Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

1 files changed, 27 insertions, 51 deletions

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 1281a40d5735..110a36479dce 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -2312,9 +2312,7 @@ static inline struct maple_enode *mte_node_or_none(struct maple_enode *enode)
 static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas)
 {
 	struct ma_state *mas = wr_mas->mas;
-	unsigned char count;
-	unsigned char offset;
-	unsigned long index, min, max;
+	unsigned char count, offset;
 
 	if (unlikely(ma_is_dense(wr_mas->type))) {
 		wr_mas->r_max = wr_mas->r_min = mas->index;
@@ -2327,34 +2325,12 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas)
 	count = wr_mas->node_end = ma_data_end(wr_mas->node, wr_mas->type,
 					       wr_mas->pivots, mas->max);
 	offset = mas->offset;
-	min = mas_safe_min(mas, wr_mas->pivots, offset);
-	if (unlikely(offset == count))
-		goto max;
-
-	max = wr_mas->pivots[offset];
-	index = mas->index;
-	if (unlikely(index <= max))
-		goto done;
-
-	if (unlikely(!max && offset))
-		goto max;
-
-	min = max + 1;
-	while (++offset < count) {
-		max = wr_mas->pivots[offset];
-		if (index <= max)
-			goto done;
-		else if (unlikely(!max))
-			break;
 
-		min = max + 1;
-	}
+	while (offset < count && mas->index > wr_mas->pivots[offset])
+		offset++;
 
-max:
-	max = mas->max;
-done:
-	wr_mas->r_max = max;
-	wr_mas->r_min = min;
+	wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max;
+	wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset);
 	wr_mas->offset_end = mas->offset = offset;
 }
 
@@ -3282,7 +3258,7 @@ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end
 
 		if (tmp < max_p)
 			memset(pivs + tmp, 0,
-			       sizeof(unsigned long *) * (max_p - tmp));
+			       sizeof(unsigned long) * (max_p - tmp));
 
 		if (tmp < mt_slots[mt])
 			memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp));
@@ -5274,25 +5250,28 @@ static inline void mas_fill_gap(struct ma_state *mas, void *entry,
  * @size: The size of the gap
  * @fwd: Searching forward or back
  */
-static inline void mas_sparse_area(struct ma_state *mas, unsigned long min,
+static inline int mas_sparse_area(struct ma_state *mas, unsigned long min,
 				unsigned long max, unsigned long size, bool fwd)
 {
-	unsigned long start = 0;
-
-	if (!unlikely(mas_is_none(mas)))
-		start++;
+	if (!unlikely(mas_is_none(mas)) && min == 0) {
+		min++;
+		/*
+		 * At this time, min is increased, we need to recheck whether
+		 * the size is satisfied.
+		 */
+		if (min > max || max - min + 1 < size)
+			return -EBUSY;
+	}
 	/* mas_is_ptr */
 
-	if (start < min)
-		start = min;
-
 	if (fwd) {
-		mas->index = start;
-		mas->last = start + size - 1;
-		return;
+		mas->index = min;
+		mas->last = min + size - 1;
+	} else {
+		mas->last = max;
+		mas->index = max - size + 1;
 	}
-
-	mas->index = max;
+	return 0;
 }
 
 /*
@@ -5321,10 +5300,8 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 		return -EBUSY;
 
 	/* Empty set */
-	if (mas_is_none(mas) || mas_is_ptr(mas)) {
-		mas_sparse_area(mas, min, max, size, true);
-		return 0;
-	}
+	if (mas_is_none(mas) || mas_is_ptr(mas))
+		return mas_sparse_area(mas, min, max, size, true);
 
 	/* The start of the window can only be within these values */
 	mas->index = min;
@@ -5380,10 +5357,8 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 	}
 
 	/* Empty set. */
-	if (mas_is_none(mas) || mas_is_ptr(mas)) {
-		mas_sparse_area(mas, min, max, size, false);
-		return 0;
-	}
+	if (mas_is_none(mas) || mas_is_ptr(mas))
+		return mas_sparse_area(mas, min, max, size, false);
 
 	/* The start of the window can only be within these values. */
 	mas->index = min;
@@ -5815,6 +5790,7 @@ int mas_preallocate(struct ma_state *mas, gfp_t gfp)
 	mas_reset(mas);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mas_preallocate);
 
 /*
  * mas_destroy() - destroy a maple state.