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, 66 insertions, 58 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index c943d1b90cc2..08341616ae7a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -632,22 +632,23 @@ bool filemap_range_has_writeback(struct address_space *mapping,
 {
 	XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
 	pgoff_t max = end_byte >> PAGE_SHIFT;
-	struct page *page;
+	struct folio *folio;
 
 	if (end_byte < start_byte)
 		return false;
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, max) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, folio, max) {
+		if (xas_retry(&xas, folio))
 			continue;
-		if (xa_is_value(page))
+		if (xa_is_value(folio))
 			continue;
-		if (PageDirty(page) || PageLocked(page) || PageWriteback(page))
+		if (folio_test_dirty(folio) || folio_test_locked(folio) ||
+				folio_test_writeback(folio))
 			break;
 	}
 	rcu_read_unlock();
-	return page != NULL;
+	return folio != NULL;
 }
 EXPORT_SYMBOL_GPL(filemap_range_has_writeback);
 
@@ -1221,15 +1222,12 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
-	bool delayacct = false;
 	unsigned long pflags;
+	bool in_thrashing;
 
 	if (bit_nr == PG_locked &&
 	    !folio_test_uptodate(folio) && folio_test_workingset(folio)) {
-		if (!folio_test_swapbacked(folio)) {
-			delayacct_thrashing_start();
-			delayacct = true;
-		}
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
@@ -1329,8 +1327,7 @@ repeat:
 	finish_wait(q, wait);
 
 	if (thrashing) {
-		if (delayacct)
-			delayacct_thrashing_end();
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
 	}
 
@@ -1378,17 +1375,14 @@ void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
-	bool delayacct = false;
 	unsigned long pflags;
+	bool in_thrashing;
 	wait_queue_head_t *q;
 	struct folio *folio = page_folio(pfn_swap_entry_to_page(entry));
 
 	q = folio_waitqueue(folio);
 	if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
-		if (!folio_test_swapbacked(folio)) {
-			delayacct_thrashing_start();
-			delayacct = true;
-		}
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
@@ -1435,8 +1429,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
 	finish_wait(q, wait);
 
 	if (thrashing) {
-		if (delayacct)
-			delayacct_thrashing_end();
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
 	}
 }
@@ -1467,7 +1460,7 @@ EXPORT_SYMBOL(folio_wait_bit_killable);
  *
  * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal.
  */
-int folio_put_wait_locked(struct folio *folio, int state)
+static int folio_put_wait_locked(struct folio *folio, int state)
 {
 	return folio_wait_bit_common(folio, PG_locked, state, DROP);
 }
@@ -1633,24 +1626,26 @@ EXPORT_SYMBOL(folio_end_writeback);
  */
 void page_endio(struct page *page, bool is_write, int err)
 {
+	struct folio *folio = page_folio(page);
+
 	if (!is_write) {
 		if (!err) {
-			SetPageUptodate(page);
+			folio_mark_uptodate(folio);
 		} else {
-			ClearPageUptodate(page);
-			SetPageError(page);
+			folio_clear_uptodate(folio);
+			folio_set_error(folio);
 		}
-		unlock_page(page);
+		folio_unlock(folio);
 	} else {
 		if (err) {
 			struct address_space *mapping;
 
-			SetPageError(page);
-			mapping = page_mapping(page);
+			folio_set_error(folio);
+			mapping = folio_mapping(folio);
 			if (mapping)
 				mapping_set_error(mapping, err);
 		}
-		end_page_writeback(page);
+		folio_end_writeback(folio);
 	}
 }
 EXPORT_SYMBOL_GPL(page_endio);
@@ -2195,30 +2190,31 @@ bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
 }
 
 /**
- * find_get_pages_contig - gang contiguous pagecache lookup
+ * filemap_get_folios_contig - Get a batch of contiguous folios
  * @mapping:	The address_space to search
- * @index:	The starting page index
- * @nr_pages:	The maximum number of pages
- * @pages:	Where the resulting pages are placed
+ * @start:	The starting page index
+ * @end:	The final page index (inclusive)
+ * @fbatch:	The batch to fill
  *
- * find_get_pages_contig() works exactly like find_get_pages_range(),
- * except that the returned number of pages are guaranteed to be
- * contiguous.
+ * filemap_get_folios_contig() works exactly like filemap_get_folios(),
+ * except the returned folios are guaranteed to be contiguous. This may
+ * not return all contiguous folios if the batch gets filled up.
  *
- * Return: the number of pages which were found.
+ * Return: The number of folios found.
+ * Also update @start to be positioned for traversal of the next folio.
  */
-unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
-			       unsigned int nr_pages, struct page **pages)
+
+unsigned filemap_get_folios_contig(struct address_space *mapping,
+		pgoff_t *start, pgoff_t end, struct folio_batch *fbatch)
 {
-	XA_STATE(xas, &mapping->i_pages, index);
+	XA_STATE(xas, &mapping->i_pages, *start);
+	unsigned long nr;
 	struct folio *folio;
-	unsigned int ret = 0;
-
-	if (unlikely(!nr_pages))
-		return 0;
 
 	rcu_read_lock();
-	for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) {
+
+	for (folio = xas_load(&xas); folio && xas.xa_index <= end;
+			folio = xas_next(&xas)) {
 		if (xas_retry(&xas, folio))
 			continue;
 		/*
@@ -2226,33 +2222,45 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 		 * No current caller is looking for DAX entries.
 		 */
 		if (xa_is_value(folio))
-			break;
+			goto update_start;
 
 		if (!folio_try_get_rcu(folio))
 			goto retry;
 
 		if (unlikely(folio != xas_reload(&xas)))
-			goto put_page;
+			goto put_folio;
 
-again:
-		pages[ret] = folio_file_page(folio, xas.xa_index);
-		if (++ret == nr_pages)
-			break;
-		if (folio_more_pages(folio, xas.xa_index, ULONG_MAX)) {
-			xas.xa_index++;
-			folio_ref_inc(folio);
-			goto again;
+		if (!folio_batch_add(fbatch, folio)) {
+			nr = folio_nr_pages(folio);
+
+			if (folio_test_hugetlb(folio))
+				nr = 1;
+			*start = folio->index + nr;
+			goto out;
 		}
 		continue;
-put_page:
+put_folio:
 		folio_put(folio);
+
 retry:
 		xas_reset(&xas);
 	}
+
+update_start:
+	nr = folio_batch_count(fbatch);
+
+	if (nr) {
+		folio = fbatch->folios[nr - 1];
+		if (folio_test_hugetlb(folio))
+			*start = folio->index + 1;
+		else
+			*start = folio->index + folio_nr_pages(folio);
+	}
+out:
 	rcu_read_unlock();
-	return ret;
+	return folio_batch_count(fbatch);
 }
-EXPORT_SYMBOL(find_get_pages_contig);
+EXPORT_SYMBOL(filemap_get_folios_contig);
 
 /**
  * find_get_pages_range_tag - Find and return head pages matching @tag.
@@ -3719,7 +3727,7 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
-		void *fsdata;
+		void *fsdata = NULL;
 
 		offset = (pos & (PAGE_SIZE - 1));
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,