Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

1 files changed, 31 insertions, 10 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 955930f41d20..70e2063ef43a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -43,8 +43,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/pagemap.h>
 
-/* How many pages do we try to swap or page in/out together? */
+/* How many pages do we try to swap or page in/out together? As a power of 2 */
 int page_cluster;
+const int page_cluster_max = 31;
 
 /* Protecting only lru_rotate.fbatch which requires disabling interrupts */
 struct lru_rotate {
@@ -295,8 +296,20 @@ void folio_rotate_reclaimable(struct folio *folio)
 	}
 }
 
-void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
+void lru_note_cost(struct lruvec *lruvec, bool file,
+		   unsigned int nr_io, unsigned int nr_rotated)
 {
+	unsigned long cost;
+
+	/*
+	 * Reflect the relative cost of incurring IO and spending CPU
+	 * time on rotations. This doesn't attempt to make a precise
+	 * comparison, it just says: if reloads are about comparable
+	 * between the LRU lists, or rotations are overwhelmingly
+	 * different between them, adjust scan balance for CPU work.
+	 */
+	cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated;
+
 	do {
 		unsigned long lrusize;
 
@@ -310,9 +323,9 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 		spin_lock_irq(&lruvec->lru_lock);
 		/* Record cost event */
 		if (file)
-			lruvec->file_cost += nr_pages;
+			lruvec->file_cost += cost;
 		else
-			lruvec->anon_cost += nr_pages;
+			lruvec->anon_cost += cost;
 
 		/*
 		 * Decay previous events
@@ -335,10 +348,10 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
-void lru_note_cost_folio(struct folio *folio)
+void lru_note_cost_refault(struct folio *folio)
 {
 	lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
-			folio_nr_pages(folio));
+		      folio_nr_pages(folio), 0);
 }
 
 static void folio_activate_fn(struct lruvec *lruvec, struct folio *folio)
@@ -968,22 +981,30 @@ void lru_cache_disable(void)
 
 /**
  * release_pages - batched put_page()
- * @pages: array of pages to release
+ * @arg: array of pages to release
  * @nr: number of pages
  *
- * Decrement the reference count on all the pages in @pages.  If it
+ * Decrement the reference count on all the pages in @arg.  If it
  * fell to zero, remove the page from the LRU and free it.
+ *
+ * Note that the argument can be an array of pages, encoded pages,
+ * or folio pointers. We ignore any encoded bits, and turn any of
+ * them into just a folio that gets free'd.
  */
-void release_pages(struct page **pages, int nr)
+void release_pages(release_pages_arg arg, int nr)
 {
 	int i;
+	struct encoded_page **encoded = arg.encoded_pages;
 	LIST_HEAD(pages_to_free);
 	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 	unsigned int lock_batch;
 
 	for (i = 0; i < nr; i++) {
-		struct folio *folio = page_folio(pages[i]);
+		struct folio *folio;
+
+		/* Turn any of the argument types into a folio */
+		folio = page_folio(encoded_page_ptr(encoded[i]));
 
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get