Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

1 files changed, 25 insertions, 26 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6c1c2fc13017..5e50b78d58ea 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -105,6 +105,9 @@ extern int page_group_by_mobility_disabled;
 #define get_pageblock_migratetype(page)					\
 	get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK)
 
+#define folio_migratetype(folio)				\
+	get_pfnblock_flags_mask(&folio->page, folio_pfn(folio),		\
+			MIGRATETYPE_MASK)
 struct free_area {
 	struct list_head	free_list[MIGRATE_TYPES];
 	unsigned long		nr_free;
@@ -293,9 +296,21 @@ static inline bool is_active_lru(enum lru_list lru)
 #define ANON_AND_FILE 2
 
 enum lruvec_flags {
-	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
-					 * backed by a congested BDI
-					 */
+	/*
+	 * An lruvec has many dirty pages backed by a congested BDI:
+	 * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim.
+	 *    It can be cleared by cgroup reclaim or kswapd.
+	 * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim.
+	 *    It can only be cleared by kswapd.
+	 *
+	 * Essentially, kswapd can unthrottle an lruvec throttled by cgroup
+	 * reclaim, but not vice versa. This only applies to the root cgroup.
+	 * The goal is to prevent cgroup reclaim on the root cgroup (e.g.
+	 * memory.reclaim) to unthrottle an unbalanced node (that was throttled
+	 * by kswapd).
+	 */
+	LRUVEC_CGROUP_CONGESTED,
+	LRUVEC_NODE_CONGESTED,
 };
 
 #endif /* !__GENERATING_BOUNDS_H */
@@ -537,7 +552,7 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg);
 void lru_gen_online_memcg(struct mem_cgroup *memcg);
 void lru_gen_offline_memcg(struct mem_cgroup *memcg);
 void lru_gen_release_memcg(struct mem_cgroup *memcg);
-void lru_gen_soft_reclaim(struct lruvec *lruvec);
+void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid);
 
 #else /* !CONFIG_MEMCG */
 
@@ -588,7 +603,7 @@ static inline void lru_gen_release_memcg(struct mem_cgroup *memcg)
 {
 }
 
-static inline void lru_gen_soft_reclaim(struct lruvec *lruvec)
+static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
 {
 }
 
@@ -1124,6 +1139,11 @@ static inline bool is_zone_movable_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_MOVABLE;
 }
+
+static inline bool folio_is_zone_movable(const struct folio *folio)
+{
+	return folio_zonenum(folio) == ZONE_MOVABLE;
+}
 #endif
 
 /*
@@ -1520,27 +1540,6 @@ static inline bool has_managed_dma(void)
 }
 #endif
 
-/* These two functions are used to setup the per zone pages min values */
-struct ctl_table;
-
-int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *,
-		size_t *, loff_t *);
-extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
-int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *,
-		size_t *, loff_t *);
-int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int,
-		void *, size_t *, loff_t *);
-int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
-		void *, size_t *, loff_t *);
-int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
-		void *, size_t *, loff_t *);
-int numa_zonelist_order_handler(struct ctl_table *, int,
-		void *, size_t *, loff_t *);
-extern int percpu_pagelist_high_fraction;
-extern char numa_zonelist_order[];
-#define NUMA_ZONELIST_ORDER_LEN	16
 
 #ifndef CONFIG_NUMA