song 
Cc: Baoquan He 
Cc: Barry Song 
Cc: Chris Li 
Cc: Kemeng Shi 
Cc: Nhat Pham 
Cc: "Rafael J . Wysocki" 
Signed-off-by: Andrew Morton