Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

1 files changed, 49 insertions, 50 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 567f12323f55..e1644a24009c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -80,29 +80,8 @@ enum mem_cgroup_events_target {
 	MEM_CGROUP_NTARGETS,
 };
 
-struct memcg_vmstats_percpu {
-	/* Local (CPU and cgroup) page state & events */
-	long			state[MEMCG_NR_STAT];
-	unsigned long		events[NR_VM_EVENT_ITEMS];
-
-	/* Delta calculation for lockless upward propagation */
-	long			state_prev[MEMCG_NR_STAT];
-	unsigned long		events_prev[NR_VM_EVENT_ITEMS];
-
-	/* Cgroup1: threshold notifications & softlimit tree updates */
-	unsigned long		nr_page_events;
-	unsigned long		targets[MEM_CGROUP_NTARGETS];
-};
-
-struct memcg_vmstats {
-	/* Aggregated (CPU and subtree) page state & events */
-	long			state[MEMCG_NR_STAT];
-	unsigned long		events[NR_VM_EVENT_ITEMS];
-
-	/* Pending child counts during tree propagation */
-	long			state_pending[MEMCG_NR_STAT];
-	unsigned long		events_pending[NR_VM_EVENT_ITEMS];
-};
+struct memcg_vmstats_percpu;
+struct memcg_vmstats;
 
 struct mem_cgroup_reclaim_iter {
 	struct mem_cgroup *position;
@@ -185,15 +164,6 @@ struct mem_cgroup_thresholds {
 	struct mem_cgroup_threshold_ary *spare;
 };
 
-#if defined(CONFIG_SMP)
-struct memcg_padding {
-	char x[0];
-} ____cacheline_internodealigned_in_smp;
-#define MEMCG_PADDING(name)      struct memcg_padding name
-#else
-#define MEMCG_PADDING(name)
-#endif
-
 /*
  * Remember four most recent foreign writebacks with dirty pages in this
  * cgroup.  Inode sharing is expected to be uncommon and, even if we miss
@@ -304,10 +274,10 @@ struct mem_cgroup {
 	spinlock_t		move_lock;
 	unsigned long		move_lock_flags;
 
-	MEMCG_PADDING(_pad1_);
+	CACHELINE_PADDING(_pad1_);
 
 	/* memory.stat */
-	struct memcg_vmstats	vmstats;
+	struct memcg_vmstats	*vmstats;
 
 	/* memory.events */
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
@@ -326,7 +296,7 @@ struct mem_cgroup {
 	struct list_head objcg_list;
 #endif
 
-	MEMCG_PADDING(_pad2_);
+	CACHELINE_PADDING(_pad2_);
 
 	/*
 	 * set > 0 if pages under this cgroup are moving to other cgroup.
@@ -350,14 +320,20 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
+#ifdef CONFIG_LRU_GEN
+	/* per-memcg mm_struct list */
+	struct lru_gen_mm_list mm_list;
+#endif
+
 	struct mem_cgroup_per_node *nodeinfo[];
 };
 
 /*
- * size of first charge trial. "32" comes from vmscan.c's magic value.
- * TODO: maybe necessary to use big numbers in big irons.
+ * size of first charge trial.
+ * TODO: maybe necessary to use big numbers in big irons or dynamic based of the
+ * workload.
  */
-#define MEMCG_CHARGE_BATCH 32U
+#define MEMCG_CHARGE_BATCH 64U
 
 extern struct mem_cgroup *root_mem_cgroup;
 
@@ -444,6 +420,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
  * - LRU isolation
  * - lock_page_memcg()
  * - exclusive reference
+ * - mem_cgroup_trylock_pages()
  *
  * For a kmem folio a caller should hold an rcu read lock to protect memcg
  * associated with a kmem folio from being released.
@@ -505,6 +482,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
  * - LRU isolation
  * - lock_page_memcg()
  * - exclusive reference
+ * - mem_cgroup_trylock_pages()
  *
  * For a kmem page a caller should hold an rcu read lock to protect memcg
  * associated with a kmem page from being released.
@@ -689,7 +667,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
 	return __mem_cgroup_charge(folio, mm, gfp);
 }
 
-int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
+int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
 				  gfp_t gfp, swp_entry_t entry);
 void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
 
@@ -959,6 +937,23 @@ void unlock_page_memcg(struct page *page);
 
 void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
 
+/* try to stablize folio_memcg() for all the pages in a memcg */
+static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
+{
+	rcu_read_lock();
+
+	if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account))
+		return true;
+
+	rcu_read_unlock();
+	return false;
+}
+
+static inline void mem_cgroup_unlock_pages(void)
+{
+	rcu_read_unlock();
+}
+
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
 				   int idx, int val)
@@ -985,15 +980,7 @@ static inline void mod_memcg_page_state(struct page *page,
 	rcu_read_unlock();
 }
 
-static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
-{
-	long x = READ_ONCE(memcg->vmstats.state[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
+unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
@@ -1238,7 +1225,7 @@ static inline int mem_cgroup_charge(struct folio *folio,
 	return 0;
 }
 
-static inline int mem_cgroup_swapin_charge_page(struct page *page,
+static inline int mem_cgroup_swapin_charge_folio(struct folio *folio,
 			struct mm_struct *mm, gfp_t gfp, swp_entry_t entry)
 {
 	return 0;
@@ -1433,6 +1420,18 @@ static inline void folio_memcg_unlock(struct folio *folio)
 {
 }
 
+static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
+{
+	/* to match folio_memcg_rcu() */
+	rcu_read_lock();
+	return true;
+}
+
+static inline void mem_cgroup_unlock_pages(void)
+{
+	rcu_read_unlock();
+}
+
 static inline void mem_cgroup_handle_over_high(void)
 {
 }
@@ -1779,7 +1778,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 {
 	struct mem_cgroup *memcg;
 
-	if (mem_cgroup_kmem_disabled())
+	if (!memcg_kmem_enabled())
 		return;
 
 	rcu_read_lock();