Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "15 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm, docs: update memory.stat description with workingset* entries
  mm: vmscan: scan until it finds eligible pages
  mm, thp: copying user pages must schedule on collapse
  dax: fix PMD data corruption when fault races with write
  dax: fix data corruption when fault races with write
  ext4: return to starting transaction in ext4_dax_huge_fault()
  mm: fix data corruption due to stale mmap reads
  dax: prevent invalidation of mapped DAX entries
  Tigran has moved
  mm, vmalloc: fix vmalloc users tracking properly
  mm/khugepaged: add missed tracepoint for collapse_huge_page_swapin
  gcov: support GCC 7.1
  mm, vmstat: Remove spurious WARN() during zoneinfo print
  time: delete current_fs_time()
  hwpoison, memcg: forcibly uncharge LRU pages

Documentation/cgroup-v2.txt

@@ -918,6 +918,18 @@ PAGE_SIZE multiple when read back.
 
 		Number of major page faults incurred
 
+	  workingset_refault
+
+		Number of refaults of previously evicted pages
+
+	  workingset_activate
+
+		Number of refaulted pages that were immediately activated
+
+	  workingset_nodereclaim
+
+		Number of times a shadow node has been reclaimed
+
   memory.swap.current
 
 	A read-only single value file which exists on non-root

Documentation/filesystems/bfs.txt

@@ -54,4 +54,4 @@ The first 4 bytes should be 0x1badface.
 If you have any patches, questions or suggestions regarding this BFS
 implementation please contact the author:
 
-Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+Tigran Aivazian <aivazian.tigran@gmail.com>

MAINTAINERS

@@ -2483,7 +2483,7 @@ S:	Maintained
 F:	drivers/net/ethernet/ec_bhf.c
 
 BFS FILE SYSTEM
-M:	"Tigran A. Aivazian" <tigran@aivazian.fsnet.co.uk>
+M:	"Tigran A. Aivazian" <aivazian.tigran@gmail.com>
 S:	Maintained
 F:	Documentation/filesystems/bfs.txt
 F:	fs/bfs/

arch/x86/kernel/cpu/microcode/amd.c

@@ -10,7 +10,7 @@
  *  Author: Peter Oruba <peter.oruba@amd.com>
  *
  *  Based on work by:
- *  Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *  Tigran Aivazian <aivazian.tigran@gmail.com>
  *
  *  early loader:
  *  Copyright (C) 2013 Advanced Micro Devices, Inc.

arch/x86/kernel/cpu/microcode/core.c

 /*
  * CPU Microcode Update Driver for Linux
  *
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * Copyright (C) 2000-2006 Tigran Aivazian <aivazian.tigran@gmail.com>
  *	      2006	Shaohua Li <shaohua.li@intel.com>
  *	      2013-2016	Borislav Petkov <bp@alien8.de>
  *

arch/x86/kernel/cpu/microcode/intel.c

 /*
  * Intel CPU Microcode Update Driver for Linux
  *
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * Copyright (C) 2000-2006 Tigran Aivazian <aivazian.tigran@gmail.com>
  *		 2006 Shaohua Li <shaohua.li@intel.com>
  *
  * Intel CPU microcode early update for Linux

fs/bfs/inode.c

 /*
  *	fs/bfs/inode.c
  *	BFS superblock and inode operations.
- *	Copyright (C) 1999-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *	Copyright (C) 1999-2006 Tigran Aivazian <aivazian.tigran@gmail.com>
  *	From fs/minix, Copyright (C) 1991, 1992 Linus Torvalds.
  *
  *      Made endianness-clean by Andrew Stribblehill <ads@wompom.org>, 2005.
@@ -19,7 +19,7 @@
 #include <linux/uaccess.h>
 #include "bfs.h"
 
-MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
+MODULE_AUTHOR("Tigran Aivazian <aivazian.tigran@gmail.com>");
 MODULE_DESCRIPTION("SCO UnixWare BFS filesystem for Linux");
 MODULE_LICENSE("GPL");
 

fs/dax.c

@@ -460,35 +460,6 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	return ret;
 }
 
-/*
- * Invalidate exceptional DAX entry if easily possible. This handles DAX
- * entries for invalidate_inode_pages() so we evict the entry only if we can
- * do so without blocking.
- */
-int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
-{
-	int ret = 0;
-	void *entry, **slot;
-	struct radix_tree_root *page_tree = &mapping->page_tree;
-
-	spin_lock_irq(&mapping->tree_lock);
-	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
-	if (!entry || !radix_tree_exceptional_entry(entry) ||
-	    slot_locked(mapping, slot))
-		goto out;
-	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
-	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
-		goto out;
-	radix_tree_delete(page_tree, index);
-	mapping->nrexceptional--;
-	ret = 1;
-out:
-	spin_unlock_irq(&mapping->tree_lock);
-	if (ret)
-		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
-	return ret;
-}
-
 /*
  * Invalidate exceptional DAX entry if it is clean.
  */
@@ -1044,7 +1015,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	 * into page tables. We have to tear down these mappings so that data
 	 * written by write(2) is visible in mmap.
 	 */
-	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+	if (iomap->flags & IOMAP_F_NEW) {
 		invalidate_inode_pages2_range(inode->i_mapping,
 					      pos >> PAGE_SHIFT,
 					      (end - 1) >> PAGE_SHIFT);
@@ -1177,6 +1148,12 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
+		goto out;
+	}
+
 	/*
 	 * Note that we don't bother to use iomap_apply here: DAX required
 	 * the file system block size to be equal the page size, which means
@@ -1185,17 +1162,11 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
 	if (error) {
 		vmf_ret = dax_fault_return(error);
-		goto out;
+		goto unlock_entry;
 	}
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
-		goto finish_iomap;
-	}
-
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		vmf_ret = dax_fault_return(PTR_ERR(entry));
-		goto finish_iomap;
+		error = -EIO;	/* fs corruption? */
+		goto error_finish_iomap;
 	}
 
 	sector = dax_iomap_sector(&iomap, pos);
@@ -1217,13 +1188,13 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto error_unlock_entry;
+			goto error_finish_iomap;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto unlock_entry;
+		goto finish_iomap;
 	}
 
 	switch (iomap.type) {
@@ -1243,7 +1214,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
 			vmf_ret = dax_load_hole(mapping, &entry, vmf);
-			goto unlock_entry;
+			goto finish_iomap;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1252,10 +1223,8 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 		break;
 	}
 
- error_unlock_entry:
+ error_finish_iomap:
 	vmf_ret = dax_fault_return(error) | major;
- unlock_entry:
-	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PAGE_SIZE;
@@ -1270,7 +1239,9 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 		 */
 		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
-out:
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+ out:
 	trace_dax_pte_fault_done(inode, vmf, vmf_ret);
 	return vmf_ret;
 }
@@ -1416,6 +1387,16 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto fallback;
+
 	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
@@ -1424,21 +1405,11 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto fallback;
+		goto unlock_entry;
 
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
-	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto finish_iomap;
-
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
 		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
@@ -1446,7 +1417,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto unlock_entry;
+			break;
 		result = dax_pmd_load_hole(vmf, &iomap, &entry);
 		break;
 	default:
@@ -1454,8 +1425,6 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 		break;
 	}
 
- unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
@@ -1471,6 +1440,8 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
 				&iomap);
 	}
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, vmf->pmd, vmf->address);

fs/ext4/file.c

@@ -257,6 +257,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
 	int result;
+	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -264,12 +265,24 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vmf->vma->vm_file);
-	}
 		down_read(&EXT4_I(inode)->i_mmap_sem);
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
+					       EXT4_DATA_TRANS_BLOCKS(sb));
+	} else {
+		down_read(&EXT4_I(inode)->i_mmap_sem);
+	}
+	if (!IS_ERR(handle))
 		result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
+	else
+		result = VM_FAULT_SIGBUS;
+	if (write) {
+		if (!IS_ERR(handle))
+			ext4_journal_stop(handle);
 		up_read(&EXT4_I(inode)->i_mmap_sem);
-	if (write)
 		sb_end_pagefault(sb);
+	} else {
+		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
 
 	return result;
 }

include/linux/dax.h

@@ -89,7 +89,6 @@ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 		    const struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
-int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,

include/linux/fs.h

@@ -1431,7 +1431,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid)
 	inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
 }
 
-extern struct timespec current_fs_time(struct super_block *sb);
 extern struct timespec current_time(struct inode *inode);
 
 /*

include/linux/vmalloc.h

@@ -6,7 +6,6 @@
 #include <linux/list.h>
 #include <linux/llist.h>
 #include <asm/page.h>		/* pgprot_t */
-#include <asm/pgtable.h>	/* PAGE_KERNEL */
 #include <linux/rbtree.h>
 
 struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
@@ -83,22 +82,14 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
 			const void *caller);
 #ifndef CONFIG_MMU
 extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags);
-#else
-extern void *__vmalloc_node(unsigned long size, unsigned long align,
-			    gfp_t gfp_mask, pgprot_t prot,
-			    int node, const void *caller);
-
-/*
- * We really want to have this inlined due to caller tracking. This
- * function is used by the highlevel vmalloc apis and so we want to track
- * their callers and inlining will achieve that.
- */
-static inline void *__vmalloc_node_flags(unsigned long size,
-					int node, gfp_t flags)
+static inline void *__vmalloc_node_flags_caller(unsigned long size, int node,
+						gfp_t flags, void *caller)
 {
-	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
-					node, __builtin_return_address(0));
+	return __vmalloc_node_flags(size, node, flags);
 }
+#else
+extern void *__vmalloc_node_flags_caller(unsigned long size,
+					 int node, gfp_t flags, void *caller);
 #endif
 
 extern void vfree(const void *addr);

kernel/gcov/base.c

@@ -98,6 +98,12 @@ void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
 }
 EXPORT_SYMBOL(__gcov_merge_icall_topn);
 
+void __gcov_exit(void)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_exit);
+
 /**
  * gcov_enable_events - enable event reporting through gcov_event()
  *

kernel/gcov/gcc_4_7.c

@@ -18,7 +18,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
+#if (__GNUC__ >= 7)
+#define GCOV_COUNTERS			9
+#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
 #define GCOV_COUNTERS			10
 #elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
 #define GCOV_COUNTERS			9

kernel/time/time.c

@@ -230,20 +230,6 @@ SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
 	return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
 }
 
-/**
- * current_fs_time - Return FS time
- * @sb: Superblock.
- *
- * Return the current time truncated to the time granularity supported by
- * the fs.
- */
-struct timespec current_fs_time(struct super_block *sb)
-{
-	struct timespec now = current_kernel_time();
-	return timespec_trunc(now, sb->s_time_gran);
-}
-EXPORT_SYMBOL(current_fs_time);
-
 /*
  * Convert jiffies to milliseconds and back.
  *

mm/khugepaged.c

@@ -612,7 +612,8 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 				      spinlock_t *ptl)
 {
 	pte_t *_pte;
-	for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) {
+	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
+				_pte++, page++, address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
 		struct page *src_page;
 
@@ -651,9 +652,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 			spin_unlock(ptl);
 			free_page_and_swap_cache(src_page);
 		}
-
-		address += PAGE_SIZE;
-		page++;
+		cond_resched();
 	}
 }
 
@@ -907,9 +906,11 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 				return false;
 			}
 			/* check if the pmd is still valid */
-			if (mm_find_pmd(mm, address) != pmd)
+			if (mm_find_pmd(mm, address) != pmd) {
+				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
 			}
+		}
 		if (ret & VM_FAULT_ERROR) {
 			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 			return false;

mm/memcontrol.c

@@ -5528,7 +5528,7 @@ static void uncharge_list(struct list_head *page_list)
 		next = page->lru.next;
 
 		VM_BUG_ON_PAGE(PageLRU(page), page);
-		VM_BUG_ON_PAGE(page_count(page), page);
+		VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
 
 		if (!page->mem_cgroup)
 			continue;

mm/memory-failure.c

@@ -539,6 +539,13 @@ static int delete_from_lru_cache(struct page *p)
 		 */
 		ClearPageActive(p);
 		ClearPageUnevictable(p);
+
+		/*
+		 * Poisoned page might never drop its ref count to 0 so we have
+		 * to uncharge it manually from its memcg.
+		 */
+		mem_cgroup_uncharge(p);
+
 		/*
 		 * drop the page count elevated by isolate_lru_page()
 		 */

mm/truncate.c

@@ -67,17 +67,14 @@ static void truncate_exceptional_entry(struct address_space *mapping,
 
 /*
  * Invalidate exceptional entry if easily possible. This handles exceptional
- * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and
- * clean entries.
+ * entries for invalidate_inode_pages().
  */
 static int invalidate_exceptional_entry(struct address_space *mapping,
 					pgoff_t index, void *entry)
 {
-	/* Handled by shmem itself */
-	if (shmem_mapping(mapping))
+	/* Handled by shmem itself, or for DAX we do nothing. */
+	if (shmem_mapping(mapping) || dax_mapping(mapping))
 		return 1;
-	if (dax_mapping(mapping))
-		return dax_invalidate_mapping_entry(mapping, index);
 	clear_shadow_entry(mapping, index, entry);
 	return 1;
 }
@@ -689,7 +686,17 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		cond_resched();
 		index++;
 	}
-
+	/*
+	 * For DAX we invalidate page tables after invalidating radix tree.  We
+	 * could invalidate page tables while invalidating each entry however
+	 * that would be expensive. And doing range unmapping before doesn't
+	 * work as we have no cheap way to find whether radix tree entry didn't
+	 * get remapped later.
+	 */
+	if (dax_mapping(mapping)) {
+		unmap_mapping_range(mapping, (loff_t)start << PAGE_SHIFT,
+				    (loff_t)(end - start + 1) << PAGE_SHIFT, 0);
+	}
 out:
 	cleancache_invalidate_inode(mapping);
 	return ret;

mm/util.c

@@ -382,7 +382,8 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	if (ret || size <= PAGE_SIZE)
 		return ret;
 
-	return __vmalloc_node_flags(size, node, flags);
+	return __vmalloc_node_flags_caller(size, node, flags,
+			__builtin_return_address(0));
 }
 EXPORT_SYMBOL(kvmalloc_node);
 

mm/vmalloc.c

@@ -1649,6 +1649,9 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+			    gfp_t gfp_mask, pgprot_t prot,
+			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
@@ -1791,7 +1794,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
  *	with mm people.
  *
  */
-void *__vmalloc_node(unsigned long size, unsigned long align,
+static void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller)
 {
@@ -1806,6 +1809,20 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 }
 EXPORT_SYMBOL(__vmalloc);
 
+static inline void *__vmalloc_node_flags(unsigned long size,
+					int node, gfp_t flags)
+{
+	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
+					node, __builtin_return_address(0));
+}
+
+
+void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags,
+				  void *caller)
+{
+	return __vmalloc_node(size, 1, flags, PAGE_KERNEL, node, caller);
+}
+
 /**
  *	vmalloc  -  allocate virtually contiguous memory
  *	@size:		allocation size

mm/vmscan.c

@@ -1449,7 +1449,7 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
  *
  * Appropriate locks must be held before calling this function.
  *
- * @nr_to_scan:	The number of pages to look through on the list.
+ * @nr_to_scan:	The number of eligible pages to look through on the list.
  * @lruvec:	The LRU vector to pull pages from.
  * @dst:	The temp list to put pages on to.
  * @nr_scanned:	The number of pages that were scanned.
@@ -1469,11 +1469,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long skipped = 0;
-	unsigned long scan, nr_pages;
+	unsigned long scan, total_scan, nr_pages;
 	LIST_HEAD(pages_skipped);
 
-	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
-					!list_empty(src); scan++) {
+	scan = 0;
+	for (total_scan = 0;
+	     scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src);
+	     total_scan++) {
 		struct page *page;
 
 		page = lru_to_page(src);
@@ -1487,6 +1489,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			continue;
 		}
 
+		/*
+		 * Do not count skipped pages because that makes the function
+		 * return with no isolated pages if the LRU mostly contains
+		 * ineligible pages.  This causes the VM to not reclaim any
+		 * pages, triggering a premature OOM.
+		 */
+		scan++;
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
 			nr_pages = hpage_nr_pages(page);
@@ -1524,9 +1533,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			skipped += nr_skipped[zid];
 		}
 	}
-	*nr_scanned = scan;
+	*nr_scanned = total_scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
-				    scan, skipped, nr_taken, mode, lru);
+				    total_scan, skipped, nr_taken, mode, lru);
 	update_lru_sizes(lruvec, lru, nr_zone_taken);
 	return nr_taken;
 }

mm/vmstat.c

@@ -1359,8 +1359,6 @@ static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
 			return zone == compare;
 	}
 
-	/* The zone must be somewhere! */
-	WARN_ON_ONCE(1);
 	return false;
 }