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, 78 insertions, 89 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6e60657875d3..0745aedebb37 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -170,21 +170,12 @@ static DEFINE_MUTEX(pcp_batch_high_lock);
 	_ret;								\
 })
 
-#define pcpu_spin_lock_irqsave(type, member, ptr, flags)		\
+#define pcpu_spin_trylock(type, member, ptr)				\
 ({									\
 	type *_ret;							\
 	pcpu_task_pin();						\
 	_ret = this_cpu_ptr(ptr);					\
-	spin_lock_irqsave(&_ret->member, flags);			\
-	_ret;								\
-})
-
-#define pcpu_spin_trylock_irqsave(type, member, ptr, flags)		\
-({									\
-	type *_ret;							\
-	pcpu_task_pin();						\
-	_ret = this_cpu_ptr(ptr);					\
-	if (!spin_trylock_irqsave(&_ret->member, flags)) {		\
+	if (!spin_trylock(&_ret->member)) {				\
 		pcpu_task_unpin();					\
 		_ret = NULL;						\
 	}								\
@@ -197,27 +188,16 @@ static DEFINE_MUTEX(pcp_batch_high_lock);
 	pcpu_task_unpin();						\
 })
 
-#define pcpu_spin_unlock_irqrestore(member, ptr, flags)			\
-({									\
-	spin_unlock_irqrestore(&ptr->member, flags);			\
-	pcpu_task_unpin();						\
-})
-
 /* struct per_cpu_pages specific helpers. */
 #define pcp_spin_lock(ptr)						\
 	pcpu_spin_lock(struct per_cpu_pages, lock, ptr)
 
-#define pcp_spin_lock_irqsave(ptr, flags)				\
-	pcpu_spin_lock_irqsave(struct per_cpu_pages, lock, ptr, flags)
-
-#define pcp_spin_trylock_irqsave(ptr, flags)				\
-	pcpu_spin_trylock_irqsave(struct per_cpu_pages, lock, ptr, flags)
+#define pcp_spin_trylock(ptr)						\
+	pcpu_spin_trylock(struct per_cpu_pages, lock, ptr)
 
 #define pcp_spin_unlock(ptr)						\
 	pcpu_spin_unlock(lock, ptr)
 
-#define pcp_spin_unlock_irqrestore(ptr, flags)				\
-	pcpu_spin_unlock_irqrestore(lock, ptr, flags)
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -798,6 +778,7 @@ static void prep_compound_head(struct page *page, unsigned int order)
 	set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
 	set_compound_order(page, order);
 	atomic_set(compound_mapcount_ptr(page), -1);
+	atomic_set(subpages_mapcount_ptr(page), 0);
 	atomic_set(compound_pincount_ptr(page), 0);
 }
 
@@ -1324,11 +1305,19 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 	}
 	switch (page - head_page) {
 	case 1:
-		/* the first tail page: ->mapping may be compound_mapcount() */
-		if (unlikely(compound_mapcount(page))) {
+		/* the first tail page: these may be in place of ->mapping */
+		if (unlikely(head_compound_mapcount(head_page))) {
 			bad_page(page, "nonzero compound_mapcount");
 			goto out;
 		}
+		if (unlikely(atomic_read(subpages_mapcount_ptr(head_page)))) {
+			bad_page(page, "nonzero subpages_mapcount");
+			goto out;
+		}
+		if (unlikely(head_compound_pincount(head_page))) {
+			bad_page(page, "nonzero compound_pincount");
+			goto out;
+		}
 		break;
 	case 2:
 		/*
@@ -1431,10 +1420,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 		VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
 
-		if (compound) {
-			ClearPageDoubleMap(page);
+		if (compound)
 			ClearPageHasHWPoisoned(page);
-		}
 		for (i = 1; i < (1 << order); i++) {
 			if (compound)
 				bad += free_tail_pages_check(page, page + i);
@@ -1547,6 +1534,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 					struct per_cpu_pages *pcp,
 					int pindex)
 {
+	unsigned long flags;
 	int min_pindex = 0;
 	int max_pindex = NR_PCP_LISTS - 1;
 	unsigned int order;
@@ -1562,8 +1550,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	/* Ensure requested pindex is drained first. */
 	pindex = pindex - 1;
 
-	/* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */
-	spin_lock(&zone->lock);
+	spin_lock_irqsave(&zone->lock, flags);
 	isolated_pageblocks = has_isolate_pageblock(zone);
 
 	while (count > 0) {
@@ -1611,7 +1598,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 		} while (count > 0 && !list_empty(list));
 	}
 
-	spin_unlock(&zone->lock);
+	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 static void free_one_page(struct zone *zone,
@@ -1715,6 +1702,11 @@ static void __free_pages_ok(struct page *page, unsigned int order,
 	if (!free_pages_prepare(page, order, true, fpi_flags))
 		return;
 
+	/*
+	 * Calling get_pfnblock_migratetype() without spin_lock_irqsave() here
+	 * is used to avoid calling get_pfnblock_migratetype() under the lock.
+	 * This will reduce the lock holding time.
+	 */
 	migratetype = get_pfnblock_migratetype(page, pfn);
 
 	spin_lock_irqsave(&zone->lock, flags);
@@ -3125,10 +3117,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
 			int migratetype, unsigned int alloc_flags)
 {
+	unsigned long flags;
 	int i, allocated = 0;
 
-	/* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */
-	spin_lock(&zone->lock);
+	spin_lock_irqsave(&zone->lock, flags);
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype,
 								alloc_flags);
@@ -3162,7 +3154,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 	 * pages added to the pcp list.
 	 */
 	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
-	spin_unlock(&zone->lock);
+	spin_unlock_irqrestore(&zone->lock, flags);
 	return allocated;
 }
 
@@ -3179,16 +3171,9 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 	batch = READ_ONCE(pcp->batch);
 	to_drain = min(pcp->count, batch);
 	if (to_drain > 0) {
-		unsigned long flags;
-
-		/*
-		 * free_pcppages_bulk expects IRQs disabled for zone->lock
-		 * so even though pcp->lock is not intended to be IRQ-safe,
-		 * it's needed in this context.
-		 */
-		spin_lock_irqsave(&pcp->lock, flags);
+		spin_lock(&pcp->lock);
 		free_pcppages_bulk(zone, to_drain, pcp, 0);
-		spin_unlock_irqrestore(&pcp->lock, flags);
+		spin_unlock(&pcp->lock);
 	}
 }
 #endif
@@ -3202,12 +3187,9 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 
 	pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
 	if (pcp->count) {
-		unsigned long flags;
-
-		/* See drain_zone_pages on why this is disabling IRQs */
-		spin_lock_irqsave(&pcp->lock, flags);
+		spin_lock(&pcp->lock);
 		free_pcppages_bulk(zone, pcp->count, pcp, 0);
-		spin_unlock_irqrestore(&pcp->lock, flags);
+		spin_unlock(&pcp->lock);
 	}
 }
 
@@ -3473,7 +3455,6 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
  */
 void free_unref_page(struct page *page, unsigned int order)
 {
-	unsigned long flags;
 	unsigned long __maybe_unused UP_flags;
 	struct per_cpu_pages *pcp;
 	struct zone *zone;
@@ -3501,10 +3482,10 @@ void free_unref_page(struct page *page, unsigned int order)
 
 	zone = page_zone(page);
 	pcp_trylock_prepare(UP_flags);
-	pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags);
+	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
 		free_unref_page_commit(zone, pcp, page, migratetype, order);
-		pcp_spin_unlock_irqrestore(pcp, flags);
+		pcp_spin_unlock(pcp);
 	} else {
 		free_one_page(zone, page, pfn, order, migratetype, FPI_NONE);
 	}
@@ -3516,10 +3497,10 @@ void free_unref_page(struct page *page, unsigned int order)
  */
 void free_unref_page_list(struct list_head *list)
 {
+	unsigned long __maybe_unused UP_flags;
 	struct page *page, *next;
 	struct per_cpu_pages *pcp = NULL;
 	struct zone *locked_zone = NULL;
-	unsigned long flags;
 	int batch_count = 0;
 	int migratetype;
 
@@ -3546,39 +3527,54 @@ void free_unref_page_list(struct list_head *list)
 	list_for_each_entry_safe(page, next, list, lru) {
 		struct zone *zone = page_zone(page);
 
-		/* Different zone, different pcp lock. */
-		if (zone != locked_zone) {
-			if (pcp)
-				pcp_spin_unlock_irqrestore(pcp, flags);
+		list_del(&page->lru);
+		migratetype = get_pcppage_migratetype(page);
+
+		/*
+		 * Either different zone requiring a different pcp lock or
+		 * excessive lock hold times when freeing a large list of
+		 * pages.
+		 */
+		if (zone != locked_zone || batch_count == SWAP_CLUSTER_MAX) {
+			if (pcp) {
+				pcp_spin_unlock(pcp);
+				pcp_trylock_finish(UP_flags);
+			}
+
+			batch_count = 0;
 
+			/*
+			 * trylock is necessary as pages may be getting freed
+			 * from IRQ or SoftIRQ context after an IO completion.
+			 */
+			pcp_trylock_prepare(UP_flags);
+			pcp = pcp_spin_trylock(zone->per_cpu_pageset);
+			if (unlikely(!pcp)) {
+				pcp_trylock_finish(UP_flags);
+				free_one_page(zone, page, page_to_pfn(page),
+					      0, migratetype, FPI_NONE);
+				locked_zone = NULL;
+				continue;
+			}
 			locked_zone = zone;
-			pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags);
 		}
 
 		/*
 		 * Non-isolated types over MIGRATE_PCPTYPES get added
 		 * to the MIGRATE_MOVABLE pcp list.
 		 */
-		migratetype = get_pcppage_migratetype(page);
 		if (unlikely(migratetype >= MIGRATE_PCPTYPES))
 			migratetype = MIGRATE_MOVABLE;
 
 		trace_mm_page_free_batched(page);
 		free_unref_page_commit(zone, pcp, page, migratetype, 0);
-
-		/*
-		 * Guard against excessive IRQ disabled times when we get
-		 * a large list of pages to free.
-		 */
-		if (++batch_count == SWAP_CLUSTER_MAX) {
-			pcp_spin_unlock_irqrestore(pcp, flags);
-			batch_count = 0;
-			pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags);
-		}
+		batch_count++;
 	}
 
-	if (pcp)
-		pcp_spin_unlock_irqrestore(pcp, flags);
+	if (pcp) {
+		pcp_spin_unlock(pcp);
+		pcp_trylock_finish(UP_flags);
+	}
 }
 
 /*
@@ -3779,15 +3775,11 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 	struct per_cpu_pages *pcp;
 	struct list_head *list;
 	struct page *page;
-	unsigned long flags;
 	unsigned long __maybe_unused UP_flags;
 
-	/*
-	 * spin_trylock may fail due to a parallel drain. In the future, the
-	 * trylock will also protect against IRQ reentrancy.
-	 */
+	/* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */
 	pcp_trylock_prepare(UP_flags);
-	pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags);
+	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (!pcp) {
 		pcp_trylock_finish(UP_flags);
 		return NULL;
@@ -3801,7 +3793,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 	pcp->free_factor >>= 1;
 	list = &pcp->lists[order_to_pindex(migratetype, order)];
 	page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list);
-	pcp_spin_unlock_irqrestore(pcp, flags);
+	pcp_spin_unlock(pcp);
 	pcp_trylock_finish(UP_flags);
 	if (page) {
 		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
@@ -5372,7 +5364,6 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 			struct page **page_array)
 {
 	struct page *page;
-	unsigned long flags;
 	unsigned long __maybe_unused UP_flags;
 	struct zone *zone;
 	struct zoneref *z;
@@ -5454,9 +5445,9 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 	if (unlikely(!zone))
 		goto failed;
 
-	/* Is a parallel drain in progress? */
+	/* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */
 	pcp_trylock_prepare(UP_flags);
-	pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags);
+	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (!pcp)
 		goto failed_irq;
 
@@ -5475,7 +5466,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 		if (unlikely(!page)) {
 			/* Try and allocate at least one page */
 			if (!nr_account) {
-				pcp_spin_unlock_irqrestore(pcp, flags);
+				pcp_spin_unlock(pcp);
 				goto failed_irq;
 			}
 			break;
@@ -5490,7 +5481,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 		nr_populated++;
 	}
 
-	pcp_spin_unlock_irqrestore(pcp, flags);
+	pcp_spin_unlock(pcp);
 	pcp_trylock_finish(UP_flags);
 
 	__count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
@@ -6874,13 +6865,11 @@ static void __ref memmap_init_compound(struct page *head,
 		set_page_count(page, 0);
 
 		/*
-		 * The first tail page stores compound_mapcount_ptr() and
-		 * compound_order() and the second tail page stores
-		 * compound_pincount_ptr(). Call prep_compound_head() after
-		 * the first and second tail pages have been initialized to
-		 * not have the data overwritten.
+		 * The first tail page stores important compound page info.
+		 * Call prep_compound_head() after the first tail page has
+		 * been initialized, to not have the data overwritten.
 		 */
-		if (pfn == head_pfn + 2)
+		if (pfn == head_pfn + 1)
 			prep_compound_head(head, order);
 	}
 }