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, 38 insertions, 10 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 06089390d81d..33fa5e94aa80 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -225,8 +225,6 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
-void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
-		  gfp_t gfp);
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
@@ -236,7 +234,6 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
 void __lock_buffer(struct buffer_head *bh);
-void ll_rw_block(blk_opf_t, int, struct buffer_head * bh[]);
 int sync_dirty_buffer(struct buffer_head *bh);
 int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
 void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
@@ -244,7 +241,9 @@ void submit_bh(blk_opf_t, struct buffer_head *);
 void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);
-int bh_submit_read(struct buffer_head *bh);
+int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
+void __bh_read_batch(int nr, struct buffer_head *bhs[],
+		     blk_opf_t op_flags, bool force_lock);
 
 extern int buffer_heads_over_limit;
 
@@ -351,12 +350,6 @@ sb_breadahead(struct super_block *sb, sector_t block)
 	__breadahead(sb->s_bdev, block, sb->s_blocksize);
 }
 
-static inline void
-sb_breadahead_unmovable(struct super_block *sb, sector_t block)
-{
-	__breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
-}
-
 static inline struct buffer_head *
 sb_getblk(struct super_block *sb, sector_t block)
 {
@@ -418,6 +411,41 @@ static inline struct buffer_head *__getblk(struct block_device *bdev,
 	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
 }
 
+static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags)
+{
+	if (!buffer_uptodate(bh) && trylock_buffer(bh)) {
+		if (!buffer_uptodate(bh))
+			__bh_read(bh, op_flags, false);
+		else
+			unlock_buffer(bh);
+	}
+}
+
+static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags)
+{
+	if (!bh_uptodate_or_lock(bh))
+		__bh_read(bh, op_flags, false);
+}
+
+/* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */
+static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags)
+{
+	if (bh_uptodate_or_lock(bh))
+		return 1;
+	return __bh_read(bh, op_flags, true);
+}
+
+static inline void bh_read_batch(int nr, struct buffer_head *bhs[])
+{
+	__bh_read_batch(nr, bhs, 0, true);
+}
+
+static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[],
+				      blk_opf_t op_flags)
+{
+	__bh_read_batch(nr, bhs, op_flags, false);
+}
+
 /**
  *  __bread() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from