Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "10 patches.

  Subsystems affected by this patch series: MAINTAINERS and mm (shmem,
  pagealloc, tracing, memcg, memory-failure, vmscan, kfence, and
  hugetlb)"

* emailed patches from Andrew Morton <[email protected]>:
  hugetlb: don't pass page cache pages to restore_reserve_on_error
  kfence: fix is_kfence_address() for addresses below KFENCE_POOL_SIZE
  mm: vmscan: fix missing psi annotation for node_reclaim()
  mm/hwpoison: retry with shake_page() for unhandlable pages
  mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim
  MAINTAINERS: update ClangBuiltLinux IRC chat
  mmflags.h: add missing __GFP_ZEROTAGS and __GFP_SKIP_KASAN_POISON names
  mm/page_alloc: don't corrupt pcppage_migratetype
  Revert "mm: swap: check if swap backing device is congested or not"
  Revert "mm/shmem: fix shmem_swapin() race with swapoff"

Author: torvalds

MAINTAINERS

@@ -4508,7 +4508,7 @@ L:	[email protected]
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
 B:	https://github.com/ClangBuiltLinux/linux/issues
-C:	irc://chat.freenode.net/clangbuiltlinux
+C:	irc://irc.libera.chat/clangbuiltlinux
 F:	Documentation/kbuild/llvm.rst
 F:	include/linux/compiler-clang.h
 F:	scripts/clang-tools/

include/linux/kfence.h

@@ -51,10 +51,11 @@ extern atomic_t kfence_allocation_gate;
 static __always_inline bool is_kfence_address(const void *addr)
 {
 	/*
-	 * The non-NULL check is required in case the __kfence_pool pointer was
-	 * never initialized; keep it in the slow-path after the range-check.
+	 * The __kfence_pool != NULL check is required to deal with the case
+	 * where __kfence_pool == NULL && addr < KFENCE_POOL_SIZE. Keep it in
+	 * the slow-path after the range-check!
 	 */
-	return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr);
+	return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && __kfence_pool);
 }
 
 /**

include/linux/memcontrol.h

@@ -612,12 +612,15 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
-						  struct mem_cgroup *memcg,
-						  bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+					 struct mem_cgroup *memcg,
+					 unsigned long *min,
+					 unsigned long *low)
 {
+	*min = *low = 0;
+
 	if (mem_cgroup_disabled())
-		return 0;
+		return;
 
 	/*
 	 * There is no reclaim protection applied to a targeted reclaim.
@@ -653,13 +656,10 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
 	 *
 	 */
 	if (root == memcg)
-		return 0;
-
-	if (in_low_reclaim)
-		return READ_ONCE(memcg->memory.emin);
+		return;
 
-	return max(READ_ONCE(memcg->memory.emin),
-		   READ_ONCE(memcg->memory.elow));
+	*min = READ_ONCE(memcg->memory.emin);
+	*low = READ_ONCE(memcg->memory.elow);
 }
 
 void mem_cgroup_calculate_protection(struct mem_cgroup *root,
@@ -1147,11 +1147,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
-						  struct mem_cgroup *memcg,
-						  bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+					 struct mem_cgroup *memcg,
+					 unsigned long *min,
+					 unsigned long *low)
 {
-	return 0;
+	*min = *low = 0;
 }
 
 static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,

include/trace/events/mmflags.h

@@ -48,7 +48,9 @@
 	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
 	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
 	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
-	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"}\
+	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"},\
+	{(unsigned long)__GFP_ZEROTAGS,		"__GFP_ZEROTAGS"},	\
+	{(unsigned long)__GFP_SKIP_KASAN_POISON,"__GFP_SKIP_KASAN_POISON"}\
 
 #define show_gfp_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",				\

mm/hugetlb.c

@@ -2476,7 +2476,7 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
 		if (!rc) {
 			/*
 			 * This indicates there is an entry in the reserve map
-			 * added by alloc_huge_page.  We know it was added
+			 * not added by alloc_huge_page.  We know it was added
 			 * before the alloc_huge_page call, otherwise
 			 * HPageRestoreReserve would be set on the page.
 			 * Remove the entry so that a subsequent allocation
@@ -4660,7 +4660,9 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(&range);
 out_release_all:
-	restore_reserve_on_error(h, vma, haddr, new_page);
+	/* No restore in case of successful pagetable update (Break COW) */
+	if (new_page != old_page)
+		restore_reserve_on_error(h, vma, haddr, new_page);
 	put_page(new_page);
 out_release_old:
 	put_page(old_page);
@@ -4776,7 +4778,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	pte_t new_pte;
 	spinlock_t *ptl;
 	unsigned long haddr = address & huge_page_mask(h);
-	bool new_page = false;
+	bool new_page, new_pagecache_page = false;
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -4799,6 +4801,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		goto out;
 
 retry:
+	new_page = false;
 	page = find_lock_page(mapping, idx);
 	if (!page) {
 		/* Check for page in userfault range */
@@ -4842,6 +4845,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 					goto retry;
 				goto out;
 			}
+			new_pagecache_page = true;
 		} else {
 			lock_page(page);
 			if (unlikely(anon_vma_prepare(vma))) {
@@ -4926,7 +4930,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	spin_unlock(ptl);
 backout_unlocked:
 	unlock_page(page);
-	restore_reserve_on_error(h, vma, haddr, page);
+	/* restore reserve for newly allocated pages not in page cache */
+	if (new_page && !new_pagecache_page)
+		restore_reserve_on_error(h, vma, haddr, page);
 	put_page(page);
 	goto out;
 }
@@ -5135,6 +5141,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	int ret = -ENOMEM;
 	struct page *page;
 	int writable;
+	bool new_pagecache_page = false;
 
 	if (is_continue) {
 		ret = -EFAULT;
@@ -5228,6 +5235,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		ret = huge_add_to_page_cache(page, mapping, idx);
 		if (ret)
 			goto out_release_nounlock;
+		new_pagecache_page = true;
 	}
 
 	ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
@@ -5291,7 +5299,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (vm_shared || is_continue)
 		unlock_page(page);
 out_release_nounlock:
-	restore_reserve_on_error(h, dst_vma, dst_addr, page);
+	if (!new_pagecache_page)
+		restore_reserve_on_error(h, dst_vma, dst_addr, page);
 	put_page(page);
 	goto out;
 }

mm/memory-failure.c

@@ -1146,7 +1146,7 @@ static int __get_hwpoison_page(struct page *page)
 	 * unexpected races caused by taking a page refcount.
 	 */
 	if (!HWPoisonHandlable(head))
-		return 0;
+		return -EBUSY;
 
 	if (PageTransHuge(head)) {
 		/*
@@ -1199,9 +1199,15 @@ static int get_any_page(struct page *p, unsigned long flags)
 			}
 			goto out;
 		} else if (ret == -EBUSY) {
-			/* We raced with freeing huge page to buddy, retry. */
-			if (pass++ < 3)
+			/*
+			 * We raced with (possibly temporary) unhandlable
+			 * page, retry.
+			 */
+			if (pass++ < 3) {
+				shake_page(p, 1);
 				goto try_again;
+			}
+			ret = -EIO;
 			goto out;
 		}
 	}

mm/page_alloc.c

@@ -3453,19 +3453,10 @@ void free_unref_page_list(struct list_head *list)
 		 * comment in free_unref_page.
 		 */
 		migratetype = get_pcppage_migratetype(page);
-		if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
-			if (unlikely(is_migrate_isolate(migratetype))) {
-				list_del(&page->lru);
-				free_one_page(page_zone(page), page, pfn, 0,
-							migratetype, FPI_NONE);
-				continue;
-			}
-
-			/*
-			 * Non-isolated types over MIGRATE_PCPTYPES get added
-			 * to the MIGRATE_MOVABLE pcp list.
-			 */
-			set_pcppage_migratetype(page, MIGRATE_MOVABLE);
+		if (unlikely(is_migrate_isolate(migratetype))) {
+			list_del(&page->lru);
+			free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE);
+			continue;
 		}
 
 		set_page_private(page, pfn);
@@ -3475,7 +3466,15 @@ void free_unref_page_list(struct list_head *list)
 	list_for_each_entry_safe(page, next, list, lru) {
 		pfn = page_private(page);
 		set_page_private(page, 0);
+
+		/*
+		 * 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(page, pfn, migratetype, 0);
 

mm/shmem.c

@@ -1696,21 +1696,14 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL;
-	struct swap_info_struct *si;
-	struct page *page = NULL;
+	struct page *page;
 	swp_entry_t swap;
 	int error;
 
 	VM_BUG_ON(!*pagep || !xa_is_value(*pagep));
 	swap = radix_to_swp_entry(*pagep);
 	*pagep = NULL;
 
-	/* Prevent swapoff from happening to us. */
-	si = get_swap_device(swap);
-	if (!si) {
-		error = EINVAL;
-		goto failed;
-	}
 	/* Look it up and read it in.. */
 	page = lookup_swap_cache(swap, NULL, 0);
 	if (!page) {
@@ -1772,8 +1765,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	swap_free(swap);
 
 	*pagep = page;
-	if (si)
-		put_swap_device(si);
 	return 0;
 failed:
 	if (!shmem_confirm_swap(mapping, index, swap))
@@ -1784,9 +1775,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 		put_page(page);
 	}
 
-	if (si)
-		put_swap_device(si);
-
 	return error;
 }
 

mm/swap_state.c

@@ -628,13 +628,6 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	if (!mask)
 		goto skip;
 
-	/* Test swap type to make sure the dereference is safe */
-	if (likely(si->flags & (SWP_BLKDEV | SWP_FS_OPS))) {
-		struct inode *inode = si->swap_file->f_mapping->host;
-		if (inode_read_congested(inode))
-			goto skip;
-	}
-
 	do_poll = false;
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;

mm/vmscan.c

@@ -100,9 +100,12 @@ struct scan_control {
 	unsigned int may_swap:1;
 
 	/*
-	 * Cgroups are not reclaimed below their configured memory.low,
-	 * unless we threaten to OOM. If any cgroups are skipped due to
-	 * memory.low and nothing was reclaimed, go back for memory.low.
+	 * Cgroup memory below memory.low is protected as long as we
+	 * don't threaten to OOM. If any cgroup is reclaimed at
+	 * reduced force or passed over entirely due to its memory.low
+	 * setting (memcg_low_skipped), and nothing is reclaimed as a
+	 * result, then go back for one more cycle that reclaims the protected
+	 * memory (memcg_low_reclaim) to avert OOM.
 	 */
 	unsigned int memcg_low_reclaim:1;
 	unsigned int memcg_low_skipped:1;
@@ -2537,15 +2540,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	for_each_evictable_lru(lru) {
 		int file = is_file_lru(lru);
 		unsigned long lruvec_size;
+		unsigned long low, min;
 		unsigned long scan;
-		unsigned long protection;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		protection = mem_cgroup_protection(sc->target_mem_cgroup,
-						   memcg,
-						   sc->memcg_low_reclaim);
+		mem_cgroup_protection(sc->target_mem_cgroup, memcg,
+				      &min, &low);
 
-		if (protection) {
+		if (min || low) {
 			/*
 			 * Scale a cgroup's reclaim pressure by proportioning
 			 * its current usage to its memory.low or memory.min
@@ -2576,6 +2578,15 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			 * hard protection.
 			 */
 			unsigned long cgroup_size = mem_cgroup_size(memcg);
+			unsigned long protection;
+
+			/* memory.low scaling, make sure we retry before OOM */
+			if (!sc->memcg_low_reclaim && low > min) {
+				protection = low;
+				sc->memcg_low_skipped = 1;
+			} else {
+				protection = min;
+			}
 
 			/* Avoid TOCTOU with earlier protection check */
 			cgroup_size = max(cgroup_size, protection);
@@ -4413,11 +4424,13 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 		.may_swap = 1,
 		.reclaim_idx = gfp_zone(gfp_mask),
 	};
+	unsigned long pflags;
 
 	trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
 					   sc.gfp_mask);
 
 	cond_resched();
+	psi_memstall_enter(&pflags);
 	fs_reclaim_acquire(sc.gfp_mask);
 	/*
 	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
@@ -4442,6 +4455,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(sc.gfp_mask);
+	psi_memstall_leave(&pflags);
 
 	trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);