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, 246 insertions, 35 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 355d842d2731..5f74891556f3 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -24,10 +24,10 @@
 #include <asm/page.h>
 
 /* Free memory management - zoned buddy allocator.  */
-#ifndef CONFIG_FORCE_MAX_ZONEORDER
+#ifndef CONFIG_ARCH_FORCE_MAX_ORDER
 #define MAX_ORDER 11
 #else
-#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER
+#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
 #endif
 #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
 
@@ -121,20 +121,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype)
 
 struct pglist_data;
 
-/*
- * Add a wild amount of padding here to ensure data fall into separate
- * cachelines.  There are very few zone structures in the machine, so space
- * consumption is not a concern here.
- */
-#if defined(CONFIG_SMP)
-struct zone_padding {
-	char x[0];
-} ____cacheline_internodealigned_in_smp;
-#define ZONE_PADDING(name)	struct zone_padding name;
-#else
-#define ZONE_PADDING(name)
-#endif
-
 #ifdef CONFIG_NUMA
 enum numa_stat_item {
 	NUMA_HIT,		/* allocated in intended node */
@@ -222,6 +208,7 @@ enum node_stat_item {
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 	PGPROMOTE_SUCCESS,	/* promote successfully */
+	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
 #endif
 	NR_VM_NODE_STAT_ITEMS
 };
@@ -307,6 +294,8 @@ static inline bool is_active_lru(enum lru_list lru)
 	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
 }
 
+#define WORKINGSET_ANON 0
+#define WORKINGSET_FILE 1
 #define ANON_AND_FILE 2
 
 enum lruvec_flags {
@@ -315,6 +304,207 @@ enum lruvec_flags {
 					 */
 };
 
+#endif /* !__GENERATING_BOUNDS_H */
+
+/*
+ * Evictable pages are divided into multiple generations. The youngest and the
+ * oldest generation numbers, max_seq and min_seq, are monotonically increasing.
+ * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An
+ * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the
+ * corresponding generation. The gen counter in folio->flags stores gen+1 while
+ * a page is on one of lrugen->lists[]. Otherwise it stores 0.
+ *
+ * A page is added to the youngest generation on faulting. The aging needs to
+ * check the accessed bit at least twice before handing this page over to the
+ * eviction. The first check takes care of the accessed bit set on the initial
+ * fault; the second check makes sure this page hasn't been used since then.
+ * This process, AKA second chance, requires a minimum of two generations,
+ * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive
+ * LRU, e.g., /proc/vmstat, these two generations are considered active; the
+ * rest of generations, if they exist, are considered inactive. See
+ * lru_gen_is_active().
+ *
+ * PG_active is always cleared while a page is on one of lrugen->lists[] so that
+ * the aging needs not to worry about it. And it's set again when a page
+ * considered active is isolated for non-reclaiming purposes, e.g., migration.
+ * See lru_gen_add_folio() and lru_gen_del_folio().
+ *
+ * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the
+ * number of categories of the active/inactive LRU when keeping track of
+ * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits
+ * in folio->flags.
+ */
+#define MIN_NR_GENS		2U
+#define MAX_NR_GENS		4U
+
+/*
+ * Each generation is divided into multiple tiers. A page accessed N times
+ * through file descriptors is in tier order_base_2(N). A page in the first tier
+ * (N=0,1) is marked by PG_referenced unless it was faulted in through page
+ * tables or read ahead. A page in any other tier (N>1) is marked by
+ * PG_referenced and PG_workingset. This implies a minimum of two tiers is
+ * supported without using additional bits in folio->flags.
+ *
+ * In contrast to moving across generations which requires the LRU lock, moving
+ * across tiers only involves atomic operations on folio->flags and therefore
+ * has a negligible cost in the buffered access path. In the eviction path,
+ * comparisons of refaulted/(evicted+protected) from the first tier and the
+ * rest infer whether pages accessed multiple times through file descriptors
+ * are statistically hot and thus worth protecting.
+ *
+ * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the
+ * number of categories of the active/inactive LRU when keeping track of
+ * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in
+ * folio->flags.
+ */
+#define MAX_NR_TIERS		4U
+
+#ifndef __GENERATING_BOUNDS_H
+
+struct lruvec;
+struct page_vma_mapped_walk;
+
+#define LRU_GEN_MASK		((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
+#define LRU_REFS_MASK		((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
+
+#ifdef CONFIG_LRU_GEN
+
+enum {
+	LRU_GEN_ANON,
+	LRU_GEN_FILE,
+};
+
+enum {
+	LRU_GEN_CORE,
+	LRU_GEN_MM_WALK,
+	LRU_GEN_NONLEAF_YOUNG,
+	NR_LRU_GEN_CAPS
+};
+
+#define MIN_LRU_BATCH		BITS_PER_LONG
+#define MAX_LRU_BATCH		(MIN_LRU_BATCH * 64)
+
+/* whether to keep historical stats from evicted generations */
+#ifdef CONFIG_LRU_GEN_STATS
+#define NR_HIST_GENS		MAX_NR_GENS
+#else
+#define NR_HIST_GENS		1U
+#endif
+
+/*
+ * The youngest generation number is stored in max_seq for both anon and file
+ * types as they are aged on an equal footing. The oldest generation numbers are
+ * stored in min_seq[] separately for anon and file types as clean file pages
+ * can be evicted regardless of swap constraints.
+ *
+ * Normally anon and file min_seq are in sync. But if swapping is constrained,
+ * e.g., out of swap space, file min_seq is allowed to advance and leave anon
+ * min_seq behind.
+ *
+ * The number of pages in each generation is eventually consistent and therefore
+ * can be transiently negative when reset_batch_size() is pending.
+ */
+struct lru_gen_struct {
+	/* the aging increments the youngest generation number */
+	unsigned long max_seq;
+	/* the eviction increments the oldest generation numbers */
+	unsigned long min_seq[ANON_AND_FILE];
+	/* the birth time of each generation in jiffies */
+	unsigned long timestamps[MAX_NR_GENS];
+	/* the multi-gen LRU lists, lazily sorted on eviction */
+	struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+	/* the multi-gen LRU sizes, eventually consistent */
+	long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+	/* the exponential moving average of refaulted */
+	unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
+	/* the exponential moving average of evicted+protected */
+	unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
+	/* the first tier doesn't need protection, hence the minus one */
+	unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1];
+	/* can be modified without holding the LRU lock */
+	atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+	atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+	/* whether the multi-gen LRU is enabled */
+	bool enabled;
+};
+
+enum {
+	MM_LEAF_TOTAL,		/* total leaf entries */
+	MM_LEAF_OLD,		/* old leaf entries */
+	MM_LEAF_YOUNG,		/* young leaf entries */
+	MM_NONLEAF_TOTAL,	/* total non-leaf entries */
+	MM_NONLEAF_FOUND,	/* non-leaf entries found in Bloom filters */
+	MM_NONLEAF_ADDED,	/* non-leaf entries added to Bloom filters */
+	NR_MM_STATS
+};
+
+/* double-buffering Bloom filters */
+#define NR_BLOOM_FILTERS	2
+
+struct lru_gen_mm_state {
+	/* set to max_seq after each iteration */
+	unsigned long seq;
+	/* where the current iteration continues (inclusive) */
+	struct list_head *head;
+	/* where the last iteration ended (exclusive) */
+	struct list_head *tail;
+	/* to wait for the last page table walker to finish */
+	struct wait_queue_head wait;
+	/* Bloom filters flip after each iteration */
+	unsigned long *filters[NR_BLOOM_FILTERS];
+	/* the mm stats for debugging */
+	unsigned long stats[NR_HIST_GENS][NR_MM_STATS];
+	/* the number of concurrent page table walkers */
+	int nr_walkers;
+};
+
+struct lru_gen_mm_walk {
+	/* the lruvec under reclaim */
+	struct lruvec *lruvec;
+	/* unstable max_seq from lru_gen_struct */
+	unsigned long max_seq;
+	/* the next address within an mm to scan */
+	unsigned long next_addr;
+	/* to batch promoted pages */
+	int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+	/* to batch the mm stats */
+	int mm_stats[NR_MM_STATS];
+	/* total batched items */
+	int batched;
+	bool can_swap;
+	bool force_scan;
+};
+
+void lru_gen_init_lruvec(struct lruvec *lruvec);
+void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+
+#ifdef CONFIG_MEMCG
+void lru_gen_init_memcg(struct mem_cgroup *memcg);
+void lru_gen_exit_memcg(struct mem_cgroup *memcg);
+#endif
+
+#else /* !CONFIG_LRU_GEN */
+
+static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
+{
+}
+
+static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+{
+}
+
+#ifdef CONFIG_MEMCG
+static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
+{
+}
+
+static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg)
+{
+}
+#endif
+
+#endif /* CONFIG_LRU_GEN */
+
 struct lruvec {
 	struct list_head		lists[NR_LRU_LISTS];
 	/* per lruvec lru_lock for memcg */
@@ -332,6 +522,12 @@ struct lruvec {
 	unsigned long			refaults[ANON_AND_FILE];
 	/* Various lruvec state flags (enum lruvec_flags) */
 	unsigned long			flags;
+#ifdef CONFIG_LRU_GEN
+	/* evictable pages divided into generations */
+	struct lru_gen_struct		lrugen;
+	/* to concurrently iterate lru_gen_mm_list */
+	struct lru_gen_mm_state		mm_state;
+#endif
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
@@ -369,13 +565,6 @@ enum zone_watermarks {
 #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1))
 #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP)
 
-/*
- * Shift to encode migratetype and order in the same integer, with order
- * in the least significant bits.
- */
-#define NR_PCP_ORDER_WIDTH 8
-#define NR_PCP_ORDER_MASK ((1<<NR_PCP_ORDER_WIDTH) - 1)
-
 #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost)
 #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost)
 #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
@@ -628,7 +817,7 @@ struct zone {
 	int initialized;
 
 	/* Write-intensive fields used from the page allocator */
-	ZONE_PADDING(_pad1_)
+	CACHELINE_PADDING(_pad1_);
 
 	/* free areas of different sizes */
 	struct free_area	free_area[MAX_ORDER];
@@ -640,7 +829,7 @@ struct zone {
 	spinlock_t		lock;
 
 	/* Write-intensive fields used by compaction and vmstats. */
-	ZONE_PADDING(_pad2_)
+	CACHELINE_PADDING(_pad2_);
 
 	/*
 	 * When free pages are below this point, additional steps are taken
@@ -677,7 +866,7 @@ struct zone {
 
 	bool			contiguous;
 
-	ZONE_PADDING(_pad3_)
+	CACHELINE_PADDING(_pad3_);
 	/* Zone statistics */
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 	atomic_long_t		vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
@@ -747,6 +936,8 @@ static inline bool zone_is_empty(struct zone *zone)
 #define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
 #define LAST_CPUPID_PGOFF	(ZONES_PGOFF - LAST_CPUPID_WIDTH)
 #define KASAN_TAG_PGOFF		(LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
+#define LRU_GEN_PGOFF		(KASAN_TAG_PGOFF - LRU_GEN_WIDTH)
+#define LRU_REFS_PGOFF		(LRU_GEN_PGOFF - LRU_REFS_WIDTH)
 
 /*
  * Define the bit shifts to access each section.  For non-existent
@@ -954,8 +1145,10 @@ typedef struct pglist_data {
 	atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */
 	unsigned long nr_reclaim_start;	/* nr pages written while throttled
 					 * when throttling started. */
-	struct task_struct *kswapd;	/* Protected by
-					   mem_hotplug_begin/done() */
+#ifdef CONFIG_MEMORY_HOTPLUG
+	struct mutex kswapd_lock;
+#endif
+	struct task_struct *kswapd;	/* Protected by kswapd_lock */
 	int kswapd_order;
 	enum zone_type kswapd_highest_zoneidx;
 
@@ -983,7 +1176,7 @@ typedef struct pglist_data {
 #endif /* CONFIG_NUMA */
 
 	/* Write-intensive fields used by page reclaim */
-	ZONE_PADDING(_pad1_)
+	CACHELINE_PADDING(_pad1_);
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	/*
@@ -997,6 +1190,21 @@ typedef struct pglist_data {
 	struct deferred_split deferred_split_queue;
 #endif
 
+#ifdef CONFIG_NUMA_BALANCING
+	/* start time in ms of current promote rate limit period */
+	unsigned int nbp_rl_start;
+	/* number of promote candidate pages at start time of current rate limit period */
+	unsigned long nbp_rl_nr_cand;
+	/* promote threshold in ms */
+	unsigned int nbp_threshold;
+	/* start time in ms of current promote threshold adjustment period */
+	unsigned int nbp_th_start;
+	/*
+	 * number of promote candidate pages at stat time of current promote
+	 * threshold adjustment period
+	 */
+	unsigned long nbp_th_nr_cand;
+#endif
 	/* Fields commonly accessed by the page reclaim scanner */
 
 	/*
@@ -1008,11 +1216,19 @@ typedef struct pglist_data {
 
 	unsigned long		flags;
 
-	ZONE_PADDING(_pad2_)
+#ifdef CONFIG_LRU_GEN
+	/* kswap mm walk data */
+	struct lru_gen_mm_walk	mm_walk;
+#endif
+
+	CACHELINE_PADDING(_pad2_);
 
 	/* Per-node vmstats */
 	struct per_cpu_nodestat __percpu *per_cpu_nodestats;
 	atomic_long_t		vm_stat[NR_VM_NODE_STAT_ITEMS];
+#ifdef CONFIG_NUMA
+	struct memory_tier __rcu *memtier;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
@@ -1026,11 +1242,6 @@ static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 	return pgdat->node_start_pfn + pgdat->node_spanned_pages;
 }
 
-static inline bool pgdat_is_empty(pg_data_t *pgdat)
-{
-	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
-}
-
 #include <linux/memory_hotplug.h>
 
 void build_all_zonelists(pg_data_t *pgdat);