[PATCH v1 0/3] mm: process_mrelease: expedite clean file folio reclaim and add auto-kill

[PATCH v1 0/3] mm: process_mrelease: expedite clean file folio reclaim and add auto-kill

[Minchan Kim]

From: Minchan Kim <minchan@google.com>

This is v1 of the patch series to expedite clean file folio reclamation in
process_mrelease() and introduce an auto-kill flag to close race windows.

Currently, process_mrelease() unmaps pages but file-backed pages stay in
the pagecache, relying on standard memory reclaim to eventually free them.
This delays memory recovery in memory pressure scenarios (e.g., Android's
LMKD), leading to redundant kills of background apps. Also, the requirement
for userspace to send SIGKILL prior to process_mrelease() introduces a
race window where the victim task clears its ->mm before the reaper can
act, failing the syscall with -ESRCH and delaying reclamation due to
arbitrary reference counts (e.g., reading /proc/<pid>/cmdline).

Summary of v1 changes since last RFC
(https://lore.kernel.org/linux-mm/20260413223948.556351-1-minchan@kernel.org/)
- Patch 1:
  - Unified free_pages_and_caches() in mm/swap.c to handle both CONFIG_SWAP
    and !CONFIG_SWAP
  - Clean up description - David
- Patch 2:
  - Used !folio_maybe_mapped_shared(folio) instead of folio_mapcount - David
- Patch 3:
  - Used mmget() instead of mmgrab() to ensure that memory reclamation is
    performed synchronously and deterministically by the reaper, avoiding
    delays caused by non-deterministic scheduling of the victim task.
  - Dropped the custom KILL_MRELEASE signal code and modifications to
    siginfo.h and signal.c. Instead, use standard kill_pid(..., 0).

Minchan Kim (3):
  mm: process_mrelease: expedite clean file folio reclaim via mmu_gather
  mm: process_mrelease: skip LRU movement for exclusive file folios
  mm: process_mrelease: introduce PROCESS_MRELEASE_REAP_KILL flag

 arch/s390/include/asm/tlb.h |  2 +-
 include/linux/swap.h        |  5 ++--
 include/uapi/linux/mman.h   |  4 +++
 mm/memory.c                 | 13 ++++++++-
 mm/mmu_gather.c             |  7 +++--
 mm/oom_kill.c               | 56 ++++++++++++++++++++++++++-----------
 mm/swap.c                   | 42 ++++++++++++++++++++++++++++
 mm/swap_state.c             | 26 -----------------
 8 files changed, 104 insertions(+), 51 deletions(-)

-- 
2.54.0.rc1.555.g9c883467ad-goog

[PATCH v1 1/3] mm: process_mrelease: expedite clean file folio reclaim via mmu_gather

[Minchan Kim]

Currently, process_mrelease() unmaps pages but file-backed pages are
not evicted and stay in the pagecache, relying on standard memory reclaim
(kswapd or direct reclaim) to eventually free them. This delays the
immediate recovery of system memory under Android's LMKD scenarios,
leading to redundant background apps kills.

This patch implements an expedited eviction mechanism for clean pagecache
folios in the mmu_gather code, similar to how swapcache folios are handled.
It drops them from the pagecache (i.e., evicting them) if they are completely
unmapped during reaping.

Within this single unified loop, anonymous pages are released via
free_swap_cache(), and file-backed folios are symmetrically released via
free_file_cache().

Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 arch/s390/include/asm/tlb.h |  2 +-
 include/linux/swap.h        |  5 ++---
 mm/mmu_gather.c             |  7 ++++---
 mm/swap.c                   | 42 +++++++++++++++++++++++++++++++++++++
 mm/swap_state.c             | 26 -----------------------
 5 files changed, 49 insertions(+), 33 deletions(-)

diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 619fd41e710e..2736dbb571a8 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -62,7 +62,7 @@ static inline bool __tlb_remove_folio_pages(struct mmu_gather *tlb,
 	VM_WARN_ON_ONCE(delay_rmap);
 	VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1));
 
-	free_pages_and_swap_cache(encoded_pages, ARRAY_SIZE(encoded_pages));
+	free_pages_and_caches(tlb->mm, encoded_pages, ARRAY_SIZE(encoded_pages));
 	return false;
 }
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 62fc7499b408..bdb784966343 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -414,7 +414,9 @@ extern int sysctl_min_unmapped_ratio;
 extern int sysctl_min_slab_ratio;
 #endif
 
+struct mm_struct;
 void check_move_unevictable_folios(struct folio_batch *fbatch);
+void free_pages_and_caches(struct mm_struct *mm, struct encoded_page **pages, int nr);
 
 extern void __meminit kswapd_run(int nid);
 extern void __meminit kswapd_stop(int nid);
@@ -433,7 +435,6 @@ static inline unsigned long total_swapcache_pages(void)
 
 void free_swap_cache(struct folio *folio);
 void free_folio_and_swap_cache(struct folio *folio);
-void free_pages_and_swap_cache(struct encoded_page **, int);
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
@@ -510,8 +511,6 @@ static inline void put_swap_device(struct swap_info_struct *si)
 	do { (val)->freeswap = (val)->totalswap = 0; } while (0)
 #define free_folio_and_swap_cache(folio) \
 	folio_put(folio)
-#define free_pages_and_swap_cache(pages, nr) \
-	release_pages((pages), (nr));
 
 static inline void free_swap_cache(struct folio *folio)
 {
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index fe5b6a031717..3c6c315d3c48 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -100,7 +100,8 @@ void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma)
  */
 #define MAX_NR_FOLIOS_PER_FREE		512
 
-static void __tlb_batch_free_encoded_pages(struct mmu_gather_batch *batch)
+static void __tlb_batch_free_encoded_pages(struct mm_struct *mm,
+		struct mmu_gather_batch *batch)
 {
 	struct encoded_page **pages = batch->encoded_pages;
 	unsigned int nr, nr_pages;
@@ -135,7 +136,7 @@ static void __tlb_batch_free_encoded_pages(struct mmu_gather_batch *batch)
 			}
 		}
 
-		free_pages_and_swap_cache(pages, nr);
+		free_pages_and_caches(mm, pages, nr);
 		pages += nr;
 		batch->nr -= nr;
 
@@ -148,7 +149,7 @@ static void tlb_batch_pages_flush(struct mmu_gather *tlb)
 	struct mmu_gather_batch *batch;
 
 	for (batch = &tlb->local; batch && batch->nr; batch = batch->next)
-		__tlb_batch_free_encoded_pages(batch);
+		__tlb_batch_free_encoded_pages(tlb->mm, batch);
 	tlb->active = &tlb->local;
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index bb19ccbece46..e44bc8cefceb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1043,6 +1043,48 @@ void release_pages(release_pages_arg arg, int nr)
 }
 EXPORT_SYMBOL(release_pages);
 
+static inline void free_file_cache(struct folio *folio)
+{
+	if (folio_trylock(folio)) {
+		mapping_evict_folio(folio_mapping(folio), folio);
+		folio_unlock(folio);
+	}
+}
+
+/*
+ * Passed an array of pages, drop them all from swapcache and then release
+ * them.  They are removed from the LRU and freed if this is their last use.
+ *
+ * If @try_evict_file_folios is true, this function will proactively evict clean
+ * file-backed folios if they are no longer mapped.
+ */
+void free_pages_and_caches(struct mm_struct *mm, struct encoded_page **pages, int nr)
+{
+	bool try_evict_file_folios = mm_flags_test(MMF_UNSTABLE, mm);
+	struct folio_batch folios;
+	unsigned int refs[PAGEVEC_SIZE];
+
+	folio_batch_init(&folios);
+	for (int i = 0; i < nr; i++) {
+		struct folio *folio = page_folio(encoded_page_ptr(pages[i]));
+
+		if (folio_test_anon(folio))
+			free_swap_cache(folio);
+		else if (unlikely(try_evict_file_folios))
+			free_file_cache(folio);
+
+		refs[folios.nr] = 1;
+		if (unlikely(encoded_page_flags(pages[i]) &
+			     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
+			refs[folios.nr] = encoded_nr_pages(pages[++i]);
+
+		if (folio_batch_add(&folios, folio) == 0)
+			folios_put_refs(&folios, refs);
+	}
+	if (folios.nr)
+		folios_put_refs(&folios, refs);
+}
+
 /*
  * The folios which we're about to release may be in the deferred lru-addition
  * queues.  That would prevent them from really being freed right now.  That's
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 6d0eef7470be..7576bf36d920 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -400,32 +400,6 @@ void free_folio_and_swap_cache(struct folio *folio)
 		folio_put(folio);
 }
 
-/*
- * Passed an array of pages, drop them all from swapcache and then release
- * them.  They are removed from the LRU and freed if this is their last use.
- */
-void free_pages_and_swap_cache(struct encoded_page **pages, int nr)
-{
-	struct folio_batch folios;
-	unsigned int refs[PAGEVEC_SIZE];
-
-	folio_batch_init(&folios);
-	for (int i = 0; i < nr; i++) {
-		struct folio *folio = page_folio(encoded_page_ptr(pages[i]));
-
-		free_swap_cache(folio);
-		refs[folios.nr] = 1;
-		if (unlikely(encoded_page_flags(pages[i]) &
-			     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
-			refs[folios.nr] = encoded_nr_pages(pages[++i]);
-
-		if (folio_batch_add(&folios, folio) == 0)
-			folios_put_refs(&folios, refs);
-	}
-	if (folios.nr)
-		folios_put_refs(&folios, refs);
-}
-
 static inline bool swap_use_vma_readahead(void)
 {
 	return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
-- 
2.54.0.rc1.555.g9c883467ad-goog

[PATCH v1 2/3] mm: process_mrelease: skip LRU movement for exclusive file folios

[Minchan Kim]

For the process_mrelease reclaim, skip LRU handling for exclusive
file-backed folios since they will be freed soon so pointless
to move around in the LRU.

This avoids costly LRU movement which accounts for a significant portion
of the time during unmap_page_range.

-   91.31%     0.00%  mmap_exit_test   [kernel.kallsyms]  [.] exit_mm
     exit_mm
     __mmput
     exit_mmap
     unmap_vmas
   - unmap_page_range
      - 55.75% folio_mark_accessed
         + 48.79% __folio_batch_add_and_move
           4.23% workingset_activation
      + 12.94% folio_remove_rmap_ptes
      + 9.86% page_table_check_clear
      + 3.34% tlb_flush_mmu
        1.06% __page_table_check_pte_clear

Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 mm/memory.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/mm/memory.c b/mm/memory.c
index 2f815a34d924..fcb57630bb8d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1640,6 +1640,8 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
 	bool delay_rmap = false;
 
 	if (!folio_test_anon(folio)) {
+		bool skip_mark_accessed;
+
 		ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm);
 		if (pte_dirty(ptent)) {
 			folio_mark_dirty(folio);
@@ -1648,7 +1650,16 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
 				*force_flush = true;
 			}
 		}
-		if (pte_young(ptent) && likely(vma_has_recency(vma)))
+
+		/*
+		 * For the process_mrelease reclaim, skip LRU handling for exclusive
+		 * file-backed folios since they will be freed soon so pointless
+		 * to move around in the LRU.
+		 */
+		skip_mark_accessed = mm_flags_test(MMF_UNSTABLE, mm) &&
+				     !folio_maybe_mapped_shared(folio);
+		if (likely(!skip_mark_accessed) && pte_young(ptent) &&
+		    likely(vma_has_recency(vma)))
 			folio_mark_accessed(folio);
 		rss[mm_counter(folio)] -= nr;
 	} else {
-- 
2.54.0.rc1.555.g9c883467ad-goog

[PATCH v1 3/3] mm: process_mrelease: introduce PROCESS_MRELEASE_REAP_KILL flag

[Minchan Kim]

Currently, process_mrelease() requires userspace to send a SIGKILL signal
prior to the call. This separation introduces a scheduling race window
where the victim task may receive the signal and enter the exit path
before the reaper can invoke process_mrelease().

When the victim enters the exit path (do_exit -> exit_mm), it clears its
task->mm immediately. This causes process_mrelease() to fail with -ESRCH,
leaving the actual address space teardown (exit_mmap) to be deferred until
the mm's reference count drops to zero. In Android, arbitrary reference counts
(e.g., async I/O, reading /proc/<pid>/cmdline, or various other remote
VM accesses) frequently delay this teardown indefinitely, defeating the
purpose of expedited reclamation.

This delay keeps memory pressure high, forcing the system to unnecessarily
kill additional innocent background apps before the memory from the first
victim is recovered.

This patch introduces the PROCESS_MRELEASE_REAP_KILL UAPI flag to support
an integrated auto-kill mode. When specified, process_mrelease() directly
injects a SIGKILL into the target task.

To solve the race condition deterministically, we grab the mm reference
via mmget() and set the MMF_UNSTABLE flag *before* sending the SIGKILL.
Using mmget() instead of mmgrab() keeps mm_users > 0, preventing the
victim from calling exit_mmap() in its own exit path. This ensures that
the memory is reclaimed synchronously and deterministically by the reaper
in the context of process_mrelease(), avoiding delays caused by
non-deterministic scheduling of the victim task.

Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 include/uapi/linux/mman.h |  4 +++
 mm/oom_kill.c             | 56 +++++++++++++++++++++++++++------------
 2 files changed, 43 insertions(+), 17 deletions(-)

diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h
index e89d00528f2f..4266976b45ad 100644
--- a/include/uapi/linux/mman.h
+++ b/include/uapi/linux/mman.h
@@ -56,4 +56,8 @@ struct cachestat {
 	__u64 nr_recently_evicted;
 };
 
+/* Flags for process_mrelease */
+#define PROCESS_MRELEASE_REAP_KILL	(1 << 0)
+#define PROCESS_MRELEASE_VALID_FLAGS	(PROCESS_MRELEASE_REAP_KILL)
+
 #endif /* _UAPI_LINUX_MMAN_H */
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5c6c95c169ee..730ba0d19b53 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -20,6 +20,7 @@
 
 #include <linux/oom.h>
 #include <linux/mm.h>
+#include <uapi/linux/mman.h>
 #include <linux/err.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
@@ -850,7 +851,7 @@ bool oom_killer_disable(signed long timeout)
 	return true;
 }
 
-static inline bool __task_will_free_mem(struct task_struct *task)
+static inline bool __task_will_free_mem(struct task_struct *task, bool ignore_exit)
 {
 	struct signal_struct *sig = task->signal;
 
@@ -862,6 +863,9 @@ static inline bool __task_will_free_mem(struct task_struct *task)
 	if (sig->core_state)
 		return false;
 
+	if (ignore_exit)
+		return true;
+
 	if (sig->flags & SIGNAL_GROUP_EXIT)
 		return true;
 
@@ -878,7 +882,7 @@ static inline bool __task_will_free_mem(struct task_struct *task)
  * Caller has to make sure that task->mm is stable (hold task_lock or
  * it operates on the current).
  */
-static bool task_will_free_mem(struct task_struct *task)
+static bool task_will_free_mem(struct task_struct *task, bool ignore_exit)
 {
 	struct mm_struct *mm = task->mm;
 	struct task_struct *p;
@@ -892,7 +896,7 @@ static bool task_will_free_mem(struct task_struct *task)
 	if (!mm)
 		return false;
 
-	if (!__task_will_free_mem(task))
+	if (!__task_will_free_mem(task, ignore_exit))
 		return false;
 
 	/*
@@ -916,7 +920,7 @@ static bool task_will_free_mem(struct task_struct *task)
 			continue;
 		if (same_thread_group(task, p))
 			continue;
-		ret = __task_will_free_mem(p);
+		ret = __task_will_free_mem(p, false);
 		if (!ret)
 			break;
 	}
@@ -1034,7 +1038,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	 * so it can die quickly
 	 */
 	task_lock(victim);
-	if (task_will_free_mem(victim)) {
+	if (task_will_free_mem(victim, false)) {
 		mark_oom_victim(victim);
 		queue_oom_reaper(victim);
 		task_unlock(victim);
@@ -1135,7 +1139,7 @@ bool out_of_memory(struct oom_control *oc)
 	 * select it.  The goal is to allow it to allocate so that it may
 	 * quickly exit and free its memory.
 	 */
-	if (task_will_free_mem(current)) {
+	if (task_will_free_mem(current, false)) {
 		mark_oom_victim(current);
 		queue_oom_reaper(current);
 		return true;
@@ -1217,8 +1221,9 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
 	unsigned int f_flags;
 	bool reap = false;
 	long ret = 0;
+	bool reap_kill;
 
-	if (flags)
+	if (flags & ~PROCESS_MRELEASE_VALID_FLAGS)
 		return -EINVAL;
 
 	task = pidfd_get_task(pidfd, &f_flags);
@@ -1236,19 +1241,33 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
 	}
 
 	mm = p->mm;
-	mmgrab(mm);
 
-	if (task_will_free_mem(p))
-		reap = true;
-	else {
-		/* Error only if the work has not been done already */
-		if (!mm_flags_test(MMF_OOM_SKIP, mm))
+	reap_kill = !!(flags & PROCESS_MRELEASE_REAP_KILL);
+	reap = task_will_free_mem(p, reap_kill);
+	if (!reap) {
+		if (reap_kill || !mm_flags_test(MMF_OOM_SKIP, mm))
 			ret = -EINVAL;
+
+		task_unlock(p);
+		goto put_task;
 	}
-	task_unlock(p);
 
-	if (!reap)
-		goto drop_mm;
+	if (reap_kill) {
+		/*
+		 * We use mmget() instead of mmgrab() to keep mm_users > 0,
+		 * preventing the victim from calling exit_mmap() in its
+		 * own exit path. This ensures that the memory is reclaimed
+		 * synchronously and deterministically by the reaper.
+		 */
+		mmget(mm);
+		task_unlock(p);
+		ret = kill_pid(task_tgid(task), SIGKILL, 0);
+		if (ret)
+			goto drop_mm;
+	} else {
+		mmgrab(mm);
+		task_unlock(p);
+	}
 
 	if (mmap_read_lock_killable(mm)) {
 		ret = -EINTR;
@@ -1263,7 +1282,10 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
 	mmap_read_unlock(mm);
 
 drop_mm:
-	mmdrop(mm);
+	if (reap_kill)
+		mmput(mm);
+	else
+		mmdrop(mm);
 put_task:
 	put_task_struct(task);
 	return ret;
-- 
2.54.0.rc1.555.g9c883467ad-goog