Merge tag 'mm-stable-2026-04-18-02-14' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:

 - "Eliminate Dying Memory Cgroup" (Qi Zheng and Muchun Song)

   Address the longstanding "dying memcg problem". A situation wherein a
   no-longer-used memory control group will hang around for an extended
   period pointlessly consuming memory

 - "fix unexpected type conversions and potential overflows" (Qi Zheng)

   Fix a couple of potential 32-bit/64-bit issues which were identified
   during review of the "Eliminate Dying Memory Cgroup" series

 - "kho: history: track previous kernel version and kexec boot count"
   (Breno Leitao)

   Use Kexec Handover (KHO) to pass the previous kernel's version string
   and the number of kexec reboots since the last cold boot to the next
   kernel, and print it at boot time

 - "liveupdate: prevent double preservation" (Pasha Tatashin)

   Teach LUO to avoid managing the same file across different active
   sessions

 - "liveupdate: Fix module unloading and unregister API" (Pasha
   Tatashin)

   Address an issue with how LUO handles module reference counting and
   unregistration during module unloading

 - "zswap pool per-CPU acomp_ctx simplifications" (Kanchana Sridhar)

   Simplify and clean up the zswap crypto compression handling and
   improve the lifecycle management of zswap pool's per-CPU acomp_ctx
   resources

 - "mm/damon/core: fix damon_call()/damos_walk() vs kdmond exit race"
   (SeongJae Park)

   Address unlikely but possible leaks and deadlocks in damon_call() and
   damon_walk()

 - "mm/damon/core: validate damos_quota_goal->nid" (SeongJae Park)

   Fix a couple of root-only wild pointer dereferences

 - "Docs/admin-guide/mm/damon: warn commit_inputs vs other params race"
   (SeongJae Park)

   Update the DAMON documentation to warn operators about potential
   races which can occur if the commit_inputs parameter is altered at
   the wrong time

 - "Minor hmm_test fixes and cleanups" (Alistair Popple)

   Bugfixes and a cleanup for the HMM kernel selftests

 - "Modify memfd_luo code" (Chenghao Duan)

   Cleanups, simplifications and speedups to the memfd_lou code

 - "mm, kvm: allow uffd support in guest_memfd" (Mike Rapoport)

   Support for userfaultfd in guest_memfd

 - "selftests/mm: skip several tests when thp is not available" (Chunyu
   Hu)

   Fix several issues in the selftests code which were causing breakage
   when the tests were run on CONFIG_THP=n kernels

 - "mm/mprotect: micro-optimization work" (Pedro Falcato)

   A couple of nice speedups for mprotect()

 - "MAINTAINERS: update KHO and LIVE UPDATE entries" (Pratyush Yadav)

   Document upcoming changes in the maintenance of KHO, LUO, memfd_luo,
   kexec, crash, kdump and probably other kexec-based things - they are
   being moved out of mm.git and into a new git tree

* tag 'mm-stable-2026-04-18-02-14' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (121 commits)
  MAINTAINERS: add page cache reviewer
  mm/vmscan: avoid false-positive -Wuninitialized warning
  MAINTAINERS: update Dave's kdump reviewer email address
  MAINTAINERS: drop include/linux/liveupdate from LIVE UPDATE
  MAINTAINERS: drop include/linux/kho/abi/ from KHO
  MAINTAINERS: update KHO and LIVE UPDATE maintainers
  MAINTAINERS: update kexec/kdump maintainers entries
  mm/migrate_device: remove dead migration entry check in migrate_vma_collect_huge_pmd()
  selftests: mm: skip charge_reserved_hugetlb without killall
  userfaultfd: allow registration of ranges below mmap_min_addr
  mm/vmstat: fix vmstat_shepherd double-scheduling vmstat_update
  mm/hugetlb: fix early boot crash on parameters without '=' separator
  zram: reject unrecognized type= values in recompress_store()
  docs: proc: document ProtectionKey in smaps
  mm/mprotect: special-case small folios when applying permissions
  mm/mprotect: move softleaf code out of the main function
  mm: remove '!root_reclaim' checking in should_abort_scan()
  mm/sparse: fix comment for section map alignment
  mm/page_io: use sio->len for PSWPIN accounting in sio_read_complete()
  selftests/mm: transhuge_stress: skip the test when thp not available
  ...

1 files changed, 97 insertions, 94 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5173a9f16721..dc3fa687759b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -115,6 +115,16 @@ struct mem_cgroup_per_node {
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 	struct mem_cgroup_reclaim_iter	iter;
 
+	/*
+	 * objcg is wiped out as a part of the objcg repaprenting process.
+	 * orig_objcg preserves a pointer (and a reference) to the original
+	 * objcg until the end of live of memcg.
+	 */
+	struct obj_cgroup __rcu	*objcg;
+	struct obj_cgroup	*orig_objcg;
+	/* list of inherited objcgs, protected by objcg_lock */
+	struct list_head objcg_list;
+
 #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
 	/* slab stats for nmi context */
 	atomic_t		slab_reclaimable;
@@ -179,6 +189,7 @@ struct obj_cgroup {
 		struct list_head list; /* protected by objcg_lock */
 		struct rcu_head rcu;
 	};
+	bool is_root;
 };
 
 /*
@@ -257,15 +268,6 @@ struct mem_cgroup {
 	seqlock_t		socket_pressure_seqlock;
 #endif
 	int kmemcg_id;
-	/*
-	 * memcg->objcg is wiped out as a part of the objcg repaprenting
-	 * process. memcg->orig_objcg preserves a pointer (and a reference)
-	 * to the original objcg until the end of live of memcg.
-	 */
-	struct obj_cgroup __rcu	*objcg;
-	struct obj_cgroup	*orig_objcg;
-	/* list of inherited objcgs, protected by objcg_lock */
-	struct list_head objcg_list;
 
 	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
 
@@ -367,9 +369,6 @@ enum objext_flags {
 #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1)
 
 #ifdef CONFIG_MEMCG
-
-static inline bool folio_memcg_kmem(struct folio *folio);
-
 /*
  * After the initialization objcg->memcg is always pointing at
  * a valid memcg, but can be atomically swapped to the parent memcg.
@@ -383,43 +382,19 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
 }
 
 /*
- * __folio_memcg - Get the memory cgroup associated with a non-kmem folio
- * @folio: Pointer to the folio.
- *
- * Returns a pointer to the memory cgroup associated with the folio,
- * or NULL. This function assumes that the folio is known to have a
- * proper memory cgroup pointer. It's not safe to call this function
- * against some type of folios, e.g. slab folios or ex-slab folios or
- * kmem folios.
- */
-static inline struct mem_cgroup *__folio_memcg(struct folio *folio)
-{
-	unsigned long memcg_data = folio->memcg_data;
-
-	VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
-	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio);
-	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);
-
-	return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
-}
-
-/*
- * __folio_objcg - get the object cgroup associated with a kmem folio.
+ * folio_objcg - get the object cgroup associated with a folio.
  * @folio: Pointer to the folio.
  *
  * Returns a pointer to the object cgroup associated with the folio,
  * or NULL. This function assumes that the folio is known to have a
- * proper object cgroup pointer. It's not safe to call this function
- * against some type of folios, e.g. slab folios or ex-slab folios or
- * LRU folios.
+ * proper object cgroup pointer.
  */
-static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
+static inline struct obj_cgroup *folio_objcg(struct folio *folio)
 {
 	unsigned long memcg_data = folio->memcg_data;
 
 	VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
 	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio);
-	VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);
 
 	return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
 }
@@ -433,21 +408,30 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
  * proper memory cgroup pointer. It's not safe to call this function
  * against some type of folios, e.g. slab folios or ex-slab folios.
  *
- * For a non-kmem folio any of the following ensures folio and memcg binding
- * stability:
+ * For a folio any of the following ensures folio and objcg binding stability:
  *
  * - the folio lock
  * - LRU isolation
  * - exclusive reference
  *
- * For a kmem folio a caller should hold an rcu read lock to protect memcg
- * associated with a kmem folio from being released.
+ * Based on the stable binding of folio and objcg, for a folio any of the
+ * following ensures folio and memcg binding stability:
+ *
+ * - cgroup_mutex
+ * - the lruvec lock
+ *
+ * If the caller only want to ensure that the page counters of memcg are
+ * updated correctly, ensure that the binding stability of folio and objcg
+ * is sufficient.
+ *
+ * Note: The caller should hold an rcu read lock or cgroup_mutex to protect
+ * memcg associated with a folio from being released.
  */
 static inline struct mem_cgroup *folio_memcg(struct folio *folio)
 {
-	if (folio_memcg_kmem(folio))
-		return obj_cgroup_memcg(__folio_objcg(folio));
-	return __folio_memcg(folio);
+	struct obj_cgroup *objcg = folio_objcg(folio);
+
+	return objcg ? obj_cgroup_memcg(objcg) : NULL;
 }
 
 /*
@@ -471,15 +455,10 @@ static inline bool folio_memcg_charged(struct folio *folio)
  * has an associated memory cgroup pointer or an object cgroups vector or
  * an object cgroup.
  *
- * For a non-kmem folio any of the following ensures folio and memcg binding
- * stability:
+ * The page and objcg or memcg binding rules can refer to folio_memcg().
  *
- * - the folio lock
- * - LRU isolation
- * - exclusive reference
- *
- * For a kmem folio a caller should hold an rcu read lock to protect memcg
- * associated with a kmem folio from being released.
+ * A caller should hold an rcu read lock to protect memcg associated with a
+ * page from being released.
  */
 static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
 {
@@ -488,18 +467,14 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
 	 * for slabs, READ_ONCE() should be used here.
 	 */
 	unsigned long memcg_data = READ_ONCE(folio->memcg_data);
+	struct obj_cgroup *objcg;
 
 	if (memcg_data & MEMCG_DATA_OBJEXTS)
 		return NULL;
 
-	if (memcg_data & MEMCG_DATA_KMEM) {
-		struct obj_cgroup *objcg;
+	objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
 
-		objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
-		return obj_cgroup_memcg(objcg);
-	}
-
-	return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
+	return objcg ? obj_cgroup_memcg(objcg) : NULL;
 }
 
 static inline struct mem_cgroup *page_memcg_check(struct page *page)
@@ -548,6 +523,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 	return (memcg == root_mem_cgroup);
 }
 
+static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg)
+{
+	return objcg->is_root;
+}
+
 static inline bool mem_cgroup_disabled(void)
 {
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
@@ -735,7 +715,15 @@ out:
  * folio_lruvec - return lruvec for isolating/putting an LRU folio
  * @folio: Pointer to the folio.
  *
- * This function relies on folio->mem_cgroup being stable.
+ * Call with rcu_read_lock() held to ensure the lifetime of the returned lruvec.
+ * Note that this alone will NOT guarantee the stability of the folio->lruvec
+ * association; the folio can be reparented to an ancestor if this races with
+ * cgroup deletion.
+ *
+ * Use folio_lruvec_lock() to ensure both lifetime and stability of the binding.
+ * Once a lruvec is locked, folio_lruvec() can be called on other folios, and
+ * their binding is stable if the returned lruvec matches the one the caller has
+ * locked. Useful for lock batching.
  */
 static inline struct lruvec *folio_lruvec(struct folio *folio)
 {
@@ -758,15 +746,6 @@ struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
 						unsigned long *flags);
 
-#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio);
-#else
-static inline
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
-{
-}
-#endif
-
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
@@ -774,23 +753,26 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 
 static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg)
 {
+	if (obj_cgroup_is_root(objcg))
+		return true;
 	return percpu_ref_tryget(&objcg->refcnt);
 }
 
-static inline void obj_cgroup_get(struct obj_cgroup *objcg)
+static inline void obj_cgroup_get_many(struct obj_cgroup *objcg,
+				       unsigned long nr)
 {
-	percpu_ref_get(&objcg->refcnt);
+	if (!obj_cgroup_is_root(objcg))
+		percpu_ref_get_many(&objcg->refcnt, nr);
 }
 
-static inline void obj_cgroup_get_many(struct obj_cgroup *objcg,
-				       unsigned long nr)
+static inline void obj_cgroup_get(struct obj_cgroup *objcg)
 {
-	percpu_ref_get_many(&objcg->refcnt, nr);
+	obj_cgroup_get_many(objcg, 1);
 }
 
 static inline void obj_cgroup_put(struct obj_cgroup *objcg)
 {
-	if (objcg)
+	if (objcg && !obj_cgroup_is_root(objcg))
 		percpu_ref_put(&objcg->refcnt);
 }
 
@@ -885,7 +867,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return match;
 }
 
-struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio);
+struct cgroup_subsys_state *get_mem_cgroup_css_from_folio(struct folio *folio);
 ino_t page_cgroup_ino(struct page *page);
 
 static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
@@ -896,7 +878,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 }
 
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
-		int zid, int nr_pages);
+		int zid, long nr_pages);
 
 static inline
 unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
@@ -966,10 +948,15 @@ void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 static inline void count_memcg_folio_events(struct folio *folio,
 		enum vm_event_item idx, unsigned long nr)
 {
-	struct mem_cgroup *memcg = folio_memcg(folio);
+	struct mem_cgroup *memcg;
 
-	if (memcg)
-		count_memcg_events(memcg, idx, nr);
+	if (!folio_memcg_charged(folio))
+		return;
+
+	rcu_read_lock();
+	memcg = folio_memcg(folio);
+	count_memcg_events(memcg, idx, nr);
+	rcu_read_unlock();
 }
 
 static inline void count_memcg_events_mm(struct mm_struct *mm,
@@ -1087,6 +1074,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 	return true;
 }
 
+static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg)
+{
+	return true;
+}
+
 static inline bool mem_cgroup_disabled(void)
 {
 	return true;
@@ -1179,11 +1171,6 @@ static inline struct lruvec *folio_lruvec(struct folio *folio)
 	return &pgdat->__lruvec;
 }
 
-static inline
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
-{
-}
-
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	return NULL;
@@ -1242,6 +1229,7 @@ static inline struct lruvec *folio_lruvec_lock(struct folio *folio)
 {
 	struct pglist_data *pgdat = folio_pgdat(folio);
 
+	rcu_read_lock();
 	spin_lock(&pgdat->__lruvec.lru_lock);
 	return &pgdat->__lruvec;
 }
@@ -1250,6 +1238,7 @@ static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
 {
 	struct pglist_data *pgdat = folio_pgdat(folio);
 
+	rcu_read_lock();
 	spin_lock_irq(&pgdat->__lruvec.lru_lock);
 	return &pgdat->__lruvec;
 }
@@ -1259,6 +1248,7 @@ static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
 {
 	struct pglist_data *pgdat = folio_pgdat(folio);
 
+	rcu_read_lock();
 	spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
 	return &pgdat->__lruvec;
 }
@@ -1479,20 +1469,28 @@ static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 	return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
 }
 
-static inline void unlock_page_lruvec(struct lruvec *lruvec)
+static inline void lruvec_lock_irq(struct lruvec *lruvec)
+{
+	rcu_read_lock();
+	spin_lock_irq(&lruvec->lru_lock);
+}
+
+static inline void lruvec_unlock(struct lruvec *lruvec)
 {
 	spin_unlock(&lruvec->lru_lock);
+	rcu_read_unlock();
 }
 
-static inline void unlock_page_lruvec_irq(struct lruvec *lruvec)
+static inline void lruvec_unlock_irq(struct lruvec *lruvec)
 {
 	spin_unlock_irq(&lruvec->lru_lock);
+	rcu_read_unlock();
 }
 
-static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
-		unsigned long flags)
+static inline void lruvec_unlock_irqrestore(struct lruvec *lruvec, unsigned long flags)
 {
 	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
+	rcu_read_unlock();
 }
 
 /* Test requires a stable folio->memcg binding, see folio_memcg() */
@@ -1511,7 +1509,7 @@ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio,
 		if (folio_matches_lruvec(folio, locked_lruvec))
 			return locked_lruvec;
 
-		unlock_page_lruvec_irq(locked_lruvec);
+		lruvec_unlock_irq(locked_lruvec);
 	}
 
 	return folio_lruvec_lock_irq(folio);
@@ -1525,7 +1523,7 @@ static inline void folio_lruvec_relock_irqsave(struct folio *folio,
 		if (folio_matches_lruvec(folio, *lruvecp))
 			return;
 
-		unlock_page_lruvec_irqrestore(*lruvecp, *flags);
+		lruvec_unlock_irqrestore(*lruvecp, *flags);
 	}
 
 	*lruvecp = folio_lruvec_lock_irqsave(folio, flags);
@@ -1549,9 +1547,14 @@ static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
 	if (mem_cgroup_disabled())
 		return;
 
+	if (!folio_memcg_charged(folio))
+		return;
+
+	rcu_read_lock();
 	memcg = folio_memcg(folio);
-	if (unlikely(memcg && &memcg->css != wb->memcg_css))
+	if (unlikely(&memcg->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
+	rcu_read_unlock();
 }
 
 void mem_cgroup_flush_foreign(struct bdi_writeback *wb);